A Real-Time Target-Tracking Algorithm Based on Improved SiamFC

Hongying, 张红颖 Zhang; Pengyi, 贺鹏艺 He; Huisan, 王汇三 Wang

doi:10.3788/lop202158.0615003

Cited by 2 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Experimental results show that the proposed target tracking algorithm has achieved good tracking results in various tracking scenarios [5]. Hongying Zhang proposed a real-time target tracking algorithm based on improved SiamFC, replacing the second layer of convolution in the original network structure with deep separable convolution, which improves the tracking speed and network recognition ability by reducing the amount of parameter calculation [6]. Junsong Zheng proposed a spatiotemporal continuous multi-feature fusion twin network algorithm, designed a robust feature that combines spatial information and semantic information from coarse to fine to express fast moving weak targets, and added feature attention mechanism.…”

Section: Related Workmentioning

confidence: 99%

Research on Dynamic Recognition and Tracking Technology for Complex Scenes of Automatic Driving

Zhang¹,

Zhang²,

Zhao³

2023

Journal of Computers

View full text Add to dashboard Cite

<p>With the development of automobile technology, intelligent vehicle and automatic driving technology will make due contributions to reducing traffic accidents. This paper aims to improve the dynamic identification and tracking technology in the current intelligent vehicle and automatic driving. First, it is improved based on the MobileNet V2 backbone network, and then a new tracking model framework is designed combining with the SiamRPN single target tracker. Secondly, it integrates space-time tracking clues to improve the stability and robustness of the algorithm. Finally, it constructs a pedestrian dynamic identification algorithm based on the dynamic pedestrian factors in the driving process. Through the training of data sets and video tracking experiments, the performance of the algorithm in this paper is proved quantitatively and qualitatively.</p> <p> </p>

show abstract

Section: Related Workmentioning

confidence: 99%