Correlation Pyramid Network for 3D Single Object Tracking
Preprint
Abstract
3D LiDAR-based single object tracking (SOT) has gained increasing attention as it plays a crucial role in 3D applications such as autonomous driving. The central problem is how to learn a target-aware representation from the sparse and incomplete point clouds. In this paper, we propose a novel Correlation Pyramid Network (CorpNet) with a unified encoder and a motion-factorized decoder. Specifically, the encoder introduces multi-level self attentions and cross attentions in its main branch to enrich the template and search region features and realize their fusion and interaction, respectively. Additionally, considering the sparsity characteristics of the point clouds, we design a lateral correlation pyramid structure for the encoder to keep as many points as possible by integrating hierarchical correlated features. The output features of the search region from the encoder can be directly fed into the decoder for predicting target locations without any extra matcher. Moreover, in the decoder of CorpNet, we design a motion-factorized head to explicitly learn the different movement patterns of the up axis and the x-y plane together. Extensive experiments on two commonly-used datasets show our CorpNet achieves state-of-the-art results while running in real-time.Keywords
All Related Versions
This publication has 11 references indexed in Scilit:
- 3D Siamese Transformer Network for Single Object Tracking on Point Clouds2022
- Backbone is All Your Need: A Simplified Architecture for Visual Object Tracking2022
- Monocular Quasi-Dense 3D Object TrackingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2022
- VoxelTrack: Multi-Person 3D Human Pose Estimation and Tracking in the WildIEEE Transactions on Pattern Analysis and Machine Intelligence, 2022
- A Bayesian Filter for Multi-View 3D Multi-Object Tracking With Occlusion HandlingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2020
- 3D-SiamRPN: An End-to-End Learning Method for Real-Time 3D Single Object Tracking Using Raw Point CloudIEEE Sensors Journal, 2020
- SiamFC++: Towards Robust and Accurate Visual Tracking with Target Estimation GuidelinesProceedings of the AAAI Conference on Artificial Intelligence, 2020
- GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the WildIEEE Transactions on Pattern Analysis and Machine Intelligence, 2019
- Quadruplet Network With One-Shot Learning for Fast Visual Object TrackingIEEE Transactions on Image Processing, 2019
- Robust 3D Object Tracking from Monocular Images Using Stable PartsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017