CN113627372A - Running test method, system and computer readable storage medium - Google Patents
Running test method, system and computer readable storage medium Download PDFInfo
- Publication number
- CN113627372A CN113627372A CN202110943179.4A CN202110943179A CN113627372A CN 113627372 A CN113627372 A CN 113627372A CN 202110943179 A CN202110943179 A CN 202110943179A CN 113627372 A CN113627372 A CN 113627372A
- Authority
- CN
- China
- Prior art keywords
- cloud data
- dimensional
- point cloud
- point
- sprint
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000010998 test method Methods 0.000 title claims abstract description 35
- 238000012360 testing method Methods 0.000 claims abstract description 94
- 238000000034 method Methods 0.000 claims abstract description 29
- 238000004590 computer program Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 description 11
- 230000006399 behavior Effects 0.000 description 6
- 230000015654 memory Effects 0.000 description 4
- 230000011218 segmentation Effects 0.000 description 4
- 230000009192 sprinting Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000003550 marker Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000004080 punching Methods 0.000 description 1
- 238000013215 result calculation Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06398—Performance of employee with respect to a job function
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The running test method comprises the following steps: sending a starting instruction and recording a starting timestamp; acquiring three-dimensional point cloud data of an area where the endpoint identifier is located in real time; extracting three-dimensional face point cloud data from the three-dimensional point cloud data of the area where the end point identification is located, and carrying out face recognition on the extracted three-dimensional face point cloud data to obtain identity information of each testing person passing through the end point identification; extracting three-dimensional human body point cloud data of each testing personnel in the sprint process from the three-dimensional point cloud data of the area where the end point identification is located, and if the fact that at least one point in the three-dimensional human body point cloud data of the testing personnel exceeds a straight line where the end point identification is located is detected, taking an acquisition time stamp of the three-dimensional human body point cloud data of the testing personnel as a sprint time stamp; the running achievement of each tester is calculated according to the starting time stamp and the sprint time stamp of each tester, the method can automatically identify the identities of a plurality of testers and calculate the running achievement at the same time, and the testing efficiency is high and the error rate is low.
Description
Technical Field
The invention relates to the technical field of machine vision, in particular to a running test method, a running test system and a computer readable storage medium.
Background
When running class sports training and examination, a plurality of runners of starting point are started together, usually the runner need run along the runway for a plurality of circles can accomplish the test, whole process needs artifical record number of circles and time spent, this kind of mode causes artifical mistake easily and influences the authenticity of achievement. Especially for colleges and universities, each student needs to run in each school period, the number of the tested students reaches tens of thousands of people, the test workload is very large, the tens of thousands of people are divided into one group of every 20 people, each tested student in each group needs to be provided with a 1-20 digital number plate, the corresponding 20 teachers respectively record the running scores of the students with the corresponding digital number plates, and the 20 teachers need to be trained independently before testing, so that the manual testing by the teachers is a very difficult task, and the testing mode is complex in management, low in efficiency and easy to make mistakes.
With the development of science and technology, infrared photoelectric timing equipment and a radio frequency identification timing system which replace manual testing appear, however, the infrared photoelectric timing cannot simultaneously record the scores of a plurality of runners passing through a terminal point, and meanwhile, the defect of inaccurate timing (the runners can also block infrared light by arms) also exists; the radio frequency identification timing system needs a runner to carry an inductor with a radio frequency function, and the running performance of the runner is easily influenced.
Disclosure of Invention
In order to solve the above technical problems, embodiments of the present invention provide a running test method, system and computer readable storage medium, which automatically identify the identities of a plurality of testers and calculate the running scores of the plurality of testers based on three-dimensional point cloud data of an area where an endpoint identifier is located, and have high test efficiency and low error rate.
In one aspect, an embodiment of the present invention provides a running test method, including:
sending a starting instruction and recording a starting timestamp;
acquiring three-dimensional point cloud data of an area where the endpoint identifier is located in real time;
extracting three-dimensional face point cloud data from the three-dimensional point cloud data of the area where the end point identifier is located, and performing face recognition on the extracted three-dimensional face point cloud data to obtain identity information of each testing person passing through the end point identifier;
extracting three-dimensional human body point cloud data of each testing person in the sprint process from the three-dimensional point cloud data of the area where the end point identification is located, and if it is detected that at least one point in the three-dimensional human body point cloud data of the testing person exceeds a straight line where the end point identification is located, taking an acquisition timestamp of the three-dimensional human body point cloud data of the testing person as a sprint timestamp;
and calculating the running achievement of each tester according to the starting time stamp and the sprint time stamp of each tester.
