Gait detection method and device, electronic equipment and storage medium

Abstract

The invention discloses a gait detection method and device, electronic equipment and a storage medium, and the method comprises the steps: comparing an obtained foot pressure image with a normal foot image, and judging whether the foot is a normal foot; if normal, contour extraction of the foot pressure image is carried out; if the detected foot pressure image is judged to be abnormal, determining a contour image of the subject under the condition that the foot is normal through the abnormal image; according to the foot contour images, the foot contour image distance is recognized, so that the distance between the two feet of the testee is judged, and the distance between the two feet of the testee is adjusted according to the test options. The distance between the two feet is automatically recognized through image recognition of foot pressure, the distance between the two feet of a subject is adjusted through the distance adjusting device for the two feet, the step pitch is conveniently and accurately adjusted, the testing result is more accurate, the subject is prevented from adjusting the step pitch for multiple times, and the burden of the subject is relieved.

Description

Technical Field

[0001] The present invention belongs to the technical field of gait detection, and in particular relates to a gait detection method, a device, an electronic device and a storage medium. Background Art

[0002] The detection method of three-posture gait is as follows: 1. Stand with both feet together for 10 seconds; 2. Stand with half-foot distance, with the toe of one foot facing the middle of the sole of the other foot together for 10 seconds; 3. Stand with the heel of one foot facing the toe of the other foot, and stay upright for 10 seconds; it is normal to maintain the above movements for 10 seconds or more, and less than 10 seconds or cannot be completed, indicating poor balance.

[0003] As modern aging becomes more and more serious, the trend of the elderly suffering from sarcopenia has increased significantly. Sarcopenia is a syndrome caused by continuous loss of skeletal muscle mass, strength and function. In the prior art, although there are various fitness guidance and correction equipment, there is a lack of equipment specifically for three-posture gait balance measurement on the market. The existing balance testing instruments are different from the three-posture gait measuring instruments in terms of application scope and function. Some instruments for three-posture gait measurement can only measure the three-posture gait by the subjects as required. However, in actual use, it is difficult for the elderly to control and adjust their gait, so it is difficult to quickly and accurately adjust to a suitable gait, resulting in low measurement accuracy and a long gait adjustment time, which increases the burden on the subjects. Summary of the invention

[0004] The object of the present invention is to provide a gait detection method, device, electronic device and storage medium, which are intended to automatically obtain and actively adjust the distance between the feet of a subject to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solution: a gait detection method, comprising the following steps: 1) Obtain foot pressure information, measure the pressure value of the detection area, and transmit it to the display terminal through current signals; 2) Compare the obtained foot pressure image with the normal foot image to determine whether it is a normal foot; 3) If normal, perform contour extraction of the foot pressure image; 4) If the detected foot pressure image is judged to be abnormal, the contour image of the subject's foot when it is normal is determined by the abnormal image; the specific method is: determine the abnormality of the subject's foot by an image recognition method, and extract the contour of the foot pressure image, determine the compensation distance of the foot contour image that needs to be compensated according to the severity of the abnormality, and adjust the position of the subject's foot contour image according to the required compensation distance; 5) Based on the foot contour image, the distance between the foot contour images is identified to determine the distance between the test subject's feet, and the distance between the test subject's feet is adjusted according to the test option.

[0006] Preferably, the test options include synchro stance, half-spacing stance and full-spacing stance.

[0007] Preferably, the image recognition method in step 4) is specifically: Collect a dataset of inversion feet that needs to be recognized by images. The dataset contains enough samples to cover various situations of target recognition. Preprocess the collected image data to improve the accuracy and efficiency of subsequent recognition; the preprocessing steps include image denoising, image enhancement, and image size adjustment; Use computer vision algorithms to extract feature information from preprocessed images. These features usually include edges, corners, textures, and color histograms. They can describe key information in the image and store them in the database. The input image is compared with the images in the database, and the most similar image is identified as the output to determine the subject's foot inversion and the inversion angle of the subject's foot inversion.

