Consult an Expert
Trademark
Design Registration
Consult an Expert
Trademark
Copyright
Patent
Infringement
Design Registration
More
Consult an Expert
Consult an Expert
Trademark
Design Registration
Login
A SYSTEM AND A METHOD FOR DETECTING AND REPORTING POTHOLE ALERTS
Extensive patent search conducted by a registered patent agent
Patent search done by experts in under 48hrs
₹999
₹399
Abstract
Information
Inventors
Applicants
Specification
Documents
ORDINARY APPLICATION
Published
Filed on 14 November 2024
Abstract
ABSTRACT A SYSTEM AND A METHOD FOR DETECTING AND REPORTING POTHOLE ALERTS The present disclosure discloses a system and a method for detecting and reporting pothole alerts. The system(100) comprises at least one vehicle(102a, 102b….102n); a communication module(104) to establish a connection with a nearby Road Side Unit (RSU) (110) over a VANETs; a plurality of sensors(106) installed on a front side of the vehicle(102a, 102b….102n) to identify and capture at least one pothole image; a buffer module (108) to transmit said input images; a RSU(110) comprising an image processing module(112) to apply a set of preprocessing techniques to generate a processed image in real-time; a pothole detection module(114) to implement an AIML-based pothole detection model(114a) to detect, classify and categorize said pothole and generate an alert signal; a transmission buffer module(116) to transmit said alerts including pothole location to said vehicle; a re-transmission buffer module(118) to extend the range of RSU communication by allowing re-transmission of said alerts among other vehicles.
Patent Information
Application ID | 202441088115 |
Invention Field | ELECTRONICS |
Date of Application | 14/11/2024 |
Publication Number | 47/2024 |
Inventors
Name | Address | Country | Nationality |
---|---|---|---|
HARI VITTAL APPINEDI | Department of Computer Science and Engineering SRM University-AP, Neerukonda, Mangalagiri Mandal, Guntur-522240, Andhra Pradesh, India | India | India |
PRAHAN ALAPARTHI | Department of Computer Science and Engineering SRM University-AP, Neerukonda, Mangalagiri Mandal, Guntur-522240, Andhra Pradesh, India | India | India |
V A S S MANI SARAN PUVVADA | Department of Computer Science and Engineering SRM University-AP, Neerukonda, Mangalagiri Mandal, Guntur-522240, Andhra Pradesh, India | India | India |
HARINATH ANKARBOINA | Department of Computer Science and Engineering SRM University-AP, Neerukonda, Mangalagiri Mandal, Guntur-522240, Andhra Pradesh, India | India | India |
AMIT KUMAR SINGH | Department of Computer Science and Engineering SRM University-AP, Neerukonda, Mangalagiri Mandal, Guntur-522240, Andhra Pradesh, India | India | India |
Applicants
Name | Address | Country | Nationality |
---|---|---|---|
SRM UNIVERSITY | Amaravati, Mangalagiri, Andhra Pradesh-522502, India | India | India |
Specification
Description:FIELD
The present disclosure generally relates to the field of notification and alerting systems. More particularly, the present disclosure relates to a system and a method for detecting and reporting pothole alerts.
BACKGROUND
The background information herein below relates to the present disclosure but is not necessarily prior art.
Existing systems for pothole detection, including manual inspections, public reporting, and vehicle-mounted sensors, face several technical limitations that hinder their effectiveness in maintaining road safety. Manual inspections, which require personnel to physically assess roads, are labor-intensive and conducted infrequently, leading to delays in identifying potholes. This often results in hazardous road conditions persisting for extended periods. Public reporting systems depend on citizens to report potholes through online platforms or mobile apps. However, these systems are reactive and inconsistent, as they rely on users to notice and report potholes after encountering them, which can result in incomplete or inaccurate information.
In some cities, vehicle-mounted sensors-such as accelerometers and cameras-are used to automate the detection process. While these sensors offer some improvements, their coverage is limited to the routes taken by sensor-equipped vehicles, leaving many roads unmonitored. Moreover, sensor-based systems often struggle with inaccurate classification, mistaking minor road imperfections for potholes or failing to distinguish between potholes of varying severity. This results in a high rate of false positives and inefficiencies in prioritizing repairs.
Another significant limitation is the lack of real-time alerts in current systems. Manual inspections and public reporting are typically delayed processes, and sensor-based systems only function while vehicles are in operation. This means that potholes can go unnoticed for long periods, posing a risk to drivers. Additionally, these existing systems lack the ability to predict future road damage, which prevents proactive maintenance strategies. Without predictive insights, municipalities are forced to react to damage after it occurs, leading to higher costs and more frequent disruptions for road users.
There is, therefore felt a need for a system and a method for detecting and reporting pothole alerts that alleviates the aforementioned drawbacks.
OBJECTS
Some of the objects of the present disclosure, which at least one embodiment herein satisfies, are as follows:
It is an object of the present disclosure to ameliorate one or more problems of the prior art or to at least provide a useful alternative.
An object of the present disclosure is to provide a system and a method for detecting and reporting pothole alerts.
Another object of the present disclosure is to provide a system that detects potholes using image processing and machine learning.
Still, another object of the present disclosure is to provide a system that real-time updates about road conditions to drivers.
Yet another object of the present disclosure is to provide a system that determines accurate pothole locations.
Still another object of the present disclosure is to provide a system that receives warnings about potholes in advance.
Yet another object of the present disclosure is to provide a system with an interactive and user-friendly interface.
Still another object of the present disclosure is to provide a system that gives statistical analysis to estimate damage probabilities based on road usage intensity.
