CU-DETR: a monocular 3D detection enhanced by local-global feature fusion and position embedding perturbation

Xi Li; Kun Ren; Tianyang Zhang; Yongping Du; Honggui Han

doi:10.1117/12.3036911

22 November 2024 CU-DETR: a monocular 3D detection enhanced by local-global feature fusion and position embedding perturbation

Xi Li, Kun Ren, Tianyang Zhang, Yongping Du, Honggui Han

Author Affiliations +

Proceedings Volume 13239, Optoelectronic Imaging and Multimedia Technology XI; 132391L (2024) https://doi.org/10.1117/12.3036911
Event: SPIE/COS Photonics Asia, 2024, Nantong, Jiangsu, China

Conference Poster

Abstract

The monocular 3D object detection methods based on Transformer have recently progressed significantly. However, most existing methods struggle to effectively handle fine-grained objects and complex scenes, particularly when capturing the features of occluded or small objects. To tackle these issues, we propose a monocular 3D object detector, CU-DETR, based on the MonoDETR framework. CU-DETR introduces the local-global fusion encoder to enhance local feature extraction and fusion and applies an uncertainty perturbation strategy in position encoding to enhance the model’s performance in handling complex scenes. Experimental results on the KITTI public dataset demonstrate that CU-DETR outperforms the MonoDETR.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Xi Li, Kun Ren, Tianyang Zhang, Yongping Du, and Honggui Han "CU-DETR: a monocular 3D detection enhanced by local-global feature fusion and position embedding perturbation", Proc. SPIE 13239, Optoelectronic Imaging and Multimedia Technology XI, 132391L (22 November 2024); https://doi.org/10.1117/12.3036911

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