CN103099622B - A kind of body steadiness evaluation methodology based on image - Google Patents

Abstract

The present invention is a kind of body steadiness evaluation methodology based on image and device, and it comprises the following steps: 1) set labelling: carry out flag settings to patient position to be measured; 2) image acquisition: to the collection of patient's specific part kinestate consecutive image; 3) image procossing: the position of the characteristic point reflecting kinestate in each image is extracted; 4) data analysis: characteristic point is processed and analyzes; Image acquisition units, for the image sequence of continuous record patient labelling position kinestate; Image Acquisition and control unit, for dynamic acquisition view data and realize the preservation of view data; Graphics processing unit, extracts for the position realizing the characteristic point reflecting kinestate in consecutive image data; Data analysis unit, for analyzing the kinestate of patient's specific part, the present invention has non-invasive measurement, easy to use, and cost is low, advantages of simple structure and simple, can be used for the early stage auxiliary diagnosis of nervous system disease.

Description

An image-based method for evaluating body stability

technical field

The invention relates to an image-based body stability evaluation method and device.

Background technique

Body stability: The normal human body has the ability to maintain stability of the body or limbs. Body or limb stability is controlled and regulated by the nervous system. In various pathological states, the ability of the body to control the stability of the body or limbs decreases, manifested as body shaking, limb tremors, and in severe cases, the hands cannot hold objects, or even stand. Previous assessments of body shaking and limb tremors relied on visual inspection. The subjectivity of this method is too strong, which obviously affects the accuracy and objectivity of the evaluation. So far, there is a lack of a simple and reliable inspection method.

Diseases that cause a decrease in body stability:

1. Parkinson's disease: The early manifestations of Parkinson's disease are tremors of limbs and body. It is the most common degenerative disease of the central nervous system in middle-aged and elderly people. One of the early typical manifestations is resting tremor. For example, Parkinson's patients show resting tremor with a frequency of 5Hz (3~8Hz), and it mostly occurs in the hands, lower limbs, mouth and head;

2. Cerebellar disease: mainly manifested as imbalance, resulting in decreased limb and body stability;

3. Hyperthyroidism: It can be manifested as subtle tremors in limbs and body;

4. Paralyzed limbs: functional defects of fine tremors of limbs and body;

Although the above-mentioned diseases have their own diagnostic methods, such as imaging detection methods: brain CT, MRI, some anatomical changes can be found, and thus the diagnosis can be made. Some chemical substances can also be detected for evaluation. For example, Parkinson's disease can be detected by homovanillic acid (HVA), the final metabolite of DA in cerebrospinal fluid. However, brain imaging changes are absent in some patients. especially in early disease stages. Therefore, the application of the body stability evaluation system can detect the clues of the disease early, and is also conducive to the auxiliary diagnosis of patients with early body stability disorders.

The scope of application of the body stability evaluation system: 1. Early auxiliary diagnosis methods for nervous system diseases; 2. Limb stability evaluation: Some types of work and occupations require a high degree of limb stability, such as fine surgery, shooting, etc. The system can be used to evaluate the limb stability of relevant practitioners; it can also be used to evaluate the training effect.

Contents of the invention

The object of the present invention is to provide an image-based body stability evaluation method and device, which has non-contact measurement and auxiliary diagnosis for body stability evaluation, and is especially suitable for auxiliary diagnosis of patients with early body stability disorders. advantage.

The present invention is realized in this way, an image-based body stability evaluation method and device, by fixing a mark on the measured part of the patient, the movement of the measured part will drive the mark to move, the image acquisition unit is fixed, and the The computer connected to the image acquisition unit collects and saves the marked dynamic images. The data processing of the image sequence is realized by the image processing unit, and the coordinate positions marked in each figure are obtained, and the continuous coordinate point positions are taken as key nodes, which are interpolated into a curve, and the motion track of the measured part is restored. The main steps of the method include:

Set the mark: set the mark on the part of the patient to be measured, and ensure that the movement of the mark is consistent with the movement of the measured part. At the same time, the shape, color and position of the mark should be convenient for image collection and data processing. For example, the mark can be a dot that is obviously different from the color of the measurement site, or it can be other similar patterns or structures, so that the mark pattern is obvious after imaging;

Image Acquisition: Acquisition of continuous images of the movement state of specific parts of the patient. The image acquisition is completed by the data acquisition unit. The acquisition unit collects the images of the markers at a uniform time interval and saves the images in order; the data acquisition unit and the measured parts The distance and angle between them satisfy the following relationship: 1) The imaging of the marker in the camera is clear; 2) The marker is always within the field of view;

