Mind the Gap: Bridging Occlusion in Gait Recognition via Residual Gap Correction
This addresses a practical limitation in gait recognition for person re-identification, though it is incremental as it builds on existing residual learning techniques.
The paper tackles the problem of occlusions in gait recognition by proposing RG-Gait, a residual learning method that improves performance on occluded sequences without compromising accuracy on holistic inputs, as demonstrated on Gait3D, GREW, and BRIAR datasets.
Gait is becoming popular as a method of person re-identification because of its ability to identify people at a distance. However, most current works in gait recognition do not address the practical problem of occlusions. Among those which do, some require paired tuples of occluded and holistic sequences, which are impractical to collect in the real world. Further, these approaches work on occlusions but fail to retain performance on holistic inputs. To address these challenges, we propose RG-Gait, a method for residual correction for occluded gait recognition with holistic retention. We model the problem as a residual learning task, conceptualizing the occluded gait signature as a residual deviation from the holistic gait representation. Our proposed network adaptively integrates the learned residual, significantly improving performance on occluded gait sequences without compromising the holistic recognition accuracy. We evaluate our approach on the challenging Gait3D, GREW and BRIAR datasets and show that learning the residual can be an effective technique to tackle occluded gait recognition with holistic retention. We release our code publicly at https://github.com/Ayush-00/rg-gait.