Real-Time visual tracking based on convolutional neural networks

doi:10.1088/1742-6596/1601/3/032053

	Real-Time visual tracking based on convolutional neural networks
	Li, Rui 1; Lian, Jirong 2
	2020-08-17
会议日期	June 19, 2020 - June 21, 2020
会议地点	Jinan, Virtual, China
关键词	Convolutional neural networks Network architectureFrames per seconds Loss functions Selection mechanism Space and time Tracking models Tracking speed Tracking strategies Visual Tracking
卷号	1601
期号	3
DOI	10.1088/1742-6596/1601/3/032053
英文摘要	Traditional target tracking is based on target detection. When the target changes significantly, such as occlusion, scale change, the update of the tracking model will waste a lot of space and time resources, resulting in a very slow tracking speed, which cannot meet the actual engineering needs. In view of the above situation, an end-To-end tracking strategy is proposed, which is simpler and faster than the existing technology. The proposed tracker only needs to detect the first frame image and use it as the input of the model, and set the multi-Task loss function to predict the position of the next frame of the target and the size of the bounding box. This paper constructs a lightweight network architecture with an additional selection mechanism to avoid wasting resources for global search and matching. Through experiments, good results can be achieved on the standard data set, and tracking speeds close to one hundred frames per second are achieved, which is very competitive with existing advanced trackers. © Published under licence by IOP Publishing Ltd.
会议录	Journal of Physics: Conference Series
会议录出版者	IOP Publishing Ltd
语种	英语
ISSN号	17426588
内容类型	会议论文
源URL	[http://ir.lut.edu.cn/handle/2XXMBERH/132618]
专题	计算机与通信学院
作者单位	1.College of Computer and Communication, Lanzhou University of Technology, Lanzhou; 730050, China; 2.College of Computer and Communication, Lanzhou University of Technology, Lanzhou; 730050, China
推荐引用方式 GB/T 7714	Li, Rui,Lian, Jirong. Real-Time visual tracking based on convolutional neural networks[C]. 见:. Jinan, Virtual, China. June 19, 2020 - June 21, 2020.