Other objects and advantages of the present disclosure will be more apparent from the following description, which is not intended to limit the scope of the present disclosure.
SUMMARY
The present disclosure envisages a system for detecting and reporting pothole alerts. The system comprises at least one vehicle, and a Road Side Unit (RSU).
The computing devices comprise a communication module, a plurality of sensors, and a buffer module.
The communication module is configured to establish a connection with a nearby Road Side Unit (RSU) over a Vehicular Ad Hoc Network (VANET).
The plurality of sensors is installed on the front side of the vehicle to cover a 180-degree region on a road surface during driving conditions and to identify and capture at least one pothole as an input image in real-time.
The buffer module is configured to receive and store the input images in a temporary buffer and transmit the input images to the Road Side Unit (RSU) when the vehicle successfully establishes a connection.
The Road Side Unit (RSU) comprises an image processing module, a pothole detection module, a transmission buffer module, and a re-transmission buffer module.
The image processing module is configured to receive and process the images and apply a set of preprocessing techniques to generate a processed image in real-time.
The pothole detection module is configured to implement an Artificial intelligence and machine learning (AIML)-based pothole detection model to detect and classify potholes and categorize the pothole based on size, depth, location, hazard history, and frequency of occurrence, and generate an alert signal before the vehicle reaches the pothole location.
The transmission buffer module is configured to receive and store the alerts in a temporary buffer and transmit the alerts including the pothole location to the vehicle before the vehicle reaches the pothole location.
The re-transmission buffer module is configured to extend the range of RSU communication by allowing the re-transmission of the alerts among other vehicles.
In an embodiment, the sensors installed on the vehicle are selected from a group consisting of radar sensors, lidar sensors, infrared cameras, and optical cameras, for enhanced accuracy in detecting potholes under various environmental conditions.
In an embodiment, the sensors include image sensors including a dash camera configured to capture high-resolution images of the road surface.
In an embodiment, the AIML-based pothole detection model is built using a neural network framework, selected from TensorFlow and Keras, and is trained on a dataset comprising images of both normal and pothole-infested roads.
In an embodiment, the re-transmission module is configured to limit re-transmission to a predefined number of retransmissions to reduce network congestion, with a limit of ten retransmissions.
In an embodiment, the communication between the vehicle and the RSU is carried out using the User Datagram Protocol (UDP) for efficient real-time data transmission.
In an embodiment, the system further comprises:
• a statistical analysis module is configured to estimate the probability of road damage based on vehicle usage data and the detected frequency of potholes; and
• a user interface is configured to allow vehicle drivers to manually report road conditions, including potholes, to supplement an automated detection system.
In an embodiment, the transmission buffer module is configured to transmit the alerts including pothole location to municipal authorities for real-time monitoring and maintenance planning of road conditions.
In an embodiment, the AI/ML-based pothole detection model is configured to perform:
• capture road images with potholes and normal conditions and label the potholes based on size, depth, and location;
• resize images to a standard resolution and normalize pixel values for consistency, reduce noise using filters including Gaussian blur, and optionally apply segmentation to focus on road areas;
• use edge detection to identify pothole boundaries, analyze texture for road surface irregularities, and further estimate pothole depth using Lidar or stereo vision if available;
• choose a model from a group of You Only Look Once (YOLO), Faster Region Convolutional Neural Network (Faster R-CNN), Deep Neural Networks, Convolutional Neural Networks (CNN), train the model using labeled, preprocessed images, and tune hyperparameters (learning rate, batch size, etc.) for better performance;
• validate the model using metrics including accuracy, precision, and recall, generate a confusion matrix to check detection accuracy; and
• classify detected potholes by size and depth (small, medium, large) and index potholes based on severity, considering size, depth, and frequency.
The present disclosure also envisages a method for detecting and reporting pothole alerts. The method comprises the following steps:
• enabling a communication module in at least one vehicle to establish a connection with a nearby Road Side Unit (RSU) over a Vehicular Ad Hoc Network (VANET).
• installing a plurality of sensors on a front side of the vehicle to cover a 180-degree region on a road surface during driving conditions, and identifying and capturing at least one pothole as an input image in real time using the sensors;
• receiving and storing, by a buffer module, the input images in a temporary buffer and transmitting the input images to the Road Side Unit (RSU) when the vehicle successfully establishes connection;
• receiving and processing, by an image processing module of the Road Side Unit (RSU), the images and applying a set of preprocessing techniques to generate a processed image in real-time;
• implementing, by a pothole detection module of the Road Side Unit (RSU), an AIML-based pothole detection model to detect and classifying potholes and categorizing the pothole based on size, depth, location, hazard history, and frequency of occurrence, and generating an alert signal before the vehicle reaches the pothole location; and
• receiving and storing, by a transmission buffer module, the alerts in a temporary buffer and transmitting the alerts including pothole location to the vehicle before the vehicle reaching to the pothole location.
BRIEF DESCRIPTION OF THE ACCOMPANYING DRAWING
A system and a method for detecting and reporting pothole alerts of the present disclosure will now be described with the help of the accompanying drawing, in which:
Figure 1 illustrates a block diagram of a system for detecting and reporting pothole alerts in accordance with an embodiment of the present disclosure;
Figure 2 illustrates a flowchart for a method for detecting and reporting pothole alerts in accordance with an embodiment of the present disclosure;
Figures 3A-3B illustrate a pothole image and a normal image in accordance with an embodiment of the present disclosure; and
Figure 4 illustrates a path map with pothole location in accordance with an embodiment of the present disclosure.
