The Unmanned Aerial Vehicle Benchmark: Object Detection, Tracking and Baseline

doi:10.1007/s11263-019-01266-1

CORC > 计算技术研究所 > 中国科学院计算技术研究所 > 中国科学院计算技术研究所期刊论文 > 英文

	The Unmanned Aerial Vehicle Benchmark: Object Detection, Tracking and Baseline
	Yu, Hongyang 2; Li, Guorong 3; Zhang, Weigang 4; Huang, Qingming 2,3,6,7; Du, Dawei 3; Tian, Qi 1; Sebe, Nicu 5
刊名	INTERNATIONAL JOURNAL OF COMPUTER VISION
	2019-12-03
页码	19
关键词	UAV Object detection Single object tracking Multiple object tracking
ISSN号	0920-5691
DOI	10.1007/s11263-019-01266-1
英文摘要	With the increasing popularity of Unmanned Aerial Vehicles (UAVs) in computer vision-related applications, intelligent UAV video analysis has recently attracted the attention of an increasing number of researchers. To facilitate research in the UAV field, this paper presents a UAV dataset with 100 videos featuring approximately 2700 vehicles recorded under unconstrained conditions and 840k manually annotated bounding boxes. These UAV videos were recorded in complex real-world scenarios and pose significant new challenges, such as complex scenes, high density, small objects, and large camera motion, to the existing object detection and tracking methods. These challenges have encouraged us to define a benchmark for three fundamental computer vision tasks, namely, object detection, single object tracking (SOT) and multiple object tracking (MOT), on our UAV dataset. Specifically, our UAV benchmark facilitates evaluation and detailed analysis of state-of-the-art detection and tracking methods on the proposed UAV dataset. Furthermore, we propose a novel approach based on the so-called Context-aware Multi-task Siamese Network (CMSN) model that explores new cues in UAV videos by judging the consistency degree between objects and contexts and that can be used for SOT and MOT. The experimental results demonstrate that our model could make tracking results more robust in both SOT and MOT, showing that the current tracking and detection methods have limitations in dealing with the proposed UAV benchmark and that further research is indeed needed.
资助项目	National Natural Science Foundation of China[61620106009] ; National Natural Science Foundation of China[61836002] ; National Natural Science Foundation of China[U1636214] ; National Natural Science Foundation of China[61931008] ; National Natural Science Foundation of China[61772494] ; National Natural Science Foundation of China[61976069] ; CAS[QYZDJ-SSW-SYS013] ; Italy-China collaboration project TALENT[2018YFE0118400] ; University of Chinese Academy of Sciences ; Youth Innovation Promotion Association CAS ; ARO[W911NF-15-1-0290] ; NEC Laboratory of America ; NEC Laboratory of Blippar
WOS研究方向	Computer Science
语种	英语
出版者	SPRINGER
WOS记录号	WOS:000500723700001
内容类型	期刊论文
源URL	[http://119.78.100.204/handle/2XEOYT63/14940]
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Li, Guorong; Huang, Qingming
作者单位	1.Univ Texas San Antonio, San Antonio, TX USA 2.Harbin Inst Technol, Harbin, Heilongjiang, Peoples R China 3.Univ Chinese Acad Sci, Beijing, Peoples R China 4.Harbin Inst Technol, Weihai, Peoples R China 5.Univ Trento, Trento, Italy 6.Chinese Acad Sci, Key Lab Big Data Min & Knowledge Management, Beijing, Peoples R China 7.Chinese Acad Sci, Inst Comp, Key Lab Intelligent Informat Proc IIP, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Yu, Hongyang,Li, Guorong,Zhang, Weigang,et al. The Unmanned Aerial Vehicle Benchmark: Object Detection, Tracking and Baseline[J]. INTERNATIONAL JOURNAL OF COMPUTER VISION,2019:19.
APA	Yu, Hongyang.,Li, Guorong.,Zhang, Weigang.,Huang, Qingming.,Du, Dawei.,...&Sebe, Nicu.(2019).The Unmanned Aerial Vehicle Benchmark: Object Detection, Tracking and Baseline.INTERNATIONAL JOURNAL OF COMPUTER VISION,19.
MLA	Yu, Hongyang,et al."The Unmanned Aerial Vehicle Benchmark: Object Detection, Tracking and Baseline".INTERNATIONAL JOURNAL OF COMPUTER VISION (2019):19.