CN115471139B - Large-scale crowd sports event comprehensive evaluation system based on image recognition technology - Google Patents
Large-scale crowd sports event comprehensive evaluation system based on image recognition technology Download PDFInfo
- Publication number
- CN115471139B CN115471139B CN202211348364.XA CN202211348364A CN115471139B CN 115471139 B CN115471139 B CN 115471139B CN 202211348364 A CN202211348364 A CN 202211348364A CN 115471139 B CN115471139 B CN 115471139B
- Authority
- CN
- China
- Prior art keywords
- evaluation module
- event
- evaluation
- module
- sports
- 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.)
- Active
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 247
- 238000005516 engineering process Methods 0.000 title claims abstract description 22
- 230000033001 locomotion Effects 0.000 claims abstract description 76
- 230000008520 organization Effects 0.000 claims description 37
- 230000008901 benefit Effects 0.000 claims description 18
- 238000012502 risk assessment Methods 0.000 claims description 10
- 230000009471 action Effects 0.000 claims description 8
- 238000004891 communication Methods 0.000 claims description 8
- 239000000463 material Substances 0.000 claims description 8
- 238000000034 method Methods 0.000 claims description 8
- 238000009395 breeding Methods 0.000 claims description 7
- 230000001488 breeding effect Effects 0.000 claims description 7
- 238000010606 normalization Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 abstract description 9
- 238000013077 scoring method Methods 0.000 description 32
- 230000006399 behavior Effects 0.000 description 7
- 238000011161 development Methods 0.000 description 3
- 230000000386 athletic effect Effects 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000037081 physical activity Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000007704 transition Effects 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
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/277—Analysis of motion involving stochastic approaches, e.g. using Kalman filters
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30241—Trajectory
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a large-scale mass sports event comprehensive evaluation system based on an image recognition technology, which comprises an event data acquisition module, an event data comprehensive evaluation module and an evaluation report generation module. According to the invention, a target tracking algorithm is introduced to perform real-time tracking on the motion state of the athlete in the safety guarantee evaluation, and a target tracking algorithm combining a Mean shift algorithm and a Kalman filtering algorithm is utilized, kalman filtering is introduced to track the target when the athlete in the competition is occluded, and a Kalman filter is utilized to perform parameter identification, so that the occluded tracking system can have subsequent state prediction capability, the motion risk is subjected to higher safety evaluation, the motion risk cannot be comprehensively evaluated, the comprehensive evaluation of the large-scale mass sports events is realized, and the evaluation requirement of the large-scale mass sports events can be better met.
Description
Technical Field
The invention relates to the technical field of event evaluation, in particular to a comprehensive evaluation system for a large-scale crowd sports event based on an image recognition technology.
Background
Physical education (abbreviated as PE or p.e.) is a complex social culture phenomenon, and it takes physical and intellectual activities as basic means, and according to the laws of human growth and development, skill formation and function improvement, it achieves a conscious, purposeful and organized social activity of promoting overall development, improving physical quality and overall education level, enhancing physique and athletic ability, improving life style and life quality. Sports can be divided into categories such as popular (mass) sports, professional sports, school sports, and the like. Along with the continuous development of social level, people pay more and more attention to the physical health of the people, and in order to meet the fitness requirements of people, people often hold a mass sports event to carry forward mass sports fitness culture.
At present, the evaluation of the sports events of the masses mainly comprises the steps of obtaining corresponding evaluation dimensions after the sports events are selected, then determining the weight values of the dimensions through an entropy method, and calculating according to the weight values to obtain comprehensive scores, however, because the evaluation dimensions related in the evaluation process only comprise an order book, an organization structure, a field guarantee, a safety guarantee, a medical guarantee and the like, namely, the evaluation is only carried out on the sports events, the problem of single evaluation index exists, the comprehensive evaluation on the sports events of the masses cannot be realized, the motion states of athletes cannot be tracked in real time in the safety guarantee evaluation, or the motion states of the athletes participating in the competition cannot be correctly tracked in the shielding process, and the motion risks cannot be comprehensively and safely evaluated. Therefore, the invention provides a comprehensive evaluation system for the sports events of the large masses based on the image recognition technology.
Disclosure of Invention
Aiming at the problems in the related art, the invention provides a comprehensive evaluation system for the sports events of the large masses based on an image recognition technology, so as to overcome the technical problems in the prior related art.
