AN IOT AND CLOUD COMPUTING BASED AUTOMATED IMAGE SEGREGATION SYSTEM AND METHOD THEREOF

Abstract

The present invention discloses an IoT and cloud computing-based automated image segregation system designed for efficient surveillance. The system integrates multiple specialized hardware components, including an Intelligent Image Compression Unit for context-aware compression, an Analog Neural Processing Unit for real-time edge computation, and a Thermal Imaging Module for enhanced detection in low-visibility conditions. The system also features an Identity Recognition Module for accurate identity detection. Images are processed locally to reduce latency and bandwidth requirements before being transmitted to a cloud platform for further analysis, segregation, and secure archival. The invention ensures efficient, real-time image segregation, optimized data transmission, and enhanced surveillance capabilities while maintaining data privacy and security.

Specification

Description:[013] The following sections of this article will provide various embodiments of the current invention with references to the accompanying drawings, whereby the reference numbers utilised in the picture correspond to like elements throughout the description. However, this invention is not limited to the embodiment described here and may be embodied in several other ways. Instead, the embodiment is included to ensure that this disclosure is extensive and complete and that individuals of ordinary skill in the art are properly informed of the extent of the invention. Numerical values and ranges are given for many parts of the implementations discussed in the following thorough discussion. These numbers and ranges are merely to be used as examples and are not meant to restrict the claims' applicability. A variety of materials are also recognised as fitting for certain aspects of the implementations. These materials should only be used as examples and are not meant to restrict the application of the innovation.
[014] Referring now to the drawings, these are illustrated in FIG. 1, the automated image segregation system consists of multiple IoT-enabled surveillance cameras strategically placed along roads. Each camera is equipped with specialized hardware, including an Intelligent Image Compression Unit, an Analog Neural Processing Unit, a Thermal Imaging Module, and an Identity Recognition Module. The captured images are processed locally by the Analog Neural Processing Unit, which performs initial image segregation based on pre-trained models and uses context-aware compression to optimize data transmission to the cloud.
[015] In accordance with another embodiment of the present invention, the Intelligent Image Compression Unit uses AI-driven algorithms to determine which portions of an image carry high-value information, such as facial details, vehicle identifiers, and road signs. It selectively compresses less important areas, thus significantly reducing the overall image size without compromising the quality of crucial information. This ensures that image transmission over low-bandwidth IoT networks is optimized.
[016] In accordance with another embodiment of the present invention, Analog Neural Processing Unit performs event-based processing, using an architecture inspired by biological neurons to efficiently classify and segregate images. The unit processes visual information in real time, classifying and flagging images of interest, such as vehicles violating traffic rules, or identifying pedestrians based on recognizable features. This edge computation reduces the dependency on cloud processing, enabling immediate detection and action.
[017] In accordance with another embodiment of the present invention, the thermal imaging module is used in conjunction with the visible light camera to enhance image segregation capabilities in low-visibility environments. This module detects temperature differences, allowing for accurate object detection and tracking during nighttime or adverse weather conditions. By combining thermal and visible light data, the system improves identity recognition and object classification performance as shown in figure 2.
[018] In accordance with another embodiment of the present invention, the identity recognition module utilizes advanced AI algorithms to accurately identify specific features such as facial characteristics, vehicle license plates, and other distinguishable identity markers. The module works alongside the Analog Neural Processing Unit and Thermal Imaging Module to provide comprehensive surveillance, allowing for the recognition of individuals or vehicles even in difficult conditions such as low light or partial obstructions.
[019] The cloud infrastructure receives compressed image data from the IoT nodes, where advanced machine learning models are used to refine the segregation. The cloud also provides long-term data archival, allowing users to search and retrieve specific images based on metadata such as location, time, or identity-recognizable features.
[020] Images are captured using the integrated visible and thermal cameras. The Analog Neural Processing Unit performs pre-processing to extract relevant features. The images are classified at the edge using the Analog Neural Processing Unit, which tags them based on pre-defined categories like vehicle type, pedestrian identification, or road assets. The Intelligent Image Compression Unit compresses the images, prioritizing high-value sections for transmission. The Identity Recognition Module processes high-priority sections of the images to identify features such as faces, license plates, and distinguishing characteristics of pedestrians or vehicles. Compressed images are sent to the cloud for further processing. The cloud server applies additional machine learning models for detailed analysis, segregation, and long-term storage. Authorized personnel can access the segregated data through a secure web interface, enabling them to monitor surveillance feeds, analyze traffic patterns, or retrieve specific events.
[021] The Analog Neural Processing Unit allows for near-instantaneous classification and segregation, reducing the need for high-latency cloud processing. The Intelligent Image Compression Unit minimizes the amount of data transmitted, making the system suitable for IoT environments with limited bandwidth. The inclusion of the Thermal Imaging Module and Identity Recognition Module ensures that identity-recognizable features are captured accurately even in low-light or adverse weather conditions. The system maintains data privacy by performing sensitive image processing at the edge before transmitting minimal data to the cloud.
[022] The invention offers an advanced solution for road surveillance, addressing current challenges with intelligent hardware features that optimize both the accuracy and efficiency of image segregation. By combining edge AI capabilities, intelligent compression, identity recognition, and multi-spectral imaging, the system ensures effective monitoring and surveillance, even in resource-constrained environments.
[023] The benefits and advantages that the present invention may offer have been discussed above with reference to particular embodiments. These benefits and advantages are not to be interpreted as critical, necessary, or essential features of any or all of the embodiments, nor are they to be read as any elements or constraints that might contribute to their occurring or becoming more evident.
[024] Although specific embodiments have been used to describe the current invention, it should be recognized that these embodiments are merely illustrative and that the invention is not limited to them. The aforementioned embodiments are open to numerous alterations, additions, and improvements. These adaptations, changes, additions, and enhancements are considered to be within the purview of the invention. , Claims:1. An Automated Image Segregation System, comprising:
a plurality of IoT-enabled surveillance cameras for capturing images, each camera including:
an Intelligent Image Compression Unit configured to perform context-aware image compression to selectively retain high-value regions, such as identity-recognizable features;
an Analog Neural Processing Unit for real-time, ultra-low-power image processing, allowing on-site classification and segregation of images with reduced latency;
a Thermal Imaging Module to assist in specialized object detection using thermal signatures, enhancing detection in low-visibility environments;
an Identity Recognition Module employing AI algorithms to identify facial details, license plates, and other identifiable features.
wherein the Intelligent Image Compression unit is configured to use AI-driven algorithms to selectively compress less critical areas of an image, thereby optimizing data transmission over IoT networks with limited bandwidth.
wherein the Analog Neural Processing unit mimics biological neural networks to classify and segregate images on-site, enabling edge computation and minimizing reliance on centralized cloud resources.
wherein the Thermal Imaging module is configured to detect temperature differences and enhance image segregation capabilities during adverse conditions such as low-light, nighttime, or foggy environments.
wherein the Identity Recognition module utilizes deep learning techniques to recognize identity features such as facial characteristics and license plates, even in partially obstructed or low-visibility scenarios.