In some embodiments, the step of, if it is detected that at least one point in the three-dimensional human body point cloud data of the test person exceeds the straight line on which the end point identifier is located, includes:
acquiring a three-dimensional coordinate of each point in the three-dimensional human body point cloud data of the tester;
establishing a space linear equation of a straight line where the endpoint identifier is located;
and obtaining the position relation of each point and the straight line where the terminal point identification is located according to the three-dimensional coordinates of each point and the space straight line equation, and judging whether at least one point in the three-dimensional human body point cloud data of the testing personnel exceeds the straight line where the terminal point identification is located according to the position relation of each point and the straight line where the terminal point identification is located.
In some embodiments, the step of taking the acquisition time stamp of the three-dimensional human body point cloud data of the test person as the sprint time stamp includes:
and if at least one point in the three-dimensional human body point cloud data of the testing personnel exceeds the straight line of the end point identification under the condition of a plurality of collecting time stamps, taking the collecting time stamp at the earliest moment as the sprint time stamp.
In some embodiments, the step of extracting three-dimensional human body point cloud data of each of the testers in the sprint process from the three-dimensional point cloud data of the area where the endpoint identifier is located includes:
calculating to obtain an estimated sprint starting timestamp and an estimated sprint ending timestamp according to the starting timestamp and a preset testing time-use threshold;
and extracting the three-dimensional human body point cloud data of each testing person in the sprint process from the three-dimensional point cloud data of the area where the end point identification is located according to the estimated sprint starting time stamp and the estimated sprint ending time stamp.
In some embodiments, the step of obtaining the three-dimensional point cloud data of the area where the endpoint identifier is located in real time further comprises:
acquiring three-dimensional point cloud data of an area where the starting mark corresponding to the starting timestamp is located;
extracting the human face characteristics of the three-dimensional human face point cloud data obtained from the three-dimensional point cloud data of the area where the starting mark is located;
comparing the extracted face features with face features in a test database to obtain a plurality of identity labels of the testers;
and obtaining the identity information of the plurality of testers according to the identity labels of the plurality of testers.
In some embodiments, the step of obtaining the three-dimensional point cloud data of the area where the start marker corresponding to the start timestamp is located further comprises:
extracting three-dimensional foot point cloud data from the three-dimensional point cloud data of the area where the starting mark is located;
and if at least one point in the three-dimensional foot point cloud data is detected to exceed the straight line of the starting point identifier, judging that the race snatching behavior exists, and returning to the step of sending a starting instruction and recording a starting timestamp.
In some embodiments, the step of determining that the running robbery exists if it is detected that at least one point in the three-dimensional foot point cloud data exceeds the straight line on which the starting point identifier exists further includes:
and obtaining corresponding three-dimensional face point cloud data of the tester according to the three-dimensional coordinates of the point exceeding the straight line where the starting point identification is located so as to identify the identity of the race test worker.
In some embodiments, in the running test process, the face features of each of the testers are extracted from the three-dimensional face point cloud data acquired from the area where the end point identifier is located and/or the area where the start point identifier is located, and are associated with the corresponding identity information of the testers and then stored in the test database.
On the other hand, the embodiment of the invention also provides a running test system, which comprises:
an instruction sending module configured to send a start instruction and record a start timestamp;
the three-dimensional data acquisition module is configured to acquire three-dimensional point cloud data of an area where the endpoint identifier is located in real time through the stereoscopic vision acquisition device;
the identity recognition module is configured to extract three-dimensional face point cloud data from the three-dimensional point cloud data of the area where the endpoint identifier is located, and perform face recognition on the extracted three-dimensional face point cloud data to obtain identity information of each testing person passing through the endpoint identifier;
the sprint time determining module is configured to extract three-dimensional human body point cloud data of each testing person in the sprint process from the three-dimensional point cloud data of the area where the endpoint identifier is located, and if the fact that at least one point in the three-dimensional human body point cloud data of the testing person exceeds a straight line where the endpoint identifier is located is detected, the collection time stamp of the three-dimensional human body point cloud data of the testing person is used as a sprint time stamp;
and the running result calculating module is configured to calculate the running result of each tester according to the starting time stamp and the sprint time stamp of each tester.
In still another aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, and the computer program, when executed by a processor, implements the running test method according to the above embodiment.