Therefore, the invention adopts the following specific technical scheme:
a system for the comprehensive evaluation of a sports event of a large crowd based on image recognition technology, the system comprising: the system comprises an event data acquisition module, an event data comprehensive evaluation module and an evaluation report generation module, wherein the event data acquisition module, the event data comprehensive evaluation module and the evaluation report generation module are sequentially connected;
the event data acquisition module is used for acquiring event evaluation data and standard historical data;
the event data comprehensive evaluation module is used for comprehensively evaluating the events from five dimensions of organization management, service guarantee, social efficiency, economic benefit and adaptability;
the evaluation report generation module is used for generating an evaluation report according to the preset weight and the evaluation result of the five dimensions of the event;
the competition data comprehensive evaluation module comprises an organization management evaluation module, a service guarantee evaluation module, a social efficiency evaluation module, an economic benefit evaluation module and a fitness evaluation module;
the organization management evaluation module is used for evaluating organization plans of the events and normative management of the events;
the service guarantee evaluation module is used for evaluating the situations of places, medical treatment and safety guarantee provided by the events for the competitors;
the social efficiency evaluation module is used for evaluating the positive influence conditions of the events on competitors and residents in other cities;
the economic benefit evaluation module is used for evaluating the socialized strength participation condition of the event and the sports consumption condition driven by the event handling;
and the matching degree evaluation module is used for evaluating the matching degree of the competition unit for evaluation work.
Furthermore, in order to evaluate the organization plan and the normative management of the events, the organization management evaluation module comprises an operation scheme evaluation module, an organization architecture evaluation module, an organization labor division evaluation module, an expense management evaluation module and a propaganda normative evaluation module;
the operation scheme evaluation module is used for integrally evaluating the operation scheme of the event by an expert scoring method;
the organization architecture evaluation module is used for integrally evaluating the organization architecture of the event by an expert scoring method;
the organization division labor assessment module is used for integrally assessing the organization division labor condition of the event by an expert scoring method;
the expense management and evaluation module is used for integrally evaluating the expense management condition of the event through an expert scoring method;
and the propaganda normative evaluation module is used for integrally evaluating the propaganda normative of the competition through an expert scoring method.
Furthermore, in order to evaluate the field, medical treatment and safety guarantee conditions provided by the event for the competitors, the service guarantee evaluation module comprises a safety guarantee evaluation module, a medical treatment guarantee evaluation module and a field guarantee evaluation module;
the safety guarantee evaluation module is used for integrally evaluating the safety guarantee condition of the event by combining an expert scoring method and an image recognition technology;
the medical insurance evaluation module is used for integrally evaluating the medical insurance status of the event by an expert scoring method;
the field guarantee evaluation module is used for integrally evaluating the field guarantee condition of the event by combining an expert scoring method with an image recognition technology.
Furthermore, in order to evaluate the positive influence condition of the events on competitors and residents in other cities, the social efficiency evaluation module comprises an event atmosphere evaluation module, a competition experience evaluation module, a physical behavior influence evaluation module and an event population cultivation evaluation module;
the event atmosphere evaluation module is used for integrally evaluating the event atmosphere of the event by an expert scoring method;
the competition experience evaluation module is used for integrally evaluating the competition experience conditions of competitors of the competition by an expert scoring method;
the sports behavior influence evaluation module is used for integrally evaluating the sports behavior influence condition of the event by an expert scoring method;
the event population breeding evaluation module is used for integrally evaluating population breeding conditions of the events by an expert scoring method.
Furthermore, in order to evaluate the social strength participation condition of the event and the sports consumption condition driven by the event handling, the economic benefit evaluation module comprises a sponsor number evaluation module and a sponsor mode evaluation module;
the sponsor number evaluation module is used for carrying out overall evaluation on the sponsor number of the event by an expert scoring method;
and the sponsorship mode evaluation module is used for carrying out overall evaluation on the sponsorship mode of the event by an expert scoring method.
Furthermore, in order to evaluate the matching degree of the competition unit aiming at the evaluation work, the matching degree evaluation module comprises a pre-competition information communication evaluation module, a post-competition material timely submission evaluation module and a data information filling accuracy evaluation module;
the pre-event information communication evaluation module is used for integrally evaluating the pre-event information communication condition of the event by an expert scoring method;
the after-event material timely submitting evaluation module is used for integrally evaluating the after-event material timely submitting condition of the event by an expert scoring method;
and the data information filling accuracy evaluation module is used for integrally evaluating the data information filling accuracy of the events by an expert scoring method.
Furthermore, in order to better realize the evaluation of the safety guarantee state in the sports events of the masses, the safety guarantee evaluation module comprises a match video acquisition module, a moving target tracking module, a moving track generation module and a moving risk evaluation module;
the match video acquisition module is used for acquiring match video data in the sports events of the large masses;
the moving target tracking module is used for tracking the moving state of the athlete in the competition video in real time by utilizing an improved target tracking algorithm;
the motion track generation module is used for generating a motion track corresponding to each feature point according to the feature points in each image sequence;
the motion risk evaluation module is used for comparing and analyzing the motion track with a preset standard motion track to realize the safety risk evaluation of the sports event.
