Occlusion detection and gait silhouette reconstruction from degraded scenes

Abstract

Gait, which is defined as the style of walking of a person, has been recognized as a potential biometric feature for identifying human beings. The fundamental nature of gait biometric of being unconstrained and captured often without a subject's knowledge or co-operation has motivated many researchers over the last one decade. However, all of the approaches found in the literature assume that there is little or no occlusion present at the time of capturing gait images, both during training and during testing and deployment. We look into this challenging problem of gait recognition in the presence of occlusion. A novel approach is proposed, which first detects the presence of occlusion and accordingly extracts clean and unclean gait cycles from the whole input sequence. In the second step, occluded silhouette frames are reconstructed using Balanced Gaussian Process Dynamical Model (BGPDM). We evaluated our approach on a new data set TUM-IITKGP featuring inter-object occlusion. Algorithms have also been tested on CMU's Mobo data set by introducing synthetic occlusion of different degrees.

Frontal gait recognition from occluded scenes

“…One of these uses polynomial interpolation, the second method uses autoregressive prediction based on stochastic linear time series, and the third approach uses the projection onto convex sets (POCS) method. Reconstruction of missing gait information is done in (Roy et al, 2011) by utilizing the Gaussian process dynamic model (GPDM). However, these methods assume availability of multiple, distinct gait sequences, so as to accomplish reconstruction of a clean gait cycle, and hence, are not suitable for real-life applications, where only a single gait sequence might be available.…”

Análisis automático del patrón de la marcha mediante visión por computador: problemas, métodos y aplicaciones

“…This process could rely on probabilistic models of gait pose transitions over 2.5. Experimental methodology time [78], or on detecting and tracking isolated body parts (e.g. the head) [83,101].…”

“…Those methods that rely on a model [44,51,78,115] have shown an outstanding ability to reconstruct incomplete body parts (due to occlusions or segmentation errors), although the resulting gait representations usually suffer from standardization without much of their individual information.…”

“…With the purpose of having heavily contaminated gait sequences, just a few works [11,78,110,115] have injected artificial major defects to human silhouette images to simulate the impact of environmental factors in the segmentation process. Common practices have been salt and pepper noise, that can potentially arise due to a continuously changing background (e.g.…”

“…The proposed approach is inspired by a statistical framework called robust statistics (RS) [35,53] Within this scope, some few works have focused on strategies to improve the quality of degraded gait silhouettes. In [78], gait cycles are modeled as chains of estimated key poses. This scheme allows to detect partially occluded and missing silhouettes in the frames of a gait sequence, which are then reconstructed using a Balanced Gaussian Process Dynamical Model.…”