Limits...
Validation of enhanced kinect sensor based motion capturing for gait assessment

View Article: PubMed Central - PubMed

ABSTRACT

Optical motion capturing systems are expensive and require substantial dedicated space to be set up. On the other hand, they provide unsurpassed accuracy and reliability. In many situations however flexibility is required and the motion capturing system can only temporarily be placed. The Microsoft Kinect v2 sensor is comparatively cheap and with respect to gait analysis promising results have been published. We here present a motion capturing system that is easy to set up, flexible with respect to the sensor locations and delivers high accuracy in gait parameters comparable to a gold standard motion capturing system (VICON). Further, we demonstrate that sensor setups which track the person only from one-side are less accurate and should be replaced by two-sided setups. With respect to commonly analyzed gait parameters, especially step width, our system shows higher agreement with the VICON system than previous reports.

No MeSH data available.


Markers and bipartite graph used for the spatial calibration.(A) The shape of the markers is easily detectable in the RGB image; the white squares in the center encode the marker id [20]. The red circles indicate the salient points which have been used for defining the position and orientation of the marker. (B) Graph illustrating the “sees / is seen” relation (edges) between sensors (blue vertices) and markers (red vertices). For example, S3 cannot see M1 directly but indirectly via M2 and S2. A second possibility is via M2 and S5.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC5391956&req=5

pone.0175813.g003: Markers and bipartite graph used for the spatial calibration.(A) The shape of the markers is easily detectable in the RGB image; the white squares in the center encode the marker id [20]. The red circles indicate the salient points which have been used for defining the position and orientation of the marker. (B) Graph illustrating the “sees / is seen” relation (edges) between sensors (blue vertices) and markers (red vertices). For example, S3 cannot see M1 directly but indirectly via M2 and S2. A second possibility is via M2 and S5.

Mentions: The spatial calibration is equivalent to estimating the position and orientation of every Kinect sensor in the global coordinate system. Inspired by the work of Kowalski et al. [20], we use two-dimensional markers which can easily be detected in the color images captured by the Kinect sensor (see Fig 3A). Using these markers, we defined the global coordinate system. In some setups however, the sensors might be so far away from each other, that not every sensor sees all markers. We extended their solution by a flexible concatenation of Euclidian transformations (e.g., rotations and translations) in order to overcome this problem. Thus, not every marker needs to be visible to every sensor and the spatial relation between the markers does not need to be known prior to calibration. The calibration procedure consists of six steps which are described in more detail in the following.


Validation of enhanced kinect sensor based motion capturing for gait assessment
Markers and bipartite graph used for the spatial calibration.(A) The shape of the markers is easily detectable in the RGB image; the white squares in the center encode the marker id [20]. The red circles indicate the salient points which have been used for defining the position and orientation of the marker. (B) Graph illustrating the “sees / is seen” relation (edges) between sensors (blue vertices) and markers (red vertices). For example, S3 cannot see M1 directly but indirectly via M2 and S2. A second possibility is via M2 and S5.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC5391956&req=5

pone.0175813.g003: Markers and bipartite graph used for the spatial calibration.(A) The shape of the markers is easily detectable in the RGB image; the white squares in the center encode the marker id [20]. The red circles indicate the salient points which have been used for defining the position and orientation of the marker. (B) Graph illustrating the “sees / is seen” relation (edges) between sensors (blue vertices) and markers (red vertices). For example, S3 cannot see M1 directly but indirectly via M2 and S2. A second possibility is via M2 and S5.
Mentions: The spatial calibration is equivalent to estimating the position and orientation of every Kinect sensor in the global coordinate system. Inspired by the work of Kowalski et al. [20], we use two-dimensional markers which can easily be detected in the color images captured by the Kinect sensor (see Fig 3A). Using these markers, we defined the global coordinate system. In some setups however, the sensors might be so far away from each other, that not every sensor sees all markers. We extended their solution by a flexible concatenation of Euclidian transformations (e.g., rotations and translations) in order to overcome this problem. Thus, not every marker needs to be visible to every sensor and the spatial relation between the markers does not need to be known prior to calibration. The calibration procedure consists of six steps which are described in more detail in the following.

View Article: PubMed Central - PubMed

ABSTRACT

Optical motion capturing systems are expensive and require substantial dedicated space to be set up. On the other hand, they provide unsurpassed accuracy and reliability. In many situations however flexibility is required and the motion capturing system can only temporarily be placed. The Microsoft Kinect v2 sensor is comparatively cheap and with respect to gait analysis promising results have been published. We here present a motion capturing system that is easy to set up, flexible with respect to the sensor locations and delivers high accuracy in gait parameters comparable to a gold standard motion capturing system (VICON). Further, we demonstrate that sensor setups which track the person only from one-side are less accurate and should be replaced by two-sided setups. With respect to commonly analyzed gait parameters, especially step width, our system shows higher agreement with the VICON system than previous reports.

No MeSH data available.