Learning convolutional self-attention module for unmanned aerial vehicle tracking

• Published in: Signal, image and video processing Vol. 17; no. 5; pp. 2323 - 2331
• Main Authors: Wang, Jun, Meng, Chenchen, Deng, Chengzhi, Wang, Yuanyun
• Format: Journal Article
• Language: English
• Published: London Springer London 01.07.2023; Springer Nature B.V
• Subjects: Artificial neural networks; Aspect ratio; Computer Imaging; Computer Science; Context; Image Processing and Computer Vision; Multimedia Information Systems; Optical tracking; Original Paper; Pattern Recognition and Graphics; Signal,Image and Speech Processing; Unmanned aerial vehicles; Vision; Siamese network; Context-related information; Convolutional neural network; Multi-head Self-attention

Siamese network-based trackers have been proven to maintain splendid performance. Recently, visual tracking has been applied in unmanned aerial vehicle(UAV) tasks. However, it is a challenging task because of the influences by aspect ratio changes, out-of-view and scale variation, etc. Some Siamese-...