CN116109672A - Intelligent training, monitoring and analyzing method for snowmobile sled track - Google Patents
Intelligent training, monitoring and analyzing method for snowmobile sled track Download PDFInfo
- Publication number
- CN116109672A CN116109672A CN202310066676.XA CN202310066676A CN116109672A CN 116109672 A CN116109672 A CN 116109672A CN 202310066676 A CN202310066676 A CN 202310066676A CN 116109672 A CN116109672 A CN 116109672A
- Authority
- CN
- China
- Prior art keywords
- snowmobile
- video
- track
- sledge
- pixel
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
- G06T7/248—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments involving reference images or patches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/292—Multi-camera tracking
-
- 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
- G06T2207/30221—Sports video; Sports image
- G06T2207/30228—Playing field
-
- 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
- G06T2207/30232—Surveillance
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Abstract
The invention discloses an intelligent training monitoring analysis method for a snowmobile sled track, which belongs to the technical field of training monitoring methods and specifically comprises the following steps: s1, arranging a plurality of shooting points at the whole-course key position of a snowmobile ski racing track, collecting corresponding video data, deriving a racing track sliding video, and reading an original video file; s2, processing the read original video file to synthesize a continuous sliding video; s3, identifying an original video file, obtaining pixel points of a snowmobile and a sledge, and analyzing pixel tracks marked by the snowmobile and the sledge in the video based on the pixel points; s4, single-view calibration is carried out by using a calibration frame, a calibration file is read, and the space size corresponding to the pixel point is obtained; s5, calculating the position speed and the acceleration of the athlete according to the pixel track marked by the athlete obtained in the S3 and the space size corresponding to the pixel point obtained in the S4; s6, integrating the speed data obtained in the step S5, outputting a corresponding result curve, and completing training, monitoring and analyzing work of the athlete according to the result curve.
Description
Technical Field
The invention relates to the technical field of training monitoring methods, in particular to an intelligent training monitoring analysis method for a snowmobile ski track.
Background
The snowmobile sledge project is used as one of winter Olympic project, and the action composition of the snowmobile sledge project is mainly divided into two parts: firstly, a starting up stage, in which an athlete needs to accelerate by pedaling a ground pushing cart (sledge) or pushing ice by two hands, and when the highest speed is reached, the athlete keeps a stable action gesture on the sledge to enter a second part of a track sliding stage; the mobilization means that the vehicle slews and the gravitational potential energy of the mobilization means that the mobilization means runs to the end point along the ice layer track with a length of thousands of meters, a vertical height difference of 121 meters and 16 curves, the highest speed per hour can reach 134.4 km/h, and the maximum acceleration is 4.7g. The snowmobile sledge sport has obvious motor skill emphasis points in different sport phases, and because the snowmobile sledge belongs to the winter ' ice road sliding down ' project, the speed of a sporter in a track is extremely high during competition training, so that a plurality of difficulties and dead zones are manufactured for the supervision and guidance of a sportsman's action technology, meanwhile, the sportsman lacks system scientific data support for the action optimization in the whole-flow track sliding of the sportsman, and more, the sportsman performs single shooting analysis action through an Ipad or a camera at a certain curve point of the local part of the track. There is also a lack of more scientific indicators of how an athlete can precisely adjust and optimize the taxiing technique.
With the development of the age, it is a trend to combine the emerging technologies with exercise training. Therefore, a full course, scientific and intelligent training system is needed to assist snowmobiles and sleigh sports teams to accurately, quantitatively, efficiently and comprehensively perform technical action measurement and analysis, and the sportsman is helped to perform special action optimization and provide guiding advice for specific physical training by analyzing the kinetic parameters of the sportsman in the specific action process of each curve. However, a full-flow intelligent monitoring training system for the whole track sliding of snowmobile skiers has not been reported yet. Based on the reasons, the application provides an intelligent training monitoring analysis method for a snowmobile ski track.
Disclosure of Invention
1. Technical problem to be solved by the invention
The invention aims to provide the intelligent training monitoring analysis method for the snowmobile ski track, which can intelligently and efficiently carry out whole-course detection and analysis of the snowmobile ski athlete and guide the athlete to promote the sliding technology by a scientific and quantitative technical means.
