Computing and evaluating view-normalized body part trajectories

Jean, Frédéric; Bergevin, Robert; Albu, Alexandra Branzan

doi:10.1016/j.imavis.2008.11.009

Cited by 52 publications

(23 citation statements)

References 26 publications

(30 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The method in [19] projects a gait texture image formed by averaging binary gait images of a gait period of a certain view onto the canonical view based on domain transformation using transform invariant low-rank textures. The method in [20] computes view-normalised trajectories of the subject's head and feet. The normalisation involves the decomposition of walking trajectory into piece-wise linear segments to transform the head and feet trajectories from different views into fronto-parallel view based on homography.…”

Section: Related Workmentioning

confidence: 99%

“…Additionally, matching gallery view detection of the probe based on entropy analysis of SGEIs is not affected by self-occlusions. This is a major challenge for the method in [20] as it requires to determine the feet trajectories of the silhouettes on a frame-byframe basis. VI-MGR computes 22 SGEIs corresponding to 22 views of a subject's GEI created by mirror reflection of its 11 views from CASIA gait dataset B walking without wearing coat or carrying a bag.…”

Section: Phase 1: Detect Matching Gallery View Of the Probementioning

confidence: 99%

“…Fig. 10 shows that if L=50, the value of N in the range [13,20] enables to achieve the optimal rank-1 W-AvgI. Since the aim of the paper is to demonstrate the efficacy of multiscale approach in gait recognition rather than achieve higher W-AvgI through intensive parameter calibration, we fix N=16 for all values of L used in VI-MGR, as very high value of N causes overlearning.…”

Section: Experiments On Usf Humanid Gait Challenge Datasetmentioning

confidence: 99%

See 2 more Smart Citations

Robust view-invariant multiscale gait recognition

Das

Tjahjadi

2015

Pattern Recognition

View full text Add to dashboard Cite

The paper proposes a two-phase view-invariant multiscale gait recognition method (VI-MGR) which is robust to variation in clothing and presence of a carried item. In phase 1, VI-MGR uses the entropy of the limb region of a gait energy image (GEI) to determine the matching gallery view of the probe using 2-dimensional principal component analysis and Euclidean distance classifier. In phase 2, the probe subject is compared with the matching view of the gallery subjects using multiscale shape analysis. In this phase, VI-MGR applies Gaussian filter to a GEI to generate a multiscale gait image for gradually highlighting the subject's inner shape characteristics to achieve insensitiveness to boundary shape alterations due to carrying conditions and clothing variation. A weighted random subspace learning based classification is used to exploit the high dimensionality of the feature space for improved identification by avoiding overlearning. Experimental analyses on public datasets demonstrate the efficacy of VI-MGR.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Phase 1: Detect Matching Gallery View Of the Probementioning

confidence: 99%

Section: Experiments On Usf Humanid Gait Challenge Datasetmentioning

confidence: 99%

See 1 more Smart Citation

Robust view-invariant multiscale gait recognition

Das

Tjahjadi

2015

Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…Jean et al [18] introduced body part trajectories as the view-invariant feature. The 2D trajectories of the feet and head were normalized to make them appear as if they were always seen from the front-to-parallel viewpoint.…”

Section: Gait Recognition Under Various Viewing Anglesmentioning

confidence: 99%

A Grassmann graph embedding framework for gait analysis

Connie

Goh

Teoh

2014

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

Gait recognition is important in a wide range of monitoring and surveillance applications. Gait information has often been used as evidence when other biometrics is indiscernible in the surveillance footage. Building on recent advances of the subspace-based approaches, we consider the problem of gait recognition on the Grassmann manifold. We show that by embedding the manifold into reproducing kernel Hilbert space and applying the mechanics of graph embedding on such manifold, significant performance improvement can be obtained. In this work, the gait recognition problem is studied in a unified way applicable for both supervised and unsupervised configurations. Sparse representation is further incorporated in the learning mechanism to adaptively harness the local structure of the data. Experiments demonstrate that the proposed method can tolerate variations in appearance for gait identification effectively.

show abstract

“…In the approaches of the first category, Jean et al [3] introduced a method to compute and evaluate viewnormalized trajectories of pedestrian body parts obtained from monocular video sequences. It used 2D trajectories of feet and head from tracked silhouettes to segment the walking trajectory into piecewise linear segments.…”

Section: Introductionmentioning

confidence: 99%

Multiple views gait recognition using View Transformation Model based on optimized Gait Energy Image

Kusakunniran

et al. 2009

2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops

171

131

View full text Add to dashboard Cite

Gait is one of well recognized biometrics that has been widely used for human identification. However, the current gait recognition might have difficulties due to viewing angle being changed. This is because the viewing angle under which the gait signature database was generated may not be the same as the viewing angle when the probe data are obtained. This paper proposes a new multi-view gait recognition approach which tackles the problems mentioned above. Being different from other approaches of same category, this new method creates a so called View Transformation Model (VTM) based on spatial-domain Gait Energy Image (GEI) by adopting Singular Value Decomposition (SVD) technique. To further improve the performance of the proposed VTM, Linear Discriminant Analysis (LDA) is used to optimize the obtained GEI feature vectors. When implementing SVD there are a few practical problems such as large matrix size and over-fitting. In this paper, reduced SVD is introduced to alleviate the effects caused by these problems. Using the generated VTM, the viewing angles of gallery gait data and probe gait data can be transformed into the same direction. Thus, gait signatures can be measured without difficulties. The extensive experiments show that the proposed algorithm can significantly improve the multiple view gait recognition performance when being compared to the similar methods in literature.

show abstract

Computing and evaluating view-normalized body part trajectories

Cited by 52 publications

References 26 publications

Robust view-invariant multiscale gait recognition

Robust view-invariant multiscale gait recognition

A Grassmann graph embedding framework for gait analysis

Multiple views gait recognition using View Transformation Model based on optimized Gait Energy Image

Contact Info

Product

Resources

About