Improved gait recognition by gait dynamics normalization

By Zongyi Joe Liu, Sudeep Sarkar. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006

352 citations recorded by the source corpus.

Potential sources for gait biometrics can be seen to derive from two aspects: gait shape and gait dynamics. We show that improved gait recognition can be achieved after normalization of dynamics and focusing on the shape information. We normalize for gait dynamics using a generic walking model, as captured by a population hidden Markov model (pHMM) defined for a set of individuals. The states of this pHMM represent gait stances over one gait cycle and the observations are the silhouettes of the corresponding gait stances. For each sequence, we first use Viterbi decoding of the gait dynamics to arrive at one dynamics-normalized, averaged, gait cycle of fixed length. The distance between two sequences is the distance between the two corresponding dynamics-normalized gait cycles, which we quantify by the sum of the distances between the corresponding gait stances. Distances between two silhouettes from the same generic gait stance are computed in the linear discriminant analysis space so as to maximize the discrimination between persons, while minimizing the variations of the same subject under different conditions. The distance computation is constructed so that it is invariant to dilations and erosions of the silhouettes. This helps us handle variations in silhouette shape that can occur with changing imaging conditions. We present results on three different, publicly available, data sets. First, we consider the HumanID gait challenge data set, which is the largest gait benchmarking data set that is available (122 subjects), exercising five different factors, i.e., viewpoint, shoe, surface, carrying condition, and time. We significantly improve the performance across the hard experiments involving surface change and briefcase carrying conditions. Second, we also show improved performance on the UMD gait data set that exercises time variations for 55 subjects. Third, on the CMU Mobo data set, we show results for matching across different walking speeds. It is worth noting that there was no separate training for the UMD and CMU data sets.

Subfields: Artificial Intelligence, Biomedical Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/dd4a82fb2e24328a7d858da6a21c98655fcb0bff

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Biomedical Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Robust arbitrary view gait recognition based on parametric 3D human body reconstruction and virtual posture synthesis (2016, methodology): “In 2D gait recognition, gait silhouettes in a period are usually averaged in various ways to form GEI [10], GFI [41], CGI [42], DNGR [43] or similar gait energy features for recognition.”
iLGaCo: Incremental Learning of Gait Covariate Factors (2020, background): “Because of these advantages, research on gait recognition is becoming more and more popular and has also made great progress in recent years [25, 37, 38, 43, 46].”
A review of biometric technology along with trends and prospects (2014, methodology): “Table 4: Summary of behavioral modalities: Modality Feature Set Recognition Techniques Datasets Voice Spectrum, Glottal pulse features, pitch, energy, duration, rhythm, temporal features, phones, idiolects, semantics, accent, pronunciation, LPCC [204], MFCC [205], VQ [206-208], HMM [209], GMM [210, ”
Human Identification Using Temporal Information Preserving Gait Template (2012, methodology): “Liu and Sarkar [22] employed population HMM to model human walking and generated the dynamics-normalized stance-frames to recognize individuals.”
GEINet: View-invariant gait recognition using a convolutional neural network (2016, methodology): “In fact, this strategy is adopted in many gait features, such as GEI [8], key-pose silhouettes using gait dynamics normalization [24], CGI [43], masked GEI [2], and GFI [21].”
Gait recognition without subject cooperation (2010, methodology): “In previous work gait recognition approaches were evaluated using a gallery set consisting of gait sequences of people under similar covariate conditions (e.g. clothing, surface, carrying, and view conditions).”
Unobtrusive User-Authentication on Mobile Phones Using Biometric Gait Recognition (2010, background): “In the machine vision approaches [8], [9], [10], [11], the system will typically consist of several digital or analog cameras with suitable optics for acquiring the gait data.”