Robust visual tracking via patch descriptor and structural local sparse representation

DOI10.3390/A11080126MaRDI QIDQ2331655zbMATH OpenOpenAlexWikidataFDO

Authors Zhiguo Song, Jifeng Sun, Jialin Yu, Shengqing Liu

Publication date 30 October 2019

Published in Algorithms (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.3390/a11080126

zbMATH Keywords

outlier-aware template update schemepatch descriptorstructural local sparse representationvisual tracking

Mathematics Subject Classification ID

Machine vision and scene understanding (68T45) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08)

Review text

Summary: Appearance models play an important role in visual tracking. Effective modeling of the appearance of tracked objects is still a challenging problem because of object appearance changes caused by factors, such as partial occlusion, illumination variation and deformation, etc. In this paper, we propose a tracking method based on the patch descriptor and the structural local sparse representation. In our method, the object is firstly divided into multiple non-overlapped patches, and the patch sparse coefficients are obtained by structural local sparse representation. Secondly, each patch is further decomposed into several sub-patches. The patch descriptors are defined as the proportion of sub-patches, of which the reconstruction error is less than the given threshold. Finally, the appearance of an object is modeled by the patch descriptors and the patch sparse coefficients. Furthermore, in order to adapt to appearance changes of an object and alleviate the model drift, an outlier-aware template update scheme is introduced. Experimental results on a large benchmark dataset demonstrate the effectiveness of the proposed method.

Recommendations

• Robust visual tracking with structured sparse representation appearance model
• Robust tracking via locally structured representation
• Robust visual tracking using information theoretical learning
• Robust visual tracking via consistent low-rank sparse learning
• Research of sparse representation-based visual object tracking: a survey

Cites work

• Learning Common and Feature-Specific Patterns: A Novel Multiple-Sparse-Representation-Based Tracker
• Occlusion-Aware Fragment-Based Tracking With Spatial-Temporal Consistency
• Robust Deformable and Occluded Object Tracking With Dynamic Graph

Cited in

(8)

• Robust tracking via locally structured representation
• Object tracking by incremental structural learning of deformable parts
• Robust visual tracking using information theoretical learning
• The trace model for spatial invariance with applications in structured pattern recognition, image patch matching and incremental visual tracking
• Robust visual tracking with structured sparse representation appearance model
• Robust decentralized multi-model adaptive template tracking
• Structure-Aware Local Sparse Coding for Visual Tracking
• Robust visual tracking via part-based template matching with low-rank regulation

Describes a project that uses

Uses Software

• PASCAL VOC

This page was built for publication: Robust visual tracking via patch descriptor and structural local sparse representation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2331655)