Point-to-Set Distance Metric Learning on Deep Representations for Visual Tracking

• Published in: IEEE Transactions on Intelligent Transportation Systems
• Main Authors: Zhang, Shengping, Qi, Yuankai, Jiang, Feng, Lan, Xiangyuan, Yuen, Pong C., Zhou, Huiyu
• Format: Article in Journal/Newspaper
• Language: English
• Published: Institute of Electrical and Electronics Engineers (IEEE) 2018
• Subjects: Metric learning; point to set; visual tracking; DML
• Online Access: http://ieeexplore.ieee.org/document/8115211/; http://hdl.handle.net/2381/41049; https://doi.org/10.1109/TITS.2017.2766093

For autonomous driving application, a car shall be able to track objects in the scene in order to estimate where and how they will move such that the tracker embedded in the car can efficiently alert the car for effective collision-avoidance. Traditional discriminative object tracking methods usually train a binary classifier via a support vector machine (SVM) scheme to distinguish the target from its background. Despite demonstrated success, the performance of the SVM-based trackers is limited because the classification is carried out only depending on support vectors (SVs) but the target's dynamic appearance may look similar to the training samples that have not been selected as SVs, especially when the training samples are not linearly classifiable. In such cases, the tracker may drift to the background and fail to track the target eventually. To address this problem, in this paper, we propose to integrate the point-to-set/image-to-imageSet distance metric learning (DML) into visual tracking tasks and take full advantage of all the training samples when determining the best target candidate. The point-to-set DML is conducted on convolutional neural network features of the training data extracted from the starting frames. When a new frame comes, target candidates are first projected to the common subspace using the learned mapping functions, and then the candidate having the minimal distance to the target template sets is selected as the tracking result. Extensive experimental results show that even without model update the proposed method is able to achieve favorable performance on challenging image sequences compared with several state-of-the-art trackers. This work was supported in part by the National Natural Science Foundation of China (Nos. 61300111 and 61672188). H. Zhou is also supported by UK EPSRC under Grants EP/G034303/1, EP/N508664/1 and EP/N011074/1. Peer-reviewed Post-print