模式识别与人工智能
Saturday, May. 3, 2025 Home      About Journal      Editorial Board      Instructions      Ethics Statement      Contact Us                   中文
  2020, Vol. 33 Issue (12): 1104-1114    DOI: 10.16451/j.cnki.issn1003-6059.202012005
Structural Learning Representation and Its Applications in Object Detection and Recognition Current Issue| Next Issue| Archive| Adv Search |
Object Detection in Degraded Thermal Image Based on Feature Alignment and Assisted Excitation of Key Points
LIU Sheng1, JIN Kun1, WANG Jun1, YE Huanran1, CHENG Haohao1
1. College of Computer Science and Technology,Zhejiang University of Technology,Hangzhou 310014

Download: PDF (2169 KB)   HTML (1 KB) 
Export: BibTeX | EndNote (RIS)      
Abstract  

In the object detection of thermal images,the image degradation phenomena,like the simple texture and the blurred object boundary,result in difficulties in localizing objects and matching the objects with the predefined anchor boxes.Therefore,an object detection algorithm for degraded thermal image based on feature alignment and assisted excitation of key points is proposed.Firstly,the visible image branch is introduced,and the similarity between the thermal domain and the visible domain is improved by calculating the feature difference of specified layers in two branches.Then,feature map concatenation and detection scale are modified to enrich the details of objects in the high-level network layers.Finally,an anchor-free detector with assisted excitation of key points is deployed,and thus the model localizes objects better and learn the instances poorly covered by the predefined anchor boxes.Comparative experiments on two datasets show that the proposed algorithm localizes thermal objects accurately and improves the accuracy of object detection in degraded thermal image effectively.

Key wordsThermal Image      Object Detection      Feature Alignment      Assisted Excitation of Key Points     
Received: 10 September 2020     
Fund:

National Key Research and Development Program of China(No.2018YFB1305200),Program of Zhejiang Provincial Department of Science and Technology(No.LGG19F020010)

Corresponding Authors: LIU Sheng,Ph.D.,associate professor.His research Interests include computer vision and digital image processing.   
About author:: JIN Kun,master student.His research interests include computer vision and object detection;WANG Jun,Ph.D.candidate.His research interests include computer vision and object tracking;YE Huanran,master student.His research interests include computer vision and semantic segmentation;CHENG Haohao,master student.His research interests include computer vision and human pose estimation.
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
LIU Sheng
JIN Kun
WANG Jun
YE Huanran
CHENG Haohao
Cite this article:   
LIU Sheng,JIN Kun,WANG Jun等. Object Detection in Degraded Thermal Image Based on Feature Alignment and Assisted Excitation of Key Points[J]. , 2020, 33(12): 1104-1114.
URL:  
http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.202012005      OR     http://manu46.magtech.com.cn/Jweb_prai/EN/Y2020/V33/I12/1104
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