Further, in order to realize real-time tracking of the sportsman, the moving target tracking module for real-time tracking the movement state of the sportsman in the competition video by using the improved target tracking algorithm comprises the following steps:
s1, selecting a moving target in a first frame of an image sequence, and setting the moving target as a tracking target;
s2, calculating a target model in the search window, wherein the target model is as follows:
in the formula, x 0 Representing the center of the target region, n representing the number of pixels in the target extraction region, K (x) representing the contour function of a kernel function K (x), h representing the window radius of the kernel function, x i Denotes the coordinates of the ith pixel, b (x) i ) To obtain x i The characteristic value of the pixel value of (a),
for judging the function, based on x i The difference range between the characteristic value of the pixel value and u is judged to be x i Whether the characteristic value of the pixel value is u or not and C is a normalization coefficient;
s3, iterating by using a Mean shift algorithm to obtain a new position of the optimal window, and recording the target state in the current frame, namely the position and the speed of the target in the current frame;
s4, judging whether the target is shielded or not according to the Pasteur distance coefficient obtained by the Mean shift algorithm, if the Pasteur distance coefficient is smaller than a preset threshold value, judging that the target is not shielded, returning to S3 to continue the operation until the end, and if the Pasteur distance coefficient is larger than the preset threshold value, judging that the target is shielded, and executing S5;
and S5, performing parameter identification by using a Kalman filter, performing subsequent state prediction on the shielded target, and returning to S3 to continue execution.
The motion track generation module comprises the following steps when generating the motion track corresponding to the characteristic point according to the characteristic point in each image sequence:
and collecting the characteristic points of the tracking target in each image sequence, and fitting the characteristic points in each image sequence through a fitting function based on the time sequence to obtain a corresponding curve, namely a motion track corresponding to the characteristic points.
The motion risk evaluation module compares and analyzes the motion track with a preset standard motion track, and the safety risk evaluation of the sports event comprises the following steps:
sequentially acquiring motion trail data of each athlete, comparing and analyzing the motion trail data with preset standard motion trail data, and judging whether the difference value between the motion trail data and the preset standard motion trail data is greater than a preset threshold value, if so, judging that potential safety hazards exist in the action of the athlete, otherwise, judging that the action of the athlete is safe;
analyzing and calculating the proportion of athletes with potential safety hazards in the total number of athletes participating in each sports item, judging whether the proportion is greater than a preset item safety threshold value, if so, judging that the potential safety hazards exist in the sports item, and generating alarm information, otherwise, judging that the sports item is safe;
analyzing and calculating the proportion of the sports items with potential safety hazards in the total number of the sports items in the sports event, judging whether the proportion is greater than a preset event safety threshold value, if so, judging that the potential safety hazards exist in the sports event, otherwise, judging that the sports items are safe, and realizing the safety risk assessment of the sports event.
The invention has the beneficial effects that:
1) The event data acquisition module is used for acquiring event evaluation data and standard historical data, comprehensively evaluating the mass sports events from five dimensions of organization management, service guarantee, social efficiency, economic benefit and adaptability under the action of the event data comprehensive evaluation module, and generating an evaluation report by combining with the evaluation report generation module based on preset weight and the evaluation result of the five dimensions of the events, so that the comprehensive evaluation of the large mass sports events is realized, and the evaluation requirement of the large mass sports events can be better met.
2) Through being provided with match video acquisition module, motion target tracking module, motion trail generation module and motion risk evaluation module, thereby can utilize match video acquisition module to acquire the match video data in the large-scale masses sports event, and utilize motion target tracking module to carry out real-time tracking to sportsman's motion state in the match video based on improved generation target tracking algorithm, thereby can follow the characteristic point of tracking the target in every image sequence and generate the motion trail that every characteristic point corresponds, again carry out comparative analysis with motion trail and predetermined standard motion trail, realize the safe risk evaluation to this sports event, thereby can satisfy the aassessment demand of large-scale masses sports event better.
3) By utilizing a target tracking algorithm combining a Mean shift algorithm and a Kalman filtering algorithm, kalman filtering is introduced to track a target when a competitor is sheltered, and a Kalman filter is utilized to identify parameters so that a sheltered tracking system can have subsequent state prediction capability, thereby effectively ensuring correct tracking of the motion state of the competitor when the shelter exists, solving the problems that the motion state of the competitor is not tracked in real time in safety guarantee evaluation or the motion state of the competitor cannot be correctly tracked when the shelter exists, further effectively improving the reliability of the competitor in motion state tracking, and better realizing the safety risk evaluation of the sport event.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
FIG. 1 is a block diagram of a system for comprehensive evaluation of a sports event of a large crowd based on image recognition technology according to an embodiment of the present invention;
fig. 2 is a block diagram illustrating a security assessment module in a comprehensive evaluation system for a sports event of a large crowd based on an image recognition technology according to an embodiment of the present invention.
In the figure:
1. an event data acquisition module; 2. the competition data comprehensive evaluation module; 21. an organization management evaluation module; 211. an operation scheme evaluation module; 212. an organization architecture assessment module; 213. an organization division evaluation module; 214. an expense management evaluation module; 215. a propaganda normative evaluation module; 22. a service guarantee evaluation module; 221. a safety guarantee evaluation module; 2211. a match video acquisition module; 2212. a moving object tracking module; 2213. a motion trail generation module; 2214. a motion risk assessment module; 222. a medical security assessment module; 223. a site guarantee evaluation module; 23. a social efficiency evaluation module; 231. an event atmosphere evaluation module; 232. a competition experience evaluation module; 233. a physical behavior impact evaluation module; 234. an event population breeding evaluation module; 24. an economic benefit evaluation module; 241. a sponsor number assessment module; 242. a sponsorship mode assessment module; 25. a fitness evaluation module; 251. a pre-competition information communication evaluation module; 252. timely submitting the material after the competition to an evaluation module; 253. the data information filling accuracy evaluation module; 3. and an evaluation report generation module.
