Upper Limb Position Sensing: A Machine Vision Approach

Abstract

-Numerous approaches to sensing limb position for controlling neural prostheses have been proposed, evaluated and even incorporated into commercial products. In general, these technologies have focused on the goals of accuracy, convenience and cost. Here we propose an approach to sensing upper limb posture for a stroke rehabilitation system that does not require any devices attached to the subject. This is achieved through the use of a machine vision approach, which involves focusing a digital video camera on the subject and processing the video stream using a specialized algorithm running on a PC. This algorithm will produce a trigger signal whenever the arm posture conforms to a predefined profile. While the approach itself can be applied to a variety of sensing and control applications, we have demonstrated it by developing and characterizing an algorithm that can accurately sense elbow flexion and extension. The machine vision algorithm performs 3-D recovery of the arm position and calculates the elbow angle accordingly, which we have compared to a commercially available goniometer. It also involves a model based prediction and correction technique that improves the accuracy where the model is trained at the outset of a sensing session. The system uses a commercial off-the-shelf webcam, which is widely available and cost effective. The experiments were done in vivo, and the results have shown that the accuracy of the system is about 90% accurate on average compared to our benchmarking device, and that it has strong potential to facilitate control of neural prostheses.

Assessment of movement quality in robot- assisted upper limb rehabilitation after stroke: a review

“…A more cost affective solution such as using webcam and off-the-shelf RGB-D cameras such as Kinect [ 117 ] outlines the problem in model fidelity [ 118 ], difficulty to assess distal segments [ 119 ] including the hand [ 120 , 121 ], large static error when benchmarked with commercial motion capture [ 122 , 123 ] and false detection of trunk rotation for compensatory movement [ 124 ]. Chen et al [ 125 ] in their survey of depth imagery concluded that the higher resolution body part modelling is required for further research to improve the distal recognition challenges in human action recognition.…”

Development of holistic physical therapy management system using multimodal sensor network

“…user interface along with sensor information display [5] is implemented to provide feedbacks to the patient as well as provide observatory to the therapist. All information such as sensor data, recognized activities, medical records, etc are resided in central repository using relational database.…”

“…With advances in sensing, intelligence, networking and communication technologies, several tele-rehabilitation systems were proposed [2,3,4,5]. Kousidou et al [2] developed roboticbased shaping therapy to regain daily motor activities.…”

“…Most of the solutions use inertial measurement sensors such as accelerometer, gyroscope and magnetometer to support remote monitoring of rehabilitation exercises [3,4]. The use of computer vision to monitor PT exercises can be found in [5]. But none of them target toward holistic management system including monitoring, collaboration and assessment to assist the therapist in managing PT exercising with multiple patients and to achieve patient-centric assessment and treatment.…”

2Vita-B Physical: An Intelligent Home Rehabilitation System Based on Microsoft Azure Kinect

“…Also, to minimize the inconvenience and cost of commuting, with home rehabilitation, the patient is allowed to perform rehabilitation activities in comfortable conditions offered by their own home. All this contributes on the one hand to improve the quality of treatment and speed up recovery (Maclean et al, 2002) and on the other hand, reduces hospitalizations and consequently, the costs of the health care system (Han et al, 2005).…”