The Potential of Computer Vision-Based Marker-Less Human Motion Analysis for Rehabilitation

Abstract

Background: Several factors, including the aging population and the recent corona pandemic, have increased the need for cost effective, easy-to-use and reliable telerehabilitation services. Computer vision-based marker-less human pose estimation is a promising variant of telerehabilitation and is currently an intensive research topic. It has attracted significant interest for detailed motion analysis, as it does not need arrangement of external fiducials while capturing motion data from images. This is promising for rehabilitation applications, as they enable analysis and supervision of clients’ exercises and reduce clients’ need for visiting physiotherapists in person. However, development of a marker-less motion analysis system with precise accuracy for joint identification, joint angle measurements and advanced motion analysis is an open challenge. Objectives: The main objective of this paper is to provide a critical overview of recent computer vision-based marker-less human pose estimation systems and their applicability for rehabilitation application. An overview of some existing marker-less rehabilitation applications is also provided. Methods: This paper presents a critical review of recent computer vision-based marker-less human pose estimation systems with focus on their provided joint localization accuracy in comparison to physiotherapy requirements and ease of use. The accuracy, in terms of the capability to measure the knee angle, is analysed using simulation. Results: Current pose estimation systems use 2D, 3D, multiple and single view-based techniques. The most promising techniques from a physiotherapy point of view are 3D marker-less pose estimation based on a single view as these can perform advanced motion analysis of the human body while only requiring a single camera and a computing device. Preliminary simulations reveal that some proposed systems already provide a sufficient accuracy for 2D joint angle estimations. Conclusions: Even though test results of different applications for some proposed techniques are promising, more rigour testing is required for validating their accuracy before they can be widely adopted in advanced rehabilitation applications.

Types of anomalies in two-dimensional video-based gait analysis in uncontrolled environments

“…However, since the results are based on the analysis of a single database, they do not necessarily cover anomalies at every measurement. It will be necessary to find situations where the two-dimensional video-based pose estimation technique can be used most effectively from a clinical point of view and develop an appropriate analysis algorithm in the future[20]. From a practical standpoint, it is also important to study analysis methods for disease signals through clinical research designs, such as comparisons between healthy and diseased groups.…”

Towards Accurate Computer Vision-Based Marker Less Human Joint Localization for Rehabilitation Purposes

“…A prototype application was developed for answering the following research question: Can existing CV-based marker-less human pose estimation techniques, based on a single camera, provide adequate joint localization accuracy for rehabilitation purposes? The technical choices and decisions made for the development are, thus, supported by a systematic review of existing 2D markerless pose estimation systems [9]. Dense human pose estimation in the wild (DensePose) [15] is a promising technique, in terms of joint localization accuracy.…”

“…Three-dimensional (3D) CV systems, such as Vicon, have been used as golden standard in the field of CV [8], however, these include advanced and precisely calibrated equipment and are thus too expensive for home use. The potential for providing cost-effective and easy-to-use solutions for home environments, marker-less CV solutions for rehabilitations applications have been of interest in the field of TR [9]. Recently, a comparison of marker-less vs. marker-based solutions for Gait analysis through a proof of concept study has been presented in [10].…”

Human motion capture algorithm for creating digital shadows of the movement process

“…If both base stations go out of sight or overlap, the signal from the sensors may be lost, which leads to incorrect data; the size and weight of trackers limit the possible number of sensors attached to a person. • Application of computer vision technologies based on a single camera, stereo cameras or a system of several synchronized cameras to obtain corrected and more accurate data on a person's position in three-dimensional space by recognizing key points of a person, including fingers and a face [7,8,9]. When using this tool, there are problems with recognizing key fragments of the silhouette of a person in fast movement and low light.…”

“…The formalization of a motion capture system based on computer vision includes a number of additional steps, since the initial data for this approach is a frame (or a sequence of frames) on which it is necessary to recognize a person and his key points. Obtaining these points is possible using various tools based, for example, on neural networks (MediaPipe BlazePose, PoseNet, MoveNet, and others) [9]. Neural networks make it possible to determine the silhouette of a person on the frame and select from 17 to 33 points with the possibility of expanding this number by highlighting key points of the face, fingers, etc.…”