With a mounting demand

Published: Last Edited:

This essay has been submitted by a student. This is not an example of the work written by our professional essay writers.

An Approach to Security Surveillance with Gait Recognition System

M. Pushpa Rani1 and G.Arumugam2

ABSTRACT: With a mounting demand for Security Surveillance, the human identification at a distance has recently emerged as an area of significant research. Gait recognition essentially aims to address this problem by identifying people based on the way they walk. Knowledge management is very crucial in any automated applications. Gait analysis is essentially gathering the unique characteristics of human walking pattern (gait knowledge) and gait recognition uses this knowledge for people identification. The use of gait for Human authentication in surveillance applications has created a lot of interest among the Computer vision researchers in recent years. Though comparatively gait is a non popular biometric, it overcomes many limitations that the other biometrics such as face, fingerprints and iris recognition suffer from; which need the user cooperation. There is a possibility that they can be obscured in many situations where serious crimes are involved. The suitability of Gait Recognition for Security Surveillance Applications emerges from the fact that gait can be perceived from a distance as well as its non-invasive nature. We propose an efficient Gait Recognition System (GRS) for human identification using modified Independent Component Analysis (MICA). We have developed a simple but an efficient Gait Recognition System based on self similarity measure in silhouettes images. When a video sequence is fed, the proposed system recognizes the gait and identifies the subject(Human). A prototype for the Security Surveillance embedded with the proposed Gait Recognition System named hereafter as Security Surveillance System [SSS] is also designed. The proposed system is tested on the gait databases and the extensive experimental results on outdoor image sequences demonstrate that the proposed algorithm possesses a pleasing recognition performance.

KEYWORDS: Gait Recognition, Security Surveillance Systems (SSS), Modified Independent Component Analysis (MICA), Human tracking, Background Subtraction, Skeletonization, Morphological operator


In this high tech society, several significant Surveillance applications demand the need for automatic human identification systems. The physiological or behavioral characteristics of humans are made use by the biometrics technology in order to authenticate their identities [3]. A biometric is a descriptive measure of knowledge based on the human behavioural or physiological characteristics which distinguishes a person uniquely among other people; this unique knowledge should be universal and permanent. The unique gait features of an individual impart the biometric knowledge of that person. This biometric knowledge is then utilized by the system to perform gait analysis which in turn, results in the recognition/ classification of the individual. Many biometric resources, for instance iris, fingerprint, palmprint, hand geometry have been systematically studied and employed in many systems. In spite of their widespread applications, these resources suffer from two main disadvantages: that they fail to match in low resolution images especially pictures taken from distance and Necessitates user cooperation for accurate results [4]. For these reasons, innovative biometric recognition methods for human identification at a distance have been an urgent need for surveillance applications . The integration of human motion analysis and gait biometrics has fascinated several security-sensitive environments such as military, banks, parks and airports etc and has turned out to be a popular research direction

Human gait recognition works from the observation that an individual's walking style is unique and can be used for human identification. So as to recognize individual's walking characteristics, gait recognition includes visual cue extraction as well as classification. But the major issue here is the representation and management of these gait features efficiently to impart the accurate knowledge needed for human recognition.

Gait has many unique advantages such as non-contact, non-invasive and perceivable at a distance. The introduction of gait has turned video-based security surveillance system [8] as a technology for the future [3]. On the other hand, gait features have a high intra-personal variation in shape and also it is influenced by external conditions like footwear, clothing and load carrying. The variation of gaits is also influenced by mood, ground surface condition and time difference [12]. In spite of its individual pros and cons, gait recognition can be thought of as an effective means for human identification at a distance.

This research paper proposes a gait recognition system for human identification using modified Independent Component Analysis (MICA). The proposed system consists of three major modules namely, i) Human detection and tracking ii) Training using Modified ICA and iii) Human recognition. The algorithm is tested on a NLPR gait database consisting of images with subjects walking at different angles in an outdoor environment. A prototype for the Security Surveillance Systems (SSS) embedded with the proposed Gait Recognition System is also designed and explained.

The rest of this paper is organized as follows: Section 2 describes review of related researches on gait recognition in order to put ours in context. Section 3 introduces Gait Recognition System based on MICA. A prototype for the Security Surveillance Application with the proposed Gait Recognition System is presented in Section 4. Experimental results are presented and analyzed in Section 5. Section 6 concludes the paper.


