Use of the image and depth sensors of the Microsoft Kinect for the detection of gait disorders

Procházka, Aleš; Vyšata, Oldřich; Vališ, Martin; Ťupa, Ondřej; Schätz, Martin; Mařı́k, Vladimı́r

doi:10.1007/s00521-015-1827-x

Cited by 43 publications

(23 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Computer-vision based techniques are the preferred method for gait performance analysis [3][4][5][6][7][8], as there is no need for on-body sensor attachments that might in turn, affect the data collection during a gait cycle and make it harder for the subjects to use. Nonetheless, there are disadvantages to this method such as higher computational power required for signal analysis and image processing and intrinsic data acquisition inaccuracies, especially in Kinect sensors [2].…”

Section: B State Of the Artmentioning

confidence: 99%

A new technique for foot-off and foot contact detection in a gait cycle based on the knee joint angle using microsoft kinect v2

Amini

Banitsas

Hosseinzadeh

2017

2017 IEEE EMBS International Conference on Biomedical &Amp; Health Informatics (BHI)

View full text Add to dashboard Cite

The Microsoft Kinect RGB-D sensor has been proven to be a reliable tool for gait analysis and rehabilitation purposes. Although it is accurate for detecting upper body part movements, even the second iteration of the Kinect sensor lacks the accuracy when it comes to lower extremities. while detecting foot-off and foot contact phases of a gait cycle is an important part of a gait performance analysis, The Kinect's intrinsic inaccuracies make it an unreliable tool to detect them accurately. We propose a new Kinect based technique for detecting foot-off and foot contact phases in a gait cycle that solely relies on a subject's knee joint relative angle. The system was tested on 11 healthy subjects walking in pre-defined pathways in 12 walking sessions while the Kinect v2 camera was placed at different heights ranging from 0.65 to 1.57 and angles ranging from 0 to 45 degrees to the ground. The algorithm's accuracy was also compared to another footstep detection method based on the subject's ankle joints height to the ground. The results showed 86.52% accuracy in detecting foot-off and foot contact events on average for both feet.

show abstract

Section: B State Of the Artmentioning

confidence: 99%

A new technique for foot-off and foot contact detection in a gait cycle based on the knee joint angle using microsoft kinect v2

Amini

Banitsas

Hosseinzadeh

2017

2017 IEEE EMBS International Conference on Biomedical &Amp; Health Informatics (BHI)

View full text Add to dashboard Cite

show abstract

“…The gait features are extracted from the absolute positions of the limbs Proposed features are gait velocity, stride length, left and right leg step length and limbs co-movement. Further information about gait reconstruction with static sensor was published in our earlier papers [7,8].…”

Section: Gait Reconstructionmentioning

confidence: 99%

Navigation of robotic platform for gait disorders monitoring

Crha

Ťupa

Mareš

et al. 2016

2016 International Conference on Applied Electronics (AE)

View full text Add to dashboard Cite

This paper is focused on control of a six-wheeled robotic platform used for gait pattern recording. Navigation of the platform has to be very precise to keep the path of the platform as narrow as possible and to maintain the distance between the subject and the platform to capture the gait pattern in the most natural way. A key component of the whole robotic platform is an MS Kinect v2 device which tracks the patients' gait. Kinect also provides the information about the distance between the robot and the patient to a microcontroller which is responsible for the wheels' control. To obtain straight trajectory, there is a camera pointing forwards on the front of the robot and a set of two beacons at the end of the operation area to be tracked by the camera. All data obtained from the camera, Kinect and encoders (attached to each wheel) are used during an offline reconstruction of the patients' gait. To process and save the data form Kinect, camera and other controllers in real-time a special multithread application was developed.

show abstract

“…In the previous studies [7,8] the Kinect device was placed stationary on a table to track people in its field of view. MS Kinect that was used for data acquisition was installed approximately 60 cm above the floor.…”

Section: Motivationmentioning

confidence: 99%

“…This feature is often used during rehabilitations to record the progress of the healing process. Several papers [7,8] discussing Kinect as a sensor of gait patterns have been written at our department. In these papers Kinect provides skeletal data that are processed for specific features like co-movement of legs and arms.…”

Section: Introductionmentioning

confidence: 99%

Mobile Gait Tracking Using Ms Kinect and Robotic Platform

Crha¹,

Ťupa²

2015

TransVSBms

Self Cite

View full text Add to dashboard Cite

Computer vision is a fast developing field of science. Activity monitoring and analysis belongs to this topic. Our application is focused on gait monitoring and analysis. The novelty of this attitude is in the combination of the MS Kinect v2 sensor for capturing the gait pattern and mobility of such sensor thanks to placing this device on a robotic platform.Crucial part of this project is the hardware solution and autonomous function of this recording set. The designed platform is a six-wheeled robotic platform controlled by a micro controller using the depth information from the Kinect sensor and the distance driven by robot provided by encoders attached to every motor.The following research is devoted to the proposal of methods for a precise and as narrow as possible control of the platform and post processing of records for a features selection and a classification of physical activities and early diagnostics of gait disorders, primarily the Parkinson's disease. AbstraktPočítačové vidění je rychle se vyvíjející odvětví vědy, kam patří i monitorování a analýza pohybu. Naše aplikace se zaměřuje na zaznamenávání a analýzu chůze a využívá nový přístup v kombinaci senzoru MS Kinect v2 pro sledování pohybových vzorů a robotické platformy jako nosiče, který umožňuje mobilitu senzoru.Stěžejní částí tohoto projektu je samotné hardwarové řešení a autonomní funkce nahrávání. Navrhnutá platforma je šestikolový podvozek řízený jednočipem s využitím hloubkových dat ze senzoru Kinect a ujeté vzdálenosti, která je získávána z šesti enkodérů upevněných na každém motoru.Následujícím úkolem je nelézt a aplikovat metody pro přesné a co nejkomplexnější řízení platformy. Získané nahrávky budou následně podrobeny analýze fyzické aktivity a použity k včasné diagnostice poruch chůze, primárně způsobených Parkinsonovou nemocí.

show abstract

Use of the image and depth sensors of the Microsoft Kinect for the detection of gait disorders

Cited by 43 publications

References 34 publications

A new technique for foot-off and foot contact detection in a gait cycle based on the knee joint angle using microsoft kinect v2

A new technique for foot-off and foot contact detection in a gait cycle based on the knee joint angle using microsoft kinect v2

Navigation of robotic platform for gait disorders monitoring

Mobile Gait Tracking Using Ms Kinect and Robotic Platform

Contact Info

Product

Resources

About