Outdoor recognition at a distance by fusing gait and face

Abstract

We explore the possibility of using both face and gait in enhancing human recognition at a distance performance in outdoor conditions. Although the individual performance of gait and face based biometrics at a distance under outdoor illumination conditions, walking surface changes, and time variations are poor, we show that recognition performance is significantly enhanced by combination of face and gait. For gait, we present a new recognition scheme that relies on computing distances based on selected, discriminatory, gait stances. Given a gait sequence, covering multiple gait cycles, it identifies the salient stances using a population hidden Markov model (HMM). An averaged representation of the detected silhouettes for these stances are then built using eigenstance shape models. Similarity between two gait sequences is based on the similarities of these averaged representations of the salient stances. This gait recognition strategy, which essentially emphasizes shape over dynamics, significantly outperforms the HumanID Gait Challenge baseline algorithm. For face, which is a mature biometric for which many recognition algorithms exists, we chose the elastic bunch graph matching based face recognition method. This method was found to be the best in the FERET 2000 studies. On a gallery database of 70 individuals and two probe sets: one with 39 individuals taken on the same day and the other with 21 individuals taken at least 3 months apart, results indicate that although the verification rate at 1% false alarm rate of individual biometrics are low, their combination performs better. Specifically, for data taken on the same day, individual verification rates are 42% and 40% for face and gait, respectively, but is 73% for their combination. Similarly, for the data taken with at least 3 months apart, the verification rates are 48% and 25% for face and gait, respectively, but is 60% for their combination. We also find that the combination of outdoor gait and one outdoor face per person is superior to using two outdoor face probes per person or using two gait probes per person, which can considered to be statistical controls for showing improvement by biometric fusion.

Gait recognition without subject cooperation

“…However, direct template matching has been shown to be sensitive to noise and small silhouette distortions by previous studies [6], [12] as well as our experiments (see Section V). To overcome this problem, statistical feature learning based on subspace Component and Discriminant Analysis (CDA) can be employed to further reduce the feature dimensionality [7].…”

“…However, direct template matching has been shown to be sensitive to noise and small silhouette distortions [6], [12]. This is because that the dimensionality of the GEI feature space is high even after feature selection (typically in the order of thousands).…”

People Identification and Tracking Through Fusion of Facial and Gait Features

“…In [41], Kale et al showed that even in single camera environment, directly combining the scores of face and gait can boost the overall performance. Based on population Hidden Markov model (pHMM), Liu and Sarkar selected gait stances for recognition in the outdoor environment [49]. Extensive experimental results were reported on handling variations in the walking surface and elapsed time covariates, based on different fusion strategies.…”

“…Extensive experimental results were reported on handling variations in the walking surface and elapsed time covariates, based on different fusion strategies. They found performance is higher when fusing gait and face than intra-model fusion (i.e., face+face or gait+gait) [49]. By claiming that the reliability of face and gait varies with different subject-camera distances, Geng et al proposed an adaptive score-level fusion scheme [15].…”

Marionette mass-spring model for 3D gait biometrics

“…Some of the benefits are that it is non-invasive, perceivable at a distance, easy to set up in public area and can be hard to conceal [11]. Gait can also be used in fusion with other biometrics to enhance the overall performance [6].…”