Feature-concatenated transformer for 3D object tracking in point clouds

Shen Qi; Shi Zhiguang; Zhang Yan; Zhang Yong

doi:10.1117/12.2689190

31 July 2023 Feature-concatenated transformer for 3D object tracking in point clouds

Shen Qi, Shi Zhiguang, Zhang Yan, Zhang Yong

Proceedings Volume 12747, Third International Conference on Optics and Image Processing (ICOIP 2023); 127471N (2023) https://doi.org/10.1117/12.2689190
Event: Third International Conference on Optics and Image Processing (ICOIP 2023), 2023, Hangzhou, China

Abstract

Feature fusion is a key problem in 3D object tracking, especially in sparse and disordered point clouds scenes. The purpose of feature fusion is to achieve the communication and integration of template features and search features, so as to obtain the fusion features with object-specific information. However, most pervious Transformer-based methods use the SelfAttention Module(SAM) and Cross-Attention Module(CAM) to conduct attention operations progressively in two steps, which is not conducive to focus on the discriminative features from the beginning. Benefiting from the flexibility of attention operations, we propose a Feature-Concatenated Attention Module (FCAM) for ego-feature enhancement and cross-feature augment at the same time. Based on FCAM, we propose a Feature-Concatenated Transformer (FCT) framework to explore more effective 3D object tracking method. This scheme is more useful to achieve deeper integration and extensive communication between template and search features, which makes feature fusion more efficient. In order to verify the performance of the proposed framework, we carried out experimental verification on KITTI datasets. The results of the experiment indicate that our method is superior to the existing schemes in tracking success and accuracy for different object categories.

Citation Download Citation

Shen Qi, Shi Zhiguang, Zhang Yan, and Zhang Yong "Feature-concatenated transformer for 3D object tracking in point clouds", Proc. SPIE 12747, Third International Conference on Optics and Image Processing (ICOIP 2023), 127471N (31 July 2023); https://doi.org/10.1117/12.2689190

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available