Learning to Know Where to See: A Visibility-Aware Approach for Occluded Person Re-identification
Citations Over TimeTop 10% of 2021 papers
Abstract
Person re-identification (ReID) has gained an impressive progress in recent years. However, the occlusion is still a common and challenging problem for recent ReID methods. Several mainstream methods utilize extra cues (e.g., human pose information) to distinguish human parts from obstacles to alleviate the occlusion problem. Although achieving inspiring progress, these methods severely rely on the fine-grained extra cues, and are sensitive to the estimation error in the extra cues. In this paper, we show that existing methods may degrade if the extra information is sparse or noisy. Thus we propose a simple yet effective method that is robust to sparse and noisy pose information. This is achieved by discretizing pose information to the visibility label of body parts, so as to suppress the influence of occluded regions. We show in our experiments that leveraging pose information in this way is more effective and robust. Besides, our method can be embedded into most person ReID models easily. Extensive experiments validate the effectiveness of our model on common occluded person ReID datasets.
Related Papers
- → Review on Parameterization Schemes of Visibility in Fog and Brief Discussion of Applications Performance(2021)13 cited
- Studies on the visibility index-classified system in Shanghai(2005)
- ASSESSMENT OF NIGHTTIME ROADWAY VISIBILITY(1957)
- Analysis of Characteristics and Trends of Atmospheric Visibility in Shizuishan City of Ningxia(2012)
- Change Trend and Prediction for Future of Visibility in Kashgar City(2013)