Athira M. Nambiar
ABSTRACT
Automatic human recognition systems based on biometrics are becoming increasingly popular in today's world. In particular, gait recognition (i.e., recognition based on the peculiar manner of walking) is especially interesting since it allows the recognition even at a distance, without explicit user co-operation. In this paper, depth information is integrated in a silhouette-based gait recognition scheme, in order to produce a hybrid 2D-3D frontal gait recognition scheme. The depth information of the human silhouette is obtained with a Kinect camera, from which a three dimentional (3D) human point cloud is obtained. In the proposed multimodal framework, feature extraction is done by considering the full 3D human point cloud, as well as three 2D projections of it, corresponding to the top, front and side-views of the human subject. The experimental results for this multimodal scheme, based on both 3D and 2D data, show superior recognition rates, when compared to existing front-view gait recognition schemes.
- L. Lee, W. Grimson, "Gait Analysis for Recognition and Classification," Proc. IEEE International Conference on Automatic Face and Gesture Recognition, pp. 155--162, Washington, DC, USA, May 2002. Google Scholar
Digital Library
- D. Cunado, M. Nixon, J. Carter, "Automatic Extraction and Description of Human Gait Models for Recognition Purposes," Computer Vision and Image Understanding, vol. 90, no. 1, pp. 1--41, April 2003. Google ScholarDigital Library
- C. Yam, M. Nixon, J. Carter. "Automated Person Recognition by Walking and Running Via Model-based Approaches," Pattern Recognition, vol. 37, no. 5, pp. 1057-- 1072, May 2004.Google ScholarCross Ref
- Y. Zhang, X. Wu, Q. Ruan, "Combining Procrustes Shape Analysis and Shape Context Descriptor for Silhouette-based Gait Recognition," Electronics Letters, vol. 45, no. 13, June 2009.Google ScholarCross Ref
- O. Barnich, M. Droogenbroeck, "Frontal-view Gait Recognition by Intra- and Inter-frame Rectangle Size Distribution," Pattern Recognition Letters, vol. 30, no. 10, pp. 893--901, July 2009. Google ScholarDigital Library
- M. Soriano, A. Araullo, C. Saloma, "Curve Spreads-A Biometric from Front View Gait Video," Pattern Recognition Letters, vol. 25,no. 14, pp. 1595--1602, October 2004. Google ScholarDigital Library
- L. Wang, T. Tan, W. Hu, H. Ning. "Automatic Gait Recognition Based on Statistical Shape Analysis," IEEE Transactions on Image Processing, vol. 12, no. 9, pp. 1120--1131, September 2003. Google ScholarDigital Library
- S. Chen, Y Gao, "An Invariant Appearance Model for Gait Recognition," Proc. IEEE Conference on Multimedia and Expo, pp. 1375--1378, Beijing, China, July 2007.Google Scholar
- K. Lee, S. Ranganath, S. Sanei, "Frontal View-based Gait Identification using Largest Lyapunov Exponents," Proc. International Conference on Acoustics, Speech, and Signal Processing, vol. 2, pp. 173--176, Toulouse, France, May 2006.Google Scholar
- M. Goffredo, J. Carter, M. Nixon, "Front-view Gait Recognition," Proc. IEEE International Conference on Biometrics: Theory, Applications and Systems, Washington, DC, USA, September 2008.Google Scholar
- S. Sivapalan, D. Chen, S. Denman, S. Sridharan, "Gait Energy Volumes and Frontal Gait Recognition using Depth Images," Proc. International Joint Conference on Biometrics, pp. 1--6, Washington, DC, USA, October 2011. Google ScholarDigital Library
- J. Ryu, S. Kamata, "Front View Gait Recognition using Spherical Space Model with Human Point Clouds," Proc. International Conference on Image Processing, pp.3209--3212, Brussels, Belgium, September 2011.Google Scholar
- Technical Description of Kinect Calibration," Available at: http://www.ros.org/wiki/kinect_calibration/technical.Google Scholar
- A. Elgammal, R. Duraiswami, D. Harwood, L. Davis, "Background and Foreground Modeling Using Nonparametric Kernel Density Estimation for Visual Surveillance," Proc. of IEEE, vol. 90, no. 7, pp. 1151--1163, July 2002.Google ScholarCross Ref
- K. Yamauchi, B. Bhanu, H. Saito, "Recognition of Walking Humans in 3D: Initial Results," Proc. Computer Vision and Pattern Recognition Workshops, pp. 45--52, Miami Beach, FL, USA, June 2009.Google Scholar
- P. Phillips, H. Moon, P. Rauss, S. Rizvi, "The FERET Evaluation Methodology for Face Recognition Algorithms," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22, no. 10, pp.1090--1104, October 2000. Google ScholarDigital Library
- J. Fazenda, D. Santos, P. Correia, "Using Gait to Recognize People," Proc. International Conference on Computer as a Tool, pp. 155--158, Belgrade, Serbia & Montenegro, November 2005.Google Scholar
- A. Ross, A. K. Jain, "Information Fusion in Biometrics," Pattern Recognition Letters, vol. 24, no. 13, pp.2115--2125, September 2003. Google ScholarDigital Library
- L. Rodriguez, A. Crespo, M. Lara, B. Mezcua, "Study of Different Fusion Techniques for Multimodal Biometric Authentication," Proc. IEEE International Conference on Wireless and Mobile Computing, pp. 666--671, Avignon, France, October 2008. Google ScholarDigital Library
- D. Tax, M. Breukelen, R. Duin, J. Kittler, "Combining Multiple Classifiers by Averaging or by Multiplying?," Pattern Recognition, vol. 33, no. 9, pp. 1475--1485, September 2000.Google ScholarCross Ref
Index Terms
- Frontal gait recognition combining 2D and 3D data
Recommendations
Gait Recognition for Human Identification using Kinect
RACS '17: Proceedings of the International Conference on Research in Adaptive and Convergent SystemsGait is a pattern of biometric movement for human identification. Unlike other biometrics such as fingerprint, iris, face, and voice recognition, human gait can be captured with unobtrusive method. In this paper, several measurements are proposed which ...
2D Pose-Invariant Face Recognition Using Single Frontal-View Face Database
AbstractPersonal identification systems that use face recognition work well for test images with frontal view face, but often fail when the input face is a pose view. Most face databases come from picture ID sources such as passports or driver’s licenses. ...
Frontal gait recognition from occluded scenes
First ever work on frontal gait recognition in the presence of occlusion.Fusion of front and back view features extracted from Kinect used for recognition.Encouraging results obtained even for high degrees of occlusion. In this paper, we propose a ...
Comments