Accurate 3D Single Object Tracker in Point Clouds with Transformer
- Resource Type
- Conference
- Authors
- Wang, Kai; Fan, Baojie; Zhang, Kexin; Zhou, Wuyang
- Source
- 2022 China Automation Congress (CAC) Automation Congress (CAC), 2022 China. :6415-6420 Nov, 2022
- Subject
- Aerospace
Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Computing and Processing
Power, Energy and Industry Applications
Robotics and Control Systems
Signal Processing and Analysis
Transportation
Point cloud compression
Target tracking
Three-dimensional displays
Fuses
Transformers
Feature extraction
Object tracking
3D single object tracking
transformer
point clouds
- Language
- ISSN
- 2688-0938
3D single object tracking (SOT) in point clouds is a fundamental task in autonomous driving and robotics. Motivated by the success of transformer trackers in 2D tracking, we develop a 3D tracker in point clouds with transformer named Trans3DT. Trans3DT consists of three main designs: 1) Different from most previous trackers that use PointNet++ as the backbone, we propose a transformer feature extraction network to efficiently weigh point features to focus on deeper target cues. 2) Instead of using cosine similarity, we propose a novel target feature embedding network that fuses template and search area features in a global manner. 3) A voxel-to-BEV target location network is applied with a lightweight channel-related convolution block (CRCB) to enhance the BEV features. Extensive experiments demonstrate that Trans3DT achieves a new state-of-the-art performance on the challenging KITTI and nuScenes tracking benchmarks.