Unfalsified visual servoing for simultaneous object recognition and pose tracking

Jiang, Ping; Cheng, Yongqiang; Wang, Xiaonian; Feng, Zuren

Abstract

In a complex environment, simultaneous object recognition and tracking has been one of the challenging topics in computer vision and robotics. Current approaches are usually fragile due to spurious feature matching and local convergence for pose determination. Once a failure happens, these approaches lack a mechanism to recover automatically. In this paper, data-driven unfalsified control is proposed for solving this problem in visual servoing. It recognizes a target through matching image features with a 3-D model and then tracks them through dynamic visual servoing. The features can be falsified or unfalsified by a supervisory mechanism according to their tracking performance. Supervisory visual servoing is repeated until a consensus between the model and the selected features is reached, so that model recognition and object tracking are accomplished. Experiments show the effectiveness and robustness of the proposed algorithm to deal with matching and tracking failures caused by various disturbances, such as fast motion, occlusions, and illumination variation.

Citation

Jiang, P., Cheng, Y., Wang, X., & Feng, Z. (2016). Unfalsified visual servoing for simultaneous object recognition and pose tracking. IEEE Transactions on Cybernetics, 46(12), 3032-3046. https://doi.org/10.1109/TCYB.2015.2495157

• Journal Article Type: Article
• Acceptance Date: Oct 10, 2015
• Publication Date: 2016-12
• Deposit Date: Feb 20, 2017
• Publicly Available Date: Feb 20, 2017
• Journal: IEEE transactions on cybernetics
• Print ISSN: 2168-2267
• Electronic ISSN: 2168-2275
• Publisher: Institute of Electrical and Electronics Engineers
• Peer Reviewed: Peer Reviewed
• Volume: 46
• Issue: 12
• Pages: 3032-3046
• DOI: https://doi.org/10.1109/TCYB.2015.2495157
• Keywords: Visual servoing, Visual tracking, Object recognition, Supervisory control, Unfalsified adaptive control
• Public URL: https://hull-repository.worktribe.com/output/448576
• Publisher URL: http://ieeexplore.ieee.org/document/7583713/
• Additional Information: This is a description of an article published in IEEE transactions on cybernetics, 2016, v.46 issue 12.