Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

MLVSNet: Multi-level Voting Siamese Network for 3D visual tracking

Wang, Zhoutao, Xie, Qian, Lai, Yukun, Wu, Jing, Long, Kun and Wang, Jun 2022. MLVSNet: Multi-level Voting Siamese Network for 3D visual tracking. Presented at: CVF/IEEE International Conference on Computer Vision (ICCV 2021), Montreal, QC, Canada, 10-17 October 2021. 2021 IEEE/CVF International Conference on Computer Vision (ICCV). IEEE, pp. 3081-3090. 10.1109/ICCV48922.2021.00309

[thumbnail of MLVSNet_ICCV2021.pdf] PDF - Accepted Post-Print Version
Download (1MB)

Abstract

Benefiting from the excellent performance of Siamese-based trackers, huge progress on 2D visual tracking has been achieved. However, 3D visual tracking is still under-explored. Inspired by the idea of Hough voting in 3D object detection, in this paper, we propose a Multi-level Voting Siamese Network (MLVSNet) for 3D visual tracking from outdoor point cloud sequences. To deal with sparsity in outdoor 3D point clouds, we propose to perform Hough voting on multi-level features to get more vote centers and retain more useful information, instead of voting only on the fi-nal level feature as in previous methods. We also design an efficient and lightweight Target-Guided Attention (TGA) module to transfer the target information and highlight the target points in the search area. Moreover, we propose a Vote-cluster Feature Enhancement (VFE) module to exploit the relationships between different vote clusters. Extensive experiments on the 3D tracking benchmark of KITTI dataset demonstrate that our MLVSNet outperforms state-of-the-art methods with significant margins. Code will be available at https://github.com/CodeWZT/MLVSNet.

Item Type: Conference or Workshop Item (Paper)
Date Type: Published Online
Status: Published
Schools: Computer Science & Informatics
Publisher: IEEE
ISBN: 9781665428132
Date of First Compliant Deposit: 2 September 2021
Date of Acceptance: 22 July 2021
Last Modified: 08 Apr 2022 12:41
URI: https://orca.cardiff.ac.uk/id/eprint/143846

Actions (repository staff only)

Edit Item Edit Item

Downloads

Downloads per month over past year

View more statistics