Vehicle Behavior Discovery and Three-Dimensional Object Detection and Tracking Based on Spatio-Temporal Dependency Knowledge and Artificial Fish Swarm Algorithm

Abstract

In complex traffic environments, 3D target tracking and detection are often occluded by various stationary and moving objects. When the target is occluded, its apparent characteristics change, resulting in a decrease in the accuracy of tracking and detection. In order to solve this problem, we propose to learn the vehicle behavior from the driving data, predict and calibrate the vehicle trajectory, and finally use the artificial fish swarm algorithm to optimize the tracking results. The experiments show that compared with the CenterTrack method, the proposed method improves the key indicators of MOTA (Multi-Object Tracking Accuracy) in 3D object detection and tracking on the nuScenes dataset, and the frame rate is 26 fps.

Keywords

• 3D object detection
• 3D object tracking
• convolutional neural networks
• knowledge-based vehicle behaviors discovery
• artificial fish swarm algorithm