RGBT tracking using randomly projected CNN features. (1st August 2023)

• Record Type: Journal Article
• Authors: Wang, Yong; Wei, Xian; Tang, Xuan; Yu, Keping; Luo, Lingkun
• Is Part Of: Expert systems with applications. Volume 223(2023)
• Publication Date: 2023-08-01
• Subjects: Convolutional neural network -- Random projection -- RGBT tracking; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2023.119865
• Languages: English
• ISSNs: 0957-4174

Abstract

Abstract: Integrating multiple complementary features has been proved to be an effective way for improving tracking results. In this paper, we exploit how to perform robust visual tracking in challenging situations by adaptively integrating information from RGB and thermal videos. Specifically, convolutional neural network (CNN) representation with random projection is proposed to depict RGB and thermal images, respectively. Furthermore, an adaptive fusion strategy based on a period of time is developed. We jointly optimize the reliable weights of different modalities. In addition, we explore the random projection to CNN features. Extensive experiments against other state-of-the-art methods demonstrate the effectiveness of the proposed method. Through analyzing quantitative tracking results, we provide basic insights in RGB and thermal data tracking. Highlights: We exploit the random projection in hierarchical CNN representation for RGBT tracking. We develop an adaptive fusion algorithm to take previous results into consideration. It presents extensive experiments against other state-of-the-art methods with RGBT inputs.