Many researches have been carried out on gait recognition and of them, a few made use of Independent Component Analysis (ICA) for gait recognition. As a potential application for gait analysis, we also review the recent literatures on automated security surveillance systems based on human motion analysis.

Using multiple feature representations and Independent Component Analysis (ICA) on human silhouettes one easy gait recognition method is proposed by Jiwen Lu and Erhu Zhang [3]. In this they have offered a gait recognition method by fusing the multiple features and views on the basis of Genetic Fuzzy Support Vector Machine (GFSVM). Their proposed method is just recognizing human through three view fusion, i.e. perpendicularity, along and oblique with the direction of human walking, But in the real environment, the angle between the walker's direction and the camera is unpredictable. A useful experiment which can determine the sensitivity of the features from different views ought to be put forward and more multiple views fusion should be performed.

Lipton et al [33] proposed a real time vision-based system to classify the moving objects as either human or vehicle based on the "dispersedness" In their study, people are assumed to have a dispersedness value smaller than vehicles, however shape metrics can vary depending on image size and distance from camera.

A real time method for measuring motion periodicity based on self-similarity was discussed by Cutler [23] ,which is used to distinguish walking people from other moving objects. On the other hand, Javed et al [32] proposed a different motion-based feature which is based on the rigidity and self-articulation nature of moving objects. The motion measurement named Recurrent Motion Image (RMI) computes the repeated internal motion to classify moving objects into single person, vehicle or group of subjects.


We propose an efficient human gait recognition system using modified Independent Component Analysis (MICA) which can be used in Security Surveillance Applications.

The proposed gait recognition system characterizes gait in terms of gait signatures computed directly from the sequence of silhouettes. The system can be seen as a generic pattern recognizer composed of the three main modules namely, i) Human detection and tracking ii) Training or Classification using Modified ICA and iii) Human recognition. Fig.1. depicts the block diagram of the Proposed Gait Recognition System


Human detection and tracking is the first step in gait recognition analysis. The proposed system works with the assumption that the video sequence to be processed is captured by a static camera, and the only moving object in the video sequence is the subject (person). Given a video sequence from a static camera, this module detects and tracks the moving silhouettes. This process comprises of two submodules:1) Foreground Modeling which generates the moving foreground objects i.e. human subject in binary by background subtraction method[34] and 2) Human tracking using skeletonization process which reduces the foreground regions of the binary image to a skeletal remnant by preserving the connectivity while removing a good number of the original foreground pixels.


We use the modified Independent Component Analysis (MICA) to extract and train the gait features . The purpose of training the skeletonized silhouettes with the modified ICA is to attain a number of independent components to represent the original gait features from a high-dimensional measurement space to a low-dimensional Eigenspace. The concept of ICA can be noticed as a generational of Principal Component Analysis (PCA) and its fundamental idea is to symbolize a set of random variables using basic functions, where the components are statistically independent or as independent as possible [25]. ICA aims to identify the vectors that describe data to its best in terms of reproducibility; nevertheless these vectors may not comprise of any effective information for classification, and may eliminate discriminative information [30]. The training process is carried out using MICA and is elaborated in our previous paper[34].


With a trained MICA in hand, the final step is to test the effectiveness of the proposed system for gait recognition. Gait recognition has been a traditional pattern classification problem which can be solved by calculating the similarities between instances in the training database and the test database. Gait can be described as a kind of spatiotemporal motion pattern; hence we transform the input gait video sequence into an equivalent parametric eigenspace using the modified ICA (section 3.2.1). Then, based on the similarity measurement computed between the reference patterns and test sample in the parametric eigenspace, we achieve gait recognition. To be more particular, we have used the L2 Norm Distance for measuring the similarity between two gaits.


To test the functionality of our Gait recognition approach, we designed a prototype to the Security Surveillance Application embedding the Proposed Gait Recognition System as shown in Figure 2.

The System Setup

A camera in mounted in the Security room which is used to capture the video sequence of the walking figure(human). This video sequence is then converted in to image frames by the Gait Recognition System for further processing. The sequence of images correspond to a single subject moving in the field of view. The length of each sequence varies with the time each person takes to traverse the field of view. The Camera should be in static position to ensure that, only the object is moving.

When a subject(person) is about to enter the Security gate, his video is being captured and is passed to the GRS. The Gait Recognition process of the individual is done with the proposed GRS in seconds and the identity of the person is examined immediately.


Extensive experiments have been carried out to portray the effectiveness of the proposed algorithm. We presented a detailed analysis on the experimental results too.

