Human Parsing Based Alignment With Multi-Task Learning For Occluded Person Re-Identification
Authors:
- 1 July 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Abstract
Person re-identification (ReID) has obtained great progress in recent years. However, the problem caused by occlusion, which is frequent under surveillance camera, is not sufficiently addressed. When human body is occluded, extracted features are flooded with background noise. Moreover, without knowing location and visibility of parts, directly matching partial images with others will cause misalignment. To tackle the issue, we propose a model named HPNet to extract part-level features and predict visibility of each part, based on human parsing. By extracting features from semantic part regions and perform comparison with consideration of visibility, our method not only reduces background noise but also achieves alignment. Furthermore, ReID and human parsing are learned in a multi-task manner, without the need for an extra part model during testing. In addition to being efficient, the performance of our model surpasses previous methods by a large margin under occlusion scenarios.Keywords
This publication has 13 references indexed in Scilit:
- Perceive Where to Focus: Learning Visibility-Aware Part-Level Features for Partial Person Re-Identification2019
- Densely Semantically Aligned Person Re-Identification2019
- Occluded Person Re-Identification2018
- Deep Spatial Feature Reconstruction for Partial Person Re-identification: Alignment-free Approach2018
- DensePose: Dense Human Pose Estimation in the Wild2018
- Human Semantic Parsing for Person Re-identification2018
- Focal Loss for Dense Object Detection2017
- Deep Residual Learning for Image Recognition2016
- Scalable Person Re-identification: A Benchmark2015
- Partial Person Re-Identification2015