• 한국멀티미디어학회논문지
• /
• 제23권8호
• /
• pp.927-939
• /
• 2020

Gait recognition can identify people's identity from a long distance, which is very important for improving the intelligence of the monitoring system. Among many human features, gait features have the advantages of being remotely available, robust, and secure. Traditional gait feature extraction, affected by the development of behavior recognition, can only rely on manual feature extraction, which cannot meet the needs of fine gait recognition. The emergence of deep convolutional neural networks has made researchers get rid of complex feature design engineering, and can automatically learn available features through data, which has been widely used. In this paper,conduct feature metric learning in the three-dimensional space by combining the three-dimensional convolution features of the gait sequence and the Siamese structure. This method can capture the information of spatial dimension and time dimension from the continuous periodic gait sequence, and further improve the accuracy and practicability of gait recognition.

• 한국지능시스템학회:학술대회논문집
• /
• 한국지능시스템학회 2007년도 추계학술대회 학술발표 논문집
• /
• pp.15-18
• /
• 2007

Identification of humans from multiple view points is an important task for surveillance and security purposes. For optimal performance the system should use the maximum information available from sensors. Multimodal biometric systems are capable of utilizing more than one physiological or behavioral characteristic for enrollment, verification, or identification. Since gait alone is not yet established as a very distinctive feature, this paper presents an approach to fuse face and gait for identification. In this paper we will use the single camera case i.e. both the face and gait recognition is done using the same set of images captured by a single camera. The aim of this paper is to improve the performance of the system by utilizing the maximum amount of information available in the images. Fusion is considered at decision level. The proposed algorithm is tested on the NLPR database.

• Journal of Information Processing Systems
• /
• 제9권2호
• /
• pp.333-348
• /
• 2013

Mobile authentication/identification has grown into a priority issue nowadays because of its existing outdated mechanisms, such as PINs or passwords. In this paper, we introduce gait recognition by using a mobile accelerometer as not only effective but also as an implicit identification model. Unlike previous works, the gait recognition only performs well with a particular mobile specification (e.g., a fixed sampling rate). Our work focuses on constructing a unique adaptive mechanism that could be independently deployed with the specification of mobile devices. To do this, the impact of the sampling rate on the preprocessing steps, such as noise elimination, data segmentation, and feature extraction, is examined in depth. Moreover, the degrees of agreement between the gait features that were extracted from two different mobiles, including both the Average Error Rate (AER) and Intra-class Correlation Coefficients (ICC), are assessed to evaluate the possibility of constructing a device-independent mechanism. We achieved the classification accuracy approximately $91.33{\pm}0.67%$ for both devices, which showed that it is feasible and reliable to construct adaptive cross-device gait recognition on a mobile phone.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권11호
• /
• pp.2690-2701
• /
• 2013

Humans are able to recognize small number of people they know well by the way they walk. This ability represents basic motivation for using human gait as the means for biometric identification. Such biometric can be captured at public places from a distance without subject's collaboration, awareness or even consent. Although current approaches give encouraging results, we are still far from effective use in practical applications. In general, methods set various constraints to circumvent the influence factors like changes of view, walking speed, capture environment, clothing, footwear, object carrying, that have negative impact on recognition results. In this paper we investigate the influence of walking speed variation to different visual based gait recognition approaches and propose normalization based on geometric transformations, which mitigates its influence on recognition results. With the evaluation on MoBo gait dataset we demonstrate the benefits of using such normalization in combination with different types of gait recognition approaches.

• 한국지능시스템학회논문지
• /
• 제21권1호
• /
• pp.6-11
• /
• 2011

본 논문에서는 고유특징 정규화 및 추출 기법(ERE: Eigenfeature Regularization and Extraction)을 이용한 걸음걸이 바이오 정보 기반 사용자 인식 시스템을 제안한다. 먼저 카메라 센서에서 취득한 걸음걸이 시퀀스로부터 사용자 인식을 위한 특징 정보로 걸음걸이 에너지 영상(GEI: Gait Energy Image)을 생성한다. 학습 단계에서는 갤러리 걸음걸이 에너지 영상에 ERE를 적용하여 정규화된 변환행렬을 획득하여 고유공간(eigenspace)에 사상된 특징정보를 구하고, 검증 단계에서는 걸음걸이 에너지 영상을 학습단계에서 생성한 고유공간에 사상하여 최근접 이웃 분류기를 이용하여 사용자를 인식한다. 제안한 시스템의 유효성 검증을 위해 CASIA 걸음걸이 데이터셋 A를 이용하여 실험하였고, 기존 연구에 비해 인식 정확도 면에서 우수한 성능을 보여주었다.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제37권5호
• /
• pp.354-362
• /
• 2010

