Parkinson hand tremor identification method based on event camera

A technology of hand tremor and recognition method, which is applied in the fields of medical health and computer vision, can solve problems such as difficult to capture clear images, overexposure, motion blur, etc., and achieve the effect of protecting patient privacy, less impact of light, and no motion blur

Pending Publication Date: 2022-07-15
DALIAN UNIVERSITY
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The disadvantage is that the detection process requires the patient to wear a complex detection device, the process is cumbersome, and the inconvenience caused by the attached connecting line and complex wearing results in unfree human-computer interaction
[0004] The data acquisition method based on the visual camera can enable the operator to perform human-computer interaction in a more natural way, and has greater flexibility, so it has received more research and attention; usually an ordinary camera (traditional RGB camera) is used for data acquisition, When the object changes slowly, it does not have much impact on the imaging, but when it encounters strong light, dimness or the object changes very fast, it is difficult for ordinary cameras to capture clear images, and there will be overexposure, underexposure or motion blur screen
Parkinson's hand tremor data collected by ordinary cameras is calculated based on each frame. If the picture of each frame is not clear, it is impossible to distinguish the patient's hand movements and their feature points
For the motion blur phenomenon, if the method of increasing the frame rate is used for shooting, in theory, the frame rate is fast enough to make the picture relatively static, but in fact, after increasing the frame rate, there will be higher requirements for the processing algorithm, which needs to be processed in a very short time. Completion of the calculation within the specified time, otherwise it will obviously lag behind the actual time flow rate
For overexposed or underexposed images caused by excessive illumination differences, some key object information will be lost, which poses a great challenge to feature recognition algorithms
For the detection of Parkinson's tremor, there is still no non-invasive simple and effective technical solution proposed in China

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Parkinson hand tremor identification method based on event camera
  • Parkinson hand tremor identification method based on event camera
  • Parkinson hand tremor identification method based on event camera

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0043] This embodiment uses the event camera to collect video data for feature extraction, realizes the non-invasive diagnosis of Parkinson's tremor detection, and avoids overexposure, underexposure or motion blur, etc. existing in the process of photographing Parkinson's hand tremor with traditional cameras. This phenomenon also greatly protects the privacy of patients. The specific implementation methods are as follows: figure 1 shown, can include the following steps:

[0044] Step 1: Use a tripod to fix the event camera Celex5 or DVS356 in the indoor scene, connect the event camera to the computer through the usb interface, and collect data through the DV platform. Start the DV software and connect the output of the event camera directly to the visualizer; select the Record configuration in the left sidebar of DV, the current configuration will be replaced with the standard recording configuration; record all events, frames, imu, and trigger data from the event camera;

[...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses an event camera-based Parkinson hand tremor recognition method, which comprises the following steps of: acquiring video data of a subject through an event camera, collecting the acquired video data by using a DV platform, and acquiring an asynchronous event stream of a hand tremor sequence; preprocessing the asynchronous event stream by adopting a noise reduction algorithm based on an optical flow speed; characteristic parameters of Parkinson's disease tremor signals are extracted from the preprocessed asynchronous event flow through discrete Fourier transform, and the characteristic parameters are divided into a training data set and a test data set; and inputting the training data set into a recognition network model for training, and judging whether the subject tremors or not through a tremor classification method based on a support vector machine (SVM). The novel sensor event camera is adopted for data collection, clinical tremor detection requirements are met, actions of a patient are not affected, the patient does not feel uncomfortable, and long-time detection can be achieved.

Description

technical field [0001] The invention relates to the technical fields of medical health and computer vision, in particular to a Parkinson's hand tremor recognition method based on an event camera. Background technique [0002] Parkinson's disease, also known as tremor palsy, is one of the most common neurodegenerative diseases, mostly in middle-aged and elderly people. Tremors, the main symptom of Parkinson's disease, are involuntary, rhythmic muscle contractions and relaxations involving wiggling or twitching movements of one or more body parts. The most common sign of tremor in Parkinson's disease is a slow tremor in the patient's hand at rest, which diminishes with voluntary movement and disappears when the patient falls asleep. Because the early symptoms of Parkinson's disease are easily confused with the aging of the patient's body function, it brings great difficulties to the early clinical diagnosis. The diagnosis of Parkinson's tremor has always been a difficult cli...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06V10/764G06V20/40G06V10/82G06K9/62G06K9/00A61B5/00A61B5/11
CPCA61B5/4082A61B5/7203A61B5/7267A61B5/1101A61B5/7257G06F2218/18G06F2218/04G06F2218/08G06F18/2411
Inventor 秦静刘燕汪祖民韩悦陈雨龙季长清
Owner DALIAN UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products