A Multi-view Method for Gait Recognition Using Static Body Parameters

Johnson, Amos; Bobick, Aaron F.

doi:10.1007/3-540-45344-x_44

Cited by 145 publications

(108 citation statements)

References 9 publications

Supporting

Mentioning

108

Contrasting

Order By: Relevance

“…Similarity plots are then assigned to the various eigengaits for recognition, obtaining a recognition rate of 93% on a database of 6 subjects. Johnson et al presented a multi-view gait recognition method using recovered static body parameters (activity-specific biometrics) of subjects [11]. The technique uses the action of walking across multiple views to extract relative body parameters of subjects.…”

Section: : Introductionmentioning

confidence: 99%

Human identification by spatio-temporal symmetry

Hayfron-Acquah

Nixon

Carter

Object Recognition Supported by User Interaction for Service Robots

View full text Add to dashboard Cite

show abstract

Section: : Introductionmentioning

confidence: 99%

Human identification by spatio-temporal symmetry

Hayfron-Acquah

Nixon

Carter

Object Recognition Supported by User Interaction for Service Robots

View full text Add to dashboard Cite

show abstract

“…The matching of the trajectories of these features rely on simple spatio-temporal correlation [15,8,11], or matching maps of silhouette correlations [1], or dynamic time warping and HMM [4,13]. Apart from these classes of approaches that tend to emphasize both the shape of the silhouette and its evolution over time, there are approaches that emphasize just the shape [3,14] or use static body parameters [6] with 0 This research was supported by funds from DARPA (F49620-00-1-00388) and NSF (EIA 0130768).…”

Section: Introductionmentioning

confidence: 99%

Simplest representation yet for gait recognition: averaged silhouette

Liu

Sarkar

2004

Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.

View full text Add to dashboard Cite

We present a robust representation for gait recognition . IntroductionPossibilities for gait recognition was demonstrated in the early 70s using light point displays. Over the past few years, a variety of approaches to gait recognition have been proposed, almost all of which are based on matching silhouettes of persons. Approaches to gait recognition, typically, involves matching time series of features extracted in each frame. The possible frame features include just the raw silhouettes as in the gait baseline algorithm [8], shape PCA coefficients [15], shape moments [12], silhouette width vector [11,4,13], and body part ellipses [10]. The matching of the trajectories of these features rely on simple spatio-temporal correlation [15,8,11], or matching maps of silhouette correlations [1], or dynamic time warping and HMM [4,13]. Apart from these classes of approaches that tend to emphasize both the shape of the silhouette and its evolution over time, there are approaches that emphasize just the shape [3,14] or use static body parameters [6] with 0 This research was supported by funds from DARPA (F49620-00-1-00388) and NSF (EIA 0130768).almost equal or better performance than the first class of approaches.Given this collective wisdom about gait recognition, it is pertinent to ask: what is the simplest representation that suffices for gait recognition? The quest for the simplest representation is meaningful from both a computational point of view and from a robustness point of view; simpler ideas tend to be generalizable across a wider range of conditions. Towards this end, we propose the averaged silhouette representation; we simply consider the sum of the silhouettes over approximately one gait cycle as the gait representation. The matching process simply considers the Euclidean distances between these average silhouettes. The representation is robust with respect to gait cycle length estimates and does not depend on the choice of the starting stance of the gait cycle. There is no need for stance matching or gait alignment before matching. The idea behind the proposed representation is somewhat similar to the summed symmetry maps proposed in [5], where bilateral symmetry map of each silhouette is first extracted and then summed over one gait cycle. We, however, do not even extract the symmetry maps. The use of cumulative images for motion-based human activity recognition is not new. Bobick and Davis [2] used temporal template, a vector-image constructed by weighted image-differencing through the motion history, to identify different human activities, such as sit-down, arms-wave, and crouch down. We show that this kind of representation seem to be sufficient also for recognition.We use the HumanID Gait Challenge framework [8] to demonstrate the efficacy of the proposed representation. The challenge problem, which is being used by the gait community [13,14,9], consists of a baseline algorithm, a set of twelve experiments (A through L), and a large data set (1870 sequences, 122 subjects, 1.2 Terabytes of d...

show abstract

“…Of the current approaches, most are based on analysis of silhouettes, including: the University of Maryland's (UM's) deployment of hidden Markov models [24] and eigenanalysis [25]; the National Institute for Standards in Technology / University of South Florida's (NIST/USF's) baseline approach matching silhouettes [26]; Georgia Institute of Technology's (GaTech's) data derivation of stride pattern [27]; Carnegie Mellon University's (CMU's) use of key frame analysis for sequence matching [28]; Southampton's newer approaches that range from a baseline-type approach by measuring area [29], to extension of technique for object description including symmetry [30] (with some justification from psychology studies [13]) and statistical moments [31]; Massachusetts Institute of Technology's (MIT's) ellipsoidal fits [32]; Curtin's use of Point Distribution Models [33]; USF use the change in the relational statistics among the detected image features (which can handle running too) [34], the Chinese Academy of Science's eigenspace transformation of an unwrapped human silhouette [35] and eigenspace transformation of distance signals derived from sequences of silhouettes [36]; and Riverside's use of kinematic and stationary features [37]. These show promise for approaches that impose low computational and storage cost, together with deployment and development of new computer vision techniques for sequence-based analysis.…”

Section: Recent Approachesmentioning

confidence: 99%

“…Accordingly, it is encouraging to note the rich variety of data that has been collected. These include: UM's surveillance data [24]; NIST/ USF's outdoor data, imaging subjects at a distance [40]; GaTech's data combining marker based motion analysis with video imagery [27]; CMU's multi-view indoor data [41]; and Southampton's data [42] which combines ground truth indoor data (processed by broadcast techniques) with video of the same subjects walking in an outdoor scenario (for computer vision analysis). Examples of Maryland's outdoor surveillance view data, a silhouette derived from CMU's treadmill data, and of Southampton's indoor and outdoor data are given in Figs.…”

Section: Available Datamentioning

confidence: 99%