The invention has the beneficial effects that: the running test method provided by the embodiment of the invention is characterized in that the three-dimensional point cloud data of the area where the end point identification is located is obtained, the three-dimensional face point cloud data of each tester is extracted from the three-dimensional point cloud data and face recognition is carried out, so that the identity of each tester in the running test is recognized, the position relation between each point of the three-dimensional body point cloud data of each tester and the straight line where the end point identification is located in the sprint process is judged, the sprint timestamp of each tester is determined, and the running score of each tester is calculated according to the recorded starting timestamp and the determined sprint timestamp of each tester. The running test method provided by the embodiment of the invention automatically identifies the identities of a plurality of testers and calculates the running scores of the testers simultaneously based on the three-dimensional point cloud data of the area where the endpoint identifier is located, and has high test efficiency and low error rate.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the example serve to explain the principles of the invention and not to limit the invention.
FIG. 1 is a schematic flow chart diagram of some embodiments of a run test method of the present invention;
FIG. 2 is a flow chart illustrating some embodiments of steps 400 of a run test method of the present invention;
FIG. 3 is a flow chart illustrating some embodiments of steps 600 of a run test method of the present invention;
FIG. 4 is a flow chart illustrating some embodiments of step 700 of a run test method of the present invention;
FIG. 5 is a schematic diagram of some embodiments of a running test system of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the drawings of the embodiments of the present invention. It is to be understood that the embodiments described are only a few embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the described embodiments of the invention without any inventive step, are within the scope of protection of the invention.
Referring to fig. 1, an embodiment of the present invention provides a running test method, including:
step 100: sending a starting instruction and recording a starting timestamp;
in the step, a starting instruction can be initiated through an electronic starting gun or a microphone and the like, the current time for sending the starting instruction is used as the starting time, namely a starting timestamp, and the starting timestamp can be recorded and then transmitted to a unified processing platform of the running test system for storage.
Step 200: acquiring three-dimensional point cloud data of an area where the endpoint identifier is located in real time;
for different running test items, the positions of the end point identifications are consistent, therefore, in the step, three-dimensional point cloud data of the area where the end point identification is located can be collected in real time through a stereoscopic vision collecting device, the collecting time stamp of the three-dimensional point cloud data and the three-dimensional point cloud data are synchronized to a unified processing platform for subsequent processing, wherein the stereoscopic vision collecting device can be a binocular stereoscopic camera, a structured light camera or a TOF camera, and specific limitation is not made herein.
Step 300: extracting three-dimensional face point cloud data from the three-dimensional point cloud data of the area where the end point identification is located, and carrying out face recognition on the extracted three-dimensional face point cloud data to obtain identity information of each testing person passing through the end point identification;
in the step, three-dimensional face point cloud data in the three-dimensional point cloud data of the area where the end point identifier is located is extracted to perform face recognition to obtain identity information of each testing person in each group of tests (namely, the face recognition processing is performed on a unified processing platform), wherein the three-dimensional face point cloud data can be obtained by performing three-dimensional segmentation on the three-dimensional point cloud data through a set segmentation threshold, in addition, the identity of each testing person is recognized by adopting a three-dimensional face recognition method based on the point cloud data, and certainly, the three-dimensional face point cloud data can also be converted into two-dimensional face data to perform face recognition, and no specific limitation is made here.
Optionally, in this embodiment, the identity information of the tester includes an identification number and a name, and for students, the identity information further includes information such as a school number, a class, or an age.
Step 400: extracting three-dimensional human body point cloud data of each testing personnel in the sprint process from the three-dimensional point cloud data of the area where the end point identification is located, and if the fact that at least one point in the three-dimensional human body point cloud data of the testing personnel exceeds a straight line where the end point identification is located is detected, taking an acquisition time stamp of the three-dimensional human body point cloud data of the testing personnel as a sprint time stamp;
in the step, the unified processing platform judges the position relation of each point in the three-dimensional human body point cloud data of each tester and the straight line where the end point identification is located in the sprint process, and determines the sprint timestamp of each tester.
Step 500: and calculating the running achievement of each tester according to the starting time stamp and the sprint time stamp of each tester.
In the step, the running time of each tester is obtained by calculating the difference value between the sprint timestamp and the starting timestamp of each tester, and the running result of each tester is obtained.
The running test method provided by the embodiment of the invention is characterized in that the three-dimensional point cloud data of the area where the end point identification is located is obtained, the three-dimensional face point cloud data of each tester is extracted from the three-dimensional point cloud data and face recognition is carried out, so that the identity of each tester in the running test is recognized, the position relation between each point of the three-dimensional body point cloud data of each tester and the straight line where the end point identification is located in the sprint process is judged, the sprint timestamp of each tester is determined, and the running score of each tester is calculated according to the recorded starting timestamp and the determined sprint timestamp of each tester. The running test method provided by the embodiment of the invention automatically identifies the identities of a plurality of testers and calculates the running scores of the testers simultaneously based on the three-dimensional point cloud data of the area where the endpoint identifier is located, and has high test efficiency and low error rate.