Detailed Description
For further explanation of the various embodiments, the drawings which form a part of the disclosure and which are incorporated in and constitute a part of this specification, illustrate embodiments and, together with the description, serve to explain the principles of operation of the embodiments, and to enable others of ordinary skill in the art to understand the various embodiments and advantages of the invention, and, by reference to these figures, reference is made to the accompanying drawings, which are not to scale and wherein like reference numerals generally refer to like elements.
According to the embodiment of the invention, a comprehensive evaluation system for the sports events of the large masses based on the image recognition technology is provided.
Referring now to the drawings and the detailed description, in accordance with an embodiment of the present invention, a system for comprehensive evaluation of a sports event of a large crowd based on image recognition technology, as shown in fig. 1-2, includes: the system comprises an event data acquisition module 1, an event data comprehensive evaluation module 2 and an evaluation report generation module 3, wherein the event data acquisition module 1, the event data comprehensive evaluation module 2 and the evaluation report generation module 3 are sequentially connected;
the event data acquisition module 1 is used for acquiring event evaluation data and standard historical data;
the event data comprehensive evaluation module 2 is used for comprehensively evaluating events from five dimensions of organization management, service guarantee, social efficiency, economic benefit and fitness;
the competition data comprehensive evaluation module 2 comprises an organization management evaluation module 21, a service guarantee evaluation module 22, a social efficiency evaluation module 23, an economic benefit evaluation module 24 and a fitness evaluation module 25;
the organization management evaluation module 21 is used for evaluating organization plan and event normative management of events;
specifically, the organization management evaluation module 21 includes an operation plan evaluation module 211, an organization architecture evaluation module 212, an organization division evaluation module 213, an expense management evaluation module 214, and a promotion normative evaluation module 215;
the operation scheme evaluation module 211 is used for integrally evaluating the operation scheme of the event by an expert scoring method;
the organization architecture evaluation module 212 is used for integrally evaluating the organization architecture of the event by an expert scoring method;
the organization division labor assessment module 213 is used for integrally assessing the organization division labor condition of the event by an expert scoring method;
the expense management evaluation module 214 is used for integrally evaluating the expense management condition of the event through an expert scoring method;
the campaign normalization assessment module 215 is configured to perform an overall assessment of the campaign's campaign normalization by expert scoring.
The service guarantee evaluation module 22 is used for evaluating the situations of places, medical treatment and safety guarantee provided by the events for the competitors;
specifically, the service guarantee evaluation module 22 includes a security guarantee evaluation module 221, a medical guarantee evaluation module 222, and a site guarantee evaluation module 223;
the safety guarantee evaluation module 221 is used for integrally evaluating the safety guarantee condition of the event by combining an expert scoring method and an image recognition technology;
the security assurance evaluation module 221 includes a competition video acquisition module 2211, a moving target tracking module 2212, a moving track generation module 2213 and a moving risk evaluation module 2214;
the game video acquisition module 2211 is used for acquiring game video data in sports events of large masses;
the moving target tracking module 2212 is used for tracking the moving state of the athletes in the competition video in real time by using an improved target tracking algorithm;
in this embodiment, when the athlete target is blocked in the image sequence, the Mean shift algorithm cannot accurately track the target, and even the target is lost. Therefore, the moving target is tracked by utilizing a tracking algorithm combining the Meanshift algorithm and the Kalman filtering. The method judges whether occlusion occurs according to a Bhattacharyya (Bhattacharyya distance) coefficient, and under the condition of occlusion, a Kalman filter is used for parameter identification, so that a tracking system after occlusion has subsequent state prediction capability, and a moving target is accurately tracked.
Specifically, the moving object tracking module 2212, in real time tracking the moving state of the athlete in the game video by using the improved object tracking algorithm, includes the following steps:
s1, selecting a moving target in a first frame of an image sequence, and setting the moving target as a tracking target;
s2, calculating a target model in the search window, wherein the target model is as follows:
in the formula, x 0 Representing the center of the target region, n representing the number of pixels in the target extraction region, K (x) representing the contour function of a kernel function K (x), h representing the window radius of the kernel function, x i Denotes the coordinates of the ith pixel, b (x) i ) To obtain x i The characteristic value of the pixel value of (b),
to determine a functionBased on x i The difference range between the characteristic value of the pixel value and u is judged to be x i Whether the characteristic value of the pixel value is u or not and C is a normalization coefficient;
s3, iterating by using a Mean shift algorithm to obtain a new position of the optimal window, and recording the target state in the current frame, namely the position and the speed of the target in the current frame;
in this embodiment, a Mean shift algorithm (Mean shift algorithm) is a method for searching a peak value by adaptive gradient ascent. The algorithm adopts a quantized color space as a feature space, and for each pixel point of a target area in an initial frame image, the probability of each feature value in the feature space is calculated, namely the target model is obtained. And performing the same calculation on a candidate region in which the target possibly exists in the next frame of image, and calculating the similarity between the target model and the candidate model by using a Bhattacharyya (Papanicolaou distance) coefficient to find the candidate model with the maximum similarity with the target model, namely completing the tracking process of the target.