LIST OF REFERENCE NUMERALS
100 - System
102a, 102b…102n - Vehicle
104 - Communication Module
106 - Plurality of Sensors
108 - Buffer Module
108a, 108b…108n - Temporary Buffer
110 - Road Side Unit (RSU)
112 - Image Processing Module
114 - Pothole Detection Module
114a - Artificial intelligence and machine learning (AIML)-based pothole detection model
116 - Transmission Buffer Module
116a, 116b…116n - Temporary Buffer
118 - Re-Transmission Module
120 - Statistical Analysis Module
122 - User Interface
DETAILED DESCRIPTION
Embodiments, of the present disclosure, will now be described with reference to the accompanying drawing.
Embodiments are provided so as to thoroughly and fully convey the scope of the present disclosure to the person skilled in the art. Numerous details, are set forth, relating to specific components, and methods, to provide a complete understanding of embodiments of the present disclosure. It will be apparent to the person skilled in the art that the details provided in the embodiments should not be construed to limit the scope of the present disclosure. In some embodiments, well-known processes, well-known apparatus structures, and well-known techniques are not described in detail.
The terminology used, in the present disclosure, is only for the purpose of explaining a particular embodiment and such terminology shall not be considered to limit the scope of the present disclosure. As used in the present disclosure, the forms "a," "an," and "the" may be intended to include the plural forms as well, unless the context clearly suggests otherwise. The terms "including," and "having," are open ended transitional phrases and therefore specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not forbid the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. The particular order of steps disclosed in the method and process of the present disclosure is not to be construed as necessarily requiring their performance as described or illustrated. It is also to be understood that additional or alternative steps may be employed.
When an element is referred to as being "engaged to," "connected to," or "coupled to" another element, it may be directly engaged, connected, or coupled to the other element. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed elements.
Existing pothole detection systems, such as manual inspections, public reporting, and vehicle-mounted sensors, suffer from key limitations including delayed detection, limited coverage, and inconsistent accuracy. Manual inspections are labor-intensive and infrequent, causing delays in identifying potholes, while public reporting is reactive and often unreliable due to incomplete or inaccurate reports. Vehicle-mounted sensors offer automation but cover limited areas and struggle with false positives or inaccurate classification of potholes. Additionally, these systems lack real-time alerts and cannot predict future road damage, leading to reactive rather than proactive maintenance, higher costs, and ongoing safety risks. Advanced, automated systems are needed to address these shortcomings by providing real-time, accurate detection and predictive maintenance capabilities.
To address the issues of the existing systems and methods, the present disclosure envisages a system (hereinafter referred to as "system 100") for detecting and reporting pothole alerts and a method (hereinafter referred to as "method 200") for detecting and reporting pothole alerts. The system 100 will now be described with reference to Figure 1 and the method 200 will be described with reference to Figure 2.
Referring to Figure 1, the system 100 comprises at least one vehicle 102a, 102b….102n, and a Road Side Unit (RSU) 110.
Each vehicle 102-1, 102-2, …, 102-N includes a communication module 104, a plurality of sensors 106, and a buffer module 108.
The communication module 104 is configured to establish a connection with a nearby Road Side Unit (RSU) (110) over a Vehicular Ad Hoc Network (VANET).
In an embodiment, the communication between the vehicle 102a, 102b….102n and the RSU 110 is carried out using the User Datagram Protocol (UDP) for efficient real-time data transmission.
In an embodiment, the communication module 104 is configured to use Vehicle-to-Infrastructure (V2I) communication protocols to establish and maintain the connection with the Road Side Unit (RSU) 110.
The plurality of sensors 106 installed on the front side of vehicle 102a, 102b….102n to cover a 180-degree region on a road surface during driving conditions and to identify and capture at least one pothole as an input image in real-time.
In an embodiment, the sensors 106 installed on vehicle 102a, 102b….102n are selected from a group consisting of radar sensors, lidar sensors, infrared cameras, and optical cameras, for enhanced accuracy in detecting potholes under various environmental conditions.
In an embodiment, the sensors 106 include image sensors including a dash camera configured to capture high-resolution images of the road surface.
The buffer module 108 is configured to receive and store the input images in a temporary buffer 108a, 108b,…108n and transmit the input images to the Road Side Unit (RSU) 110 when the vehicle 102a, 102b….102n successfully establishes a connection.
The Road Side Unit (RSU) 110 includes an image processing module 112, a pothole detection module 114, a transmission buffer module 116, and a re-transmission buffer module 118.
In an embodiment, the Road Side Unit (RSU) 110 further comprises a local database to store historical pothole data, allowing the system to predict the likelihood of future potholes based on road conditions, frequency of prior pothole formation, and road traffic data.
The image processing module 112 is configured to receive and process the images and apply a set of preprocessing techniques to generate a processed image in real-time.
The pothole detection module 114 is configured to implement an Artificial intelligence and machine learning (AIML)-based pothole detection model 114a to detect and classify potholes and categorize the pothole based on size, depth, location, hazard history, and frequency of occurrence, and generate an alert signal before the vehicle 102a, 102b….102n reaches the pothole location.
In an embodiment, the AIML-based pothole detection model 114a is built using a neural network framework, selected from TensorFlow and Keras, and is trained on a dataset comprising images of both normal and pothole-infested roads.
In an embodiment, the AI/ML-based pothole detection model 114a is configured to continuously improve its classification accuracy by incorporating real-time feedback and historical data of pothole occurrences.
