CN114187171B - System for recording throwing shot score based on artificial intelligence - Google Patents
System for recording throwing shot score based on artificial intelligence Download PDFInfo
- Publication number
- CN114187171B CN114187171B CN202111527737.5A CN202111527737A CN114187171B CN 114187171 B CN114187171 B CN 114187171B CN 202111527737 A CN202111527737 A CN 202111527737A CN 114187171 B CN114187171 B CN 114187171B
- Authority
- CN
- China
- Prior art keywords
- throwing
- module
- detection
- algorithm
- video
- 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
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 15
- 238000001514 detection method Methods 0.000 claims abstract description 85
- 238000007781 pre-processing Methods 0.000 claims abstract description 16
- 238000002360 preparation method Methods 0.000 claims abstract description 11
- 238000012545 processing Methods 0.000 claims description 21
- 238000000605 extraction Methods 0.000 claims description 16
- 230000004927 fusion Effects 0.000 claims description 12
- 230000001629 suppression Effects 0.000 claims description 12
- 238000000034 method Methods 0.000 claims description 8
- 230000009466 transformation Effects 0.000 claims description 7
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims description 6
- 238000003708 edge detection Methods 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 6
- 238000010586 diagram Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 238000011176 pooling Methods 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 230000001960 triggered effect Effects 0.000 claims description 3
- 239000011435 rock Substances 0.000 claims description 2
- 238000005259 measurement Methods 0.000 abstract description 6
- 101100465000 Mus musculus Prag1 gene Proteins 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G06T3/02—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformation in the plane of the image
- G06T3/40—Scaling the whole image or part thereof
- G06T3/4038—Scaling the whole image or part thereof for image mosaicing, i.e. plane images composed of plane sub-images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- 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
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention discloses a shot throwing score recording system based on artificial intelligence, which is characterized in that a preparation area and a score area are arranged in a throwing field, a throwing starting line is arranged in the preparation area, and 1 camera is arranged in the throwing field; n athletes in the throwing field wear different number plates in sequence according to the sequence of going out of the field, and an industrial personal computer, a display screen and a loudspeaker are arranged on one side of the throwing field; the industrial personal computer is provided with the following components: the system comprises a data acquisition module, a preprocessing module, a number matching module, a timing module, a personnel position detection module, a violation detection module, a track detection module, a landing detection module and a score output module. The invention utilizes artificial intelligence to realize intelligent measurement of throwing distance, thereby improving accuracy and fairness of measurement.
Description
Technical Field
The invention belongs to the field of artificial intelligence, and particularly relates to a shot throwing performance recording system based on artificial intelligence.
Background
In the shot game, most of throwing results for athletes are calculated and counted manually, which takes time and labor. Therefore, the design of the shot throwing score recording system which is quick, time-saving, labor-saving and accurate and can prevent cheating of athletes has important significance.
Disclosure of Invention
The invention aims to solve the defects of the prior art, and provides a shot throwing score recording system based on artificial intelligence, which aims to realize intelligent timing of throwing time and intelligent measurement of throwing distance by using the artificial intelligence and timely feed back the illegal situation, thereby reducing the on-site participation of staff, ensuring fair score, saving time and labor and improving the accuracy of timing and measurement.
In order to achieve the aim of the invention, the invention adopts the following technical scheme:
the invention relates to an artificial intelligence-based shot throwing score recording system, which is characterized in that a preparation area and a score area are arranged in a throwing field, the preparation area is circular, the score area is fan-shaped, a throwing starting line is arranged in the preparation area, the throwing starting line is an arc, and the arc and the fan-shaped arc of the score area are concentric arcs; 1 camera is arranged in the throwing field; n athletes in the throwing field wear different number plates in sequence according to the order of going out of the field, the front of each athlete is stuck with the number plate with the same number; an industrial personal computer, a display screen and a loudspeaker are arranged on one side of the throwing field;
the industrial personal computer is provided with: the system comprises a data acquisition module, a preprocessing module, a number matching module, a timing module, a personnel position detection module, a personnel gesture detection module, a landing detection module, a violation detection module and a score output module;
after the nth athlete enters the detection area, the data acquisition module acquires a throwing video of the nth athlete by using the camera and sends the throwing video to the preprocessing module;
the preprocessing module cuts the received current n throwing video, extracts video key frames of each frame of the cut video, and cuts and rotates the video key frames to obtain an n target data set;
the number matching module identifies the number of the first frame image in the nth target data set, if the number identification result is the same as the number broadcasted by the loudspeaker, the timing module is triggered, otherwise, the number is misplaced by the loudspeaker;
the timing module is used for counting the time stamp t of the first frame image of the current nth throwing video 0 Starting timing and finishing timing when the falling point detection module detects that the shot falls to the ground, so as to obtain the throwing time of the nth athlete and then clearing;
the personnel position detection module carries out personnel position processing on the nth target data set to obtain the position of the athlete in the current nth throwing video;
the violation detection module judges whether the foot of the sportsman exceeds the throwing line or not when throwing according to the position of the sportsman in the current nth throwing video, if yes, the violation is judged, otherwise, whether the current throwing time of the nth sportsman is overtime or not is judged, if overtime, the violation is judged, otherwise, the timing and detection are continued;
the track detection module carries out track tracking processing on the nth target data set to obtain a moving track of the shot in the current throwing video;
the landing point detection module carries out landing point detection processing on the nth target data set to obtain the landing point of the shot in the current nth throwing video, and calculates the throwing distance between the landing point and the throwing line;
and the score output module outputs the throwing distance of the nth athlete to the display screen for display according to the number identification result.