[0008] Preferably, the specific steps of identifying the distance between the two foot images in step 4) are as follows: first, compare the sizes of the two foot contour images. If the sizes of the two foot images are the same, select the two points with the smallest grayscale values ​​at the sole position and the heel position in the grayscale image, divide the foot contour image into left and right parts with a line connecting the two points, and connect the midpoints of the left and right parts, then obtain a mirror image of the left foot contour image, translate the mirror image to the right, translate the right foot contour image up and down, so that the mirror image coincides with the midpoint of the line connecting the midpoints of the right foot contour image, and measure the distance between the mirror image and the left foot contour image at this position, which is the distance between the subject's two feet. The purpose of this step is to avoid the problem of incorrect measurement of the distance between the two feet caused by different angles of the two feet when the subject is standing.

[0009] Preferably, if the sizes of the images of the two feet are different, the images of the two feet are scaled according to the average value of the pressure of the two feet and the ratio of the pressure of each foot, so that the scaled images of the two feet have the same size, and the problem of incorrect measurement of the distance between the two feet caused by different angles of the two feet when standing is solved according to the above steps.

[0010] Preferably, the specific method for determining the compensation distance of the footstep contour image that needs to be compensated in step 4) is: taking the ankle joint as the center of the circle A, the length from the ankle joint to the sole of the foot as l, and the inversion angle of the foot b, the contour of the subject's foot can be equated with an arc, and the offset distance can be determined by calculation. The offset distance is πlb / 180. To improve accuracy, the calculated offset distance is often greater than the actual value, and the error value is usually subtracted from the calculated result.

[0011] Preferably, in step 1), the foot pressure information is obtained by a pressure sensor, and the pressure sensor is arranged on the double-foot distance adjustment device, and the double-foot distance adjustment device also includes a shell, and a flat plate that can move left and right is arranged on the shell, and the pressure sensor is installed on the flat plate. A ball screw module driven by a motor is provided in the shell, and the ball screw module is connected to the flat plate. The flat plates on both sides are driven by the motor to move inward or outward, thereby adjusting the distance between the test subject's feet.

[0012] A gait detection device, comprising: Pressure acquisition module: used to obtain foot pressure information, measure the pressure value of the detection area, and transmit it to the display terminal through current signals; Image comparison module: used to compare the obtained foot pressure image with the normal foot image to determine whether it is a normal foot; Contour extraction module: used to extract the contour of normal foot pressure images; Distance compensation module: if the detected foot pressure image is judged to be abnormal, the contour image of the subject's foot under normal conditions is determined through the abnormal image; the specific method is: determine the abnormal condition of the subject's foot through an image recognition method, and extract the contour of the foot pressure image, determine the compensation distance of the foot contour image that needs to be compensated according to the severity of the abnormal condition, and adjust the position of the subject's foot contour image according to the required compensation distance; Distance adjustment module: used to identify the distance between the foot contour images based on the foot contour images, thereby determining the distance between the tester's feet and adjusting the distance between the tester's feet according to the test options.

[0013] An electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the gait detection method according to any one of claims 1 to 7.

[0014] A computer-readable storage medium stores computer instructions, wherein the computer instructions are used to enable a processor to implement the gait detection method according to any one of claims 1 to 7 when executed.

[0015] The technical effects and advantages of the present invention are as follows: by visually identifying the pressure on the feet, the distance between the two feet is automatically identified, and the distance between the two feet of the subject is adjusted by the two-foot distance adjustment device, so that the stride distance can be accurately adjusted, the test result is more accurate, and the subject is prevented from adjusting the stride distance multiple times, thereby reducing the burden on the subject; It also has the function of compensating for abnormal foot spacing, which solves the problem of abnormal stride caused by the change of foot pressure position due to foot diseases, thereby causing the acquired foot pressure image to shift, further improving the test accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a flow chart of the gait detection method of the present invention; Figure 2 It is a schematic structural diagram of the double-foot distance adjustment device of the present invention; Figure 3 This is a schematic diagram of the compensation distance calculation of the present invention; Figure 4 The present invention provides a schematic structural diagram of an electronic device. DETAILED DESCRIPTION

