Fuzzy-aided solution for out-of-view challenge in visual tracking under IoT-assisted complex environment

• Published in: Neural computing & applications Vol. 33; no. 4; pp. 1055 - 1065
• Main Authors: Liu, Shuai, Liu, Xinyu, Wang, Shuai, Muhammad, Khan
• Format: Journal Article
• Language: English
• Published: London Springer London 01.02.2021; Springer Nature B.V
• Subjects: Artificial Intelligence; Computational Biology/Bioinformatics; Computational Science and Engineering; Computer Science; Computer vision; Data Mining and Knowledge Discovery; Image Processing and Computer Vision; Internet of Things; Optical tracking; Original Article; Probability and Statistics in Computer Science; Target detection; Tracking; Internet of things; Visual tracking; Out of view; Complex environment; Fuzzy aided; Template update
• ISSN: 0941-0643; 1433-3058
• DOI: 10.1007/s00521-020-05021-3

With the rapid development in computer vision domain, research on object tracking has directed more attention by scholars. Out of view (OV) is an important challenge often encountered in the tracking process of objects, especially in Internet of Things surveillance. Therefore, this paper proposes a fuzzy-aided solution for OV challenge. This solution uses a fuzzy-aided system to detect whether the target is poorly tracked by using the response matrix of samples. When poor tracking occurs, the target is relocated according to the stored template. The proposed solution is tested on OTB100 dataset, where the experimental results show that the auxiliary solution is effective for the OV challenge. The proposed solution also ensures the tracking speed and overall success rate of visual tracking as well as improves the robustness to a certain extent for IoT-assisted complex environment.