EigenGait: Motion-Based Recognition of People Using Image Self-Similarity

Abstract

Abstract. We present a novel technique for motion-based recognition of individual gaits in monocular sequences. Recent work has suggested that the image self-similarity plot of a moving person/object is a projection of its planar dynamics. Hence we expect that these plots encode much information about gait motion patterns, and that they can serve as good discriminants between gaits of different people. We propose a method for gait recognition that uses similarity plots the same way that face images are used in eigenface-based face recognition techniques. Specifically, we first apply Principal Component Analysis (PCA) to a set of training similarity plots, mapping them to a lower dimensional space that contains less unwanted variation and offers better separability of the data. Recognition of a new gait is then done via standard pattern classification of its corresponding similarity plot within this simpler space. We use the k-nearest neighbor rule and the Euclidian distance. We test this method on a data set of 40 sequences of six different walking subjects, at 30 FPS each. We use the leave-one-out crossvalidation technique to obtain an unbiased estimate of the recognition rate of 93%.

Multi-example feature-constrained back-projection method for image super-resolution

“…This paper makes full use of edges and texture structures, and other image features, with using a feature-constrained interpolation method for initialization. In addition, in images, it is often the case that many patterns appear repeatedly in the image [21][22][23], especially in regions with regular structures. This property is called image self-similarity, and is very helpful to fix pixels with disturbing artifacts.…”

Matching Gait Image Sequences in the Frequency Domain for Tracking People at a Distance

“…To evaluate the efficiency of our method, we compared the following five methods: which is obtained by inverse Fourier transform of G (x, y, k). -SSP: normalized correlation of the self-similarity plots proposed in [10].…”

“…In the SSP method, we compute the normalized correlation of the self-similarity plots generated from gait sequences. Though the method of comparing the self-similarity plots is different from the one proposed in [10], we compare the effectiveness as a cue for identification by normalized correlation. In the Temp., Temp.(Princ.)…”

“…Liu and Picard [9] used a spatio-temporal volume and detected the periodicity in a motion by 1D Fourier analysis for each pixel of the image. BenAbdelkader et al [10] used self-similarity plots, in which each pixel had correlations with the frames of an image sequence. Liu et al [11] used a frieze pattern to represent gait motion; a pattern created by summing up the white pixels of a binarized image of a gait along the rows and columns of an image.…”

Active Shape Model-Based Gait Recognition Using Infrared Images

“…unwrapped silhouette [8]; silhouette similarity [9]; relational statistics [10]; self similarity [11]; key frame analysis [12]; frieze patterns [13]; area [14]; symmetry [15]; key poses [16] eigenspace sequences [19]; average silhouette [20]; moments [21]; ellipsoidal fits [22]; kinematic features [23]; gait style and content [24] stride parameters [25]; human parameters [26]; joint trajectories [27]; hidden Markov model [28][29]; articulated model [32]; dual oscillator [33]; linked feature trajectories [34] video oscillations [30] Accurate infrared target tracking is critical in many military weapons systems where common knowledge indicates that improving infrared target detection and tracking has the potential to simultaneously minimize unwanted collateral damage and maximize the probability of successful target elimination [35].…”