A Predictive Model for Gait Recognition

Enokida, Shuichi; Shimomoto, R.; Wada, Tomohito; Ejima, Toshiaki

doi:10.1109/bcc.2006.4341630

Cited by 8 publications

(8 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many factors exist that may impact the accuracy of a gaitbased recognition system, such as shoe, clothes, walking speed and terrain. Previous studies have shown that the accuracy will decrease when the test and training samples of the person's walking are obtained using different shoe types and clothes [36]. Indeed, as shown in Section VI-E, the accuracy of KEH-Gait decreases when session 1 is used for training and session 2 is used for testing.…”

Section: B Factors Affecting Gait Recognitionmentioning

confidence: 93%

KEH-Gait: Towards a Mobile Healthcare User Authentication System by Kinetic Energy Harvesting

Xu¹,

Lan²,

Qi³

et al. 2017

Proceedings 2017 Network and Distributed System Security Symposium

View full text Add to dashboard Cite

Accelerometer-based gait recognition for mobile healthcare systems has became an attractive research topic in the past years. However, a major bottleneck of such system is it requires continuous sampling of accelerometer, which reduces battery life of wearable sensors. In this paper, we present KEH-Gait, which advocates use of output voltage signal from kinetic energy harvester (KEH) as the source for gait recognition. KEH-Gait is motivated by the prospect of significant power saving by not having to sample the accelerometer at all. Indeed, our measurements show that, compared to conventional accelerometerbased gait detection, KEH-Gait can reduce energy consumption by 78.15%. The feasibility of KEH-Gait is based on the fact that human gait has distinctive movement patterns for different individuals, which is expected to leave distinctive patterns for KEH as well. We evaluate the performance of KEH-Gait using two different types of KEH hardware on a data set of 20 subjects. Our experiments demonstrate that, although KEH-Gait yields slightly lower accuracy than accelerometer-based gait detection when single step is used, the accuracy problem can be overcome by the proposed Multi-Step Sparse Representation Classification (MSSRC). We discuss the advantages and limitations of our approach in detail and give practical insights to the use of KEH in a real-world environment. Permission to freely reproduce all or part of this paper for noncommercial purposes is granted provided that copies bear this notice and the full citation on the first page. Reproduction for commercial purposes is strictly prohibited without the prior written consent of the Internet Society, the first-named author (for reproduction of an entire paper only), and the author's employer if the paper was prepared within the scope of employment.

show abstract

Section: B Factors Affecting Gait Recognitionmentioning

confidence: 93%

KEH-Gait: Towards a Mobile Healthcare User Authentication System by Kinetic Energy Harvesting

Xu¹,

Lan²,

Qi³

et al. 2017

Proceedings 2017 Network and Distributed System Security Symposium

View full text Add to dashboard Cite

show abstract

“…Although some previous studies reported performance decrease when the test and template samples of the person's walking were obtained using different shoe types, there was no attempt to verify any relationship between the shoe attributes and recognition performance [21]. There are many characteristics of the footwear that can play an important role during the gait process.…”

Section: Authentication With Respect To the Shoe Typesmentioning

confidence: 98%

“…Studies show that when the test and template samples of the person are collected using different shoe types, the performance can significantly decrease [21]. In many previous gait recognition experiments, subjects were walking with their own footwear ("random footwear").…”

Section: Research Objectivesmentioning

confidence: 99%

Towards understanding the uniqueness of gait biometric

Gafurov

Snekkenes

2008

2008 8th IEEE International Conference on Automatic Face &Amp; Gesture Recognition