5.1. The Progressive Phases on Gait Recognition

The publicly available NLPR gait database is employed in training the Recognition System with MICA. The intermediate results of the presented GRS are depicted in the following Figures 3,4 and 5.


We have evaluated the effectiveness of the proposed system with a set of gait images available in the NLPR database. We have measured the Acceptance Rate AR(A) for authorized set of gait Images and Rejection Rate RR(U) for the authorized set of input Images. We in turn calculated the False Rejection Rate FRR and False Acceptance Rate FAR to the above classified set of images.


The Complete knowledge on Gait is unique and is a good source of biometric of an individual. But to identify the hidden knowledge in human walk and the accurate representation of gait features is the challenging task today. As the human gait pattern is rhythmic and periodic, the gait recognition system can be considered as an ideal and attractive starting point for human detection and recognition. The complementary studies from psychology and other disciplines have also supported the concept that gait is unique for every person and people can recognize each other by the way they walk[31]. The prototype on Security Surveillance System presented in this paper will be highly useful to implement the working model of GRS in such Surveillance applications. The proposed System has been tested on the gait databases and, the extensive experimental results on outdoor image sequences demonstrated that the proposed algorithm possesses a pleasing recognition performance.


  1. D. Gavrila, "The Visual Analysis of Human Movement: A Survey," Computer Vision and Image Understanding, Vol. 73, No. 1, pp. 82-98, 1999.
  2. L. Wang, W.M. Hu, and T.N. Tan, "Recent Developments in Human Motion Analysis", Pattern Recognition, Vol. 36, No. 3, pp. 585-601, 2003.
  3. Jiwen Lu, Erhu Zhang, "Gait recognition for human identification based on ICA and fuzzy SVM through multiple views fusion", Pattern Recognition Letters, Vol. 28, pp. 2401-2411, 2007.
  4. Dacheng Tao, Xuelong Li, Xindong Wu, and Stephen J. Maybank, "General Tensor Discriminant Analysis and Gabor Features for Gait Recognition", IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 29, No. 10, pp. 1700-1715, October 2007.
  5. Liang Wang, Tieniu Tan, Huazhong Ning, and Weiming Hu, "Silhouette Analysis-Based Gait Recognition for Human Identification", IEEE transactions on pattern analysis and machine intelligence, Vol. 25, No. 12, December 2003.
  6. "Gait Database" from http://www.cbsr.ia.ac.cn/english/IrisDatabases.asp
  7. X. Yang, Y. Zhou, T. Zhang, G. Shu, J. Yang, "Gait Recognition Based on Dynamic Region Analysis," Signal Processing, Vol. 88, No. 9, pp. 2350-2356, September 2008.
  8. W.M. Hu, T.N. Tan, L. Wang, S. Maybank, "A survey of visual surveillance of object motion and behaviours", IEEE Trans. Syst. Man Cybern., Part C, Vol. 34, No. 3, pp. 334-352, 2004.
  9. Jianyi Liu, Nanning Zheng, and Lei Xiong, "Silhouette quality quantification for gait sequence analysis and recognition", Signal Processing, Vol. 89, No. 7, pp. 1417-1427, July 2009.
  10. Xiaoli Zhou and Bir Bhanu, "Feature fusion of side face and gait for video-based human identification", Pattern Recognition, Part Special issue: Feature Generation and Machine Learning for Robust Multimodal Biometrics, Vol. 41, No. 3, pp. 778-795, March 2008.
  11. Changhong Chen, Jimin Liang, Heng Zhao, Haihong Hu and Jie Tian, "Frame difference energy image for gait recognition with incomplete silhouettes", Pattern Recognition Letters, Vol. 30, No. 11, pp. 977-984, 1 August 2009.
  12. Seungkyu Lee, Yanxi Liu, Collins, R., "Shape Variation-Based Frieze Pattern for Robust Gait Recognition", IEEE Conference on Computer Vision and Pattern Recognition, CVPR '07, pp. 1-8, 17-22 June 2007.
  13. Chan-Su Lee, Ahmed Elgammal, "Gait Style and Gait Content: Bilinear Models for Gait Recognition Using Gait Re-sampling", Proceedings. Sixth IEEE International Conference on Automatic Face and Gesture Recognition, pp. 147-152, May 2004.
