Feature extraction for person gait recognition applications

In this paper we present some features that may be used in person gait recognition applications. Gait recognition is an interesting way of people identification. During a gait cycle, each person creates unique patterns that can be used for people identification. Also, gait recognition methods ordinarily do not need interaction with a person and that is the main advantage of these methods. Features used in a person gait recognition methods can be obtained with widely available RGB and RGB-D cameras. In this paper we present a two features which are suitable for use in gait recognition applications. Mentioned features are height of a person and step length of a person. They may be extracted and were extracted from depth images obtained from RGB-D camera. For experimental purposes, we used a custom dataset created in outdoor environment using a long-range stereo camera.

Download Full-text

A Method for Human Gait Recognition from Video Streams Using Silhouette, Height and Step Length

Journal of Circuits System and Computers ◽

10.1142/s0218126620501017 ◽

2019 ◽

Vol 29 (07) ◽

pp. 2050101 ◽

Cited By ~ 1

Author(s):

Adnan Ramakić ◽

Zlatko Bundalo ◽

Dušanka Bundalo

Keyword(s):

Gait Cycle ◽

Gait Recognition ◽

Multiple Comparisons ◽

Step Length ◽

High Accuracy ◽

Outdoor Environment ◽

Human Gait ◽

Average Height ◽

Video Streams ◽

Biometric Features

This paper proposes and presents one way for people recognition from video streams. People recognition can be realized using various biometric features, behavioral or physiological, and methods based on that features. This work proposes and describes an algorithm for people recognition from video streams that is composed of two modules, module for dataset creation and module for recognition. Module for dataset creation involves creation of various types of person images and parameters. Module for recognition includes multiple comparisons of the images and different parameters comparison. These parameters are average height and average step length of a person during a gait cycle. For experimental purposes, a dataset for 15 persons in gait is created using a long-range stereo camera in outdoor environment. The algorithm has high accuracy in people recognition and easily can be upgraded with additional steps and modules, so it is suitable for use in various applications.

Download Full-text

Skeleton Silhouette Based Disentangled Feature Extraction Network for Invariant Gait Recognition

2021 International Conference on Information Networking (ICOIN) ◽

10.1109/icoin50884.2021.9334007 ◽

2021 ◽

Author(s):

Jae-Seok Yoo ◽

Kwang-Hyun Park

Keyword(s):

Feature Extraction ◽

Gait Recognition

Download Full-text

Multimodal Low Resolution Face and Frontal Gait Recognition from Surveillance Video

Electronics ◽

10.3390/electronics10091013 ◽

2021 ◽

Vol 10 (9) ◽

pp. 1013

Author(s):

Sayan Maity ◽

Mohamed Abdel-Mottaleb ◽

Shihab S. Asfour

Keyword(s):

Face Recognition ◽

High Resolution ◽

Gait Cycle ◽

Gait Recognition ◽

Recognition System ◽

Multimodal Fusion ◽

Surveillance Video ◽

Low Resolution ◽

Model Free ◽

Face Images

Biometric identification using surveillance video has attracted the attention of many researchers as it can be applicable not only for robust identification but also personalized activity monitoring. In this paper, we present a novel multimodal recognition system that extracts frontal gait and low-resolution face images from frontal walking surveillance video clips to perform efficient biometric recognition. The proposed study addresses two important issues in surveillance video that did not receive appropriate attention in the past. First, it consolidates the model-free and model-based gait feature extraction approaches to perform robust gait recognition only using the frontal view. Second, it uses a low-resolution face recognition approach which can be trained and tested using low-resolution face information. This eliminates the need for obtaining high-resolution face images to create the gallery, which is required in the majority of low-resolution face recognition techniques. Moreover, the classification accuracy on high-resolution face images is considerably higher. Previous studies on frontal gait recognition incorporate assumptions to approximate the average gait cycle. However, we quantify the gait cycle precisely for each subject using only the frontal gait information. The approaches available in the literature use the high resolution images obtained in a controlled environment to train the recognition system. However, in our proposed system we train the recognition algorithm using the low-resolution face images captured in the unconstrained environment. The proposed system has two components, one is responsible for performing frontal gait recognition and one is responsible for low-resolution face recognition. Later, score level fusion is performed to fuse the results of the frontal gait recognition and the low-resolution face recognition. Experiments conducted on the Face and Ocular Challenge Series (FOCS) dataset resulted in a 93.5% Rank-1 for frontal gait recognition and 82.92% Rank-1 for low-resolution face recognition, respectively. The score level multimodal fusion resulted in 95.9% Rank-1 recognition, which demonstrates the superiority and robustness of the proposed approach.

