Quantitative evaluation system and evaluation method for multidimensional visual hand function rehabilitation

Abstract

The invention discloses a multi-dimensional vision hand function rehabilitation quantitative evaluation system and an evaluation method. The system comprises an optical motion capturing device, a video capture device, a hand function quantitative evaluation system, an interactive touch screen and a collection platform, wherein the optical motion capture device acquires three-dimensional space data and motion vector information of each joint of fingers, a palms and each joints of a hand wrists in real time by an intelligent algorithm; the optical motion capture device outputs motion parameters which are then input into the hand function quantitative evaluation system, the hand function quantitative evaluation system preprocesses data, preprocessing results are screened and stored in a database, and by aiming at evaluation schemes of different evaluated motions, an evaluation result is provided. According to the multi-dimensional vision hand function rehabilitation quantitative evaluation system and the evaluation method, three-dimensional space parameter computation precision of hand joints of a patient can be improved; by combining a computer vision technology with optical intelligent motion capture, more precise quantitative rehabilitation evaluation data is provided, and assists to the a doctor to perform rehabilitation diagnosis on the patients.

Description

technical field [0001] The invention relates to a system and an evaluation method, in particular to a multi-dimensional visual hand function rehabilitation quantitative evaluation system and evaluation method. Background technique [0002] According to epidemiological statistics, stroke has a large number of patients and a high disability rate, and the dysfunction it brings often has a serious impact on the lives of patients, especially the sequelae of hand dysfunction, which is difficult and slow in the rehabilitation process . However, looking at home and abroad, the treatment and assessment of hand function after stroke have shown inaccurate and incomplete conditions. Currently, the more representative scales used to evaluate hand function include Manual Muscle Test (MMT), Modified Ashworth Spasticity Scale, Brunnstrom Scale, Fugl-Meyer Rating Scale (Fugl-Meyer Assessment Scale). , FMA), Motor Status Scale (Motor Status Scale, MSS), Motor Assessment Scale (Motor Assessm...

AI Technical Summary

Problems solved by technology

The advantage is that the calculation is relatively simple, and the accuracy of the information such as acceleration is high. The disadvantage is that it cannot meet the accuracy requirements for the relatively high evaluation requirements in hand function rehabilitation such as spatial positioning, and it cannot be achieved due to differences in patient age and gender. The uniformity of wearable devices makes it impossible to achieve consistent comparability of evaluation data

Although the non-contact solution based on the video data collected by the camera can achieve no different requirements for the patient's hand, it only needs to be placed at a designated position, but due to the current computer vision and pattern recognition algorithms and engineering technology The development is still far from being able to recognize any human hand movements. Even though some very complex algorithms have a high recognition rate for human hand movements after a variety of deep learning, but because the affected hands of stroke patients are difficult to move in terms of movement, flexion and extension, etc. Its function is relatively weak, and the motion characteristics of abnormal human hands can be compared, so it further increases the difficulty of completely relying on visual algorithm recognition, not to mention that in the actual test, there are still unsolvable problems such as hand joint occlusion, overlapping, and motion ambiguity.

Images