본 연구는 동적 베이스 망을 이용하여, 사람의 보행 동작을 보행 방향과 보행 자세로 분리하여 계층적으로 분석하는 방법을 제안한다. DBN의 일종인 FHMM을 기본 바탕으로 하여, 걸음걸이 동작 특성을 고려하여 순환 고리형 상태 공간 구조로 '보행 동작 디코더'(Gait Motion Decoder, GMD)를 설계한다. 기존 연구에는 보행자의 식별에만 치중을 하고 보행 방향의 변화, 관찰 각도에 제한적이거나 보행 동작에 대한 분석이 없었다. 반면에 본 연구에서는 동작과 자세를 적극적으로 표현하여 임의 방향의 보행, 방향의 변화, 보행 자세까지 인식할 수 있도록 하였다. 실험 결과 동작과 자세의 관점에서 걸음걸이 방향을 분석한 결과 96.5%의 방향 인식률을 기록하였다. 본 연구는 보행 동작을 방향과 보행 자세로 계층적으로 분석하는 최초의 방법 및 시도이며 향후 상황별 휴먼 동작 분석에 크게 활용할 수 있을 것이다.

• 한국지능시스템학회논문지
• /
• 제18권1호
• /
• pp.72-77
• /
• 2008

개인 식별 연구는 보안, 감시 시스템에서 중요한 부분이다. 최선의 성능을 가진 시스템을 설계하기 위하여 감지기들로부터 최대 정보를 이용할 수 있도록 설계한다. 다양한 생체 인식 시스템은 등록, 확인, 또는 개인 식별을 위하여 생리 특성이나 행동 특성을 하나이상 활용한다. 발걸음 인식만을 가지고는 아직 개인별 변별적 특징을 안정적으로 나타내지 못하므로, 본 논문에서는 얼굴과 발걸음을 결합한 개인 식별 시스템을 제안한다. 본 논문에서 우리는 한 개의 카메라를 이용한다. 즉, 얼굴과 발걸음 인식 모두 하나의 카메라를 이용하여 획득된 같은 이미지 셋을 사용한다. 본 논문의 중점은 이미지들에서 이용할 수 있는 최대 정보량을 활용하는 것으로 시스템의 성능을 향상시키는 것이다. 결합은 결정 단계에서 고려된다. 제안된 알고리듬은 NLPR 데이터베이스를 사용한다.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제16권2호
• /
• pp.87-94
• /
• 2016

In this paper, we discuss a gait representation based on the width of silhouette in terms of discriminative power and robustness against the noise in silhouette image for gait recognition. Its sensitivity to the noise in silhouette image are rigorously analyzed using probabilistic noisy silhouette model. In addition, we develop a gait recognition system using width representation and identify subjects using the decision level fusion based on majority voting. Experiments on CASIA gait dataset A and the SOTON gait database demonstrate the recognition performance with respect to the noise level added to the silhouette image.

• 제어로봇시스템학회논문지
• /
• 제15권5호
• /
• pp.511-518
• /
• 2009

The surveillance robot has been an important component in the field of service robot industry. In the surveillance robot technology, one of the most important technology is to identify a person. In this paper, we propose a gait recognition method based on contourlet and fuzzy LDA (Linear Discriminant Analysis) for surveillance robots. After decomposing a gait image into directional subband images by contourlet, features are obtained in each subband by the fuzzy LDA. The final gait recognition is performed by a fusion technique that effectively combines similarities calculated respectively in each local subband. To show the effectiveness of the proposed algorithm, various experiments are performed for CBNU and NLPR DB datasets. From these, we obtained better classification rates in comparison with the result produced by previous methods.

• 한국산업융합학회 논문집
• /
• 제22권4호
• /
• pp.459-465
• /
• 2019

There is an increasing interest in health and research on methods for measuring human body information. The importance of continuously observing information such as the step change and the walking speed is increasing. At a person's gait, information about the disease and the currently weakened area can be known. In this paper, gait is measured using wearable walking module built in shoes. We want to make continuous measurement possible by simplifying gait measurement method. This module is designed to receive information of gyro sensor and acceleration sensor. The designed module is capable of WiFi communication and the collected walking information is stored in the server. The information stored in the server is corrected by integrating the acceleration sensor and the gyro sensor value. A band-pass filter was used to reduce the error. This data is categorized by the Gait Finder into walking and waiting states. When walking, each step is divided and stored separately for analysis.