Spatiotemporal KSVD Dictionary Learning for Online Multi-target Tracking

TL;DR

This paper introduces a novel spatiotemporal KSVD dictionary learning algorithm (STKSVD) for online multi-target tracking, effectively handling appearance variations due to posture, occlusion, and background changes, and demonstrating superior performance on standard datasets.

Contribution

The paper proposes a new STKSVD algorithm that models spatial and temporal information for improved appearance learning in online multi-target tracking, outperforming existing methods.

Findings

Outperforms existing learning methods on 2DMOT2015 dataset.

Uses a two-stage association with different similarity measures.

Effectively handles appearance variations due to occlusion and background changes.

Abstract

In this paper, we present a new spatial discriminative KSVD dictionary algorithm (STKSVD) for learning target appearance in online multi-target tracking. Different from other classification/recognition tasks (e.g. face, image recognition), learning target's appearance in online multi-target tracking is impacted by factors such as posture/articulation changes, partial occlusion by background scene or other targets, background changes (human detection bounding box covers human parts and part of the scene), etc. However, we observe that these variations occur gradually relative to spatial and temporal dynamics. We characterize the spatial and temporal information between target's samples through a new STKSVD appearance learning algorithm to better discriminate sparse code, linear classifier parameters and minimize reconstruction error in a single optimization system. Our appearance learning algorithm and tracking framework employ two different methods of calculating appearance similarity score in each stage of a two-stage association: a linear classifier in the first stage, and minimum residual errors in the second stage. The results tested using 2DMOT2015 dataset and its public Aggregated Channel features (ACF) human detection for all comparisons show that our method outperforms the existing related learning methods.