-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zheng_2021_ICCV, author = {Zheng, Chaoda and Yan, Xu and Gao, Jiantao and Zhao, Weibing and Zhang, Wei and Li, Zhen and Cui, Shuguang}, title = {Box-Aware Feature Enhancement for Single Object Tracking on Point Clouds}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2021}, pages = {13199-13208} }
Box-Aware Feature Enhancement for Single Object Tracking on Point Clouds
Abstract
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% improvement in terms of precision while running 20% faster.
Related Material