In some embodiments, referring to FIG. 2, step 400 of a running test method of the present invention comprises:
step 403: acquiring a three-dimensional coordinate of each point in three-dimensional human body point cloud data of a tester;
step 404: establishing a space linear equation of a straight line where the endpoint identifier is located;
in the step, the space linear equation of the straight line where the end point mark is located can be established by extracting the coordinates of any two points of the straight line where the end point mark is located.
Step 405: and obtaining the position relation of each point and the straight line of the terminal mark according to the three-dimensional coordinates of each point and a space straight line equation, and judging whether at least one point in the three-dimensional human body point cloud data of the tester exceeds the straight line of the terminal mark according to the position relation of each point and the straight line of the terminal mark.
In the step, the position relation of each point and the straight line of the terminal point identification is judged by using a simple geometric midpoint and straight line position relation judgment method, and when one point exceeds the straight line of the terminal point identification, the three-dimensional human body point cloud data is the three-dimensional point cloud data when a tester sprints.
Of course, in this embodiment, the position relationship between each point and the vertical plane (Z plane) where the endpoint identifier is located may be determined by a simple geometric midpoint and plane position relationship determination method, and when one point exceeds the vertical plane where the endpoint identifier is located, it is described that the three-dimensional human body point cloud data is the three-dimensional point cloud data when the tester sprints.
In some embodiments, in step 400 of the running test method of the present invention, if at least one point in the three-dimensional human body point cloud data of the test person exceeds the straight line where the endpoint identifier is located under the plurality of collection time stamps, the collection time stamp at the earliest time is used as the sprint time stamp.
Because at least one point in the three-dimensional human body point cloud data of the testers exceeds the straight line of the terminal point identification in the process that each tester punches, the collecting timestamp at the earliest moment is used as the punching timestamp according to the time sequence.
In some embodiments, referring to FIG. 2, step 400 of a running test method of the present invention further comprises:
step 401: calculating to obtain an estimated sprint starting timestamp and an estimated sprint ending timestamp according to the starting timestamp and a preset testing time-use threshold;
step 402: and extracting the three-dimensional human body point cloud data of each testing person in the sprint process from the three-dimensional point cloud data of the area where the terminal point identifier is located according to the estimated sprint starting time stamp and the estimated sprint ending time stamp.
Different running test items and different runway settings make the situation of the end point identification different during the running test, for example: the sprint test (hectometer test) process is carried out only once through the end point identification, namely sprinting; in the middle and long distance running test, the running of the three-dimensional human body point cloud data during sprinting can be obtained by determining the time range of the final sprinting because the three-dimensional human body point cloud data can be obtained by running a plurality of times around the annular runway and passing the end point identification for a plurality of times in the middle.
In the embodiment, the testing time-consuming threshold value can be preset according to different running test items, so that the estimated sprint time range is calculated according to the recorded starting timestamp, and the three-dimensional human body point cloud data in the corresponding time range is extracted. The preset test-time threshold is determined according to previous test experience, and is not specifically limited herein.
Certainly, the three-dimensional human body point cloud data of the final sprint can also be determined in other manners, for example, by a manner of recording the number of turns, that is, recording the number of turns of running of each tester passing through the endpoint identifier, and if the number of turns of running of each tester reaches a preset number of turns threshold, extracting the three-dimensional human body point cloud data of each tester from the three-dimensional point cloud data of the area where the endpoint identifier corresponding to the last turn is located.
In some embodiments, referring to fig. 3, step 200 of a running test method of the present invention further comprises:
step 601: acquiring three-dimensional point cloud data of an area where a starting mark corresponding to a starting timestamp is located;
step 602: extracting the human face characteristics of the three-dimensional human face point cloud data obtained from the three-dimensional point cloud data of the area where the starting mark is located;
step 603: comparing the extracted face features with face features in a test database to obtain identity labels of a plurality of testers;
in the step, the test database is pre-established on the unified processing platform, the face features of all testers and the identity tags associated with the face features are stored in the test database, and the identity tags of each tester can be found through face feature comparison.
Step 604: and obtaining the identity information of the plurality of testers according to the identity labels of the plurality of testers.