Image processing: first binarize the image, get the image corresponding to the mark and remove the data part other than the mark, through the central calculation method

(1)

(2)

Among them, threshold is the threshold set during binarization, p(i,j) is the pixel value of each point in the picture, m and n are the maximum values of the row and column respectively, and the coordinate position marked in the picture is obtained. Record the coordinate position point marked in the picture And the sequence number K of the corresponding picture, that is, the key point sequence reflecting the motion characteristics of the measured part is obtained;

Data analysis: Carry out curve interpolation on the discrete key point sequence to obtain the continuous curve of the continuous movement of the measured part during the measurement process. The amplitude, frequency and distribution parameters of the trajectory curve are extracted, and the evaluation results used to characterize the body stability are obtained by classifying and comparing the parameters.

The technical effect of the present invention is: the present invention provides an image-based body stability evaluation method and system, which is characterized by non-contact and automatic measurement, and further obtains its motion characteristics through image acquisition and image processing of specific parts of the patient. The result parameter. Therefore, the results are objective, reliable, and can be evaluated quantitatively.

Description of drawings

Fig. 1 is a flowchart of main steps of the present invention.

Fig. 2 is a structural schematic diagram of a specific embodiment of the present invention.

Fig. 3 is a schematic diagram of a characteristic marker for head movement according to the present invention.

Fig. 4 is a continuous graph obtained by interpolating marker points after a group of head movement measurements.

In the figure, 1, a camera 2, a lens 3, a measuring distance 4, a computer 5, a part to be measured 6, and a mark.

Detailed ways

The image-based body stability evaluation method and system provided by the present invention adopt the technical scheme of image acquisition unit + image acquisition and control unit + image processing unit + data analysis unit. Realize the evaluation of body stability, the specific process is as follows: the marker 6 with relatively obvious contrast is fixed on the part 5 to be tested of the object to be diagnosed, the imaging and analog-to-digital conversion of the marker 6 are realized by the image acquisition unit, and the image acquisition and control unit according to The set time continuously collects and saves multiple images marked with 6, and the image processing unit realizes the binarization processing of the image sequence and the calculation of the center coordinates of the marked points, and records the corresponding picture serial number and marked coordinate value, data analysis The unit interpolates all the marker points into a continuous curve, and calculates the amplitude and frequency characteristics of the interpolated continuous curve and analyzes the distribution of the curve to obtain the result parameters representing the motion characteristics of the body stability, and Classification of features according to parameters enables evaluation of body stability.

The present invention will be described in further detail below in conjunction with accompanying drawing and specific embodiment, but not as limiting the present invention;

As shown in Figure 2 and Figure 3, the first step is to set the mark, using a mark 6 with a relatively obvious contrast, and fixing the mark 6 on the measured part 5, the mark 6 is imaged to the camera 1 through the lens 2, and the measurement distance can be adjusted 3 To make the imaging clear, the data acquisition unit includes a lens 2 and a camera 1; the second step is to collect images, and the computer 4 connected to the acquisition unit completes the automatic collection and preservation of image data; the third step is to process the images, and the computer 3 completes the images The binarization and coordinate position calculation of the mark center, record the serial number of the current picture and the coordinate position of the mark center in the corresponding picture; the fourth step is to analyze the image, perform curve interpolation on the position coordinates of the mark points in each figure, and interpolate Calculate the amplitude and frequency characteristics of the final curve and analyze the distribution of the curves, classify and compare the parameters, and obtain the evaluation results used to characterize the stability of the body; in actual measurement, the part 5 to be measured can be made Make a hat, such as by marking the black dot 6 on the top of the hat, and then fix the hat on the top of the measured patient's head, so as to realize the marking of the head movement characteristics.

Fig. 1 is the main working steps of the image-based body stability evaluation method of the present invention, the first step is to set the mark; the second step is to collect the image; the third step is to process the image; the fourth step is to analyze the image. Except that the first step needs to be set before measurement, other steps are automatically realized by the software of the auxiliary diagnosis system.

Fig. 4 is a group of continuous curves obtained by interpolation of marker points after head movement measurement, and the curve reflects the continuous trajectory of the patient's head movement. Analyze the trajectory curve to obtain the amplitude, frequency and distribution characteristics of the measured part during movement, classify and compare the parameters, and obtain the evaluation results used to characterize the body stability.

