Target-Aware Deep Feature Compression for Power Intelligent Inspection Tracking. (21st February 2022)

• Record Type: Journal Article
• Authors: Jiang, Wei; Guo, Zhimin; Zhang, Huanlong; Cheng, Liyun; Tian, Yangyang
• Other Names: Li Yang Academic Editor.
• Is Part Of: Journal of electrical and computer engineering. Volume 2022(2022)
• Publication Date: 2022-02-21
• Subjects: Computer engineering -- Periodicals; Electrical engineering -- Periodicals; 621.3905
• DOI: 10.1155/2022/3161551
• Languages: English
• ISSNs: 2090-0147

Abstract

Abstract : Deep learning has brought revolutionary progress to computer vision, so intelligent inspection equipment based on computer vision has developed rapidly. However, due to the large number of existing deep features, it is difficult to deploy it on mobile devices to achieve real-time tracking speed. This paper presents a target-aware deep feature compression for power intelligent inspection tracking. First, a negative balance loss function is designed to mine channel features suitable for the current inspection scene by shrinking the contribution of pure background negative samples and enhancing the impact of difficult negative samples. Based on this, the deep feature compression model is combined with Siamese tracking framework to achieve real-time and robust tracking. Finally, we evaluate the proposed method on real application scenarios and general data to prove the practicability of the proposed method.