Fully Convolutional Single-Crop Siamese Networks for Real-Time Visual Object Tracking

Electronics

Dong-Hyun Lee¹ 

[1] Department of IT Convergence Engineering, Kumoh National Institute of Technology, 61 Daehak-ro, Gumi 39177, Gyeongbuk, Korea;

关键词: visual object tracking;    deep learning;    convolutional neural networks;    Siamese networks;   

DOI  :  10.3390/electronics8101084

来源: DOAJ

【 摘 要 】

The visual object tracking problem seeks to track an arbitrary object in a video, and many deep convolutional neural network-based algorithms have achieved significant performance improvements in recent years. However, most of them do not guarantee real-time operation due to the large computation overhead for deep feature extraction. This paper presents a single-crop visual object tracking algorithm based on a fully convolutional Siamese network (SiamFC). The proposed algorithm significantly reduces the computation burden by extracting multiple scale feature maps from a single image crop. Experimental results show that the proposed algorithm demonstrates superior speed performance in comparison with that of SiamFC.

【 授权许可】

Unknown