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

## TL;DR

This paper introduces a method for 3D object detection and tracking in traffic by learning vehicle behavior and using an artificial fish swarm algorithm to improve accuracy and speed.

## Contribution

A novel approach combining vehicle behavior learning and the artificial fish swarm algorithm for 3D object tracking.

## Key findings

- The proposed method improves MOTA on the nuScenes dataset compared to CenterTrack.
- The method achieves a frame rate of 26 fps for 3D object detection and tracking.

## 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.