The artificial intelligence-based shot throwing achievement recording system is also characterized in that the preprocessing module processes throwing videos by adopting a residual error dense jumper network and an affine change method;
the residual dense jumper network comprises: the device comprises a shallow feature extraction unit SFE, a dense block unit RDB, a dense feature fusion unit DFF and an image UP-acquisition unit UP;
the shallow feature extraction unit SFE extracts low-frequency information of each frame of image in the throwing video;
the dense block unit RDB performs layered extraction on the low-frequency information to obtain an RDB layer characteristic diagram;
the dense feature fusion unit DFF includes: a global feature fusion unit GFF and a global residual error learning unit GRL;
the global feature fusion unit GFF performs feature extraction on the RDB layer feature map to obtain a global feature map;
the global residual error learning unit GRL performs feature extraction on the RDB layer feature map to obtain a local feature map;
forming an image feature map from the global feature map and the local feature map;
the image UP-acquisition unit UP acquires a super-resolution image after UP-acquisition processing of the image feature image;
and carrying out rotary transformation processing on the super-resolution image line by utilizing affine transformation to obtain the super-resolution image after correcting the angle.
The personnel position detection module adopts a Yolo network structure to detect and process the personnel position; the Yolo network structure comprises an Input part, a Backbone part, a rock part and a Head part;
the Input part enhances the target data set to obtain an image feature map;
the backbox part carries out maximum pooling treatment on the image feature images, and the feature images with different scales are spliced to obtain spliced image feature images;
the Neck part fuses the spliced image feature images in an up-sampling mode to obtain a predicted feature image;
and the Head part judges the prediction frame of the prediction feature map to obtain an optimal prediction frame which is used as the position of the athlete.
The track detection module carries out track tracking processing on the target data set by adopting a Deep Sort algorithm;
the Deep Sort algorithm includes: YOLOv5 target detection algorithm, non-maximum suppression algorithm, kalman filter algorithm and hungarian algorithm;
the YOLOv5 target detection algorithm is used for extracting depth characteristics of a target data set so as to obtain candidate frames of a moving target;
the non-maximum suppression algorithm is used for removing overlapping frames in the candidate frames of the moving target, so that a plurality of moving target detection frames are obtained;
the Kalman filtering algorithm is used for predicting the position and the state of the next frame of the moving target detection frame in the throwing video to obtain the state parameter of the moving target detection frame at the next moment;
and the Hungary algorithm optimally matches a plurality of moving object detection frames between two adjacent frames to obtain the moving track of the moving object detection frames in the throwing video.
The landing point detection module performs landing point detection processing by adopting a circle fitting algorithm, wherein the circle fitting algorithm comprises: an edge detection algorithm, a non-maximum suppression algorithm and a least square fitting algorithm;
the edge detection algorithm is used for acquiring edge characteristics of a moving object in the object data set so as to obtain candidate frames of the moving object;
the non-maximum suppression algorithm is used for removing overlapping frames in the candidate frames of the moving target, so that a plurality of moving target detection frames are obtained;
the least square fitting algorithm is used for performing circle fitting on the target state parameters in the moving target detection frame to obtain the distance between the landing point of the moving target in the throwing video and the throwing starting line.
Compared with the prior art, the invention has the beneficial effects that:
1. according to the invention, the residual dense jumper network is adopted to process the throwing video and affine transformation to the image, so that the resolution of the throwing video and the image is improved, the shooting angle of the video image is corrected, and the throwing result is more accurate.
2. According to the invention, the personnel position detection module is used for detecting the personnel position of the athlete, so that the intelligent position detection of the athlete is realized, the on-site violation condition is timely fed back, and the evidence can be checked;
3. according to the invention, the falling point detection module is used for detecting the falling point of the shot thrown by the athlete, so that the intelligent measurement of the throwing score of the athlete is realized, and the throwing score is more accurate;
drawings
FIG. 1 is a flow chart of intelligent measurement of the ball throwing performance of the invention;
FIG. 2 is a flow chart of the video image preprocessing of the present invention;
FIG. 3 is a flow chart of the personnel position detection of the present invention;
fig. 4 is a flow chart of the landing detection of the present invention.