S4, judging whether the target is shielded or not according to the Pasteur distance coefficient obtained by the Mean shift algorithm, if the Pasteur distance coefficient is smaller than a preset threshold value, judging that the target is not shielded, returning to S3 to continue the operation until the end, and if the Pasteur distance coefficient is larger than the preset threshold value, judging that the target is shielded, and executing S5;
and S5, performing parameter identification by using a Kalman filter, performing subsequent state prediction on the shielded target, and returning to S3 to continue execution.
The Kalman filtering is a simple and common state estimation rapid algorithm, the algorithm is an optimal data recursive processing method, a mean square error minimum principle is followed, and a system is described by a state equation and a measurement equation by using a system estimation theory. The Kalman filtering is characterized in that the storage of the past measurement data is not required, only the observation value of the current frame and the estimation value of the previous moment are used, and the new estimation value can be calculated by predicting the estimation value of the moment through the state transition equation of the system and according to the prediction and correction equation. This algorithm has many advantages, such as it is an optimal, unbiased minimum variance estimate under white gaussian noise conditions, and it is also the best linear filter for non-gaussian noise. Due to the characteristics of the device, a large amount of past data does not need to be stored, so that the calculation is simple. A change in the detection process that can be adapted, etc.
The motion track generation module 2213 is configured to generate a motion track corresponding to each feature point according to the feature point in each image sequence;
specifically, the motion trajectory generating module 2213 includes the following steps when generating the motion trajectory corresponding to the feature point according to the feature point in each image sequence:
and collecting the characteristic points of the tracking target in each image sequence, and fitting the characteristic points in each image sequence through a fitting function based on the time sequence to obtain a corresponding curve, namely a motion track corresponding to the characteristic points.
The motion risk assessment module 2214 is configured to compare and analyze the motion trajectory with a preset standard motion trajectory, so as to implement security risk assessment on the athletic event.
Specifically, the exercise risk assessment module 2214 compares and analyzes the exercise trajectory with a preset standard exercise trajectory, and the following steps are included when the security risk assessment of the exercise event is implemented:
sequentially acquiring motion trail data of each athlete, comparing and analyzing the motion trail data with preset standard motion trail data, and judging whether the difference value between the motion trail data and the preset standard motion trail data is greater than a preset threshold value, if so, judging that potential safety hazards exist in the action of the athlete, otherwise, judging that the action of the athlete is safe;
analyzing and calculating the proportion of athletes with potential safety hazards in the total number of athletes participating in each sports item, judging whether the proportion is greater than a preset item safety threshold value, if so, judging that the potential safety hazards exist in the sports item, and generating alarm information, otherwise, judging that the sports item is safe;
and analyzing and calculating the proportion of the sports items with potential safety hazards in the total number of the sports items in the sports event, judging whether the proportion is greater than a preset event safety threshold value, if so, judging that the potential safety hazards exist in the sports event, otherwise, judging that the sports items are safe, and realizing the safety risk assessment of the sports event.
The medical insurance evaluation module 222 is used for performing overall evaluation on the medical insurance status of the event by an expert scoring method;
the field guarantee evaluation module 223 is used for integrally evaluating the field guarantee condition of the event by combining an expert scoring method and an image recognition technology.
The social efficiency evaluation module 23 is used for evaluating the positive influence conditions of the events on the competitors and residents in other cities;
specifically, the social efficiency evaluation module 23 includes an event atmosphere evaluation module 231, a competition experience evaluation module 232, a physical activity influence evaluation module 233, and an event population breeding evaluation module 234;
the event atmosphere evaluation module 231 is used for integrally evaluating the event atmosphere of the event by an expert scoring method;
the competition experience evaluation module 232 is used for integrally evaluating the competition experience conditions of competitors of the competition by an expert scoring method;
the sports behavior influence evaluation module 233 is used for overall evaluation of sports behavior influence conditions of the events by an expert scoring method; the sports behavior influence represents the willingness of the competitor to participate in the event again, and can promote the formation of the sports habit of participating in the event;
the event population breeding evaluation module 234 is used for integrally evaluating population breeding conditions of the events by an expert scoring method; the competition population cultivation represents the intention of the competitor to recommend others to watch or participate in the competition, and can participate in the sport meeting to stimulate the daily exercise of citizens.
The economic benefit evaluation module 24 is used for evaluating the socialized strength participation condition of the event and the sports consumption condition driven by the holding of the event;
specifically, the economic benefit evaluation module 24 includes a sponsor number evaluation module 241 and a sponsorship mode evaluation module 242;
the sponsor number evaluation module 241 is used for carrying out overall evaluation on the sponsor number of the event by an expert scoring method;
the sponsorship assessment module 242 is configured to assess the overall sponsorship of the event through expert scoring.