To measure the head of a patient, the first step is to mark a black dot on the top of the white cap with a diameter of about 2mm. The measured patient wears the cap with the black mark, sits on the seat naturally, and ensures that the cap relatively fixed to the head. Adjust the bracket, adjust the camera to about 100mm from the top of the head, select the CMOS imaging sensor for the camera, and adjust the camera lens so that the black mark is clearly imaged in the camera. Keep the camera position and lens fixed. Step 2: The operator starts the image acquisition process, and the acquisition ends after one minute through the data acquisition and control unit. The sampling frequency is set to 10Hz, and the data acquisition program automatically completes the data storage in the designated folder. Step 3: From the first image to the last image, binarize the image and calculate the center coordinates of the marks in each image , saved to the array. Step 4: Interpolate the discrete coordinate points in the array into a continuous curve, that is, get the trajectory of the patient’s head movement within one minute of measurement, and calculate and analyze the value of the curve to obtain the amplitude, frequency and Distribution and other characteristic parameters, classify and compare the parameters, and obtain the evaluation results used to characterize the body stability; Table 1 Correspondence table of several common types of body stability and parameters,

.

Requirements for camera parameters in the above embodiments: the continuous acquisition speed is not less than 10 frames per second. In order to ensure that the measurement of small movements can reach 0.1mm, and it is suitable for the measurement of patients with large movement ranges, the resolution of the sensor should be greater than 1000*1000 pixels.

Certainly, the present invention also can have its multiple embodiment, under the situation of not departing from the spirit and essence of the invention, those skilled in the art can make various corresponding changes and distortions according to the present invention, but these corresponding changes All changes and modifications should belong to the appended claims and protection scope of the present invention.

Claims (8)

1. An image-based body stability evaluation method, characterized in that it comprises the steps: Set markers: set markers for the parts to be measured in patients with neurological lesions; Image acquisition: Acquisition of continuous images of the movement state of the parts to be measured in patients with neurological lesions; Image processing: extract the position of the feature points reflecting the motion state in each image; Data analysis: process and analyze the feature points to obtain the evaluation results used to represent the stability of the body. 2 . The image-based body stability evaluation method according to claim 1 , wherein the mark is a spot fixed on the site to be tested, so as to form a picture with obvious contrast after the final imaging of the mark. 3 . 3. a kind of body stability evaluation method based on image according to claim 1, it is characterized in that described image acquisition, in acquisition process, acquisition unit marks the position of patient according to unified time interval and unified working distance Carry out automatic continuous acquisition of images. 4. a kind of image-based body stability evaluation method according to claim 1, is characterized in that described image processing, comprises the binarization processing of image, feature point coordinate position in picture and the order sequence of picture extract; Among them, after the image is binarized and the data other than the marker is removed to obtain the feature point image, the central coordinate position (X, Y) of the feature point can be realized by formula (1) and formula (2), ,(1) ,(2) Among them, threshold is the threshold set during binarization, p(i,j) is the pixel value of each point in the figure, m and n are the maximum values of row and column respectively, ni and nj are the row and column directions of the image respectively The integral of the gray value greater than the threshold, N is the number of pixels greater than the threshold in the image; Record the coordinate position point marked in the picture And the serial number K of the corresponding picture, that is, the serial number of the key point reflecting the movement characteristics of the measured part is obtained. 5. A kind of body stability evaluation method based on image according to claim 1, it is characterized in that described data analysis, carry out curve interpolation to the position coordinate of mark point in each figure, and to the curve after interpolation, extract The amplitude and frequency characteristics of the trajectory curve and the curve distribution parameters are classified and compared to obtain the evaluation results used to characterize the body stability. 6. A kind of body stability evaluation method based on image according to claim 1, it is characterized in that comprising: image acquisition unit, is used for continuously recording the image sequence of patient's mark position motion state; Image acquisition and control unit, and image The acquisition unit is connected to be used to dynamically collect image data and realize the preservation of image data; the image processing unit is used to realize the position extraction of feature points reflecting the motion state in continuous image data; the data analysis unit is used to analyze many feature points The data is analyzed to analyze the movement state of the marked parts of the patient, so as to obtain the evaluation results used to characterize the stability of the body. 7. A method for evaluating body stability based on images according to claim 6, characterized in that said image acquisition unit comprises two parts, a camera and a lens. 8. A method for evaluating body stability based on images according to claim 6, characterized in that said image processing unit realizes the calculation and extraction of feature point position information reflecting the motion state of the parts to be measured in the image data.