Visual tracking using locality‐constrained linear coding under a particle filtering framework

Abstract

Visual target tracking has long been a challenging problem because of the variable appearance of the target with changing spatiotemporal factors. Therefore, it is important to design an effective and efficient appearance model for tracking tasks. This study proposes a tracking algorithm based on locality-constrained linear coding (LLC) under a particle filtering framework. A local feature descriptor is presented that can evenly represent the local information of each patch in the tracking region. LLC uses the locality constraints to project each local feature descriptor into its local-coordinate system. Compared with sparse coding, LLC can be performed very quickly for appearance modelling because it has an analytical solution derived by a three-step matrix calculation, and the computational complexity of the proposed tracking algorithm is o(η × m × n). Both quantitative and qualitative experimental results demonstrate that the authors' proposed algorithm performs favourably against the 10 state-of-the-art trackers on 12 challenging test sequences. However, related experimental results show that the performance of their tracker is not effective enough for small tracking targets owing to a lack of sufficient local region information.

Visual Tracking With Online Assessment and Improved Sampling Strategy

“…As a representative of random sampling, particle sampling is based on Monte Carlo methodology. Since both the computational burden and tracking accuracy are proportional to the particle number, real-time performance is always a huge challenge for particle filter-based trackers [22], [23]. In tracking tasks, dense sampling is to collect all the subwindows with a certain step size in the target's neighborhood.…”

Learning Compact Target-Oriented Feature Representations for Visual Tracking

“…A biologically inspired method is proposed by Zhang et al [48] to model the target appearance via a coding layer, and tracking is carried out in a particle filter framework. With the same tracking framework, other coding algorithms are employed to design effective trackers, such as locality-constrained linear coding [12] and sparse and local linear coding [42]. Different from them, we jointly learn the feature code and the correlation filter in a unified optimization framework so as to yield a more compact, discriminative and target-oriented feature representation.…”