In this step, the identity information of a plurality of testers can be stored in a KT tree data structure in advance, and corresponding identity information can be rapidly inquired in the KT tree according to the identity tag.
And synchronizing the three-dimensional point cloud data of the area where the starting mark corresponding to the starting timestamp acquired in the step is located to a unified processing platform, and performing face recognition and identity determination on the unified processing platform.
In some embodiments, referring to fig. 4, step 601 of a running test method of the present invention further comprises:
step 701: extracting three-dimensional foot point cloud data from the three-dimensional point cloud data of the area where the starting mark is located;
in the step, the three-dimensional foot point cloud data can be obtained by performing three-dimensional segmentation on the three-dimensional point cloud data through the set segmentation threshold.
Step 702: and if at least one point in the three-dimensional foot point cloud data is detected to exceed the straight line of the starting point identifier, judging that the race snatching behavior exists, and returning to the step of sending a starting instruction and recording a starting timestamp.
In the step, the position relation between each point in the three-dimensional foot point cloud data and the straight line where the starting point identification is located is judged by using a simple geometric midpoint and straight line position relation judging method, and when one point exceeds the straight line where the starting point identification is located, the race snatching behavior is shown.
In this embodiment, the race starting behavior is determined according to the three-dimensional foot point cloud number of the area where the start mark corresponding to the start timestamp is located, and when the race starting behavior exists, the running test fails, and the race starting is restarted.
In some embodiments, referring to FIG. 4, step 702 of a running test method of the present invention further comprises:
step 703: and obtaining the three-dimensional face point cloud data of the corresponding tester according to the three-dimensional coordinates of the point exceeding the straight line where the starting point identification is located so as to identify the identity of the race test worker.
In many countries or international running competitions, the competitor who has a race snatching behavior is punished, in this embodiment, the three-dimensional face point cloud data of the corresponding tester is obtained according to the three-dimensional coordinates of the point exceeding the straight line where the starting point identifier is located, and face recognition is performed to determine the identity of the race snatching tester.
In some embodiments, step 100 of a method of running testing of the present invention is preceded by:
acquiring three-dimensional face point cloud data and identity information of each tester in advance;
extracting the face characteristics of each tester from the three-dimensional face point cloud data of each tester, associating the face characteristics with the identity information of the corresponding tester, and storing the face characteristics in a test database.
In some embodiments, in the running test process, the running test method extracts the face features of each tester from the three-dimensional face point cloud data acquired from the area where the end point identifier is located and/or the area where the start point identifier is located, associates the face features with the identity information of the corresponding tester, and stores the face features in the test database.
In order to ensure the recognition accuracy, in this embodiment, all three-dimensional face point cloud data acquired in a starting point identification area and/or a terminal point identification area in the whole test process are extracted to obtain face features, and the face features are associated with the identity information of corresponding testers and then stored in a test database so as to enrich the face features of the testers in the test database.
On the other hand, referring to fig. 5, an embodiment of the present invention further provides a running test system 1, including:
an instruction transmitting module 10 configured to transmit a start instruction and record a start time stamp;
the three-dimensional data acquisition module 20 is configured to acquire three-dimensional point cloud data of an area where the endpoint identifier is located in real time through a stereoscopic vision acquisition device;
the identity recognition module 30 is configured to extract three-dimensional face point cloud data from the three-dimensional point cloud data of the area where the endpoint identifier is located, and perform face recognition on the extracted three-dimensional face point cloud data to obtain identity information of each testing person subjected to the endpoint identifier;
the sprint time determining module 40 is configured to extract three-dimensional human body point cloud data of each testing person in the sprint process from the three-dimensional point cloud data of the area where the endpoint identifier is located, and if it is detected that at least one point in the three-dimensional human body point cloud data of the testing person exceeds a straight line where the endpoint identifier is located, the collection time stamp of the three-dimensional human body point cloud data of the testing person is used as a sprint time stamp;
and the running result calculating module 50 is configured to calculate the running result of each tester according to the starting time stamp and the sprint time stamp of each tester.
It should be noted that the running test system of this embodiment may be composed of one or more stereoscopic vision collecting devices disposed in the endpoint identification area, and a unified processing platform connected with the stereoscopic vision collecting devices by wire or wirelessly, where the unified processing platform is composed of an instruction sending module, an identity recognition module, a sprint time determination module, and a running result calculation module.
The specific details of each module of the running test system have been described in detail in the corresponding running test method, and therefore are not described herein again.
