You Can Run but not Hide: Improving Gait Recognition with Intrinsic Occlusion Type Awareness
This addresses a critical issue for gait recognition in uncontrolled outdoor environments, though it is an incremental improvement over existing methods.
The paper tackles the occlusion problem in gait recognition by proposing an occlusion-aware method that improves recognition performance on challenging datasets like GREW and BRIAR, showing enhanced results compared to baseline methods.
While gait recognition has seen many advances in recent years, the occlusion problem has largely been ignored. This problem is especially important for gait recognition from uncontrolled outdoor sequences at range - since any small obstruction can affect the recognition system. Most current methods assume the availability of complete body information while extracting the gait features. When parts of the body are occluded, these methods may hallucinate and output a corrupted gait signature as they try to look for body parts which are not present in the input at all. To address this, we exploit the learned occlusion type while extracting identity features from videos. Thus, in this work, we propose an occlusion aware gait recognition method which can be used to model intrinsic occlusion awareness into potentially any state-of-the-art gait recognition method. Our experiments on the challenging GREW and BRIAR datasets show that networks enhanced with this occlusion awareness perform better at recognition tasks than their counterparts trained on similar occlusions.