METHOD FOR DETECTING HUMAN ACTIONS

Abstract

ABSTRACT A method (100) for detecting heart disease, the method (100) comprising the steps of capturing input data comprising at least one of image or video data, re-processing the input data to extract relevant features, feeding the extracted features into a machine learning model, detecting a human action based on the output of the machine learning model and classifying the detected human action into one or more predefined action categories.

Specification

Description:FIELD OF THE DISCLOSURE
[0001] This invention generally relates to human action detection, specifically to methods and systems for detecting human actions using machine learning models that analyses sensor data or visual data to classify actions in real-time or from recorded data.
BACKGROUND

[0002] The subject matter discussed in the background section should not be assumed to be prior art merely as a result of its mention in the background section. Similarly, a problem mentioned in the background section or associated with the subject matter of the background section should not be assumed to have been previously recognized in the prior art. The subject matter in the background section merely represents different approaches, which in and of themselves may also correspond to implementations of the claimed technology.
[0003] Human action detection plays a critical role in various fields, including security surveillance, healthcare, sports analytics, and human-computer interaction. Traditional methods for de , Claims:1. A method 100 for detecting human actions, the method 100 comprising the steps of:
capturing input data comprising at least one of image or video data;
re-processing the input data to extract relevant features;
feeding the extracted features into a machine learning model;
detecting a human action based on the output of the machine learning model;
classifying the detected human action into one or more predefined action categories.
2. The method 100 of claim 1, wherein the machine learning model is trained using labelled datasets that include examples of human actions from one or more categories, and the model is adapted to recognize patterns in the features corresponding to different human actions.
3. The method 100 of claim 1, wherein the machine learning model is a deep neural network, a convolutional neural network, or a recurrent neural network.
4. The method 100 of claim 1, wherein the captured input data is pre-processed by applying one or more of noise reduction, image normalization, object segmentat

Documents