In still another aspect, the present invention provides an electronic device, including: a processor and a memory, the memory having stored thereon computer readable instructions, which when executed by the processor, implement a running test method as described in the embodiments above.
In yet another aspect, the present invention further provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the running test method according to the above embodiments.
Those skilled in the art will appreciate that all or part of the steps in the methods of the above embodiments may be implemented by associated hardware instructed by a program, which may be stored in a computer-readable storage medium, and the storage medium may include: flash disks, read-only memories (ROMs), Random Access Memories (RAMs), magnetic or optical disks, and the like.
Although the embodiments of the present invention have been described above, the above description is only for the convenience of understanding the present invention, and is not intended to limit the present invention. It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. A running test method, comprising:
sending a starting instruction and recording a starting timestamp;
acquiring three-dimensional point cloud data of an area where the endpoint identifier is located in real time;
extracting three-dimensional face point cloud data from the three-dimensional point cloud data of the area where the end point identifier is located, and performing face recognition on the extracted three-dimensional face point cloud data to obtain identity information of each testing person passing through the end point identifier;
extracting three-dimensional human body point cloud data of each testing person in the sprint process from the three-dimensional point cloud data of the area where the end point identification is located, and if it is detected that at least one point in the three-dimensional human body point cloud data of the testing person exceeds a straight line where the end point identification is located, taking an acquisition timestamp of the three-dimensional human body point cloud data of the testing person as a sprint timestamp;
and calculating the running achievement of each tester according to the starting time stamp and the sprint time stamp of each tester.
2. The running test method of claim 1, wherein the step of, if it is detected that at least one point in the three-dimensional human point cloud data of the tester exceeds a straight line on which the end point identifier is located, comprises:
acquiring a three-dimensional coordinate of each point in the three-dimensional human body point cloud data of the tester;
establishing a space linear equation of a straight line where the endpoint identifier is located;
and obtaining the position relation of each point and the straight line where the terminal point identification is located according to the three-dimensional coordinates of each point and the space straight line equation, and judging whether at least one point in the three-dimensional human body point cloud data of the testing personnel exceeds the straight line where the terminal point identification is located according to the position relation of each point and the straight line where the terminal point identification is located.
3. A running test method according to claim 1, wherein the step of taking the collection time stamp of the three-dimensional human point cloud data of the test person as a sprint time stamp comprises:
and if at least one point in the three-dimensional human body point cloud data of the testing personnel exceeds the straight line of the end point identification under the condition of a plurality of collecting time stamps, taking the collecting time stamp at the earliest moment as the sprint time stamp.
4. The running test method according to claim 1, wherein the step of extracting three-dimensional human body point cloud data of each tester in the sprint process from the three-dimensional point cloud data of the area where the endpoint identifier is located comprises:
calculating to obtain an estimated sprint starting timestamp and an estimated sprint ending timestamp according to the starting timestamp and a preset testing time-use threshold;
and extracting the three-dimensional human body point cloud data of each testing person in the sprint process from the three-dimensional point cloud data of the area where the end point identification is located according to the estimated sprint starting time stamp and the estimated sprint ending time stamp.
5. A running test method according to any one of claims 1 to 4, wherein the step of obtaining three-dimensional point cloud data of an area where the endpoint identifier is located in real time further comprises:
acquiring three-dimensional point cloud data of an area where the starting mark corresponding to the starting timestamp is located;
extracting the human face characteristics of the three-dimensional human face point cloud data obtained from the three-dimensional point cloud data of the area where the starting mark is located;
comparing the extracted face features with face features in a test database to obtain a plurality of identity labels of the testers;
and obtaining the identity information of the plurality of testers according to the identity labels of the plurality of testers.
6. The running test method according to claim 5, wherein the step of obtaining the three-dimensional point cloud data of the area where the start mark corresponding to the start time stamp is located further comprises:
extracting three-dimensional foot point cloud data from the three-dimensional point cloud data of the area where the starting mark is located;
and if at least one point in the three-dimensional foot point cloud data is detected to exceed the straight line of the starting point identifier, judging that the race snatching behavior exists, and returning to the step of sending a starting instruction and recording a starting timestamp.
7. The running test method according to claim 6, wherein the step of determining that the running robbing behavior exists if it is detected that at least one point in the three-dimensional foot point cloud data exceeds the straight line on which the starting point identifier exists further comprises:
and obtaining corresponding three-dimensional face point cloud data of the tester according to the three-dimensional coordinates of the point exceeding the straight line where the starting point identification is located so as to identify the identity of the race test worker.