2. Technical proposal
In order to achieve the above purpose, the present invention provides the following technical solutions:
the intelligent training, monitoring and analyzing method for the snowmobile sled track comprises the following steps:
s1, arranging a plurality of shooting points at the whole-course key position of a snowmobile ski racing track, collecting corresponding video data, deriving a racing track sliding video, and reading an original video file;
s2, processing the original video file read in the S1, and synthesizing the original video file into a continuous sliding video;
s3, identifying an original video file, obtaining pixel points of a snowmobile and a sledge, and analyzing pixel tracks marked by the snowmobile and the sledge in the video based on the pixel points;
s4, single-view calibration is carried out by using a calibration frame, and a calibration file is obtained; reading a calibration file to obtain the space size corresponding to the pixel point;
s5, calculating the position speed and the acceleration of the athlete according to the pixel track marked by the athlete obtained in the S3 and the space size corresponding to the pixel point obtained in the S4;
s6, integrating the speed data obtained in the step S5, outputting a corresponding result curve, and completing training, monitoring and analyzing work of the athlete according to the result curve.
Preferably, the S2 specifically includes the following: based on video motion recognition, video clipping and video splicing technologies, whether a snowmobile and a sledge scratch the scene is judged by combining an inter-frame difference method, when the frames do not have the snowmobile and the sledge, the next video of the sequence is read, the frames of the snowmobile and the sledge are extracted, and after all the videos are processed at one time, the continuous sliding video of the snowmobile and the sledge is obtained.
Preferably, the S3 specifically includes the following:
and judging whether the snowmobile and the sled scratch the scene or not by combining an inter-frame difference method and a color recognition algorithm, recognizing corresponding pixel points of the snowmobile and the sled in the image, and removing the influence of miscellaneous points in the image by using a mask plate to obtain clear pixel tracks scratched by the snowmobile and the sled.
3. Advantageous effects
The invention can help a coach to analyze and optimize the motion of the whole flow sliding track of the athlete on the whole track, and can find the optimal path of the athlete sliding on the track based on the motion, thereby improving the competition result of the athlete.
Drawings
FIG. 1 is a flow chart of a snowmobile ski track intelligent training monitoring analysis method provided by the invention;
FIG. 2 is a schematic diagram illustrating pixel identification in embodiment 1 of the present invention;
FIG. 3 is a schematic illustration of a reticle and single view calibration in embodiment 1 of the present invention;
FIG. 4 is a graph showing the displacement and velocity curves in example 1 of the present invention;
FIG. 5 is a schematic diagram of the kinematic analysis in example 1 of the present invention.
Detailed Description
The invention provides a snowmobile ski track intelligent training monitoring analysis method which is described in detail below with reference to the accompanying drawings and specific embodiments.
Also, it is to be understood that the following embodiments are the best and preferred embodiments for the purpose of making the embodiments more detailed, and that other alternatives may be employed by those skilled in the art; and the accompanying drawings are only for the purpose of describing the embodiments more specifically and are not intended to limit the invention specifically.
The invention is intended to cover any alternatives, modifications, equivalents, and variations that fall within the spirit and scope of the invention. In the following description of preferred embodiments of the invention, specific details are set forth in order to provide a thorough understanding of the invention, and the invention will be fully understood to those skilled in the art without such details. In other instances, well-known methods, procedures, flows, components, circuits, and the like have not been described in detail so as not to unnecessarily obscure aspects of the present invention.
Example 1:
the invention takes a central competitive track of a snowmobile of a Yangqing country as an example, the full length of the track is 1975 m, the competition length is 1615 m, the vertical drop is 121 m, the straight track is 315 m, the length of a curve is 1300 m (accounting for 85% of the total length), and the track consists of 16 curves with different angles and inclinations. According to the invention, core kinematic data such as displacement, speed and acceleration of a certain curve or point athlete are measured through capturing sliding track videos of the athlete at 16 curves and special positions of the track by the 33 cameras arranged on the periphery of the 1975 m long track, and related icons such as a graph are generated, so that the method can be used for comparing and analyzing the data of multiple athletes, and specifically comprises the following contents.
