InnovativePractice1_SUSTech

Project's name is Joint Detection and Tracking for Automatic Annotation of 3D Data.

The project is based on SUSTechPOINTS platform.

Teammates	Contributions
Ruihao Zhang (ObsisMc)	Object Detection; Pose Adjustment; Visualization; Data Processing
Shuheng Zhang (jidantang55)	Object Tracking; Trajectory prediction & complement; Data Processing
Lingrui Zhang (zlrzz)	Object Tracking; Size Adjustment; Data Processing

System Structure

For details, please read our report.

Main References

Object Detection

1. PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
2. PointPillars: Fast Encoders for Object Detection from Point Clouds
3. PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection

Object Tracking

1. AB3DMOT: A Baseline for 3D Multi-Object Tracking and New Evaluation Metrics

Others

1. Offboard 3D Object Detection from Point Cloud Sequences
2. Auto4D: Learning to Label 4D Objects from Sequential Point Clouds