In an embodiment, the AI/ML-based pothole detection model 114a is configured to:
• capture road images with potholes and normal conditions and label the potholes based on size, depth, and location;
• resize images to a standard resolution and normalize pixel values for consistency, reduce noise using filters including Gaussian blur, and optionally apply segmentation to focus on road areas;
• use edge detection to identify pothole boundaries, analyze texture for road surface irregularities, and further estimate pothole depth using Lidar or stereo vision if available;
• choose a model from a group of You Only Look Once (YOLO), Faster Region Convolutional Neural Network (Faster R-CNN), Deep Neural Networks, Convolutional Neural Networks (CNN), train the model using labeled, preprocessed images, and tune hyperparameters (learning rate, batch size, etc.) for better performance;
• validate the model using metrics including accuracy, precision, and recall, generate a confusion matrix to check detection accuracy; and
• classify detected potholes by size and depth (small, medium, large) and index potholes based on severity, considering size, depth, and frequency.
In an embodiment, the AI/ML-based pothole detection model 114a is pre-trained using a dataset of road images containing various potholes and road surface anomalies under different environmental conditions (e.g., rain, night, snow) to improve robustness and accuracy.
In an embodiment, the AI/ML-based pothole detection model 114a is configured to continuously improve through machine learning feedback loops, utilizing real-time feedback from vehicles and road reports to refine its detection and classification accuracy.
The transmission buffer module 116 is configured to receive and store the alerts in a temporary buffer 116a, 116b,…116n and transmit the alerts including pothole location to the vehicle 102a, 102b….102n before the vehicle 102a, 102b….102n reaches to the pothole location.
In an embodiment, the transmission buffer module 116 is configured to transmit the alerts including pothole locations to municipal authorities for real-time monitoring and maintenance planning of road conditions.
In an embodiment, the real-time pothole alert signal includes additional information including:
• recommended vehicle speed reduction,
• detour suggestions,
• or road maintenance schedules, and
• to enhance driver safety and road planning.
The re-transmission buffer module 118 is configured to extend the range of RSU communication by allowing the re-transmission of the alerts among other vehicles.
In an embodiment, the transmission buffer module 116 is configured to store alerts and retransmit them to vehicles 102a, 102b….102n in case of initial transmission failure or weak signal conditions.
In an embodiment, the system 100 further comprises:
• a statistical analysis module 120 is configured to estimate the probability of road damage based on vehicle usage data and the detected frequency of potholes; and
• a user interface 122 is configured to allow vehicle drivers to manually report road conditions, including potholes, to supplement an automated detection system.
In an embodiment, the alert generated by the pothole detection module 114 is prioritized based on the size, depth, and hazard history of the pothole, sending more urgent alerts for larger or more dangerous potholes.
In an embodiment, the re-transmission module 118 is configured to limit re-transmission to a predefined number of retransmissions to reduce network congestion, with a limit of ten retransmissions.
In one embodiment, the system for pothole detection and reporting comprises a network of vehicles equipped with sensors and communication modules that operate within a Vehicular Ad Hoc Network (VANET). Each vehicle is fitted with a plurality of sensors, such as radar, lidar, optical cameras, and infrared cameras, to cover a 180-degree region of the road surface. The sensors capture real-time images of the road and identify potholes based on surface irregularities. These images are temporarily stored in the vehicle's buffer module and transmitted to a nearby Road Side Unit (RSU) when the vehicle establishes a connection.
The RSU includes an image processing module that applies preprocessing techniques such as noise reduction, edge detection, and image resizing to enhance the quality of the captured images. The system uses an AI/ML-based pothole detection model within the RSU to classify potholes based on their size, depth, and location, and generate an alert before the vehicle reaches the pothole. These alerts are transmitted back to the vehicle through a transmission buffer module, ensuring the driver receives real-time notifications about potential hazards ahead.
In another embodiment, the system further comprises a re-transmission buffer module, designed to extend the communication range of the RSU by enabling vehicles to forward pothole alerts to other vehicles within the network. When a vehicle detects a pothole, it not only transmits the alert to the RSU but also allows for re-transmission of the alert to nearby vehicles that may not be directly connected to the RSU.
This embodiment leverages a predefined retransmission limit (e.g., ten retransmissions) to avoid network congestion while still allowing wide coverage for pothole alerts. This setup is particularly beneficial in rural or sparsely populated areas, where RSU coverage might be limited. By enabling vehicles to act as intermediary nodes in the communication chain, the system ensures that all vehicles in the area are informed of potholes, even when they are outside the direct communication range of the RSU.
In still another embodiment, the system integrates public reporting capabilities with automated pothole detection. Each vehicle is equipped with a user interface, allowing drivers to manually report road conditions, including potholes, to supplement the automated detection system. This interface enables drivers to confirm the system's detections or report additional road damage that may not have been captured by the sensors.
This embodiment further includes a statistical analysis module that compiles data from both automated and manual reports to estimate the probability of road damage based on vehicle usage data and pothole frequency. By combining automated AI/ML detection with manual reporting, the system enhances its coverage and accuracy, ensuring that even hard-to-detect potholes are addressed in a timely manner.
In yet embodiment, the pothole detection system utilizes an AI/ML-based model built on neural networks (e.g., TensorFlow, Keras) and trained using a dataset of road images that include both potholes and normal road surfaces under various environmental conditions. The model applies preprocessing techniques such as Gaussian blur for noise reduction and segmentation to isolate road regions.
The system is designed to continuously improve its accuracy through machine learning feedback loops. As vehicles report potholes and encounter road conditions, the system collects real-time feedback and integrates it into the model. This continuous learning ensures that the AI/ML model refines its detection and classification capabilities over time, improving the system's ability to identify potholes of different sizes, depths, and severity levels.