View full text Add to dashboard Cite

In this paper, we provide some insights towards understanding the uniqueness of gait (ankle motion) by relating the discriminativeness of gait to the shoe type, direction of the motion and gait cycle. For analysis, we use gait samples of the people when all of them walk with the same specific types of footwear, thus eliminating the randomness (noise) introduced by the shoe variability. We collect gait using an accelerometer sensor, which is attached to the ankle of the person. The accelerometer records ankle motion in three directions: up-down, forward-backward and sideway. The verification method is based on detecting and averaging gait cycles in acceleration signal. Our gait data set consists of 480 samples from 30 persons. Each person walked with the 4 different types of footwear. Our analysis reveal that heavy footwear reduces the discrimination and the sideway motion of the foot has the most discriminating power compared to the up-down or forward-backward directions of the motion. Furthermore, various gait cycle parts contribute differently to the recognition performance. In addition, our analysis confirm that recognition performance can significantly decrease when the test and template samples are obtained using different shoe types. The recognition performance in terms of EER was in the range of 5%-18.3% mainly depending on the shoe type and the direction of motion.

show abstract

“…Previous studies have shown that the accuracy will decrease when the test and training samples of the person's walking are obtained using different shoe types and clothes [46]. Indeed, as shown in Section 5.5.5, the accuracy of KEH-Gait decreases when session 1 is used for training and session 2 is used for testing.…”

Section: Factors Affecting Gait Recognitionmentioning

confidence: 97%

“…The focus of our study is to demonstrate the feasibility of gait recognition using KEH and improve its performance. In fact, there has been several attempts to study the relationship between recognition performance and different factors [46,104]. For example, in terms of walking speed, Muhammad and Claudia [104] found that normal walking has the best results and fast walking is slightly better than slow walking.…”

Section: Factors Affecting Gait Recognitionmentioning

confidence: 99%

Sensor-based smart recognition system For wearable devices

Xu¹

View full text Add to dashboard Cite

With recent advances in wireless sensor networks and embedded computing technologies, on-body wearable devices such as smartphones and smart watches have become increasingly popular and play significant roles in our daily lives. The prevalence of smart wearable devices has sparked a new set of mobile computing applications that leverage the abundant information from sensors. In this thesis, I address three problems for wearable devices. These three problems correspond to three different recognition tasks: to help the user recognize a subject (face recognition), to assist the device to authenticate the identity of another device (device pairing) and to authenticate user (user authentication). The first problem is to implement a robust and efficient face recognition system on smart glass. The main challenge is the tension between the high computation requirements of accurate face recognition algorithms and the resource constraints of smart glasses. To address this challenge, I propose a robust and efficient sensor-assisted face recognition system on smart glasses by exploring the power of multimodal sensors including the camera and Inertial Measurement Unit (IMU) sensors. Extensive evaluation results show the proposed system improves recognition accuracy by up to 15% while achieving the same level of system overhead compared to the existing face recognition system (OpenCV algorithms) on smart glasses. The second problem is to generate a cryptographic key for legitimate devices so that devices on the same user's body can be paired together. I propose an automatic key generation system for wearable devices based on the user's unique gait. The intuition of the proposed key generation approach is that the devices on the same body experience similar motion signals that are produced by the unique walking pattern of the user. Therefore, the unique gait signal can be exploited as shared information to generate secret keys for all on-body devices. The evaluation results show that the proposed system can generate a common 128-bit key for two legitimate devices with 98.3% probability. The third problem is to develop a gait-based user authentication system by using Kinetic Energy Harvesting (KEH). The main feature of the proposed system is it utilizes the output voltage signal of the energy harvester to achieve gait recognition rather than the accelerometer. Compared with traditional accelerometer-based gait recognition system, the proposed system can reduce energy consumption by 78% while achieving comparable recognition accuracy.

show abstract

A Predictive Model for Gait Recognition

Cited by 8 publications

References 11 publications

KEH-Gait: Towards a Mobile Healthcare User Authentication System by Kinetic Energy Harvesting

KEH-Gait: Towards a Mobile Healthcare User Authentication System by Kinetic Energy Harvesting

Towards understanding the uniqueness of gait biometric

Sensor-based smart recognition system For wearable devices

Contact Info

Product

Resources

About