[0017] The specific embodiments of the present invention are further described below in conjunction with the accompanying drawings. It should be noted that the description of these embodiments is used to help understand the present invention, but does not constitute a limitation of the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0018] The present invention provides a gait detection method as shown in the figure, comprising the following steps: Step 1: Obtain foot pressure information through the thin film pressure sensor on the double-foot distance adjustment device. The thin film pressure sensor can measure the pressure value of the detection area through the change of the piezoresistance of the pressure acquisition board with the pressure, and transmit it to the display terminal through the current signal; the displayed footstep pressure picture shows the size of the pressure through different colors; Step 2: Compare the obtained foot pressure image with the normal foot image to determine whether it is a normal foot. If it is normal, extract the contour of the foot pressure image; Step 3: Obtain the foot pressure distribution map and convert the image into a grayscale image; use the Sobel operator to calculate the gradient amplitude and direction of the image; traverse the image, if the grayscale value of a pixel is not the largest in its gradient direction, set it to zero, that is, it is a non-edge point; use the double threshold algorithm to detect and connect the edge points to obtain the final contour image; Step 4: Identify the distance between the two feet images, thereby determining the distance between the tester's feet, and remind the tester to adjust the appropriate distance between the two feet according to the test options; The specific steps of identifying the distance between the two foot images are as follows: first, compare the sizes of the two foot contour images. If the sizes of the two foot images are the same, select the two points with the smallest grayscale values ​​at the sole position and the heel position in the grayscale image. The sole position and the heel position are the two areas with the largest sole pressure. These two positions can be easily identified through image recognition. Then, compare the grayscale values ​​of the pixels in the two areas respectively, and identify the points with the smallest grayscale values ​​in the two areas. If there are several points with the smallest grayscale in the two areas, take the outermost minimum point as the contour, and identify the center point of the contour. Use the center point as the representation of the point with the smallest grayscale value. Use the line connecting the two points to divide the foot contour image into left and right parts, and connect the midpoints of the left and right parts. Then obtain the mirror image of the left foot contour image, translate the mirror image to the right, translate the right foot contour image up and down, so that the midpoint of the mirror image and the line connecting the midpoints of the right foot contour image coincide with each other, and measure the distance between the mirror image and the left foot contour image at this position, which is the distance between the subject's feet. The purpose of this step is to avoid the problem of incorrect measurement of the distance between the feet caused by different angles of the two feet when the subject is standing.

[0019] If the sizes of the images of the two feet are different, the images of the two feet are scaled according to the average pressure of the two feet and the ratio of the pressure of each foot, so that the scaled images of the two feet are the same size, and the above steps are followed to solve the problem of incorrect measurement of the distance between the two feet caused by different angles of the two feet when standing.

[0020] Step 5: If the detected foot pressure image is judged to be abnormal, the contour image of the subject's foot under normal conditions is determined through the abnormal image; here, the foot inversion is used as an example for explanation; when the foot is inverted, the subject's foot contour image cannot correctly reflect the standing state of the foot under normal conditions, and is closer to the outside than the normal foot contour image. Therefore, the subject's specific foot inversion condition can be determined through an image recognition method, thereby determining the foot contour image of the subject with inverted feet under normal conditions. The specific method is as follows: Data collection: Collect a dataset of inversion feet that needs to be recognized by image recognition. The dataset contains enough samples to cover various situations of target recognition. Data preprocessing: preprocess the collected image data to improve the accuracy and efficiency of subsequent recognition; the preprocessing steps include image denoising (calculating the weighted average of pixels in the window through Gaussian function to smooth the image), image enhancement (adjusting the histogram distribution of the image through histogram equalization to make the grayscale distribution of the image more uniform, thereby improving the contrast), image resizing (correcting geometric distortion in the image, such as rotation, scaling, and translation), and other operations; Feature extraction: Use computer vision algorithms to extract useful feature information from preprocessed images. These features usually include edges, corners, textures, color histograms, etc. They can describe the key information in the image and store them in the database; Search and match: compare the input image with the images in the database, identify the most similar image as output, determine the subject's foot inversion, and determine the inversion angle of the subject's foot inversion; According to the condition of inversion of the foot, the compensation distance of the footstep contour image that needs to be compensated is determined. The compensation distance can be determined based on experience and the severity level, or can be determined by calculation. According to the required compensation distance, the position of the subject's foot contour image is adjusted, and the distance between the two feet is calculated according to the adjusted foot contour image; Specifically, the test options include standing with feet together, standing with half feet apart, and standing with full feet apart.

