
Research Article
Region-Based Multiple Object Tracking with LSTM Supported Trajectories
@INPROCEEDINGS{10.1007/978-3-031-17292-2_5, author={Manish Khare and Manan Mapara and Noopur Srivastava and Bakul Gohel}, title={Region-Based Multiple Object Tracking with LSTM Supported Trajectories}, proceedings={Computer Science and Education in Computer Science. 18th EAI International Conference, CSECS 2022, On-Site and Virtual Event, June 24-27, 2022, Proceedings}, proceedings_a={CSECS}, year={2022}, month={11}, keywords={Multi-object tracking LSTM Dataset Object detection}, doi={10.1007/978-3-031-17292-2_5} }
- Manish Khare
Manan Mapara
Noopur Srivastava
Bakul Gohel
Year: 2022
Region-Based Multiple Object Tracking with LSTM Supported Trajectories
CSECS
Springer
DOI: 10.1007/978-3-031-17292-2_5
Abstract
Object Tracking is the growing field in computer vision with its demands in various areas in monitoring and surveillance. Areas of surveillance can be improved with proper and efficient trackers that can ensure people’s safety on roads, the safety of children in school, and in many other areas. Object tracking is a super-set of elements object classification, object detection, etc. Most of the work done consists of tracking based on visual features, so we have worked on region-based features. In this context, a method is proposed for tracking, based on region features extracted with the help of intersection over union and prediction of trajectories with the help of LSTM in case of occlusion. Comparison for the same is being carried out with the traditional centroid tracking algorithm.