Robust Online Learned Spatio-Temporal Context Model for Visual Tracking

Abstract

Abstract-Visual tracking is an important but challenging problem in the computer vision field. In the real world, the appearances of the target and its surroundings change continuously over space and time, which provides effective information to track the target robustly. However, enough attention has not been paid to the spatio-temporal appearance information in previous works. In this paper, a robust spatio-temporal context model based tracker is presented to complete the tracking task in unconstrained environments. The tracker is constructed with temporal and spatial appearance context models. The temporal appearance context model captures the historical appearance of the target to prevent the tracker from drifting to the background in a long-term tracking. The spatial appearance context model integrates contributors to build a supporting field. The contributors are the patches with the same size of the target at the key-points automatically discovered around the target. The constructed supporting field provides much more information than the appearance of the target itself, and thus, ensures the robustness of the tracker in complex environments. Extensive experiments on various challenging databases validate the superiority of our tracker over other state-of-the-art trackers.

Minimum Barrier Distance-Based Object Descriptor for Visual Tracking

“…In general, the generative models focus on the characterization of the target and ignore the background information; hence, they are prone to drift when the target changes dramatically and often fail in a cluttered background [21]. In contrast, discriminative trackers build a binary classifier, which focuses on differentiating the target from the background [32]. Belonging to discriminative trackers, adaptive tracking-by-detection approaches build a classifier during tracking and update the classifier using generated binary labeled training samples around the current object location [21].…”

Multi-level visual tracking with hierarchical tree structural constraint

“…In [21], a multiple instance learning strategy is adopted to minimize the effects of occlusion by collecting bags of image patches as the training samples. Other methods [34][35][36] exploit the context information to overcome the occlusion problem. However, none of the above trackers consider deformation.…”

Online Visual Tracking Using Temporally Coherent Part Cluster

“…Both Babenko et al [4] and Wen et al [30] present an online method based on multiple instance learning so that the effects of occlusions can be suppressed during the learning process. Others [32,28,29] reduce the occlusion impacts by mining the context information to assist tracking. Compared with the above approaches, our tracker not only can handle severe occlusions but cope well with large structural deformations.…”