Download Full-text

Progressive Spatio-Temporal Feature Extraction Model For Gait Recognition

10.1109/icip42928.2021.9506490 ◽

2021 ◽

Author(s):

Jingran Su ◽

Yang Zhao ◽

Xuelong Li

Keyword(s):

Feature Extraction ◽

Gait Recognition ◽

Spatio Temporal ◽

Extraction Model ◽

Temporal Feature

Download Full-text

A Gait Feature Extraction Algorithm Based on Fusion of Spatial and Frequency Feature

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.291-294.2492 ◽

2013 ◽

Vol 291-294 ◽

pp. 2492-2495

Author(s):

Xiao Ke Zhu ◽

Xiao Pan Chen ◽

Fan Zhang

Keyword(s):

Feature Extraction ◽

Moving Objects ◽

Gait Recognition ◽

Morphological Processing ◽

Moving Object ◽

Classification Rate ◽

Feature Extraction Algorithm ◽

Extraction Algorithm ◽

Gait Feature ◽

Frequency Feature

In order to enhance the accuracy of gait recognition, a new gait feature extraction algorithm is proposed. Firstly, the gait images are preprocessed to extract moving objects, including background modeling, moving object extracting and morphological processing. Secondly, an equidistant slicing curve model based on system of polar coordinate is designed to slice the moving object, and the slicing vector is used to describe the spatial feature; Thirdly, the slicing vector is converted into frequency signal by Fourier transform to extract the frequency feature. Finally, the above two features are fused and used for the classification. The experimental results show that proposed algorithm provides higher correct classification rate than the algorithms using single feature, and meets the requirements of the real-time.

Download Full-text

Spatio-temporal silhouette sequence reconstruction for gait recognition against occlusion

IPSJ Transactions on Computer Vision and Applications ◽

10.1186/s41074-019-0061-3 ◽

2019 ◽

Vol 11 (1) ◽

Cited By ~ 1

Author(s):

Md. Zasim Uddin ◽

Daigo Muramatsu ◽

Noriko Takemura ◽

Md. Atiqur Rahman Ahad ◽

Yasushi Yagi

Keyword(s):

Gait Cycle ◽

Gait Recognition ◽

Real Life ◽

Image Sequence ◽

Body Parts ◽

Generative Adversarial Network ◽

Adversarial Network ◽

Hinge Loss ◽

Sequence Reconstruction ◽

Spatio Temporal

AbstractGait-based features provide the potential for a subject to be recognized even from a low-resolution image sequence, and they can be captured at a distance without the subject’s cooperation. Person recognition using gait-based features (gait recognition) is a promising real-life application. However, several body parts of the subjects are often occluded because of beams, pillars, cars and trees, or another walking person. Therefore, gait-based features are not applicable to approaches that require an unoccluded gait image sequence. Occlusion handling is a challenging but important issue for gait recognition. In this paper, we propose silhouette sequence reconstruction from an occluded sequence (sVideo) based on a conditional deep generative adversarial network (GAN). From the reconstructed sequence, we estimate the gait cycle and extract the gait features from a one gait cycle image sequence. To regularize the training of the proposed generative network, we use adversarial loss based on triplet hinge loss incorporating Wasserstein GAN (WGAN-hinge). To the best of our knowledge, WGAN-hinge is the first adversarial loss that supervises the generator network during training by incorporating pairwise similarity ranking information. The proposed approach was evaluated on multiple challenging occlusion patterns. The experimental results demonstrate that the proposed approach outperforms the existing state-of-the-art benchmarks.

Download Full-text

Altering Footwear Type Influences Gait During Level Walking and Downhill Transitions

Journal of Applied Biomechanics ◽

10.1123/jab.28.5.481 ◽

2012 ◽

Vol 28 (5) ◽

pp. 481-490 ◽

Cited By ~ 4

Author(s):

Keith A. Stern ◽

Jinger S. Gottschall

Keyword(s):

Gait Cycle ◽

Dynamic Balance ◽

Step Length ◽

Lower Leg ◽

Step Width ◽

Lateral Gastrocnemius ◽

Gait Patterns ◽

Level Walking ◽

Stance Time ◽

Stable Gait

The purpose of our study was to determine if altering the insoles within footwear or walking barefoot, as an attempt to increase or decrease cutaneous stimuli, would improve dynamic balance during a hill-walking task. We hypothesize that compared with foam insoles or iced bare feet, textured insoles or bare feet will result in greater speeds, longer step lengths, narrower step width, shorter stance time, and less tibialis anterior (TA), soleus (SOL), and lateral gastrocnemius (LG) activity during key gait cycle phases. Ten, healthy college students, 5 men and 5 women, completed the protocol that consisted of level walking and downhill transition walking in five different footwear insole or barefoot conditions. During level walking, conditions with the hypothesized greater cutaneous stimuli resulted in greater step length, which relates to a more stable gait. In detail, the texture insole condition average step length was 3% longer than the regular insole condition, which was 5% longer than the ice condition (p < .01). The same signals of increased stability were evident during the more challenging downhill transition stride. Step length during the barefoot condition was 8% longer than the ice condition (p < .05) and step width during the regular footwear condition was 5% narrower than the foam condition (p = .05). To add, during the preswing phase of level walking, TA activity of the textured insole condition was 30% less than the foam insole. Although our data show that footwear conditions alter gait patterns and lower leg muscle activity during walking, there is not enough evidence to support the hypothesis that textured insoles will improve dynamic balance as compared with other footwear types.

Download Full-text