Referring to fig. 1, a snowmobile ski track intelligent training, monitoring and analyzing method includes the following steps:
s1, setting 33 shooting points at the whole-course key position of a snowmobile ski racing track, collecting corresponding video data, deriving a racing track sliding video, and reading an original video file;
s2, processing the original video file read in the S1, and synthesizing the original video file into a continuous sliding video;
the method comprises the following steps:
judging whether the snowmobile and the sledge scratch the scene or not by combining an inter-frame difference method based on video motion recognition, video clipping and video splicing technology, reading a sequence next video and extracting a snowmobile and sledge picture when the picture does not have the snowmobile and sledge, and processing all the videos at one time to obtain a continuous sliding video of the snowmobile and the sledge;
s3, identifying an original video file, obtaining pixel points (shown in fig. 2) of the snowmobile and the sledge, and analyzing pixel tracks marked by the snowmobile and the sledge in the video based on the pixel points;
the method comprises the following steps: referring to fig. 2-3, judging whether the snowmobile and the sledge scratch the scene by combining an inter-frame difference method and a color recognition algorithm, recognizing corresponding pixel points of the snowmobile and the sledge in the image, and simultaneously removing the influence of miscellaneous points in the image by using a mask plate to obtain clear pixel tracks scratched by the snowmobile and the sledge;
s4, single-view calibration is carried out by using a calibration frame, and a calibration file is obtained; reading a calibration file to obtain the space size corresponding to the pixel point;
s5, calculating the position speed and the acceleration of the athlete according to the pixel track marked by the athlete obtained in the S3 and the space size corresponding to the pixel point obtained in the S4 (shown in fig. 4);
s6, please refer to FIG. 5, the calculated speed data in S5 are integrated, a corresponding result curve is output, and training, monitoring and analyzing work of the athlete is completed according to the result curve.
The foregoing is only a preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art, who is within the scope of the present invention, should make equivalent substitutions or modifications according to the technical solution and the modified concept thereof, within the scope of the present invention.
Claims (3)
1. The intelligent training, monitoring and analyzing method for the snowmobile sled track is characterized by comprising the following steps of:
s1, arranging a plurality of shooting points at the whole-course key position of a snowmobile ski racing track, collecting corresponding video data, deriving a racing track sliding video, and reading an original video file;
s2, processing the original video file read in the S1, and synthesizing the original video file into a continuous sliding video;
s3, identifying an original video file, obtaining pixel points of a snowmobile and a sledge, and analyzing pixel tracks marked by the snowmobile and the sledge in the video based on the pixel points;
s4, single-view calibration is carried out by using a calibration frame, and a calibration file is obtained; reading a calibration file to obtain the space size corresponding to the pixel point;
s5, calculating the position speed and the acceleration of the athlete according to the pixel track marked by the athlete obtained in the S3 and the space size corresponding to the pixel point obtained in the S4;
s6, integrating the speed data obtained in the step S5, outputting a corresponding result curve, and completing training, monitoring and analyzing work of the athlete according to the result curve.
2. The method for intelligent training, monitoring and analyzing of a snowmobile ski track according to claim 1, wherein S2 specifically comprises the following steps: based on video motion recognition, video clipping and video splicing technologies, whether a snowmobile and a sledge scratch the scene is judged by combining an inter-frame difference method, when the frames do not have the snowmobile and the sledge, the next video of the sequence is read, the frames of the snowmobile and the sledge are extracted, and after all the videos are processed at one time, the continuous sliding video of the snowmobile and the sledge is obtained.