Additionally, the model can classify potholes into categories such as minor, moderate, and severe based on predefined thresholds, allowing authorities to prioritize repairs and send urgent alerts for larger or more dangerous potholes.
In still another embodiment, the system includes a feature that transmits pothole alerts to municipal authorities for real-time monitoring and maintenance planning. The system uses a local database within the RSU to store historical pothole data, including the size, depth, location, and frequency of detected potholes. Municipal authorities can access this data to assess the current condition of roads and plan maintenance schedules accordingly.
Moreover, the system's statistical analysis module analyzes historical data to predict future pothole occurrences, based on patterns such as road traffic, weather conditions, and prior damage. This allows municipalities to implement proactive maintenance strategies, addressing potential road damage before it becomes a hazard, reducing repair costs, and improving road safety for drivers.
In yet another embodiment, the system's communication between vehicles and the RSU uses Vehicle-to-Infrastructure (V2I) protocols and the User Datagram Protocol (UDP) to ensure fast and efficient data transmission. By using UDP, the system minimizes the delay in sending and receiving pothole alerts, providing drivers with real-time notifications about upcoming road hazards.
This embodiment also optimizes network traffic by compressing the images before transmission to reduce bandwidth usage. The system's buffer modules store and manage the data efficiently, ensuring that pothole alerts are transmitted to the vehicles with minimal latency, even in cases of weak network signals or high vehicle density.
Figure 2 illustrates a flowchart for a method for detecting and reporting pothole alerts in accordance with an embodiment of the present disclosure. The order in which method 200 is described is not intended to be construed as a limitation, and any number of the described method steps may be combined in any order to implement method 200, or an alternative method. Furthermore, method 200 may be implemented by processing resource or computing device(s) through any suitable hardware, non-transitory machine-readable medium/instructions, or a combination thereof. The method 200 comprises the following steps:
At step 202, the method 200 includes enabling a communication module in at least one vehicle 102a, 102b….102n to establish a connection with a nearby Road Side Unit (RSU) 110 over a Vehicular Ad Hoc Network (VANET).
At step 204, the method 200 includes installing a plurality of sensors 106 on a front side of the vehicle 102a, 102b….102n to cover a 180-degree region on a road surface during driving conditions, and identifying and capturing at least one pothole as an input image in real-time using the sensors.
At step 206, the method 200 includes receiving and storing, by a buffer module 108, the input images in a temporary buffer 108a, 108b…108n and transmitting the input images to the Road Side Unit (RSU) 110 when the vehicle 102a, 102b….102n successfully establishes a connection.
At step 208, the method 200 includes receiving and processing, by an image processing module 112 of the Road Side Unit (RSU) 110, the images and applying a set of preprocessing techniques to generate a processed image in real-time.
At step 210, the method 200 includes implementing, by a pothole detection module 114 of the Road Side Unit (RSU) 110, an AIML-based pothole detection model 114a to detect and classifying potholes and categorizing the pothole based on size, depth, location, hazard history, and frequency of occurrence, and generating an alert signal before the vehicle 102a, 102b….102n reaches the pothole location.
At step 212, the method 200 includes receiving and storing, by a transmission buffer module 116, the alerts in a temporary buffer 116a, 116b…116n and transmitting the alerts including pothole location to vehicles 102a, 102b….102n before the vehicle 102a, 102b….102n reaching to the pothole location.
Figures 3A-3B illustrate a pothole image and a normal image in accordance with an embodiment of the present disclosure. Figure 3A shows the potholes detected in a captured image. The pothole image shown in Figure 3A is a training sample for the pothole detection algorithm. Further, it shows the input format and the patterns the model can learn for the classification of pothole images Figure 3B shows the normal image, where no potholes were detected. The image shows a pothole-free road loaded into the code editor. The image works as a negative training sample for the pothole detection algorithm. The image illustrates the input format for the algorithm and provides a pattern for the model to learn from
Figure 4 illustrates the path map with pothole location in accordance with an embodiment of the present disclosure. Figure 4 shows when SUMO (Simulation of Urban Mobility) simulates vehicle movement on the custom map.OMNeT++ simulates vehicular communications using the Veins framework. The TraCI synchronizes SUMO and OMNeT++, ensuring real-time interaction between traffic and network layers.
Application:
• Pothole Detection and Reporting: The system automatically detects potholes using image processing and machine learning. This capability allows for timely reporting to RSUs, which can then alert nearby vehicles, enhancing road safety significantly.
• Real-time Traffic Management: By integrating with VANETs, the system can provide real-time updates about road conditions to drivers. This application helps in managing traffic flow and reducing congestion caused by potholes, making travel more efficient.
• Municipal Maintenance Support: The system can assist municipal authorities by providing accurate data on pothole locations. This enables quicker response times for repairs, ultimately leading to safer roads and reduced accident rates.
• Enhanced Vehicle Safety: Vehicles equipped with this technology can receive warnings about potholes in advance, allowing drivers to take preventive actions, such as slowing down or changing lanes. This application directly contributes to passenger safety and vehicle health.
• Data Collection for Infrastructure Improvement: The system can gather valuable data on road conditions over time, which can be used for infrastructure planning and maintenance. This long-term application supports better road management and investment decisions.
• User Engagement and Awareness: By making the system interactive and user-friendly, it encourages more users to participate in reporting and monitoring road conditions, fostering a community-driven approach to road safety.