[0021] Specifically, Figure 3 As shown, the method for determining the compensation distance by calculation is to take the ankle joint as the center of the circle A, and the length from the ankle joint to the sole of the foot as l. According to step five, the inversion angle b of the foot inversion (i.e., the deflection angle of the line connecting the ankle joint to the sole of the foot) can be known, and because the inversion angle is limited, the contour of the subject's foot can be equated with an arc, and the offset distance can be determined by calculation. The offset distance is πlb / 180. To improve accuracy, the calculated offset distance is often greater than the actual value. Usually, the error value is subtracted from the calculated result, and the error value is 0.2-1cm.

[0022] Specifically, Figure 2 As shown, the device for adjusting the distance between two feet includes a shell 1, on which a flat plate that can move left and right is arranged, on which a pressure sensor 2 is installed, and the pressure sensor 2 is a thin film pressure sensor, and a ball screw module driven by a motor is provided in the shell 1, and the ball screw module is connected to the flat plate, and the flat plates on both sides are driven by the motor to move inward or outward, thereby adjusting the distance between the two feet of the subject.

[0023] Figure 4 The electronic device 10 is a block diagram for implementing an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0024] like Figure 4As shown, the electronic device 10 includes at least one processor 11, and a read-only memory (ROM) 12, a random access memory (RAM) 13, etc. that are communicatively connected to the at least one processor 11, wherein the memory stores a computer program that can be executed by the at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13, and various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12 and RAM 13 are connected to each other through the CAN bus 14; the host computer 15 is also connected to the bus 14 through the CAN control module.

[0025] Multiple components in the electronic device 10 are connected to the host computer 15, including: an input unit 16, which refers to a pressure sensor for inputting foot pressure; an output unit 17, which refers to a display for outputting a foot pressure image; a storage unit 18, such as a disk, an optical disk, etc.; and a controller 19, such as a plc controller, for controlling the movement of the ball screw module; The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a gait detection method.

[0026] In some embodiments, the gait detection method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the gait detection method described above may be performed, and the ball screw module may be controlled by the controller 19 to adjust the distance between the feet of the subject.

[0027] When using it, the subject stands barefoot on the flat board and starts the three-position test. After hearing the voice prompt "Start the test" from the device, he / she performs the first action. The first action, 'standing with feet together', required the subjects to stand according to the foot image on the flat board to meet the requirement of standing with feet together; The second action test 'half-foot stance' can be performed only after the first action is completed; After completing the second action test 'half-foot-distance standing', the third action test 'full-foot-distance standing' was performed; After completing the second step test 'half-foot stance', proceed to the third step test 'full-foot stance'; The test is completed by maintaining each test action for 10 seconds.

[0028] No less than 4 detection points are set on each of the left and right foot images on the tablet to detect whether there is pressure there. When the number of pressure detection points on both feet detected is equal to 8 points or exceeds 8 points, the test can be performed. When the number of pressure detection points on both feet detected is less than 4, or there is no pressure value at all detection points of one foot, the user is prompted to check whether the standing position is correct.

[0029] Compared with the traditional method, the present invention does not need to rely on the subjective judgment of the tester, and automatically adjusts the distance between the two feet accurately, thereby greatly improving the accuracy of the test results.

[0030] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A gait detection method, characterized in that: The steps include: 1) Obtain foot pressure information, measure the pressure value of the detection area, and transmit it to the display terminal through current signals; 2) Compare the obtained foot pressure image with the normal foot image to determine whether it is a normal foot; 3) If normal, perform contour extraction of the foot pressure image; 4) If the detected foot pressure image is judged to be abnormal, the contour image of the subject's foot when it is normal is determined by the abnormal image; the specific method is: determine the abnormality of the subject's foot by an image recognition method, and extract the contour of the foot pressure image, determine the compensation distance of the foot contour image that needs to be compensated according to the severity of the abnormality, and adjust the position of the subject's foot contour image according to the required compensation distance; 5) Based on the foot contour image, the distance between the foot contour images is identified to determine the distance between the test subject's feet, and the distance between the test subject's feet is adjusted according to the test option.

