RoadTrack: Tracking Road Agents in Dense and Heterogeneous Environments
arxiv(2019)
摘要
We present an algorithm to track traffic agents in dense videos. Our approach is designed for heterogeneous traffic scenarios that consist of different agents such as pedestrians, two-wheelers, cars, buses etc. sharing the road. We present a novel Heterogeneous Traffic Motion and Interaction model (HTMI) to predict the motion of agents by modeling collision avoidance and interactions between the agents. We implement HTMI within the tracking-by-detection paradigm and use background subtracted representations of traffic agents to extract binary tensors for accurate tracking. We highlight the performance on a dense traffic videos and observe an accuracy of 75.8%. We observe up to 4 times speedup over prior tracking algorithms on standard traffic datasets.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络