In an operative configuration, the system for detecting and reporting pothole alerts is designed to ensure efficient communication between vehicles and roadside infrastructure, enabling real-time pothole detection, classification, and alert generation. The system 100 is comprised of multiple key components, including vehicles 102a, 102b…102n equipped with advanced sensor arrays, communication modules, and buffer systems, as well as Road Side Units (RSUs) 110 for processing and transmitting data. Each vehicle 102a, 102b…102n is equipped with a communication module 104 that establishes a connection with nearby RSUs using Vehicular Ad Hoc Networks (VANETs). The vehicles are fitted with a plurality of sensors 106 on the front side, covering a 180-degree region on the road surface during driving. These sensors can include radar, lidar, infrared cameras, and optical cameras, which continuously capture images and identify road conditions, including potholes, in real-time.
The captured data, such as pothole images, are temporarily stored in a buffer module 108 within the vehicle. When the vehicle successfully connects to an RSU, the buffer module 108 transmits the stored data, ensuring continuous and timely communication without data loss. The RSU 110 is configured to receive and process the data sent by the vehicles. It is equipped with an image processing module 112 that applies a set of preprocessing techniques (e.g., resizing, noise reduction, and edge detection) to enhance image quality and generate a processed image in real-time.
The pothole detection module 114 within the RSU 110 implements an AI/ML-based pothole detection model 114a. This model is responsible for identifying and classifying potholes based on various characteristics such as size, depth, and location. The model also categorizes potholes by hazard history and frequency of occurrence, ensuring a robust and accurate detection process.
Once a pothole is detected, the RSU 110 generates an alert signal, which is transmitted to vehicles before they reach the pothole location. The transmission buffer module 116 temporarily stores these alerts before transmitting them back to the approaching vehicles. In addition, the RSU 110 may include a re-transmission buffer module 118, allowing other vehicles 102a, 102b…102n in the network to forward alerts, thus extending the communication range and improving system coverage.
The system is designed to prioritize real-time communication between the vehicle and RSU 110. Using Vehicle-to-Infrastructure (V2I) communication protocols, such as the User Datagram Protocol (UDP) for fast and efficient data transmission, the system 100 ensures that drivers receive timely alerts about upcoming potholes. This enables proactive action, such as reducing speed or changing lanes to avoid the hazard. The system 100 also includes a statistical analysis module 120 for predicting road damage based on vehicle usage data and the frequency of potholes detected. Further, a user interface 122 allows drivers to manually report road conditions, complementing the automated pothole detection system.
For improved operational efficiency, the transmission buffer module 116 can also transmit pothole alerts and location data to municipal authorities, aiding in road maintenance and planning. Furthermore, the system's AI/ML model continuously improves through machine learning feedback loops, incorporating real-time feedback from vehicles and historical pothole data to enhance detection accuracy over time.
Advantageously, the system 100 for detecting and reporting pothole alerts. The system 100 enhances road safety and operational efficiency. Real-time pothole detection is enabled through the use of advanced sensors installed on vehicles, capturing high-resolution images and detecting potholes instantly. The system's AI/ML-based detection model is trained on diverse datasets and capable of accurately classifying potholes under varying environmental conditions (e.g., rain, snow, night), improving detection reliability. Seamless communication is ensured through a Vehicular Ad Hoc Network (VANET), allowing real-time data transmission between the vehicle and the Road Side Unit (RSU) 110 with minimal latency. This allows drivers to receive immediate alerts about upcoming potholes, enabling them to take preventive action and avoid accidents or vehicle damage. Additionally, the AI/ML model categorizes potholes based on factors like size, depth, and hazard history, allowing for prioritized alerts and efficient maintenance scheduling.
The system 100 further enhances communication coverage with a re-transmission module, which extends the communication range by allowing vehicles to forward alerts to others, improving system reach in areas with limited RSU deployment. By incorporating a re-transmission limit, the system ensures that network congestion is reduced, preventing communication delays. With the inclusion of a statistical analysis module, the system can estimate the likelihood of road damage based on historical pothole frequency and vehicle usage, enabling predictive road maintenance. Furthermore, a manual reporting interface allows drivers to supplement automated detection by reporting road conditions directly, enhancing the system's accuracy and comprehensiveness.
The system 100 incorporates preprocessing techniques such as noise reduction and edge detection, which improve image clarity and contribute to the overall detection accuracy. The continuous learning feature of the AI/ML model ensures that detection accuracy improves over time through feedback loops from real-time and historical data. The system's ability to transmit alerts to municipal authorities allows for real-time road monitoring and more effective road maintenance planning, making it a valuable tool for maintaining road infrastructure.
• Automated Pothole Detection: The system 100 employs advanced image processing and machine learning to automatically detect potholes. This reduces human error and increases the accuracy of data collection.
• Real-time Communication: The system 100 utilizes Vehicular Ad Hoc Networks (VANETs) to facilitate immediate communication between vehicles and Road Side Units (RSUs). This real-time data sharing allows vehicles to receive timely alerts about pothole locations, enhancing road safety significantly compared to existing technologies that lack such dynamic communication capabilities.
• Enhanced User Experience: The system 100 is designed to be user-friendly and interactive, making it more appealing for widespread adoption. This focus on user experience is a notable improvement over current systems that may not prioritize ease of use.
• Increased Range of Communication: The re-transmission feature allows for an extended communication range of RSUs without additional hardware. This innovation ensures that more vehicles can access crucial information about road conditions, addressing the limitations of current systems that may have restricted communication ranges.
• Statistical Analysis for Damage Estimation: The system 100 incorporates statistical analysis to estimate damage probabilities based on road usage intensity, providing a more comprehensive understanding of road conditions compared to existing technologies that may not utilize such analytical approaches.
