1. PG-Net: Pixel to Global Matching Network for Visual Tracking
- Author
-
Chenye Wang, Bingyan Liao, Jun Yin, Wang Yaonong, and Wang Yayun
- Subjects
0209 industrial biotechnology ,Matching (statistics) ,Similarity (geometry) ,Pixel ,Artificial neural network ,Computer science ,business.industry ,02 engineering and technology ,Tracking (particle physics) ,020901 industrial engineering & automation ,Feature (computer vision) ,0202 electrical engineering, electronic engineering, information engineering ,Eye tracking ,020201 artificial intelligence & image processing ,Computer vision ,Artificial intelligence ,business - Abstract
Siamese neural network has been well investigated by tracking frameworks due to its fast speed and high accuracy. However, very few efforts were spent on background-extraction by those approaches. In this paper, a Pixel to Global Matching Network (PG-Net) is proposed to suppress t+he influence of background in search image while achieving state-of-the-art tracking performance. To achieve this purpose, each pixel on search feature is utilized to calculate the similarity with global template feature. This calculation method can appropriately reduce the matching area, thus introducing less background interference. In addition, we propose a new tracking framework to perform correlation-shared tracking and multiple losses for training, which not only reduce the computational burden but also improve the performance. We conduct comparison experiments on various public tracking datasets, which obtains state-of-the-art performance while running with fast speed.
- Published
- 2020