  14. R. T. Collins, R. Bross, and J. Shi, "Silhouette-based Human Identification from Body Shape and Gait," Proc. IEEE Int'l Conf. Automatic Face and Gesture Recognition, Washington DC, pp. 351-356, 2002.
  15. J. Han and B. Bhanu, "Statistical Feature Fusion for Gait-Based Human Recognition," Proc. IEEE Int'l Conf. Computer Vision and Pattern Recognition, Washington, DC, vol. 2, pp. 842-847, 2004.
  16. A. Kale, A. Sundaresan, A. N. Rajagopalan, N. P. Cuntoor, A. K. Roy-Chowdhury, V. Kruger, and R. Chellappa, "Identification of Humans using Gait," IEEE Trans. Image Processing, vol. 13, no. 9, pp. 1,163-1,173, 2004.
  17. L. Lee and W. E. L. Grimson, "Gait Analysis for Recognition and Classification," Proc. IEEE Int'l Conf. Automatic Face and Gesture Recognition, pp. 155-162, Washington, DC, 2002.
  18. Y. Liu, R.T. Collins, and Y. Tsin, "Gait Sequence Analysis using Frieze Patterns," Proc. of Europe Conf. Computer Vision, vol. 2, pp. 657-671, 2002.
  19. Z. Liu and S. Sarkar, "Simplest Representation yet for Gait Recognition: Averaged Silhouette," Proc. IEEE Int'l Conf. Pattern Recognition, vol. 4, pp. 211-214, 2004.
  20. R. Tanawongsuwan and A. Bobick, "Gait Recognition from Time-normalized Joint-angle Trajectories in the Walking Plane," Proc. IEEE Int'l Conf. Computer Vision and Pattern Recognition, vol. 2, pp. 726-731, Kauai HI, 2001.
  21. A. Bobick and A. Johnson, "Gait Recognition using Static Activity-specific Parameters," Proc. IEEE Int'l Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 423-430, Kauai, HI, 2001.
  22. D. Cunado, M. Nixon, and 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, 2003.
  23. R. Cutler and L. Davis, "Robust Periodic Motion and Motion Symmetry Detection," Proc. IEEE Int'l Conf. Computer Vision and Pattern Recognition, pp. 615-622, Hilton Head, SC, 2000.
  24. Jiwen Lu, Erhu Zhang, Zhigang Zhang, and Yanxue Xue, "Gait Recognition Using Independent Component Analysis", J. Wang, X. Liao, and Z. Yi (Eds.): Springer-Verlag Berlin Heidelberg, Vol. LNCS 3497, pp. 183-188, 2005.
  25. Hyvarinen, A., Oja, E., "Independent Component Analysis: Algorithm and Applications", Neural Networks, Vol. 13, pp. 411-430, 2000.
  26. Blum, H., "A Transformation for Extracting New Descriptors of Shape," in Models for the Perception of Speech and Visual Forms, W. Wathen-Dunn, Ed. Cambridge, MA: M.I.T: Press, 1967.
  27. Lantuejoul, C., "Skeletonization in Quantitative Metallography," in Issues of Digital Image Proc., R.M. Haralick and J.C. Simon, Eds., The Netherlands: Sijthoff and Noordhoff, 1980
  28. Maragos, P., and RW.Schafer, "Morphological Skeleton Representation and Coding of Binary Images", IEEE Trans. Acoust., Speech, Signal Processing, vol. ASSP-34, pp.1228-1244, Oct.1986.
  29. P Phillips, S Sarkar, I Robledo, P Grother and K Bowyer " Baseline Results for Challenge Problem of Human ID Using Gait Analysis" Proc. Int'l Conf. Automatic Face and Gesture Recognition, pp 137-142 ,2002
  30. C BenAbdelkader, R Cutler and L Davis, "Motion-Based Recognition of People in EigenGait Space", Proc . Int'l Conf. Automatic Face and Gesture Recognition, pp267-274, 2002
  31. Imed Bouchrika, Gait Analysis and Recognition f or Automated Visual Surveillance thesis submitted for the degree of Doctor of Philosophy , June 2008
  32. O. Javed and M. Shah. Tracking and Object Classification for Automated Surveil- lance. In Proceedings of the European Conference on Computer Vision, 4:343-357,2002.
  33. A. J. Lipton, H. Fujiyoshi, and R. S. Patil. Moving Target Classification and Track- ing from Real-Time Video. In Proceedings of IEEE Workshop on Applications of Computer Vision, 14, 1998.
  34. M. Pushpa Rani and G.Arumugam, "An Efficient Gait Recognition System For Human Identification Using Modified ICA ",International Journal of Computer Science & Information Technology, vol. 2, No 1, pp 55-67,January 2010.