The functions described herein may be implemented in hardware, software executed by a processor, firmware, or any combination thereof. If implemented in software executed by a processor, the functions may be stored on or transmitted over as one or more instructions or code on a computer-readable medium. Other examples and implementations are within the scope and spirit of the disclosure and appended claims. For example, due to the nature of software, functions described above can be implemented using software executed by a processor, hardware, firmware, hardwiring, or combinations of any of these. Features implementing functions may also be physically located at various positions, including being distributed such that portions of functions are implemented at different physical locations.
The foregoing description of the embodiments has been provided for purposes of illustration and is not intended to limit the scope of the present disclosure. Individual components of a particular embodiment are generally not limited to that particular embodiment, but are interchangeable. Such variations are not to be regarded as a departure from the present disclosure, and all such modifications are considered to be within the scope of the present disclosure.
TECHNICAL ADVANCEMENTS
The present disclosure described herein above has several technical advantages including, but not limited to, the realization of a system and a method for detecting and reporting pothole alerts that:
• enhances road safety through real-time pothole detection and reporting;
• improves the efficiency of information dissemination regarding road conditions;
• reduces accidents caused by potholes;
• broadcasts the pothole information to vehicles within its range;
• automates the detection process; and
• improves the overall communication network, ensuring that more vehicles can receive timely information about road conditions.
The embodiments herein and the various features and advantageous details thereof are explained with reference to the non-limiting embodiments in the following description. Descriptions of well-known components and processing techniques are omitted so as to not unnecessarily obscure the embodiments herein. The examples used herein are intended merely to facilitate an understanding of ways in which the embodiments herein may be practiced and to further enable those of skill in the art to practice the embodiments herein. Accordingly, the examples should not be construed as limiting the scope of the embodiments herein.
The foregoing description of the specific embodiments so fully reveals the general nature of the embodiments herein that others can, by applying current knowledge, readily modify and/or adapt for various applications such specific embodiments without departing from the generic concept, and, therefore, such adaptations and modifications should and are intended to be comprehended within the meaning and range of equivalents of the disclosed embodiments. It is to be understood that the phraseology or terminology employed herein is for the purpose of description and not of limitation. Therefore, while the embodiments herein have been described in terms of preferred embodiments, those skilled in the art will recognize that the embodiments herein can be practiced with modification within the spirit and scope of the embodiments as described herein.
The use of the expression "at least" or "at least one" suggests the use of one or more elements or ingredients or quantities, as the use may be in the embodiment of the disclosure to achieve one or more of the desired objects or results.
While considerable emphasis has been placed herein on the components and component parts of the preferred embodiments, it will be appreciated that many embodiments can be made and that many changes can be made in the preferred embodiments without departing from the principles of the disclosure. These and other changes in the preferred embodiment as well as other embodiments of the disclosure will be apparent to those skilled in the art from the disclosure herein, whereby it is to be distinctly understood that the foregoing descriptive matter is to be interpreted merely as illustrative of the disclosure and not as a limitation. , Claims:WE CLAIM:
1. A system (100) for detecting and reporting pothole alerts, said system (100) comprising:
• at least one vehicle (102a, 102b….102n), each vehicle comprising:
o a communication module (104) configured to establish a connection with a nearby Road Side Unit (RSU) (110) over a Vehicular Ad Hoc Network (VANETs);
o a plurality of sensors (106) installed on the front side of the vehicle (102a, 102b….102n) to cover a 180-degree region on a road surface during driving conditions and to identify and capture at least one pothole as an input image in real time; and
o a buffer module (108) configured to receive and store said input images in a temporary buffer (108a, 108b,…108n) and transmit said input images to said Road Side Unit (RSU) (110) when said vehicle (102a, 102b….102n) successfully establishes connection; and
• said Road Side Unit (RSU) (110) comprising:
o an image processing module (112) configured to receive and process said images and apply a set of preprocessing techniques to generate a processed image in real-time;
o a pothole detection module (114) configured to implement an Artificial intelligence and machine learning (AIML)-based pothole detection model (114a) to detect and classify potholes and categorize said pothole based on size, depth, location, hazard history, and frequency of occurrence, and generate an alert signal before said vehicle (102a, 102b….102n) reaches the pothole location;
o a transmission buffer module (116) configured to receive and store said alerts in a temporary buffer (116a, 116b,…116n) and transmit said alerts including pothole location to said vehicle (102a, 102b….102n) before said vehicle (102a, 102b….102n) reaches to the pothole location; and
o a re-transmission buffer module (118) configured to extend the range of RSU communication by allowing re-transmission of said alerts among other vehicles.
2. The system (100) as claimed in claim 1, wherein the sensors (106) installed on the vehicle (102a, 102b….102n) are selected from a group consisting of radar sensors, lidar sensors, infrared cameras, and optical cameras, for enhanced accuracy in detecting potholes under various environmental conditions.
3. The system (100) as claimed in claim 1, wherein the AIML-based pothole detection model (114a) is built using a neural network framework, selected from TensorFlow and Keras, and is trained on a dataset comprising images of both normal and pothole-infested roads.
4. The system (100) as claimed in claim 1, wherein the re-transmission module (118) is configured to limit re-transmission to a predefined number of retransmissions to reduce network congestion, with a limit of 10 retransmissions.
5. The system (100) as claimed in claim 1, said system (100) further comprises:
• a statistical analysis module (120) configured to estimate the probability of road damage based on vehicle usage data and the detected frequency of potholes; and
• a user interface (122) is configured to allows vehicle drivers to manually report road conditions, including potholes, to supplement an automated detection system.
6. The system (100) as claimed in claim 1, wherein the transmission buffer module (116) is configured to transmit said alerts including pothole location to municipal authorities for real-time monitoring and maintenance planning of road conditions.
