中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 视频内容安全团队
Tiny drone object detection in videos guided by the bio-inspired magnocellular computation model

文献类型：期刊论文

作者Wang, Gang1,2; Yang, Xin1; Li, Liang1; Gao, Kai1; Gao, Jin3; Zhang, Jia-yi4; Xing, Da-jun5,6; Wang, Yi-zheng1
刊名APPLIED SOFT COMPUTING
出版日期2024-09-01
卷号163页码:13
关键词Retinal magnocellular pathway Video object detection Tiny drone detection Deep convolutional networks Visual motion information
ISSN号1568-4946
DOI10.1016/j.asoc.2024.111892
通讯作者Wang, Gang(g_wang@foxmail.com)
英文摘要Detecting drones in infrared videos is highly desired in many realistic scenarios, e.g. , unauthorized drone monitoring around airports. Nevertheless, automated drone detection is rather challenging when the targets appear as tiny objects ( <= 10 x 10 pixels) against complex backgrounds. Conventional object detection algorithms, which mainly use static visual features, can hardly distinguish tiny objects from undesired artefacts in complex backgrounds. To alleviate this problem, we learn from the early biological visual pathway (including the parvocellular and magnocellular pathways), which process static and motion information simultaneously. Therefore, we propose a magnocellular inspired method for video tiny -object detection (Magno-VTOD) that integrates both static and motion visual information. The Magno-VTOD firstly employs a retinal magnocellular computation model to extract the motion strength of moving objects. The motion responses are then used to enhance the areas of the flying tiny drones effectively and efficiently, thereby facilitating the subsequent target detection procedure. We implement the video tiny -object detection method based on the widely adopted deep neural networks guided by the magnocellular computation model. Experimental results obtained on the large-scale Anti-UAV dataset (304451 video frames) validate that the proposed Magno-VTOD method significantly outperforms the competing state-of-the-art object detection methods on the tiny drone detection task. Particularly, the AP value is increased by 15.4% for tiny object detection, and by 17.1%/13.7% against wood/mountain backgrounds.
WOS关键词RETINA ; CONTRAST ; IMAGE
资助项目National Natural Science Foundation of China[62102443] ; Beijing Municipal Natural Science Foundation, China[4214060] ; Beijing Nova Program, China[2022038]
WOS研究方向Computer Science
语种英语
WOS记录号WOS:001264451100001
出版者ELSEVIER
资助机构National Natural Science Foundation of China ; Beijing Municipal Natural Science Foundation, China ; Beijing Nova Program, China
源URL[http://ir.ia.ac.cn/handle/173211/59210]  
专题自动化研究所_模式识别国家重点实验室_视频内容安全团队
通讯作者Wang, Gang
作者单位1.Beijing Inst Basic Med Sci, Beijing 100850, Peoples R China
2.Chinese Inst Brain Res CIBR, Beijing 100010, Peoples R China
3.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
4.Fudan Univ, MOE Frontiers Ctr Brain Sci, Inst Brain Sci, State Key Lab Med Neurobiol, Shanghai 200032, Peoples R China
5.Beijing Normal Univ, State Key Lab Cognit Neurosci & Learning, Beijing 100875, Peoples R China
6.Beijing Normal Univ, IDG McGovern Inst Brain Res, Beijing 100875, Peoples R China
推荐引用方式
GB/T 7714		 Wang, Gang,Yang, Xin,Li, Liang,et al. Tiny drone object detection in videos guided by the bio-inspired magnocellular computation model[J]. APPLIED SOFT COMPUTING,2024,163:13.
APA Wang, Gang.,Yang, Xin.,Li, Liang.,Gao, Kai.,Gao, Jin.,...&Wang, Yi-zheng.(2024).Tiny drone object detection in videos guided by the bio-inspired magnocellular computation model.APPLIED SOFT COMPUTING,163,13.
MLA Wang, Gang,et al."Tiny drone object detection in videos guided by the bio-inspired magnocellular computation model".APPLIED SOFT COMPUTING 163(2024):13.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。