3. The method for intelligent training, monitoring and analyzing of a snowmobile ski track according to claim 1, wherein S3 specifically comprises the following steps:
and judging whether the snowmobile and the sled scratch the scene or not by combining an inter-frame difference method and a color recognition algorithm, recognizing corresponding pixel points of the snowmobile and the sled in the image, and removing the influence of miscellaneous points in the image by using a mask plate to obtain clear pixel tracks scratched by the snowmobile and the sled.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310066676.XA CN116109672A (en) | 2023-01-13 | 2023-01-13 | Intelligent training, monitoring and analyzing method for snowmobile sled track |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310066676.XA CN116109672A (en) | 2023-01-13 | 2023-01-13 | Intelligent training, monitoring and analyzing method for snowmobile sled track |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116109672A true CN116109672A (en) | 2023-05-12 |
Family
ID=86255718
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310066676.XA Pending CN116109672A (en) | 2023-01-13 | 2023-01-13 | Intelligent training, monitoring and analyzing method for snowmobile sled track |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116109672A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103020577A (en) * | 2011-09-20 | 2013-04-03 | 佳都新太科技股份有限公司 | Moving target identification method based on hog characteristic and system |
| CN109345568A (en) * | 2018-09-19 | 2019-02-15 | 深圳市赢世体育科技有限公司 | Sports ground intelligent implementing method and system based on computer vision algorithms make |
| CN113384861A (en) * | 2021-05-20 | 2021-09-14 | 上海奥视达智能科技有限公司 | Table tennis training device, table tennis training method, and computer-readable storage medium |
| CN114359343A (en) * | 2021-12-31 | 2022-04-15 | 北京市商汤科技开发有限公司 | Motion trail management method, device and equipment and computer readable storage medium |
| CN114679619A (en) * | 2022-03-18 | 2022-06-28 | 咪咕数字传媒有限公司 | Method, system, equipment and storage medium for enhanced display of ski competition information |
| CN115375733A (en) * | 2022-08-24 | 2022-11-22 | 东北大学 | Snow vehicle sled three-dimensional sliding track extraction method based on videos and point cloud data |
-
2023
- 2023-01-13 CN CN202310066676.XA patent/CN116109672A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103020577A (en) * | 2011-09-20 | 2013-04-03 | 佳都新太科技股份有限公司 | Moving target identification method based on hog characteristic and system |
| CN109345568A (en) * | 2018-09-19 | 2019-02-15 | 深圳市赢世体育科技有限公司 | Sports ground intelligent implementing method and system based on computer vision algorithms make |
| CN113384861A (en) * | 2021-05-20 | 2021-09-14 | 上海奥视达智能科技有限公司 | Table tennis training device, table tennis training method, and computer-readable storage medium |
| CN114359343A (en) * | 2021-12-31 | 2022-04-15 | 北京市商汤科技开发有限公司 | Motion trail management method, device and equipment and computer readable storage medium |
| CN114679619A (en) * | 2022-03-18 | 2022-06-28 | 咪咕数字传媒有限公司 | Method, system, equipment and storage medium for enhanced display of ski competition information |
| CN115375733A (en) * | 2022-08-24 | 2022-11-22 | 东北大学 | Snow vehicle sled three-dimensional sliding track extraction method based on videos and point cloud data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Parmar et al. | What and how well you performed? a multitask learning approach to action quality assessment | |
| Lin et al. | Human in events: A large-scale benchmark for human-centric video analysis in complex events | |
| CN106853289B (en) | Table tennis ball serving based on video identification judges auxiliary system detection method | |
| McNally et al. | Golfdb: A video database for golf swing sequencing | |
| CN108229294B (en) | Motion data acquisition method and device, electronic equipment and storage medium | |
| Conaire et al. | Tennissense: A platform for extracting semantic information from multi-camera tennis data | |
| Marsland et al. | Using micro-sensor data to quantify macro kinematics of classical cross-country skiing during on-snow training | |
| Kim et al. | Applying pose estimation to predict amateur golf swing performance using edge processing | |
| Hsu et al. | Coachai: A project for microscopic badminton match data collection and tactical analysis | |
| CN114100103B (en) | Rope skipping counting detection system and method based on key point identification | |
| CN114550067A (en) | Automatic live broadcast and guide method, device, equipment and storage medium for sports events | |
| CN116109672A (en) | Intelligent training, monitoring and analyzing method for snowmobile sled track | |
| Li et al. | UniVS: Unified and Universal Video Segmentation with Prompts as Queries | |
| CN113177476A (en) | Identification method, system and test method for heel key points of standing long jump | |
| Woinoski et al. | Swimmer stroke rate estimation from overhead race video | |
| CN103927517A (en) | Motion detection method based on human body global feature histogram entropies | |
| Barbosa et al. | Classification of Taekwondo Techniques using Deep Learning Methods: First Insights. | |
| CN114302234B (en) | Quick packaging method for air skills | |
| Steinkellner et al. | Evaluation of object detection systems and video tracking in skiing videos | |
| Nelikanti et al. | An optimization based deep lstm predictive analysis for decision making in cricket | |
| Sen et al. | Fine-grained soccer actions classification using deep neural network | |
| CN110969133B (en) | Intelligent data acquisition method for table tennis game video | |
| CN117315147A (en) | Snowmobile sled 3D track reconstruction method based on single camera | |
| CN109977819A (en) | A kind of Weakly supervised individual part localization method of application template matching process | |
| CN113139496A (en) | Pedestrian re-identification method and system based on time sequence multi-scale fusion |
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 |