7. The system (100) as claimed in claim 1, wherein the AI/ML-based pothole detection model (114a) is configured to perform:
• capture road images with potholes and normal conditions and label the potholes based on size, depth, and location;
• resize images to a standard resolution and normalize pixel values for consistency, reduce noise using filters including Gaussian blur, and optionally apply segmentation to focus on road areas;
• use edge detection to identify pothole boundaries, analyze texture for road surface irregularities, and further estimate pothole depth using Lidar or stereo vision if available;
• choose a model from a group of You Only Look Once (YOLO), Faster Region Convolutional Neural Network (Faster R-CNN), Deep Neural Networks, Convolutional Neural Networks (CNN), train the model using labeled, preprocessed images, and tune hyperparameters (learning rate, batch size, etc.) for better performance;
• validate the model using metrics including accuracy, precision, and recall, generate a confusion matrix to check detection accuracy; and
• classify detected potholes by size and depth (small, medium, large) and index potholes based on severity, considering size, depth, and frequency.
8. The system (100) as claimed in claim 1, wherein the alert generated by the pothole detection module (114) is prioritized based on the size, depth, and hazard history of the pothole, sending more urgent alerts for larger or more dangerous potholes.
9. The system (100) as claimed in claim 1, wherein the Road Side Unit (RSU) (110) further comprises a local database to store historical pothole data, allowing the system to predict the likelihood of future potholes based on road conditions, frequency of prior pothole formation, and road traffic data.
10. A method (200) for detecting and reporting pothole alerts, said method (200) comprising:
• enabling a communication module in at least one vehicle (102a, 102b….102n) to establish a connection with a nearby Road Side Unit (RSU) (110) over a Vehicular Ad Hoc Network (VANET);
• installing a plurality of sensors (106) on the front side of the vehicle (102a, 102b….102n) to cover a 180-degree region on a road surface during driving conditions, and identifying and capturing at least one pothole as an input image in real-time using the sensors;
• receiving and storing, by a buffer module (108), said input images in a temporary buffer (108a, 108b,…108n) and transmitting said input images to said Road Side Unit (RSU) (110) when said vehicle (102a, 102b….102n) successfully establishes connection;
• receiving and processing, by an image processing module (112) of said Road Side Unit (RSU) (110), said images and applying a set of preprocessing techniques to generate a processed image in real-time;
• implementing, by a pothole detection module (114) of said Road Side Unit (RSU) (110), an AIML-based pothole detection model (114a) to detect and classifying potholes and categorizing said pothole based on size, depth, location, hazard history, and frequency of occurrence, and generating an alert signal before said vehicle (102a, 102b….102n) reaches the pothole location; and
• receiving and storing, by a transmission buffer module (116), said alerts in a temporary buffer (116a, 116b,…116n) and transmitting said alerts including pothole location to said vehicle (102a, 102b….102n) before said vehicle (102a, 102b….102n) reaching to the pothole location.
Dated this 14th Day of November, 2024
_______________________________
MOHAN RAJKUMAR DEWAN, IN/PA - 25
OF R. K. DEWAN & CO.
AUTHORIZED AGENT OF APPLICANT
TO,
THE CONTROLLER OF PATENTS
THE PATENT OFFICE, AT CHENNAI
Documents
Name | Date |
---|---|
202441088115-FORM-26 [15-11-2024(online)].pdf | 15/11/2024 |
202441088115-COMPLETE SPECIFICATION [14-11-2024(online)].pdf | 14/11/2024 |
202441088115-DECLARATION OF INVENTORSHIP (FORM 5) [14-11-2024(online)].pdf | 14/11/2024 |
202441088115-DRAWINGS [14-11-2024(online)].pdf | 14/11/2024 |
202441088115-EDUCATIONAL INSTITUTION(S) [14-11-2024(online)].pdf | 14/11/2024 |
202441088115-EVIDENCE FOR REGISTRATION UNDER SSI [14-11-2024(online)].pdf | 14/11/2024 |
202441088115-EVIDENCE FOR REGISTRATION UNDER SSI(FORM-28) [14-11-2024(online)].pdf | 14/11/2024 |
202441088115-FORM 1 [14-11-2024(online)].pdf | 14/11/2024 |
202441088115-FORM 18 [14-11-2024(online)].pdf | 14/11/2024 |
202441088115-FORM FOR SMALL ENTITY(FORM-28) [14-11-2024(online)].pdf | 14/11/2024 |
202441088115-FORM-9 [14-11-2024(online)].pdf | 14/11/2024 |
202441088115-PROOF OF RIGHT [14-11-2024(online)].pdf | 14/11/2024 |
202441088115-REQUEST FOR EARLY PUBLICATION(FORM-9) [14-11-2024(online)].pdf | 14/11/2024 |
202441088115-REQUEST FOR EXAMINATION (FORM-18) [14-11-2024(online)].pdf | 14/11/2024 |
Talk To Experts
Calculators
Downloads
By continuing past this page, you agree to our Terms of Service,, Cookie Policy, Privacy Policy and Refund Policy © - Uber9 Business Process Services Private Limited. All rights reserved.
Uber9 Business Process Services Private Limited, CIN - U74900TN2014PTC098414, GSTIN - 33AABCU7650C1ZM, Registered Office Address - F-97, Newry Shreya Apartments Anna Nagar East, Chennai, Tamil Nadu 600102, India.
Please note that we are a facilitating platform enabling access to reliable professionals. We are not a law firm and do not provide legal services ourselves. The information on this website is for the purpose of knowledge only and should not be relied upon as legal advice or opinion.