Multi-mode hand rehabilitation system and method based on monocular vision guidance

Abstract

The invention discloses a multi-mode hand rehabilitation system and method based on monocular vision guidance. The system comprises a hand three-dimensional posture data acquisition system, a main controller, a pneumatic rehabilitation glove and a motor nerve reconstruction system based on visual feedback stimulation. The system uses a monocular camera to obtain three-dimensional coordinates of key points of a healthy side hand, identifies a movement mode of the healthy side hand, and realizes guide control of the pneumatic rehabilitation glove. The system provides three modes of active assistance, mirror image simulation and double-side cooperation, the mirror image simulation is that the rehabilitation glove drives the hand of a patient to simulate the motion of the healthy side hand, and the double-side cooperation is that the system generates an interactive cooperation motion state which should be executed by the opposite side hand on line according to the motion of the healthy side hand by using an offline constructed cooperation model. Meanwhile, the movement process of the two hands is displayed on a screen in real time through a virtual hand model, motor neural pathway reconstruction is achieved through sensory stimulation on a patient, and the problems that in existing rehabilitation training, the rehabilitation mode is single, the patient participation degree is low, and the rehabilitation efficiency is poor are solved.

Description

technical field [0001] The invention relates to the technical field of rehabilitation training robots, in particular to a multi-mode hand rehabilitation system and method based on monocular vision guidance. Background technique [0002] There are many hand movement styles, flexibility and high precision, and it is very difficult to restore the hand movement function. At present, clinical hands-on functional rehabilitation mainly relies on one-to-one physical therapy for patients by physicians. This method is time-consuming, labor-intensive, and costly. A large number of patients often miss the best treatment period because they cannot obtain effective rehabilitation training in time. Robots are suitable for long-term and repetitive work, and their combination with rehabilitation medicine provides a new way to solve the problem of hand movement rehabilitation. [0003] In recent years, researchers have developed a variety of hand exercise rehabilitation systems, but most of ...

AI Technical Summary

Problems solved by technology

Wearing a data glove on the healthy hand of the patient will affect its flexibility and increase the operating burden and system cost; while the existing method of using optical sensors either requires specific equipment, is expensive, or the system layout is more complicated; and At present, all the hand rehabilitation equipment actively controlled by the patient can only drive the affected hand to imitate the movement of the healthy hand, and cannot realize bilateral coordinated movements such as folding / unrolling paper, tying knots, twisting pen caps, and single-person finger-guessing. And these movements help to restore the patient's bilateral coordination and control ability; furthermore, the current hand rehabilitation system only focuses on limb / muscle movement rehabilitation, and does not consider the reconstruction of motor nerve pathways. In fact, for patients with hemiplegia caused by stroke, it is often Disruption of the motor nerve pathway leads to impaired motor function, so more attention should be paid to the reconstruction of the motor nerve pathway

Images