The fitness evaluation module 25 is used for evaluating the fitness of the event unit for the evaluation work.
Specifically, the fitness evaluation module 25 includes a pre-match information communication evaluation module 251, a post-match material timely submission evaluation module 252, and a data information reporting accuracy evaluation module 253;
the pre-event information communication evaluation module 251 is used for integrally evaluating the pre-event information communication condition of the event by an expert scoring method;
the post-event material timely submitting evaluation module 252 is used for integrally evaluating the post-event material timely submitting status of the event by an expert scoring method;
the data information reporting accuracy assessment module 253 is used for performing overall assessment on the data information reporting accuracy of the event by an expert scoring method.
The evaluation report generation module 3 is used for generating an evaluation report according to the preset weight and the evaluation result of the five dimensions of the event;
specifically, an organization management score A, a service guarantee score B, a social efficiency score C, an economic benefit score D and a matching degree score F are respectively obtained, corresponding weights are set according to the importance degrees of five dimensions and are respectively marked as x 1 、x 2 、x 3 、x 4 、x 5 Finally, a composite score P = x may be calculated 1 A+x 2 B+x 3 C+x 4 D+x 5 And F, obtaining the comprehensive score of the sports events of the large masses.
In summary, according to the technical scheme of the invention, the event evaluation data and the standard historical data are acquired through the event data acquisition module, the mass sports events can be comprehensively evaluated from five dimensions of organization management, service guarantee, social efficiency, economic benefit and fitness under the action of the event data comprehensive evaluation module, and the evaluation report is generated by combining the evaluation report generation module based on the preset weight and the evaluation result of the five dimensions of the events, so that the comprehensive evaluation of the mass sports events is realized, and the evaluation requirement of the mass sports events can be better met.
In addition, through being provided with match video acquisition module, motion target tracking module, motion trail generation module and motion risk evaluation module, thereby can utilize match video acquisition module to acquire the match video data in the sports event of large-scale masses, and utilize motion target tracking module to carry out real-time tracking to sportsman's motion state in the match video based on improved generation target tracking algorithm, thereby can follow the motion trail that the characteristic point of tracking target corresponds in every image sequence and generate every characteristic point, again with the motion trail with the analysis of comparing of predetermined standard motion trail, realize the safety risk evaluation to this sports event, thereby can satisfy the aassessment demand in the sports event of large-scale masses better.
In addition, through the target tracking algorithm combining the Mean shift algorithm and the Kalman filtering algorithm, kalman filtering is introduced to track a target when a competitor is sheltered, and the Kalman filter is used for parameter identification, so that the sheltered tracking system can have subsequent state prediction capability, thereby effectively ensuring the correct tracking of the motion state of the competitor when the shelter exists, solving the problems that the motion state of the competitor is not tracked in real time in safety guarantee evaluation or the motion state of the competitor cannot be correctly tracked when the shelter exists, further effectively improving the reliability of the competitor in motion state tracking, and better realizing the safety risk evaluation of the sport event.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (7)
1. A comprehensive evaluation system for a sports event of a large crowd based on an image recognition technology is characterized by comprising: the system comprises an event data acquisition module (1), an event data comprehensive evaluation module (2) and an evaluation report generation module (3), wherein the event data acquisition module (1), the event data comprehensive evaluation module (2) and the evaluation report generation module (3) are sequentially connected;
the event data acquisition module (1) is used for acquiring event evaluation data and standard historical data;
the event data comprehensive evaluation module (2) is used for comprehensively evaluating events from five dimensions of organization management, service guarantee, social efficiency, economic benefit and fitness;
the evaluation report generation module (3) is used for generating an evaluation report according to the preset weight and the evaluation result of the five dimensions of the event;
the event data comprehensive evaluation module (2) comprises an organization management evaluation module (21), a service guarantee evaluation module (22), a social efficiency evaluation module (23), an economic benefit evaluation module (24) and a fitness evaluation module (25);
the organization management evaluation module (21) is used for evaluating organization plan and event normative management of events;
the service guarantee evaluation module (22) is used for evaluating the situations of places, medical treatment and safety guarantee provided by the events for the competitors;
the social efficiency evaluation module (23) is used for evaluating the positive influence conditions of the events on the competitors and residents in other cities;
the economic benefit evaluation module (24) is used for evaluating the socialized strength participation condition of the event and the sports consumption condition driven by the event handling;
the matching degree evaluation module (25) is used for evaluating the matching degree of the competition unit aiming at the evaluation work;
the service guarantee evaluation module (22) comprises a safety guarantee evaluation module (221), a medical guarantee evaluation module (222) and a site guarantee evaluation module (223);
