PointIT: A Fast Tracking Framework Based on 3D Instance Segmentation

Abstract

Recently most popular tracking frameworks focus on 2D image sequences. They seldom track the 3D object in point clouds. In this paper, we propose PointIT, a fast, simple tracking method based on 3D on-road instance segmentation. Firstly, we transform 3D LiDAR data into the spherical image with the size of 64 x 512 x 4 and feed it into instance segment model to get the predicted instance mask for each class. Then we use MobileNet as our primary encoder instead of the original ResNet to reduce the computational complexity. Finally, we extend the Sort algorithm with this instance framework to realize tracking in the 3D LiDAR point cloud data. The model is trained on the spherical images dataset with the corresponding instance label masks which are provided by KITTI 3D Object Track dataset. According to the experiment results, our network can achieve on Average Precision (AP) of 0.617 and the performance of multi-tracking task has also been improved.

References in corpus (8)

• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• Simple Online and Realtime Tracking
• Feature Pyramid Networks for Object Detection
• VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection
• Simple Online and Realtime Tracking with a Deep Association Metric
• PointSeg: Real-Time Semantic Segmentation Based on 3D LiDAR Point Cloud
• Fully Convolutional Instance-aware Semantic Segmentation
• SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation

Cited by in corpus (2)

• 3D-SiamRPN: An End-to-End Learning Method for Real-Time 3D Single Object Tracking Using Raw Point Cloud
• PointTrackNet: An End-to-End Network For 3-D Object Detection and Tracking From Point Clouds