Anti-occlusion person re-identification via body topology information restoration and similarity evaluation

In real-world scenarios, pedestrian images often suffer from occlusion, where certain body features become invisible, making it challenging for existing methods to accurately identify pedestrians with the same ID. Traditional approaches typically focus on matching only the visible body parts, which can lead to misalignment when the occlusion patterns vary. To address this issue and alleviate misalignment in occluded pedestrian images, the authors propose a novel framework called body topology information generation and matching. The framework consists of two main modules: the body topology information generation module and the body topology information matching module. The body topology information generation module employs an adaptive detection mechanism and capsule generative adversarial network to restore a holistic pedestrian image while preserving the body topology information. The body topology information matching module leverages the restored holistic image from body topology information generation to overcome spatial misalignment and utilises cosine distance as the similarity measure for matching. By combining the body topology information generation and body topology information matching modules, the authors achieve consistency in the body topology information features of pedestrian images, ranging from restoration to retrieval. Extensive experiments are conducted on both holistic person re-identification datasets (Market-1501, DukeMTMC-ReID) and occluded person re-identification datasets (Occluded-DukeMTMC, Occluded-ReID). The results demonstrate the superior performance of the authors proposed model, and visualisations of the generation and matching modules are provided to illustrate their effectiveness. Furthermore, an ablation study is conducted to validate the contributions of the proposed framework. The authors have introduced a novel framework called body topology information generation and matching (BTIGM) for occluded person ReID tasks. To address the issue of spatial dislocation caused by traditional feature alignment methods, the authors propose a novel approach that focuses on matching pedestrian body topology information. The proposed framework consists of two main modules: the body topology information generation (BTIG) module and the body topology information matching (BTIM) module. The BTIG module is responsible for restoring a holistic pedestrian image with body topological information constraints. To achieve this, the authors develop an adaptive detection mechanism that detects occluded areas for masking operations. By utilising body topology information, the authors aim to alleviate the spatial dislocation problem and enhance the representation of occluded pedestrians. In the BTIM module, cosine distance is utilised to measure the similarity between features extracted from the person re-identification model using the capsule network. This module ensures effective matching of the body topology information features and improves the accuracy of occluded person ReID. Extensive experiments have been conducted on occlusion and holistic datasets to validate the effectiveness of our proposed framework. The results demonstrate that our BTIGM framework outperforms existing methods in occluded person ReID tasks, highlighting the importance of body topology information in addressing occlusion challenges.image

Automated summary

This paper proposes a novel framework called body topology information generation and matching (BTIGM) to address the challenge of occlusion in pedestrian image recognition. By restoring holistic pedestrian images with body topology information and utilizing cosine distance for matching, the proposed framework achieves better performance compared to existing methods. Extensive experiments on different datasets validate the effectiveness of the framework.