2. A gait detection method according to claim 1, characterized in that: The test options include synchro stance, half-spacing stance, and full-spacing stance.

3. A gait detection method according to claim 1, characterized in that: The image recognition method in step 4) is specifically as follows: Collect a dataset of inversion feet that needs to be recognized by images. The dataset contains enough samples to cover various situations of target recognition. Preprocess the collected image data to improve the accuracy and efficiency of subsequent recognition; the preprocessing steps include image denoising, image enhancement, and image size adjustment; Use computer vision algorithms to extract feature information from preprocessed images. These features usually include edges, corners, textures, and color histograms. They can describe key information in the image and store them in the database. The input image is compared with the images in the database, and the most similar image is identified as the output to determine the subject's foot inversion and the inversion angle of the subject's foot inversion.

4. A gait detection method according to claim 1, characterized in that: The specific steps for identifying the distance between the two foot images in step 4) are as follows: first, compare the sizes of the two foot contour images. If the sizes of the two foot images are the same, select the two points with the smallest grayscale values ​​at the sole position and the heel position in the grayscale image, divide the foot contour image into left and right parts with a line connecting the two points, and connect the midpoints of the left and right parts, then obtain a mirror image of the left foot contour image, translate the mirror image to the right, translate the right foot contour image up and down, so that the mirror image coincides with the midpoint of the line connecting the midpoints of the right foot contour image, and measure the distance between the mirror image and the left foot contour image at this position, which is the distance between the subject's two feet. The purpose of this step is to avoid the problem of incorrect measurement of the distance between the two feet caused by different angles of the two feet when the subject is standing.

5. A gait detection method according to claim 4, characterized in that: If the sizes of the images of the two feet are different, the images of the two feet are scaled according to the average value of the pressure of the two feet and the ratio of the pressure of each foot, so that the sizes of the scaled images of the two feet are the same, and the problem of incorrect measurement of the distance between the two feet caused by different angles of the two feet when standing is solved according to the above steps.

6. A gait detection method according to claim 1, characterized in that: The specific method for determining the compensation distance of the footstep contour image that needs to be compensated in step 4) is: taking the ankle joint as the center of the circle A, the length from the ankle joint to the sole of the foot as l, and the inversion angle of the foot b, the contour of the subject's foot can be equated with an arc, and the offset distance can be determined by calculation. The offset distance is πlb / 180. To improve accuracy, the calculated offset distance is often greater than the actual value, and the error value is usually subtracted from the calculated result.

7. A gait detection method according to claim 1, characterized in that: In the step 1), the pressure sensor (2) is used to obtain the foot pressure information. The pressure sensor (2) is arranged on the double-foot distance adjustment device. The double-foot distance adjustment device further comprises a housing (1). A flat plate that can move left and right is arranged on the housing (1). The pressure sensor (2) is mounted on the flat plate. A ball screw module driven by a motor is provided in the housing (1). The ball screw module is connected to the flat plate. The flat plates on both sides are driven by the motor to move inward or outward, thereby adjusting the distance between the two feet of the subject.

8. A gait detection device, characterized in that: include: Pressure acquisition module: used to obtain foot pressure information, measure the pressure value of the detection area, and transmit it to the display terminal through current signals; Image comparison module: used to compare the obtained foot pressure image with the normal foot image to determine whether it is a normal foot; Contour extraction module: used to extract the contour of normal foot pressure images; Distance compensation module: if the detected foot pressure image is judged to be abnormal, the contour image of the subject's foot under normal conditions is determined through the abnormal image; the specific method is: determine the abnormal condition of the subject's foot through an image recognition method, and extract the contour of the foot pressure image, determine the compensation distance of the foot contour image that needs to be compensated according to the severity of the abnormal condition, and adjust the position of the subject's foot contour image according to the required compensation distance; Distance adjustment module: used to identify the distance between the foot contour images based on the foot contour images, thereby determining the distance between the tester's feet and adjusting the distance between the tester's feet according to the test options.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the gait detection method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the gait detection method according to any one of claims 1 to 7 when executed.

Images