The humanID gait challenge problem: data sets, performance, and analysis

Abstract

Identification of people by analysis of gait patterns extracted from video has recently become a popular research problem. However, the conditions under which the problem is "solvable" are not understood or characterized. To provide a means for measuring progress and characterizing the properties of gait recognition, we introduce the HumanID Gait Challenge Problem. The challenge problem consists of a baseline algorithm, a set of 12 experiments, and a large data set. The baseline algorithm estimates silhouettes by background subtraction and performs recognition by temporal correlation of silhouettes. The 12 experiments are of increasing difficulty, as measured by the baseline algorithm, and examine the effects of five covariates on performance. The covariates are: change in viewing angle, change in shoe type, change in walking surface, carrying or not carrying a briefcase, and elapsed time between sequences being compared. Identification rates for the 12 experiments range from 78 percent on the easiest experiment to 3 percent on the hardest. All five covariates had statistically significant effects on performance, with walking surface and time difference having the greatest impact. The data set consists of 1,870 sequences from 122 subjects spanning five covariates (1.2 Gigabytes of data). The gait data, the source code of the baseline algorithm, and scripts to run, score, and analyze the challenge experiments are available at http://www.GaitChallenge.org. This infrastructure supports further development of gait recognition algorithms and additional experiments to understand the strengths and weaknesses of new algorithms. The more detailed the experimental results presented, the more detailed is the possible meta-analysis and greater is the understanding. It is this potential from the adoption of this challenge problem that represents a radical departure from traditional computer vision research methodology.

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

“…Since the temporal alignment is necessary for the other methods, their computational cost is higher than that of the Amplitude method. Second, we tested our method by using a database of gait image sequence from University of South Florida; for details of the database, refer to [12]. The database consists of gallery (watch-list) and probe (input data) image sequences, which are compared in the experiment.…”

“…The size of images we use is normalized to 88 × 128 pixels, and the number of frames for matching is 128. We compared three methods, Amplitude, No DC and Baseline [12]. Figure 13 shows identification and verification rates for each probe.…”

“…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. Sarker et al [12] proposed a baseline algorithm of gait recognition, which computes the similarity of gait sequences by spatial-temporal correlation. Han and Bhanu [13] proposed a representation of gait image sequence, called a gait energy image, which is computed by taking average of a silhouette image sequence.…”

Clothing and carrying condition invariant gait recognition based on rotation forest

“…3(j)-(k)). The boundary of a silhouette is obtained by the application of Hp-Gf using D approximately in the range [18,22] for the USF dataset [22]. Since the silhouette boundary corresponds to the sharpest image, e.g., Fig.…”

“…Thus, [4,20] is considered to be the ideal range of cut-off frequencies. focus value in the range [22,0]. Fig.…”