Cross-modal deformable DETR for RGB-D object detection

Siyuan Qin; Zongqing Lu; An Wang; Nan Su

doi:10.1117/12.2682571

26 May 2023 Cross-modal deformable DETR for RGB-D object detection

Siyuan Qin, Zongqing Lu, An Wang, Nan Su

Proceedings Volume 12700, International Conference on Electronic Information Engineering and Data Processing (EIEDP 2023); 1270010 (2023) https://doi.org/10.1117/12.2682571
Event: International Conference on Electronic Information Engineering and Data Processing (EIEDP 2023), 2023, Nanchang, China

Abstract

RGB-D object detection is a challenging task due to the demand of effectively processing of visible modality and depth modality features. However, pre-existing RGB-D object detection models have several deficiencies, including demand for hand-crafted settings, and insufficient ability of fusing cross-modal features. In this paper, we propose a novel Cross-modal RGB-D object detection model, based on Deformable DETR, named as CM-DETR. Our proposed model can effectively fuse multi-modal information, and don’t need hand-crafted settings resulted from prior information. Extensive experiments show that our model has achieved extraordinary improvement, which exceeds the baseline by more than 4.6% mAP on SUN-RGBD and 6.9% mAP on NYUDv2.

Citation Download Citation

Siyuan Qin, Zongqing Lu, An Wang, and Nan Su "Cross-modal deformable DETR for RGB-D object detection", Proc. SPIE 12700, International Conference on Electronic Information Engineering and Data Processing (EIEDP 2023), 1270010 (26 May 2023); https://doi.org/10.1117/12.2682571

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