8. The running test method according to claim 5, wherein in the running test process, the face features of each tester are extracted from the three-dimensional face point cloud data acquired from the area where the end point identifier is located and/or the area where the start point identifier is located, and are stored in the test database after being associated with the corresponding identity information of the tester.
9. A running test system, comprising:
an instruction sending module configured to send a start instruction and record a start timestamp;
the three-dimensional data acquisition module is configured to acquire three-dimensional point cloud data of an area where the endpoint identifier is located in real time through the stereoscopic vision acquisition device;
the identity recognition module is configured to extract three-dimensional face point cloud data from the three-dimensional point cloud data of the area where the endpoint identifier is located, and perform face recognition on the extracted three-dimensional face point cloud data to obtain identity information of each testing person passing through the endpoint identifier;
the sprint time determining module is configured to extract three-dimensional human body point cloud data of each testing person in the sprint process from the three-dimensional point cloud data of the area where the endpoint identifier is located, and if the fact that at least one point in the three-dimensional human body point cloud data of the testing person exceeds a straight line where the endpoint identifier is located is detected, the collection time stamp of the three-dimensional human body point cloud data of the testing person is used as a sprint time stamp;
and the running result calculating module is configured to calculate the running result of each tester according to the starting time stamp and the sprint time stamp of each tester.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out a running test method according to any one of the claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110943179.4A CN113627372B (en) | 2021-08-17 | 2021-08-17 | Running test method, running test system and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110943179.4A CN113627372B (en) | 2021-08-17 | 2021-08-17 | Running test method, running test system and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113627372A true CN113627372A (en) | 2021-11-09 |
| CN113627372B CN113627372B (en) | 2024-01-05 |
Family
ID=78386011
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110943179.4A Active CN113627372B (en) | 2021-08-17 | 2021-08-17 | Running test method, running test system and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113627372B (en) |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120130515A1 (en) * | 2009-05-01 | 2012-05-24 | Homsi Kristopher L | Athletic performance rating system |
| CN109999469A (en) * | 2019-04-05 | 2019-07-12 | 福建省通通发科技发展有限公司 | A kind of football around rod examination intelligent judgment system |
| CN110639197A (en) * | 2019-09-27 | 2020-01-03 | 上海淡竹体育科技有限公司 | Sports test method, device and system |
| CN110991413A (en) * | 2019-12-20 | 2020-04-10 | 西南交通大学 | Running detection method based on ReiD |
| CN111081375A (en) * | 2019-12-27 | 2020-04-28 | 北京深测科技有限公司 | Early warning method and system for health monitoring |
| CN111144275A (en) * | 2019-12-24 | 2020-05-12 | 中石化第十建设有限公司 | Intelligent running test system and method based on face recognition |
| CN111275030A (en) * | 2020-05-06 | 2020-06-12 | 西南交通大学 | Straight running detection and timing system and method based on face and human body recognition |
| CN111811828A (en) * | 2020-04-17 | 2020-10-23 | 新奇点智能科技集团有限公司 | Unmanned vehicle driving test method, device, system and storage medium |
| CN212782050U (en) * | 2020-07-29 | 2021-03-23 | 南京信息工程大学 | Running test system |
| CN112807617A (en) * | 2021-02-22 | 2021-05-18 | 苏州进动智能科技有限公司 | Running safety monitoring and guiding method and equipment based on three-dimensional camera |
| CN112973098A (en) * | 2021-03-19 | 2021-06-18 | 洛阳理工学院 | Self-service automatic testing device and testing method for sprint project |
| CN113011343A (en) * | 2021-03-23 | 2021-06-22 | 安徽一视科技有限公司 | Running intelligent timing method based on artificial intelligence |
| WO2021134296A1 (en) * | 2019-12-30 | 2021-07-08 | 深圳元戎启行科技有限公司 | Obstacle detection method and apparatus, and computer device and storage medium |
| CN216456825U (en) * | 2021-08-17 | 2022-05-10 | 北京伟景智能科技有限公司 | Running test system |
-
2021
