Adaptive Correlation Model for Visual Tracking Using Keypoints Matching and Deep Convolutional Feature.

Although correlation filter (CF)-based visual tracking algorithms have achieved appealing results, there are still some problems to be solved. When the target object goes through long-term occlusions or scale variation, the correlation model used in existing CF-based algorithms will inevitably learn some non-target information or partial-target information. In order to avoid model contamination and enhance the adaptability of model updating, we introduce the keypoints matching strategy and adjust the model learning rate dynamically according to the matching score. Moreover, the proposed approach extracts convolutional features from a deep convolutional neural network (DCNN) to accurately estimate the position and scale of the target. Experimental results demonstrate that the proposed tracker has achieved satisfactory performance in a wide range of challenging tracking scenarios.

Consistently Sampled Correlation Filters with Space Anisotropic Regularization for Visual Tracking.

Most existing correlation filter-based tracking algorithms, which use fixed patches and cyclic shifts as training and detection measures, assume that the training samples are reliable and ignore the inconsistencies between training samples and detection samples. We propose to construct and study a consistently sampled correlation filter with space anisotropic regularization (CSSAR) to solve these two problems simultaneously. Our approach constructs a spatiotemporally consistent sample strategy to alleviate the redundancies in training samples caused by the cyclical shifts, eliminate the inconsistencies between training samples and detection samples, and introduce space anisotropic regularization to constrain the correlation filter for alleviating drift caused by occlusion. Moreover, an optimization strategy based on the Gauss-Seidel method was developed for obtaining robust and efficient online learning. Both qualitative and quantitative evaluations demonstrate that our tracker outperforms state-of-the-art trackers in object tracking benchmarks (OTBs).

Alleviate Similar Object in Visual Tracking via Online Learning Interference-Target Spatial Structure.

Correlation Filter (CF) based trackers have demonstrated superior performance to many complex scenes in smart and autonomous systems, but similar object interference is still a challenge. When the target is occluded by a similar object, they not only have similar appearance feature but also are in same surrounding context. Existing CF tracking models only consider the target's appearance information and its surrounding context, and have insufficient discrimination to address the problem. We propose an approach that integrates interference-target spatial structure (ITSS) constraints into existing CF model to alleviate similar object interference. Our approach manages a dynamic graph of ITSS online, and jointly learns the target appearance model, similar object appearance model and the spatial structure between them to improve the discrimination between the target and a similar object. Experimental results on large benchmark datasets OTB-2013 and OTB-2015 show that the proposed approach achieves state-of-the-art performance.

Multi-View Structural Local Subspace Tracking.

In this paper, we propose a multi-view structural local subspace tracking algorithm based on sparse representation. We approximate the optimal state from three views: (1) the template view; (2) the PCA (principal component analysis) basis view; and (3) the target candidate view. Then we propose a unified objective function to integrate these three view problems together. The proposed model not only exploits the intrinsic relationship among target candidates and their local patches, but also takes advantages of both sparse representation and incremental subspace learning. The optimization problem can be well solved by the customized APG (accelerated proximal gradient) methods together with an iteration manner. Then, we propose an alignment-weighting average method to obtain the optimal state of the target. Furthermore, an occlusion detection strategy is proposed to accurately update the model. Both qualitative and quantitative evaluations demonstrate that our tracker outperforms the state-of-the-art trackers in a wide range of tracking scenarios.