TrADe Re-ID -- Live Person Re-Identification using Tracking and Anomaly Detection

TL;DR

This paper introduces TrADe, a novel live person re-identification method that combines tracking and anomaly detection to create higher quality galleries, significantly improving performance over previous approaches.

Contribution

TrADe is the first approach to integrate tracking and anomaly detection for live Re-ID, reducing gallery size and improving match accuracy in real-world scenarios.

Findings

TrADe outperforms baseline methods on the PRID-2011 dataset.

It generates smaller, higher-quality galleries for live Re-ID.

Significant performance improvements demonstrated in experiments.

Abstract

Person Re-Identification (Re-ID) aims to search for a person of interest (query) in a network of cameras. In the classic Re-ID setting the query is sought in a gallery containing properly cropped images of entire bodies. Recently, the live Re-ID setting was introduced to represent the practical application context of Re-ID better. It consists in searching for the query in short videos, containing whole scene frames. The initial live Re-ID baseline used a pedestrian detector to build a large search gallery and a classic Re-ID model to find the query in the gallery. However, the galleries generated were too large and contained low-quality images, which decreased the live Re-ID performance. Here, we present a new live Re-ID approach called TrADe, to generate lower high-quality galleries. TrADe first uses a Tracking algorithm to identify sequences of images of the same individual in the gallery. Following, an Anomaly Detection model is used to select a single good representative of each tracklet. TrADe is validated on the live Re-ID version of the PRID-2011 dataset and shows significant improvements over the baseline.