Deep Person Re-identification for Probabilistic Data Association in Multiple Pedestrian Tracking

TL;DR

This paper introduces a deep learning-based person re-identification method for improving the accuracy and robustness of multiple pedestrian tracking in videos, especially under occlusions and crossing paths.

Contribution

It presents a novel data association approach that integrates deep re-ID features into a probabilistic tracking model, enhancing performance over baseline methods.

Findings

Significant improvement in tracking robustness against occlusions.

Enhanced accuracy in distinguishing individuals with similar appearances.

Validated on two video sequences showing superior performance.

Abstract

We present a data association method for vision-based multiple pedestrian tracking, using deep convolutional features to distinguish between different people based on their appearances. These re-identification (re-ID) features are learned such that they are invariant to transformations such as rotation, translation, and changes in the background, allowing consistent identification of a pedestrian moving through a scene. We incorporate re-ID features into a general data association likelihood model for multiple person tracking, experimentally validate this model by using it to perform tracking in two evaluation video sequences, and examine the performance improvements gained as compared to several baseline approaches. Our results demonstrate that using deep person re-ID for data association greatly improves tracking robustness to challenges such as occlusions and path crossings.