- 2021-08-17 CN CN202110943179.4A patent/CN113627372B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120130515A1 (en) * | 2009-05-01 | 2012-05-24 | Homsi Kristopher L | Athletic performance rating system |
| CN109999469A (en) * | 2019-04-05 | 2019-07-12 | 福建省通通发科技发展有限公司 | A kind of football around rod examination intelligent judgment system |
| CN110639197A (en) * | 2019-09-27 | 2020-01-03 | 上海淡竹体育科技有限公司 | Sports test method, device and system |
| CN110991413A (en) * | 2019-12-20 | 2020-04-10 | 西南交通大学 | Running detection method based on ReiD |
| CN111144275A (en) * | 2019-12-24 | 2020-05-12 | 中石化第十建设有限公司 | Intelligent running test system and method based on face recognition |
| CN111081375A (en) * | 2019-12-27 | 2020-04-28 | 北京深测科技有限公司 | Early warning method and system for health monitoring |
| WO2021134296A1 (en) * | 2019-12-30 | 2021-07-08 | 深圳元戎启行科技有限公司 | Obstacle detection method and apparatus, and computer device and storage medium |
| CN111811828A (en) * | 2020-04-17 | 2020-10-23 | 新奇点智能科技集团有限公司 | Unmanned vehicle driving test method, device, system and storage medium |
| CN111275030A (en) * | 2020-05-06 | 2020-06-12 | 西南交通大学 | Straight running detection and timing system and method based on face and human body recognition |
| CN212782050U (en) * | 2020-07-29 | 2021-03-23 | 南京信息工程大学 | Running test system |
| CN112807617A (en) * | 2021-02-22 | 2021-05-18 | 苏州进动智能科技有限公司 | Running safety monitoring and guiding method and equipment based on three-dimensional camera |
| CN112973098A (en) * | 2021-03-19 | 2021-06-18 | 洛阳理工学院 | Self-service automatic testing device and testing method for sprint project |
| CN113011343A (en) * | 2021-03-23 | 2021-06-22 | 安徽一视科技有限公司 | Running intelligent timing method based on artificial intelligence |
| CN216456825U (en) * | 2021-08-17 | 2022-05-10 | 北京伟景智能科技有限公司 | Running test system |
Non-Patent Citations (5)
| Title |
|---|
| SIMON CHOPPIN等: "The potential of the Microsoft Kinect in sports analysis and biomechanics", 《SPORTS TECHNOLOGY》, vol. 6, no. 2, pages 78 - 85 * |
| 刘桥等: "短距离冲刺跑动作的视觉三维重建方法研究", 计算机仿真, vol. 34, no. 3, pages 225 - 228 * |
| 夏明等: "跑步运动压缩裤压力预测模型的建立", 《产业用纺织品》, vol. 37, no. 3, pages 31 - 36 * |
| 常桐博: "不同触地模式慢跑的足踝生物力学分析", 《中国优秀硕士学位论文全文数据库 社会科学II辑》, no. 2019, pages 134 - 186 * |
| 王国伟: "基于视觉图像的田径失误动作识别仿真", 《计算机仿真》, vol. 33, no. 4, pages 274 - 277 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113627372B (en) | 2024-01-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109740446A (en) | Classroom students ' behavior analysis method and device | |
| CN110645986B (en) | Positioning method and device, terminal and storage medium | |
| CN103942811B (en) | Distributed parallel determines the method and system of characteristic target movement locus | |
| CN110639197A (en) | Sports test method, device and system | |
| CN103996036B (en) | A kind of map data collecting method and device | |
| ZA202300610B (en) | System and method for crop monitoring | |
| JP2020502683A5 (en) | ||
| CN108830213A (en) | Car plate detection and recognition methods and device based on deep learning | |
| CN111144275A (en) | Intelligent running test system and method based on face recognition | |
| CN111968152B (en) | Dynamic identity recognition method and device | |
| CN110309768A (en) | The staff's detection method and equipment of car test station | |
| CN115294651A (en) | Behavior analysis method based on farming scene and server | |
| CN110399804A (en) | A kind of food inspection recognition methods based on deep learning | |
| CN113627372A (en) | Running test method, system and computer readable storage medium | |
| CN216456825U (en) | Running test system | |
| CN216824742U (en) | Running examination system | |
| CN110738167A (en) | pedestrian identification method based on multi-domain spatial attribute correlation analysis | |
| CN116311433A (en) | Middle-distance running test method, device, equipment and medium based on vision technology | |
| CN110309737A (en) | A kind of information processing method applied to cigarette sales counter, apparatus and system | |
| CN215833962U (en) | Running examination system | |
| CN114067427A (en) | Snake-shaped running assessment method and system, electronic equipment and storage medium | |
| CN112766230A (en) | Video streaming personnel online time length estimation method and corresponding system | |
| CN111666786B (en) | Image processing method, device, electronic equipment and storage medium | |
| CN113160450A (en) | Running assessment system, method and device and storage medium | |
| CN111753665A (en) | Park abnormal behavior identification method and device based on attitude estimation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |