A method and device for detecting a slither

Abstract

The application discloses a snake running detection method and a detection device. The method comprises the following steps: receiving an image of an examination area, wherein the image comprises a ground image and a plurality of stand images; setting a rectangular area at each stand in the image of the examination area, wherein the rectangular area covers the stand image, and size information of each rectangular area is extracted; based on an image pixel array, edge pixels of the stand image in the rectangular area are identified to obtain an edge pixel identification column and an edge pixel identification total number; and according to the size information of the rectangular area and the edge pixel identification total number, the stand in the examination area is calibrated to determine whether the stand exists in the rectangular area. The application especially improves the accuracy of stand detection in snake running, and avoids the influence of the environment and light on the detection result.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of sports measurement, in particular to a snake run detection method and a detection device. BACKGROUND

[0002] In order to improve the speed and sensitivity comprehensive quality, the rapid change direction movement ability, the snake run is the test item in the sports training examination, and the detailed training method and the rule breaking action are stipulated, the judgment whether the vertical rod falls in the traditional snake run adopts the artificial detection, and the detection is not accurate. The snake run test equipment based on computer vision appears on the market, some of these devices are based on the color of the vertical rod to calculate and judge whether the vertical rod falls, but because of the environment, the light is complex, etc., the color of the vertical rod will change with the change of the light, so the measurement result is unstable, some devices add sensors, but increase the cost and complexity of the device, and the stability is not good. SUMMARY

[0003] Based on this, the present application provides a snake run detection method and a detection device, which solves the problems of low detection accuracy of the vertical rod in the snake run and the influence of the detection result by the environment and light.

[0004] The snake run detection method provided by the present application comprises:

[0005] Receiving an image of an evaluation area, the image comprising a ground image and a plurality of vertical rod images;

[0006] Setting a rectangular area at each vertical rod in the image of the evaluation area, the rectangular area covering the vertical rod image, and extracting size information of each rectangular area;

[0007] Based on an image pixel array, identifying edge pixels of the vertical rod image in the rectangular area to obtain an edge pixel identification column and an edge pixel identification total number;

[0008] According to the size information of the rectangular area and the edge pixel identification total number, calibrating the vertical rod of the evaluation area to determine whether the vertical rod exists in the rectangular area.

[0009] Further, the method for covering the vertical rod image by the rectangular area is:

[0010] The rectangular area only covers a part of the vertical rod close to the ground end.

[0011] Further, the extraction of the size information of each rectangular area comprises:

[0012] Extracting a vertex pixel coordinate, a horizontal direction pixel length and a vertical direction pixel length of the rectangular area in the image of the evaluation area.

[0013] Further, the image pixel array is based on, the edge pixel of the vertical rod image in the rectangular region is identified, the edge pixel identification column and the edge pixel identification total number are obtained, comprising:

[0014] The edge pixel value of the vertical rod image in the rectangular region is set to 1, and the pixel value of the pixel in the rectangular region except the edge of the vertical rod image is set to 0;

[0015] The rectangular region corresponds to a pixel matrix, in the pixel matrix, starting from the coordinates of the top vertex pixel of the rectangular region, the edge pixel value of the vertical rod image is identified along the pixel length of the horizontal direction of the rectangular region column by column, when the number of pixels with the edge pixel value of 1 continuously appearing on any column is greater than or equal to a preset pixel number, the continuous pixel is recorded as an edge pixel identification column, and the number of edge pixels in the column is recorded;

[0016] The pixel number of all the columns is accumulated to obtain the edge pixel identification total number.

[0017] Further, the vertical rod of the evaluation region is calibrated according to the size information of the rectangular region and the edge pixel identification total number, whether the vertical rod exists in the rectangular region is determined, comprising:

[0018] The pixel ratio is obtained by taking the ratio of the edge pixel identification total number and twice the pixel length of the vertical direction of the rectangular region;

[0019] The pixel ratio is compared with a preset threshold value, if the pixel ratio is greater than the preset threshold value, it is determined that the vertical rod exists in the rectangular region, otherwise, the vertical rod does not exist in the rectangular region.

[0020] Further, the detection method further comprises: starting the test when the image of the first time when the testee enters the evaluation region is received after all the rectangular regions are calibrated with the vertical rod.

[0021] The image of the evaluation region in the test process is obtained in real time, the corresponding edge pixel identification total number of each rectangular region is identified, whether the corresponding vertical rod is calibrated in each rectangular region is determined, if yes, the test is ended when the image of the testee reaching the end point of the evaluation region is received, and the test time is obtained; if not, it is determined that the vertical rod is reversed and the test result is invalid.

[0022] Further, the method for obtaining the test time comprises: the difference between the time when the image of the testee reaching the end point of the evaluation region is received and the time when the image of the testee first entering the evaluation region is received.

[0023] The application also provides a snake-shaped running detection device, the device comprises:

[0024] receiving an image of the examination area, the image comprising a ground image and a plurality of pole images;

[0025] setting a rectangular region at each pole in the image of the examination area, the rectangular region covering the pole image, and extracting size information of each rectangular region;

[0026] identifying edge pixels of the pole image in the rectangular region based on an image pixel array, obtaining an edge pixel identification column and an edge pixel identification total number;

[0027] calibrating the pole in the examination area according to the size information of the rectangular region and the edge pixel identification total number, and determining whether the pole exists in the rectangular region.

[0028] Further, the device further comprises:

[0029] starting timing when it is determined that all the rectangular regions are calibrated with the poles, and receiving an image of the first time when the tester enters the examination area;

[0030] determining whether the corresponding pole is calibrated in each rectangular region after the image of the examination area in the test process is obtained in real time by the receiving module, and the corresponding edge pixel identification total number of each rectangular region is identified by the identification module, if yes, obtaining the test time when the test ends, if no, determining that the pole is reversed and the test result is invalid;

[0031] ending timing when it is determined that the corresponding pole exists in each rectangular region by the result judgment module, and receiving an image of the tester reaching the end point of the examination area.

[0032] The present application provides a method for detecting a snake run, which sets a rectangular region at each pole in the image of the examination area, extracts size information of each rectangular region, then identifies edge pixels of the pole image in the rectangular region based on an image pixel array, obtains an edge pixel identification column and an edge pixel identification total number, and finally calibrates whether the pole exists in the set rectangular region according to the size information of each rectangular region and the edge pixel identification total number. The present application improves the accuracy of the pole detection in the snake run, and avoids the influence of the environment and light on the detection result. BRIEF DESCRIPTION OF DRAWINGS

[0033] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments. Obviously, the drawings described below only constitute some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative effort based on these drawings.

[0034] Figure 1 A flowchart of a serpentine running detection method provided by the embodiment of the present application is shown in the figure.

[0035] Figure 2 A flowchart of obtaining edge pixel identification vertical column and total number of edge pixel identification provided by the embodiment of the present application is shown in the figure.

[0036] Figure 3 A flowchart of pole erecting calibration provided by the embodiment of the present application is shown in the figure.

[0037] Figure 4 A flowchart of another serpentine running detection method provided by the embodiment of the present application is shown in the figure.

[0038] Figure 5 A schematic diagram of a serpentine running detection device provided by the embodiment of the present application is shown in the figure.

[0039] Figure 6 A schematic diagram of another serpentine running detection device provided by the embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0040] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used in the description of the specification herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the description and the claims herein and the above description of drawings herein contain terminology that the applicant believes are not under patent or application in patent by another party; the terminology of the specification and the claims herein and the above description of drawings herein contains the terms“comprising”,“having” and“including” and their variations thereof that are intended to cover a non-exclusive inclusion; the terms“first”,“second”, and the like in the description and the claims herein and the above description of drawings herein are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order.

[0041] Reference herein to“an embodiment” means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase that in various places in the specification are not necessarily all referring to the same embodiment, nor are they necessarily mutually exclusive of one another. It is expressly understood that the embodiments described herein are merely examples from a whole class of embodiments of which the application is a part. It is further expressly understood that the application is intended to encompass all structures and their equivalents that do not depart from the spirit of the application.

[0042] In order to make the purposes, technical solutions and advantages of the present application clearer, further detailed description will be made to the present application in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not used to limit the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0043] In the following description, the suffix such as "module", "component" or "unit" used to represent elements is only for the convenience of the description of the present application, and has no specific meaning in itself.

[0044] Embodiment 1

[0045] As shown in the flowchart of a snake running detection method provided by an embodiment of the present application, the method comprises: Figure 1

[0046] Step S1: receiving an image of an evaluation area, the image comprising a ground image and a plurality of pole images;

[0047] Specifically, in the present embodiment, a total of 7 poles are arranged in the evaluation area, and the 7 poles are arranged in staggered manner on the left and right sides along the advancing direction of the tester, wherein 4 poles are arranged on the same straight line on one side, 3 poles are arranged on the same straight line on the other side, and the two straight lines are parallel. In the evaluation process, the tester needs to start from the left side where 4 poles are arranged, pass by all the poles in order, and finally return to the right side where 3 poles are arranged to complete the test. After the evaluation area is arranged, the image information of the evaluation area is obtained by an external device, specifically by a test device with camera function. The image information comprises ground image information and pole image information.

[0048] Step S2: setting a rectangular area at each pole in the image of the evaluation area, the rectangular area covering the pole image, and extracting the size information of each rectangular area;

[0049] Specifically, the rectangular areas of the 7 poles are marked in the image of the evaluation area by manual or automatic recognition, the rectangular areas cover the pole images, and then the size information of each rectangular area in the image is extracted. The marked rectangular area serves as the basis for pole detection. It should be noted that the rectangular frame area does not change with the movement of the pole without calibration operation.

[0050] Step S3: based on the image pixel array, identifying the edge pixels of the pole image in the rectangular area to obtain the edge pixel identification column and the total number of edge pixel identification;

[0051] ​Specifically, a rectangular region corresponds to an image pixel matrix, edge pixels of a vertical rod image in the rectangular region are identified, if the edge pixels meet the continuity condition in the column where the image pixel matrix is located, the continuous pixels are marked as edge pixel identification columns, and the length of the edge pixel identification column is the number of the continuous pixels. The pixel number of all edge pixel identification columns is accumulated to obtain the total number of edge pixel identification.

[0052] Step S4: According to the size information of the rectangular region and the total number of edge pixel identification, the vertical rod in the evaluation region is calibrated to determine whether the vertical rod exists in the rectangular region.

[0053] Specifically, according to the size information of the rectangular region obtained in step S2 and the total number of edge pixel identification obtained in step S3, whether the vertical rod exists in the set rectangular region is calibrated.

[0054] In some embodiments, the method for covering the vertical rod image by the rectangular region is that the rectangular region only covers a part of the vertical rod close to the ground.

[0055] Specifically, the set rectangular region only needs to cover a part of the vertical rod close to the ground. For example, the commonly used vertical rod is a red and white alternating color section vertical rod, and the rectangular region only needs to cover a color section close to the ground, so that the data processing amount can be reduced.

[0056] In some embodiments, the size information of each rectangular region includes the coordinates of a top pixel of the rectangular region in the image of the evaluation region, the horizontal pixel length and the vertical pixel length. The top point can be the top left corner of the rectangular region, and the pixel length is a specific number of pixels.

[0057] Specifically, after setting each rectangular region, the size information of the rectangular region of each vertical rod is set by manual or automatic identification. , wherein, is the coordinates of the top left corner pixel of the rectangular region, is the horizontal pixel length of the rectangular region, i.e. the width, is the vertical pixel length of the rectangular region, i.e. the height.

[0058] In some embodiments, as shown in Figure 2 , it is a flowchart for obtaining edge pixel identification columns and the total number of edge pixel identification provided by the embodiment of the present application, and step S3 includes:

[0059] Step S31: Set the edge pixel value of the vertical rod image in the rectangular region to 1, and the pixel value in the rectangular region except the edge of the vertical rod image to 0;

[0060] Step S32: The rectangular region corresponds to a pixel matrix. In the pixel matrix, starting from the coordinates of the vertex pixel of the rectangular region, the edge pixel values ​​of the pole image are identified column by column along the horizontal pixel length of the rectangular region. When any column has consecutive pixels with an edge pixel value of 1 and the number of such pixels is greater than or equal to a preset number of pixels, the consecutive pixels are recorded as forming an edge pixel identification column and the number of edge pixels in the column is recorded.

[0061] Step S33: Accumulate the number of pixels in all the columns to obtain the total number of edge pixels identified.

[0062] Specifically, within the defined rectangular region, pixels at the pole's edge are set to 1, while pixels outside the edge are set to 0. In the pixel matrix corresponding to the rectangular region, starting from the coordinates of the top-left vertex pixel of the rectangular region, the edge pixel values ​​of the pole image are identified column by column along the horizontal pixel length of the rectangular region. When any column contains consecutive pixels with an edge pixel value of 1 and the number of such pixels is greater than or equal to a preset number of pixels, the edge pixel value is determined. (like If the consecutive pixels form an edge pixel identification column, then record the number of edge pixels in the column; accumulate the number of pixels in all columns to obtain the total number of edge pixel identifications, specifically: Let This refers to the number of edge pixels in a specific column of an image array that is identified in real time. In order to be in After meeting certain conditions, the edge pixel recognition columns are then all edge pixel recognition columns. Number of edge pixels in The sum is the total number of edge pixels identified. .set up These are the pixel coordinates in the image pixel array. The x-axis is... The vertical axis is , For pixel values, The horizontal pixel length of the rectangular region. This represents the vertical pixel length of the rectangular region. The following is an example of edge pixel identification in the vertical column:

[0063]

[0064] In some embodiments, such as Figure 3 The diagram shown is a flowchart of a pole calibration method according to an embodiment of the present invention. Step S4 includes:

[0065] Step S41: The pixel ratio is obtained by comparing the total number of edge pixels with twice the vertical pixel length of the rectangular region;

[0066] Step S42: comparing the pixel ratio with a preset threshold value, if the pixel ratio is greater than the preset threshold value, it is determined that the vertical rod exists in the rectangular region, otherwise, the vertical rod does not exist in the rectangular region.

[0067] Specifically, in the embodiment of the present application, the preset threshold value is (as ), the total number of edge pixel recognition is , the total number of edge pixel recognition is twice the pixel ratio of the pixel length in the vertical direction of the rectangular region (that is, the height of the rectangular region). The pixel ratio is:

[0068]

[0069] If is greater than , it is determined that the vertical rod exists in the rectangular region, otherwise, the vertical rod does not exist in the rectangular region.

[0070] In some embodiments, as shown in Figure 4 , another flowchart of the detection method provided by the embodiment of the present application is provided, and the detection method further comprises:

[0071] Step S51: after determining that all the rectangular regions are marked with vertical rods, starting the test when the image of the first time when the testee enters the test area is received;

[0072] Step S52: real-time acquiring the image of the test area in the test process, identifying the corresponding total number of edge pixel recognition of each rectangular region, determining whether the corresponding vertical rod is marked in each rectangular region, if yes, ending the test when the image of the testee reaching the end of the test area is received and acquiring the test time; if no, determining that the vertical rod is reversed and the test result is invalid.

[0073] Specifically, after determining that all the rectangular regions are marked with vertical rods, starting the test when the image of the first time when the testee enters the test area is received; real-time acquiring the image of the test area in the test process, identifying the corresponding total number of edge pixel recognition of each rectangular region, and the preset threshold value is (as ), the total number of edge pixel recognition is , the total number of edge pixel recognition is twice the pixel ratio of the pixel length in the vertical direction of the rectangular region (that is, the height of the rectangular region). The pixel ratio is:

[0074]

[0075] If greater than , it is determined that no inverted pole appears in each rectangular region, the test is ended and the test time is obtained when the image of the tester reaching the end point of the test area is received; if not, it is determined that there is an inverted pole and the test result is invalid.

[0076] In some embodiments, the method for obtaining the test time comprises: subtracting the time when the image of the tester reaching the end point of the test area is received from the time when the image of the tester first entering the test area is received.

