MBPTrack: Improving 3D point cloud tracking with memory networks and box priors

Xu, Tian-Xing, Guo, Yuan-Chen, Lai, Yukun ORCID: https://orcid.org/0000-0002-2094-5680 and Zhang, Song-Hai 2023. MBPTrack: Improving 3D point cloud tracking with memory networks and box priors. Presented at: International Conference on Computer Vision (ICCV), Paris, France, 1-6 October 2023. Proceedings of IEEE/CVF International Conference on Computer Vision. IEEE, pp. 9877-9886. 10.1109/ICCV51070.2023.00909

Preview

PDF - Accepted Post-Print Version Download (1MB) | Preview

Abstract

3D single object tracking has been a crucial problem for decades with numerous applications such as autonomous driving. Despite its wide-ranging use, this task remains challenging due to the significant appearance variation caused by occlusion and size differences among tracked targets. To address these issues, we present MBPTrack, which adopts a Memory mechanism to utilize past information and formulates localization in a coarse-to-fine scheme using Box Priors given in the first frame. Specifically, past frames with targetness masks serve as an extenral memory, and a transformer-based module propagates tracked target cues from the memory to the current frame. To precisely localize objects of all sizes, MBPTrack first predicts the target center via Hough voting. By leveraging box priors given in the first frame, we adaptively sample reference points around the target center that roughly cover the target of different sizes. Then, we obtain dense feature maps by aggregating point features into the reference points, where localization can be performed more effectively. Extensive experiments demonstrate that MBPTrack achieves state-of-the-art performance on KITTI, nuScenes and Waymo Open Dataset, while running at 50 FPS on a single RTX3090 GPU.

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Publication
Status:	Published
Schools:	Computer Science & Informatics
Publisher:	IEEE
ISBN:	9798350307191
ISSN:	1550-5499
Date of First Compliant Deposit:	25 September 2023
Date of Acceptance:	14 July 2023
Last Modified:	21 Feb 2024 15:20
URI:	https://orca.cardiff.ac.uk/id/eprint/162705

Actions (repository staff only)

Edit Item