2. The Automated Image Segregation System as claimed in claim 1, wherein the system is configured to reduce latency by performing real-time edge computation, minimizing the data required for cloud processing and thereby increasing efficiency in surveillance operations.
3. The Automated Image Segregation System as claimed in claim 1, wherein the system is designed to provide comprehensive surveillance by integrating visible light, thermal data, and identity recognition for accurate object classification and identity tracking in challenging conditions.

4. The Automated Image Segregation System as claimed in claim 1, wherein the system ensures data privacy and security by performing sensitive identity feature recognition and segregation at the edge before transmitting the data to the cloud, reducing the risk of unauthorized data access.

5. A Method for Automated Image Segregation, comprising:
a) capturing images using visible and thermal cameras integrated into IoT-enabled surveillance devices;
b) performing initial image processing and segregation using an Analog Neural Processing Unit for on-site classification;
c) applying intelligent compression to images using an Intelligent Image Compression Unit to prioritize high-value sections for transmission;
d) recognizing identity features using an Identity Recognition Module;
e) transmitting compressed images to a cloud computing platform for further analysis, segregation, and long-term storage;
f) enabling access to segregated data through a secure web interface for monitoring and retrieval by authorized users.

6. The Method as claimed in claim 5, wherein the Analog Neural Processing Unit performs event-based processing to classify and flag images of interest, such as vehicles violating traffic regulations or identifying pedestrians based on unique features.

7. The Method as claimed in claim 5, wherein the Intelligent Image Compression Unit utilizes AI-driven algorithms to identify and retain high-value regions, including facial details and vehicle identifiers, ensuring efficient bandwidth utilization.

8. The Method as claimed in claim 5, wherein the Thermal Imaging Module collaborates with the visible light camera to enhance identity recognition, particularly in low-light or adverse weather conditions.

Documents