Litcius/Paper detail

Learning Deep Lucas-Kanade Siamese Network for Visual Tracking

Siyuan Yao, Xiaoguang Han, Hua Zhang, Xiao Wang, Xiaochun Cao

2021IEEE Transactions on Image Processing43 citationsDOI

Abstract

In most recent years, Siamese trackers have drawn great attention because of their well-balanced accuracy and efficiency. Although these approaches have achieved great success, the discriminative power of the conventional Siamese trackers is still limited by the insufficient template-candidate representation. Most of the existing approaches take non-aligned features to learn a similarity function for template-candidate matching, while the target object's geometrical transformation is seldom explored. To address this problem, we propose a novel Siamese tracking framework, which enables to dynamically transform the template-candidate features to a more discriminative viewpoint for similarity matching. Specifically, we reformulate the template-candidate matching problem of the conventional Siamese tracker from the perspective of Lucas-Kanade (LK) image alignment approach. A Lucas-Kanade network (LKNet) is proposed and incorporated to the Siamese architecture to learn aligned feature representations in data-driven trainable manner, which is able to enhance the model adaptability in challenging scenarios. Within this framework, we propose two Siamese trackers named LK-Siam and LK-SiamRPN to validate the effectiveness. Extensive experiments conducted on the prevalent datasets show that the proposed method is more competitive over a number of state-of-the-art methods.

Topics & Concepts

Discriminative modelBitTorrent trackerArtificial intelligenceComputer sciencePattern recognition (psychology)Matching (statistics)Feature (linguistics)Eye trackingTransformation (genetics)Computer visionRepresentation (politics)MathematicsPolitical sciencePhilosophyLawChemistryPoliticsBiochemistryGeneLinguisticsStatisticsVideo Surveillance and Tracking MethodsHuman Pose and Action RecognitionAdvanced Image and Video Retrieval Techniques
Learning Deep Lucas-Kanade Siamese Network for Visual Tracking | Litcius