Abstract:In this paper, a novel method for people detection and tracking is proposed, based on stereo vision. Each person is represented by a group of the feature points. In this method feature point extraction and 2D space construction of projected points on the ground plane is performed in order to provide top view. Occlusion, as a main challenge in tracking systems, can be addressed by top view scene. A robust kernel density estimation method is employed to categorize points. Then Kalman filter is applied to reduce … Show more
In video surveillance system, the most complex thing is to detect individuals. In recent years, the research is done using deep learning technique, which gives powerful individuals detection results. A model in Deep Learning i.e. YOLO (You Only Look Once) has explored in individual detection in all the angles of a individuals. The model is tested and trained on viewing person dataset. Further, counting individuals has done through information of classified bounding box. The trained model is going to verify by giving several testable data set and takes two datasets for training and testing. Trained model is tested rigorously to find out the accuracy of a model. This methodology gives efficient results for counting individual in real world.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.