Box-Aware Feature Enhancement for Single Object Tracking on Point Clouds

by   Chaoda Zheng, et al.

Current 3D single object tracking approaches track the target based on a feature comparison between the target template and the search area. However, due to the common occlusion in LiDAR scans, it is non-trivial to conduct accurate feature comparisons on severe sparse and incomplete shapes. In this work, we exploit the ground truth bounding box given in the first frame as a strong cue to enhance the feature description of the target object, enabling a more accurate feature comparison in a simple yet effective way. In particular, we first propose the BoxCloud, an informative and robust representation, to depict an object using the point-to-box relation. We further design an efficient box-aware feature fusion module, which leverages the aforementioned BoxCloud for reliable feature matching and embedding. Integrating the proposed general components into an existing model P2B, we construct a superior box-aware tracker (BAT). Experiments confirm that our proposed BAT outperforms the previous state-of-the-art by a large margin on both KITTI and NuScenes benchmarks, achieving a 12.8  20


page 3

page 8

page 13


STTracker: Spatio-Temporal Tracker for 3D Single Object Tracking

3D single object tracking with point clouds is a critical task in 3D com...

Beyond 3D Siamese Tracking: A Motion-Centric Paradigm for 3D Single Object Tracking in Point Clouds

3D single object tracking (3D SOT) in LiDAR point clouds plays a crucial...

A Lightweight and Detector-free 3D Single Object Tracker on Point Clouds

Recent works on 3D single object tracking treat the tracking as a target...

3D Siamese Voxel-to-BEV Tracker for Sparse Point Clouds

3D object tracking in point clouds is still a challenging problem due to...

P2B: Point-to-Box Network for 3D Object Tracking in Point Clouds

Towards 3D object tracking in point clouds, a novel point-to-box network...

Towards Efficient Training with Negative Samples in Visual Tracking

Current state-of-the-art (SOTA) methods in visual object tracking often ...

Higher Performance Visual Tracking with Dual-Modal Localization

Visual Object Tracking (VOT) has synchronous needs for both robustness a...

Code Repositories


The official implementation of ICCV paper "Box-Aware Feature Enhancement for Single Object Tracking on Point Clouds".

view repo

Please sign up or login with your details

Forgot password? Click here to reset