[0077] Specifically, in the test process, the tester needs to start from a first time point at which four vertical poles are arranged on one side, pass all the vertical poles in sequence, and finally return to the end point at which three vertical poles are arranged on the other side to complete a second time point, and the time difference between the first time point and the second time point is the test time.

[0078] Embodiment 2

[0079] Based on the above snake running detection method, the embodiment of the present application provides a schematic diagram of a snake running detection device, as shown in Figure 5 , which comprises:

[0080] The receiving module 401 is configured to receive the image of the test area, wherein the image comprises a ground image and a plurality of vertical pole images.

[0081] The setting module 402 is configured to set a rectangular region at each vertical pole in the image of the test area, wherein the rectangular region covers the vertical pole image, and the size information of each rectangular region is extracted.

[0082] The identification module 403 is configured to identify the edge pixels of the vertical pole image in the rectangular region based on the image pixel array, and obtain the edge pixel identification column and the total number of edge pixel identifications.

[0083] The calibration module 404 is configured to calibrate the vertical pole of the test area according to the size information of the rectangular region and the total number of edge pixel identifications, and determine whether the vertical pole exists in the rectangular region.

[0084] In some embodiments, as shown in Figure 6 , another schematic diagram of a snake running detection device is provided, and the device further comprises:

[0085] The timing starting module 405 is configured to start timing when the image of the tester first entering the test area is received after it is determined that all the rectangular regions are calibrated with vertical poles in the image of the test area.

[0086] The achievement judging module 406 is configured to determine whether a corresponding vertical rod is calibrated in each of the rectangular regions after the receiving module acquires the image of the test area in real time and the identifying module identifies the total number of corresponding edge pixels of each of the rectangular regions. If yes, the test time is acquired when the test ends. If no, it is determined that the rod is inverted and the test result is invalid.

[0087] The timing ending module 407 is configured to end the timing when the achievement judging module determines that the corresponding vertical rod exists in each of the rectangular regions and the image of the testee reaching the end point of the test area is received.

[0088] For other details of the implementation of the above technical solutions by each module in the above snake running detection device, refer to the description of the snake running detection method provided in the above application embodiments, which will not be repeated here.

[0089] The above provides a detailed introduction to the technical solutions of the present application. The principles and implementation manners of the present application are described by using specific examples. The above example is only used to help understand the method and core idea of the present application. Meanwhile, for those skilled in the art, the specific implementation manners and application ranges will be changed according to the idea of the present application. In conclusion, the content of the specification should not be understood as a limitation of the present application.

Claims

1. A method of detecting a snake run, characterized by, The method comprises: receiving an image of an examination area, the image comprising a ground image and a plurality of pole images; setting a rectangular area at each pole in the image of the examination area, the rectangular area covering the pole image, and extracting size information of each rectangular area; based on an image pixel array, identifying edge pixels of the pole image in the rectangular area, to obtain an edge pixel identification column and an edge pixel identification total number; wherein a rectangular area corresponds to an image pixel matrix, and the edge pixels of the pole image in the rectangular area are identified, if the edge pixels meet the continuity condition in the column where the image pixel array is located, the continuous pixels are marked as the edge pixel identification column, and the length of the edge pixel identification column is the number of the continuous pixels, and the pixel numbers of all the edge pixel identification columns are accumulated to obtain the edge pixel identification total number; based on the size information of the rectangular area and the edge pixel identification total number, calibrating the pole of the examination area, to determine whether the pole exists in the rectangular area; the calibration of the pole of the examination area based on the size information of the rectangular area and the edge pixel identification total number to determine whether the pole exists in the rectangular area comprises: using the edge pixel identification total number and twice the pixel length of the vertical direction of the rectangular area as a ratio to obtain a pixel ratio; comparing the pixel ratio with a preset threshold value, if the pixel ratio is greater than the preset threshold value, it is determined that the pole exists in the rectangular area, otherwise, the pole does not exist in the rectangular area.

2. The snake run detection method according to claim 1, wherein the method for covering the pole image by the rectangular area comprises: the rectangular area only covers a part of the pole close to the ground.

