Single and Multiple Object Tracking Using a Multi-Feature Joint Sparse Representation

Abstract

Abstract:In this paper, we propose a tracking algorithm based on a multi-feature joint sparse representation.The templates for the sparse representation can include pixel values, textures, and edges. In the multi-feature joint optimization, noise or occlusion is dealt with using a set of trivial templates. A sparse weight constraint is introduced to dynamically select the relevant templates from the full set of templates. A variance ratio measure is adopted to adaptively adjust the weights of different features. The multi-feature template set is updated adaptively. We further propose an algorithm for tracking multi-objects with occlusion handling based on the multi-feature joint sparse reconstruction. The observation model based on sparse reconstruction automatically focuses on the visible parts of an occluded object by using the information in the trivial templates. The multi-object tracking is simplified into a joint Bayesian inference. The experimental results show the superiority of our algorithm over several state-of-the-art tracking algorithms.

Object Tracking by a Combination of Discriminative Global and Generative Multi-Scale Local Models

“…The threshold 0  in Equation (8) is 0.04. The parameters 0 , 1 and 2 in Equation (14) are set to 0.8, 0.85 and 0.95.…”

“…The work in [13] presented a tracking algorithm based on the two-view sparse representation, where the tracked objects are sparsely represented by both templates and candidate samples in the current frame. To encode more information, Hu et al [14] proposed a multi-feature joint sparse representation for object tracking. In discriminative methods, the tracking is treated as a binary classification problem aiming to find a decision boundary that can best separate the target from the background.…”

“…frame. To encode more information, Hu et al [14] proposed a multi-feature joint sparse representation for object tracking. In discriminative methods, the tracking is treated as a binary classification problem aiming to find a decision boundary that can best separate the target from the background.…”

Online Salient Object Segmentation with Local Weight Assignment

“…This enables the common Euclidean operations of covariance matrices in the logarithmic domain while preserving their geometric structure. 3 (2) The dimension of L2ECM feature vector is only related with the dimension of raw feature vectors regardless of the size and shape of estimated region such as super-pixel, which implies a certain scale and rotation invariance over the regions in different images. This kind of feature is better applicable to region-based algorithm than features that other region-based video segmentation methods used.…”

“…For example, [2] proposed a Fisher linear discriminant to measure the discriminate performance of each feature map. In [3], a variance ratio measurement is adopted to adaptively adjust the weights of different features. [4] measures the discriminate power by computing the KL distance of histogram.…”