The Accuracy of the Microsoft Kinect V2 Sensor for Human Gait Analysis. A Different Approach for Comparison with the Ground Truth
Several studies have examined the accuracy of the Kinect V2 sensor during gait analysis. Usually the data retrieved by the Kinect V2 sensor are compared with the ground truth of certified systems using a Euclidean comparison. Due to the Kinect V2 sensor latency, the application of a uniform temporal...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-08-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/16/4405 |
| _version_ | 1797559756746915840 |
|---|---|
| author | Diego Guffanti Alberto Brunete Miguel Hernando Javier Rueda Enrique Navarro Cabello |
| author_facet | Diego Guffanti Alberto Brunete Miguel Hernando Javier Rueda Enrique Navarro Cabello |
| author_sort | Diego Guffanti |
| collection | DOAJ |
| description | Several studies have examined the accuracy of the Kinect V2 sensor during gait analysis. Usually the data retrieved by the Kinect V2 sensor are compared with the ground truth of certified systems using a Euclidean comparison. Due to the Kinect V2 sensor latency, the application of a uniform temporal alignment is not adequate to compare the signals. On that basis, the purpose of this study was to explore the abilities of the dynamic time warping (DTW) algorithm to compensate for sensor latency (3 samples or 90 ms) and develop a proper accuracy estimation. During the experimental stage, six iterations were performed using the a dual Kinect V2 system. The walking tests were developed at a self-selected speed. The sensor accuracy for Euclidean matching was consistent with that reported in previous studies. After latency compensation, the sensor accuracy demonstrated considerably lower error rates for all joints. This demonstrated that the accuracy was underestimated due to the use of inappropriate comparison techniques. On the contrary, DTW is a potential method that compensates for the sensor latency, and works sufficiently in comparison with certified systems. |
| first_indexed | 2024-03-10T17:49:51Z |
| format | Article |
| id | doaj.art-5fd2facf4b284c14b0c0e1c1745d96ee |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T17:49:51Z |
| publishDate | 2020-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-5fd2facf4b284c14b0c0e1c1745d96ee2023-11-20T09:23:24ZengMDPI AGSensors1424-82202020-08-012016440510.3390/s20164405The Accuracy of the Microsoft Kinect V2 Sensor for Human Gait Analysis. A Different Approach for Comparison with the Ground TruthDiego Guffanti0Alberto Brunete1Miguel Hernando2Javier Rueda3Enrique Navarro Cabello4Centre for Automation and Robotics (CAR UPM-CSIC), Universidad Politécnica de Madrid, 28012 Madrid, SpainCentre for Automation and Robotics (CAR UPM-CSIC), Universidad Politécnica de Madrid, 28012 Madrid, SpainCentre for Automation and Robotics (CAR UPM-CSIC), Universidad Politécnica de Madrid, 28012 Madrid, SpainDepartment of Human Health and Performance, Faculty of Sports Sciences, Universidad Politécnica de Madrid, 28040 Madrid, SpainDepartment of Human Health and Performance, Faculty of Sports Sciences, Universidad Politécnica de Madrid, 28040 Madrid, SpainSeveral studies have examined the accuracy of the Kinect V2 sensor during gait analysis. Usually the data retrieved by the Kinect V2 sensor are compared with the ground truth of certified systems using a Euclidean comparison. Due to the Kinect V2 sensor latency, the application of a uniform temporal alignment is not adequate to compare the signals. On that basis, the purpose of this study was to explore the abilities of the dynamic time warping (DTW) algorithm to compensate for sensor latency (3 samples or 90 ms) and develop a proper accuracy estimation. During the experimental stage, six iterations were performed using the a dual Kinect V2 system. The walking tests were developed at a self-selected speed. The sensor accuracy for Euclidean matching was consistent with that reported in previous studies. After latency compensation, the sensor accuracy demonstrated considerably lower error rates for all joints. This demonstrated that the accuracy was underestimated due to the use of inappropriate comparison techniques. On the contrary, DTW is a potential method that compensates for the sensor latency, and works sufficiently in comparison with certified systems.https://www.mdpi.com/1424-8220/20/16/4405kinect sensorgait analysisdynamic time warpinglatency |
| spellingShingle | Diego Guffanti Alberto Brunete Miguel Hernando Javier Rueda Enrique Navarro Cabello The Accuracy of the Microsoft Kinect V2 Sensor for Human Gait Analysis. A Different Approach for Comparison with the Ground Truth Sensors kinect sensor gait analysis dynamic time warping latency |
| title | The Accuracy of the Microsoft Kinect V2 Sensor for Human Gait Analysis. A Different Approach for Comparison with the Ground Truth |
| title_full | The Accuracy of the Microsoft Kinect V2 Sensor for Human Gait Analysis. A Different Approach for Comparison with the Ground Truth |
| title_fullStr | The Accuracy of the Microsoft Kinect V2 Sensor for Human Gait Analysis. A Different Approach for Comparison with the Ground Truth |
| title_full_unstemmed | The Accuracy of the Microsoft Kinect V2 Sensor for Human Gait Analysis. A Different Approach for Comparison with the Ground Truth |
| title_short | The Accuracy of the Microsoft Kinect V2 Sensor for Human Gait Analysis. A Different Approach for Comparison with the Ground Truth |
| title_sort | accuracy of the microsoft kinect v2 sensor for human gait analysis a different approach for comparison with the ground truth |
| topic | kinect sensor gait analysis dynamic time warping latency |
| url | https://www.mdpi.com/1424-8220/20/16/4405 |
| work_keys_str_mv | AT diegoguffanti theaccuracyofthemicrosoftkinectv2sensorforhumangaitanalysisadifferentapproachforcomparisonwiththegroundtruth AT albertobrunete theaccuracyofthemicrosoftkinectv2sensorforhumangaitanalysisadifferentapproachforcomparisonwiththegroundtruth AT miguelhernando theaccuracyofthemicrosoftkinectv2sensorforhumangaitanalysisadifferentapproachforcomparisonwiththegroundtruth AT javierrueda theaccuracyofthemicrosoftkinectv2sensorforhumangaitanalysisadifferentapproachforcomparisonwiththegroundtruth AT enriquenavarrocabello theaccuracyofthemicrosoftkinectv2sensorforhumangaitanalysisadifferentapproachforcomparisonwiththegroundtruth AT diegoguffanti accuracyofthemicrosoftkinectv2sensorforhumangaitanalysisadifferentapproachforcomparisonwiththegroundtruth AT albertobrunete accuracyofthemicrosoftkinectv2sensorforhumangaitanalysisadifferentapproachforcomparisonwiththegroundtruth AT miguelhernando accuracyofthemicrosoftkinectv2sensorforhumangaitanalysisadifferentapproachforcomparisonwiththegroundtruth AT javierrueda accuracyofthemicrosoftkinectv2sensorforhumangaitanalysisadifferentapproachforcomparisonwiththegroundtruth AT enriquenavarrocabello accuracyofthemicrosoftkinectv2sensorforhumangaitanalysisadifferentapproachforcomparisonwiththegroundtruth |