3. The snake run detection method of claim 1, wherein the extraction of the size information of each rectangular area comprises: extracting the coordinates of a vertex pixel of the rectangular area in the image of the examination area, the horizontal pixel length and the vertical pixel length.

4. The snake run detection method of claim 3, wherein the identification of the edge pixels of the pole image in the rectangular area based on the image pixel array to obtain the edge pixel identification column and the edge pixel identification total number comprises: setting the edge pixels of the pole image in the rectangular area as 1, and the pixels other than the edge pixels of the pole image in the rectangular area as 0; the rectangular area corresponds to a pixel matrix, in which, starting from the coordinates of the vertex pixel of the rectangular area, the edge pixel values of the pole image are identified column by column along the horizontal pixel length of the rectangular area, and when the pixels with the edge pixel value of 1 appear continuously in any column and the number of the pixels is greater than or equal to a preset pixel number, the continuous pixels are recorded as an edge pixel identification column, and the number of the edge pixels in the column is recorded; the pixel numbers of all the columns are accumulated to obtain the edge pixel identification total number.

5. The serpentine running detection method as described in claim 1, characterized in that, the detection method further comprises: when it is determined that all the rectangular areas are calibrated with the poles in the image of the examination area, starting from the image when the tester first enters the examination area, the test is started. Real-time image of the test area is acquired, the total number of the corresponding edge pixels of each rectangular area is identified, it is determined whether the corresponding vertical rod is calibrated in each rectangular area, if yes, the test is ended and the test time is acquired when the image of the terminal point of the test area reached by the tester is received; if not, it is determined that the vertical rod is inverted and the test result is invalid.

6. The snake run detection method of claim 5, wherein, The method for acquiring the test time comprises: subtracting the time when the image of the terminal point of the test area reached by the tester is received from the time when the image of the tester entering the test area for the first time is received.

7. A serpentine running detection device characterized by comprising: The device comprises: a receiving module for receiving the image of the test area, the image comprising a ground image and a plurality of vertical rod images; a setting module for setting a rectangular area at each vertical rod in the image of the test area, the rectangular area covering the vertical rod image, and extracting the size information of each rectangular area; an identifying module for identifying the edge pixels of the vertical rod image in the rectangular area based on the image pixel array, obtaining the edge pixel identification column and the total number of the edge pixels; wherein one rectangular area corresponds to one image pixel matrix, the edge pixels of the vertical rod image in the rectangular area are identified, if the edge pixels meet the continuity condition in the column where the image pixel array is located, the continuous pixels are marked as the edge pixel identification column, and the length of the edge pixel identification column is the number of the continuous pixels, and the total number of the edge pixels is obtained by accumulating the number of pixels of all the edge pixel identification columns; a calibration module for calibrating the vertical rod of the test area according to the size information of the rectangular area and the total number of the edge pixels, and determining whether the vertical rod exists in the rectangular area, the calibration of the vertical rod of the test area according to the size information of the rectangular area and the total number of the edge pixels, and the determination of whether the vertical rod exists in the rectangular area, comprises: obtaining a pixel ratio by dividing the total number of the edge pixels by twice the length of the pixels in the vertical direction of the rectangular area; comparing the pixel ratio with a preset threshold value, if the pixel ratio is greater than the preset threshold value, it is determined that the vertical rod exists in the rectangular area, otherwise, the vertical rod does not exist in the rectangular area.

8. The serpentine run detection device of claim 7, wherein, The device further comprises: a timing starting module for starting timing when the image of the tester entering the test area for the first time is received after it is determined that all the rectangular areas are calibrated with the vertical rod in the image of the test area; a result judging module for determining whether the corresponding vertical rod is calibrated in each rectangular area after the image of the test area during the test is acquired by the receiving module and the total number of the corresponding edge pixels of each rectangular area is identified by the identifying module, if yes, the test time is acquired when the test is ended; if not, it is determined that the vertical rod is inverted and the test result is invalid; a timing ending module for ending timing when the image of the terminal point of the test area reached by the tester is received after it is determined by the result judging module that the corresponding vertical rod exists in each rectangular area.

Images