模式识别与人工智能
Thursday, Apr. 3, 2025 Home      About Journal      Editorial Board      Instructions      Ethics Statement      Contact Us                   中文
Pattern Recognition and Artificial Intelligence  2024, Vol. 37 Issue (8): 663-677    DOI: 10.16451/j.cnki.issn1003-6059.202408001
Detection and Recognition Algorithms in Realistic Scene Current Issue| Next Issue| Archive| Adv Search |
Window Anchored Offset Constrained Dynamic Snake Convolutional Network for Aerial Small Target Detection
ZHANG Rongguo1, QIN Zhen1, HU Jing1, WANG Lifang1, LIU Xiaojun2
1. College of Computer Science and Technology, Taiyuan University of Science and Technology, Taiyuan 030024;
2. School of Mechanical Engineering, Hefei University of Technology, Hefei 230009

Download: PDF (6317 KB)   HTML (1 KB) 
Export: BibTeX | EndNote (RIS)      
Abstract  To obtain the key and effective information from limited features of small targets and improve the localization ability and detection accuracy of small targets, a window anchored offset constrained dynamic snake convolutional network for aerial small target detection is proposed. Firstly, the offset constrained dynamic snake convolution is constructed. By dynamical offsetting in different directions, the constrained snake convolution kernel adaptively focuses on feature regions of different sizes and shapes, making feature extraction concentrate on tiny local structures and thereby facilitating the capture of small target features. Secondly, by employing two-stage multi-scale feature fusion method, feature alignment fusion and injection are performed on different layer-order feature maps to enhance the fusion of the underlying detail information and the high-level semantic information, and strengthen the transmission of target information of different sizes. Thus, the detection capability of the method for small targets is improved. Meanwhile, the window anchored bounding box regression loss function is designed. The function performs the bounding regression based on the auxiliary bounding box and the minimum point distance to achieve more accurate regression results and enhance the small target localization capability of the model. Finally, comparative experiments on three aerial photography datasets show that the proposed method makes the improvements with different degrees in small target detection performance.
Key wordsSmall Object Detection      Feature Extraction      Feature Fusion      Multi-scale Features      Bounding Box Regression Loss Function     
Received: 07 April 2024     
ZTFLH: TP391.41  
Fund:National Natural Science Foundation of China(No.52375178), Natural Science Foundation of Shanxi Province(No.202203021211206,202203021211189), Program of Shanxi Provincial Education Department(No.2022YJJG192), Graduate Innovation Program of Taiyuan University of Science and Technology(No.SY2023039)
Corresponding Authors: ZHANG Rongguo, Ph.D., professor. His research interests include image processing, computer vision and pattern recognition.   
About author:: QIN Zhen, Master student. His research interests include image processing and computer vision. HU Jing, Ph.D., professor. Her research interests include image processing and pattern recognition. WANG Lifang, Ph.D., associate profe-ssor. Her research interests include image processing and computer vision. LIU Xiaojun, Ph.D., professor. Her research interests include modern design theory and method, and pattern recognition.
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
ZHANG Rongguo
QIN Zhen
HU Jing
WANG Lifang
LIU Xiaojun
Cite this article:   
ZHANG Rongguo,QIN Zhen,HU Jing等. Window Anchored Offset Constrained Dynamic Snake Convolutional Network for Aerial Small Target Detection[J]. Pattern Recognition and Artificial Intelligence, 2024, 37(8): 663-677.
URL:  
http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.202408001      OR     http://manu46.magtech.com.cn/Jweb_prai/EN/Y2024/V37/I8/663
Copyright © 2010 Editorial Office of Pattern Recognition and Artificial Intelligence
Address: No.350 Shushanhu Road, Hefei, Anhui Province, P.R. China Tel: 0551-65591176 Fax:0551-65591176 Email: bjb@iim.ac.cn
Supported by Beijing Magtech  Email:support@magtech.com.cn