the safety guarantee evaluation module (221) comprises a competition video acquisition module (2211), a moving target tracking module (2212), a moving track generation module (2213) and a moving risk evaluation module (2214);
the match video acquisition module (2211) is used for acquiring match video data in a sports event of a large crowd;
the moving target tracking module (2212) is used for tracking the moving state of the athletes in the competition video in real time by utilizing an improved target tracking algorithm;
the motion track generation module (2213) is used for generating a motion track corresponding to each feature point according to the feature points in each image sequence;
the motion risk assessment module (2214) is used for comparing and analyzing the motion track with a preset standard motion track to realize the safety risk assessment of the motion event;
wherein the moving target tracking module (2212) tracks the moving state of the athlete in real time in the game video by using the improved target tracking algorithm, and comprises the following steps:
s1, selecting a moving target in a first frame of an image sequence, and setting the moving target as a tracking target;
s2, calculating a target model in the search window, wherein the target model is as follows:
in the formula, x 0 Representing the center of the target region, n representing the number of pixels in the target extraction region, K (x) representing the contour function of a kernel function K (x), h representing the window radius of the kernel function, x i Denotes the coordinates of the ith pixel, b (x) i ) To obtain x i The characteristic value of the pixel value of (a),
for judging the function, based on x i The difference range between the characteristic value of the pixel value and u is judged to be x i OfWhether the characteristic value of the pixel value is u or not and C is a normalization coefficient;
s3, iterating by using a Mean shift algorithm to obtain a new position of the optimal window, and recording the target state in the current frame, namely the position and the speed of the target in the current frame;
s4, judging whether the target is shielded or not according to the Papanicolaou distance coefficient obtained by the Mean shift algorithm, if the Papanicolaou distance coefficient is smaller than a preset threshold value, judging that the target is not shielded, returning to S3 to continue the process until the process is finished, and if the Papanicolaou distance coefficient is larger than the preset threshold value, judging that the target is shielded, and executing S5;
and S5, performing parameter identification by using a Kalman filter, performing subsequent state prediction on the shielded target, and returning to S3 to continue execution.
2. The system for comprehensive evaluation of sports events of masses based on image recognition technology as claimed in claim 1, wherein the organization management evaluation module (21) comprises an operation scheme evaluation module (211), an organization architecture evaluation module (212), an organization division evaluation module (213), an expense management evaluation module (214) and a promotion normative evaluation module (215).
3. The system for comprehensively evaluating the sports events of the large masses based on the image recognition technology as claimed in claim 1, wherein the social efficiency evaluation module (23) comprises an event atmosphere evaluation module (231), a competition experience evaluation module (232), a sports behavior influence evaluation module (233) and an event population breeding evaluation module (234).
4. The system for the comprehensive evaluation of the sports events of the masses based on the image recognition technology as claimed in claim 1, wherein the economic benefit evaluation module (24) comprises a sponsor number evaluation module (241) and a sponsorship manner evaluation module (242).
5. The system for comprehensively evaluating the sports events of the masses based on the image recognition technology as claimed in claim 1, wherein the fitness evaluation module (25) comprises a pre-event information communication evaluation module (251), a post-event material timely submission evaluation module (252) and a data information reporting accuracy evaluation module (253).
6. The system for comprehensive evaluation of sports events of masses based on image recognition technology as claimed in claim 5, wherein the motion trail generation module (2213) comprises the following steps when generating the motion trail corresponding to the feature point according to the feature point in each image sequence:
and collecting the characteristic points of the tracking target in each image sequence, and fitting the characteristic points in each image sequence through a fitting function based on the time sequence to obtain a corresponding curve, namely a motion track corresponding to the characteristic points.
7. The system for comprehensively evaluating the sports events of the masses based on the image recognition technology as claimed in claim 4, wherein the sports risk evaluation module (2214) comprises the following steps when comparing and analyzing the sports track with the preset standard sports track to evaluate the security risk of the sports event:
sequentially acquiring motion trail data of each athlete, comparing and analyzing the motion trail data with preset standard motion trail data, and judging whether the difference value between the motion trail data and the preset standard motion trail data is greater than a preset threshold value, if so, judging that potential safety hazards exist in the action of the athlete, otherwise, judging that the action of the athlete is safe;
analyzing and calculating the proportion of athletes with potential safety hazards in the total number of athletes participating in each sports item, judging whether the proportion is greater than a preset item safety threshold value, if so, judging that the potential safety hazards exist in the sports item, and generating alarm information, otherwise, judging that the sports item is safe;
