Object detection algorithm based on mixed dilated convolution pyramid

Tingjian Yu; Zemin Yuan; Tao Huang; Xiang Fu

doi:10.1117/12.2684527

1 August 2023 Object detection algorithm based on mixed dilated convolution pyramid

Tingjian Yu, Zemin Yuan, Tao Huang, Xiang Fu

Proceedings Volume 12754, Third International Conference on Computer Vision and Pattern Analysis (ICCPA 2023); 127542F (2023) https://doi.org/10.1117/12.2684527
Event: 2023 3rd International Conference on Computer Vision and Pattern Analysis (ICCPA 2023), 2023, Hangzhou, China

Abstract

To address the problem that FPN in the one-stage object detection algorithm loses a large amount of semantic information after upsampling and downsampling fusion, leading to difficulties in detecting small objects in dense scenes. This paper proposes a new FPN structure, Residual dilated FPN (RdFPN), compared to the traditional FPN, which uses multiple Dilated Block instead of the standard convolution in the FPN horizontal structure to mix the receptive fields of different layers in the feature map and expand the object size range of the feature map, while improving the network's ability to extract features at different scales. Experimental results show that RdFPN improves the mAP of the one-stage object detection algorithms RetinaNet, FCOS, and GFL by 0.9%, 0.7%, and 0.8% on the MS COCO dataset, enough to improve the overall performance of the detector.

Citation Download Citation

Tingjian Yu, Zemin Yuan, Tao Huang, and Xiang Fu "Object detection algorithm based on mixed dilated convolution pyramid", Proc. SPIE 12754, Third International Conference on Computer Vision and Pattern Analysis (ICCPA 2023), 127542F (1 August 2023); https://doi.org/10.1117/12.2684527

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

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
5 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Object detection

Convolution

Detection and tracking algorithms

Feature fusion

Image fusion

Deep learning

Image processing

Keywords/Phrases

Search In:

Publication Years