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

Abstract

Abstract-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 collisionavoidance. 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-toset/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 favourable performance on challenging image sequences compared to several state-of-the-art trackers.Index Terms-metric learning, point to set, visual tracking.

Deep person re-identification in UAV images

“…Transfer learning [41][42][43] is a common approach to handle lack of training data in a dataset. It is widely believed that networks trained on the ImageNet dataset [44] are able to learn general features from it; then, this network can be fine-tuned on other datasets for a specific task such as face recognition [45,46], classification [47][48][49], detection [50,51], and visual tracking [52][53][54]. Therefore, it makes transfer learning an essential approach, especially for the small datasets.…”

Multistage Analysis of Abnormal Human Behavior in Complex Scenes

“…When the training sample is nonlinear, the tracker will not be able to track the target. To address this problem, Zhang et al [3] proposed a distance-based distance learning method based on deep learning. Experiments have shown that even without model updates, the proposed method achieves favorable performance on challenging images.…”

Online non-negative discriminative dictionary learning for tracking

“…In [31], a variety of usual feature extraction methods were used to combine and form new features by utilizing complementary information between features. In the research [6,7,[32][33][34][35], deep leaning (DL) was used as the extraction method of tracking algorithm and obtained great success. Wang et al [32] proposed the point-to-set distance metric learning which was conducted on convolutional neural network features of the training data extracted from the starting frames.…”

“…In the research [6,7,[32][33][34][35], deep leaning (DL) was used as the extraction method of tracking algorithm and obtained great success. Wang et al [32] proposed the point-to-set distance metric learning which was conducted on convolutional neural network features of the training data extracted from the starting frames. Lei Qu et al [36] integrated fast histogram of oriented gradient (FHOG) and discriminative color descriptors (DD) to further boost the tracking performance.…”