SIA OpenIR  > 光电信息技术研究室
DAGN: A Real-Time UAV Remote Sensing Image Vehicle Detection Framework
Zhang ZY(张钟毓)1,2,3,4,5; Liu YP(刘云鹏)1,2,4,5; Liu TC(刘天赐)1,2,3,4,5; Lin ZY(林智远)1,2,3,4,5; Wang SK(王思奎)1,2,3,4,5
Department光电信息技术研究室
Source PublicationIEEE Geoscience and Remote Sensing Letters
ISSN1545-598X
2020
Volume17Issue:11Pages:1884-1888
Indexed BySCI ; EI
EI Accession number20204609480754
WOS IDWOS:000583714200009
Contribution Rank1
KeywordAttention block candidate merging algorithm depthwise-separable convolution small vehicle detection
Abstract

Real-time small object detection from the remote sensing images taken by unmanned aerial vehicles (UAVs) is a challenging but fundamental problem for many UAV applications because of the complex scales, densities, and shapes of objects that are the result of the shooting angle of the UAV. In this letter, we focus on real-time small vehicle detection for UAV remote sensing images and propose a depthwise-separable attention-guided network (DAGN) based on YOLOv3. First, we combine the feature concatenation and attention block to provide the model with the excellent ability to distinguish important and inconsequential features. Then, we improve the loss function and candidate merging algorithm in YOLOv3. Through these strategies, the performance of vehicle detection is improved, while some detection speed is sacrificed. To accelerate our model, we replace some standard convolutions with depthwise-separable convolutions. Compared to YOLOv3 and other two-stage state-of-the-art models that are applied to Vehicle Detection in Aerial Imagery (VEDAI) data sets, DAGN has a detection accuracy of 0.671, which is 5.5% better than that of YOLOv3, and it achieves the same results as two-stage methods. In addition, DAGN achieves real-time detection using GeForce GTX 1080Ti.

Language英语
WOS SubjectGeochemistry & Geophysics ; Engineering, Electrical & Electronic ; Remote Sensing ; Imaging Science & Photographic Technology
WOS KeywordFEATURES
WOS Research AreaGeochemistry & Geophysics ; Engineering ; Remote Sensing ; Imaging Science & Photographic Technology
Citation statistics
Cited Times:4[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.sia.cn/handle/173321/27906
Collection光电信息技术研究室
Corresponding AuthorZhang ZY(张钟毓)
Affiliation1.Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China
2.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang 110016, China
3.University of Chinese Academy of Sciences, Beijing 100049, China
4.Key Laboratory of Opto-Electronic Information Processing, Chinese Academy of Sciences, Shenyang 110016, China
5.Key Laboratory of Image Understanding and Computer Vision, Shenyang 110016, China
Recommended Citation
GB/T 7714
Zhang ZY,Liu YP,Liu TC,et al. DAGN: A Real-Time UAV Remote Sensing Image Vehicle Detection Framework[J]. IEEE Geoscience and Remote Sensing Letters,2020,17(11):1884-1888.
APA Zhang ZY,Liu YP,Liu TC,Lin ZY,&Wang SK.(2020).DAGN: A Real-Time UAV Remote Sensing Image Vehicle Detection Framework.IEEE Geoscience and Remote Sensing Letters,17(11),1884-1888.
MLA Zhang ZY,et al."DAGN: A Real-Time UAV Remote Sensing Image Vehicle Detection Framework".IEEE Geoscience and Remote Sensing Letters 17.11(2020):1884-1888.
Files in This Item:
File Name/Size DocType Version Access License
DAGN_ A Real-Time UA(1516KB)期刊论文出版稿开放获取CC BY-NC-SAView Application Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhang ZY(张钟毓)]'s Articles
[Liu YP(刘云鹏)]'s Articles
[Liu TC(刘天赐)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhang ZY(张钟毓)]'s Articles
[Liu YP(刘云鹏)]'s Articles
[Liu TC(刘天赐)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhang ZY(张钟毓)]'s Articles
[Liu YP(刘云鹏)]'s Articles
[Liu TC(刘天赐)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: DAGN_ A Real-Time UAV Remote Sensing Image Vehicle Detection Framework.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.