and analyzing and calculating the proportion of the sports items with potential safety hazards in the total number of the sports items in the sports event, judging whether the proportion is greater than a preset event safety threshold value, if so, judging that the potential safety hazards exist in the sports event, otherwise, judging that the sports items are safe, and realizing the safety risk assessment of the sports event.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211348364.XA CN115471139B (en) | 2022-10-31 | 2022-10-31 | Large-scale crowd sports event comprehensive evaluation system based on image recognition technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211348364.XA CN115471139B (en) | 2022-10-31 | 2022-10-31 | Large-scale crowd sports event comprehensive evaluation system based on image recognition technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115471139A CN115471139A (en) | 2022-12-13 |
| CN115471139B true CN115471139B (en) | 2023-02-10 |
Family
ID=84336801
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211348364.XA Active CN115471139B (en) | 2022-10-31 | 2022-10-31 | Large-scale crowd sports event comprehensive evaluation system based on image recognition technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115471139B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116433709A (en) * | 2023-04-14 | 2023-07-14 | 北京拙河科技有限公司 | Tracking method and device for sports ground monitoring |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2010014223A2 (en) * | 2008-07-29 | 2010-02-04 | Pvi Virtual Media Services, Llc | System and method for analyzing data from athletic events |
| CN107767392A (en) * | 2017-10-20 | 2018-03-06 | 西南交通大学 | A kind of ball game trajectory track method for adapting to block scene |
| CN108876820A (en) * | 2018-06-11 | 2018-11-23 | 广东工业大学 | A kind of obstruction conditions based on average drifting move down object tracking method |
| CN112535857A (en) * | 2020-11-18 | 2021-03-23 | 温州大学 | Safety assessment system for outdoor sports |
| CN113256104A (en) * | 2021-05-24 | 2021-08-13 | 北京奥邦体育赛事评估有限责任公司 | Comprehensive benefit evaluation system for mass sports events based on entropy method |
| CN114118864A (en) * | 2021-12-07 | 2022-03-01 | 武汉体育学院 | Large-scale crowd's sports event comprehensive assessment system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210174406A1 (en) * | 2019-12-06 | 2021-06-10 | Shawn T. Lemoto | Method For Evaluating A Sports Related Individual, Team Or Institution |
-
2022
- 2022-10-31 CN CN202211348364.XA patent/CN115471139B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2010014223A2 (en) * | 2008-07-29 | 2010-02-04 | Pvi Virtual Media Services, Llc | System and method for analyzing data from athletic events |
| CN107767392A (en) * | 2017-10-20 | 2018-03-06 | 西南交通大学 | A kind of ball game trajectory track method for adapting to block scene |
| CN108876820A (en) * | 2018-06-11 | 2018-11-23 | 广东工业大学 | A kind of obstruction conditions based on average drifting move down object tracking method |
| CN112535857A (en) * | 2020-11-18 | 2021-03-23 | 温州大学 | Safety assessment system for outdoor sports |
| CN113256104A (en) * | 2021-05-24 | 2021-08-13 | 北京奥邦体育赛事评估有限责任公司 | Comprehensive benefit evaluation system for mass sports events based on entropy method |
| CN114118864A (en) * | 2021-12-07 | 2022-03-01 | 武汉体育学院 | Large-scale crowd's sports event comprehensive assessment system |
Non-Patent Citations (1)
| Title |
|---|
| 复合赋权云模型在户外体育赛事风险研究中的应用;李凯玲等;《安全与环境学报》;20220623;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115471139A (en) | 2022-12-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11755952B2 (en) | System and method for predictive sports analytics using body-pose information | |
| CN108256433B (en) | Motion attitude assessment method and system | |
| CN115471139B (en) | Large-scale crowd sports event comprehensive evaluation system based on image recognition technology | |
| CN103164315A (en) | Computer using time prompting method and system based on intelligent video analysis | |
| CN111905350B (en) | Automatic table tennis hitting performance evaluation method and system based on motion data | |
| Eggels et al. | Expected goals in soccer: Explaining match results using predictive analytics | |
| Wenninger et al. | Performance of machine learning models in application to beach volleyball data. | |
| Kusmakar et al. | Machine learning enabled team performance analysis in the dynamical environment of soccer | |
| Hu et al. | Basketball activity classification based on upper body kinematics and dynamic time warping | |
| Abhishek et al. | Predictive analysis of IPL match winner using machine learning techniques | |
| Wang et al. | Analyzing the feature extraction of football player’s offense action using machine vision, big data, and internet of things | |
| Hu | IoT-based analysis of tennis player’s serving behavior using image processing | |
| CN105893499A (en) | Athletics competition data displaying method and device | |
| US20210295184A1 (en) | Predicting And Mitigating Athlete Injury Risk | |
| CN111773651A (en) | Badminton training monitoring and evaluating system and method based on big data | |
| Gill et al. | Sports Game Classification and Detection Using ResNet50 Model Through Machine Learning Techniques Using Artificial Intelligence | |
| Yin et al. | Automatic detection of stereotypical behaviors of captive wild animals based on surveillance videos of zoos and animal reserves | |
| Chakraborty et al. | Deep Learning-Based Prediction of Football Players’ Performance During Penalty Shootout | |
| CN112749625B (en) | Time sequence behavior detection method, time sequence behavior detection device and terminal equipment | |
| Chopra et al. | A key-frame extraction for object detection and human action recognition in soccer game videos | |
| Zin et al. | Body condition score assessment of depth image using artificial neural network | |
| Chaudhary | Artificial Intellegence In Sports | |
| Aközbek | Finding patterns: Assessing defensive pressure in football using machine learning | |
| Zhang | Adaptive Monitoring Technology of Basketball Video Image under Intelligent Network | |
| CN117275092A (en) | Intelligent skiing action evaluation method, system, equipment and medium |
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 |