Detailed Description
In this embodiment, referring to fig. 1, an artificial intelligence-based shot throwing performance recording system is provided with a preparation area and a performance area in a throwing field, wherein the preparation area is circular, the performance area is fan-shaped, a throwing starting line is provided in the preparation area, the throwing starting line is an arc, and the arc and the fan-shaped arc of the performance area are concentric arcs; 1 camera is arranged in the throwing field; n athletes in the throwing field wear different number plates in sequence according to the order of going out, the front of each athlete is stuck with the number plate with the same number; an industrial personal computer, a display screen and a loudspeaker are arranged on one side of the throwing field;
the industrial personal computer is provided with: the system comprises a data acquisition module, a preprocessing module, a number matching module, a timing module, a personnel position detection module, a personnel gesture detection module, a landing detection module, a violation detection module and a score output module;
after the nth athlete enters the detection area, the data acquisition module acquires a throwing video of the nth athlete by using a camera and sends the throwing video to the preprocessing module;
the preprocessing module cuts the received current nth throwing video, extracts video key frames of each frame of the cut video, cuts and rotates the video key frames, and accordingly an nth target data set is obtained;
the number matching module identifies the number of the first frame image in the nth target data set, if the number identification result is the same as the number broadcasted by the loudspeaker, the timing module is triggered, otherwise, the error is reported by the loudspeaker;
the timing module is used for timing according to the time stamp t of the first frame image of the current nth throwing video 0 Starting timing and finishing timing when the falling point detection module detects that the shot falls to the ground, so as to obtain the throwing time of the nth athlete and then clearing;
the personnel position detection module carries out personnel position processing on the nth target data set to obtain the position of the athlete in the current nth throwing video;
the violation detection module judges whether the foot of the mobilizer exceeds the throwing line when throwing according to the position of the athlete in the current nth throwing video, if yes, the violation is judged, otherwise, whether the current throwing time of the nth athlete is overtime is judged, if overtime, the violation is judged, otherwise, the timing and detection are continued;
the track detection module carries out track tracking processing on the nth target data set to obtain a moving track of the shot in the current throwing video;
the landing point detection module carries out landing point detection processing on the nth target data set to obtain the landing point of the shot in the current nth throwing video, and calculates the throwing distance between the landing point and the starting throwing line;
and the score output module outputs the throwing distance of the nth athlete to the display screen for display according to the number identification result.
In specific implementation, referring to fig. 2, a video image shot by a camera is processed by a preprocessing module; the preprocessing module carries out super-resolution processing on the video image by adopting a residual dense jumper network in the system operation, and carries out angle correction processing on the super-resolution image by adopting radiation change; the residual dense jumper network comprises: the device comprises a shallow feature extraction unit SFE, a dense block unit RDB, a dense feature fusion unit DFF and an image UP-acquisition unit UP;
the shallow feature extraction unit SFE includes two convolution layers, mainly maps an image to a multi-channel, and primarily extracts low frequency information of an input image. The first convolution layer in the unit convolves with 64 small convolution check images of size 3 x 3 to increase the total number of feature maps, followed by a first step of shallow feature extraction; the second convolution layer is used for convolution mapping to obtain low-frequency information of each frame of image in the throwing video.
The dense block unit RDB performs layered extraction on the low-frequency information, and a continuous storage mechanism is realized by transmitting the state output of the previous residual dense block RDB to each layer of the current residual dense block RDB, so as to obtain an RDB layer characteristic diagram;
the dense feature fusion unit DFF includes: a global feature fusion unit GFF and a global residual error learning unit GRL;
the global feature fusion unit GFF performs feature extraction on the RDB layer feature map to obtain a global feature map;
the global residual error learning unit GRL performs feature extraction on the RDB layer feature map to obtain a local feature map;
forming an image feature map by the global feature map and the local feature map;
the image UP-acquisition unit UP acquires a super-resolution image after UP-acquisition processing of the image feature image;
and performing rotary transformation on the super-resolution image line by utilizing affine transformation to obtain the super-resolution image after correcting the angle.
In specific implementation, referring to fig. 3, the personnel position detection performs detection processing by using a Yolo network structure, where the Yolo network structure includes an Input part, a backup part, a nack part and a Head part;
the Input part enhances the target data set to obtain an image feature map;
the backbox part performs maximum pooling treatment on the image feature images, and the feature images with different scales are spliced to obtain spliced image feature images;
the Neck part fuses the spliced image feature images in an up-sampling mode to obtain a prediction feature image;
and the Head part judges the prediction frame of the prediction feature map to obtain an optimal prediction frame which is used as the position of the athlete.
In the embodiment, the track detection module performs track tracking processing on the target data set by adopting a Deep Sort algorithm; the Deep Sort algorithm includes: YOLOv5 target detection algorithm, non-maximum suppression algorithm, kalman filter algorithm and hungarian algorithm;
the YOLOv5 target detection algorithm is used for extracting depth characteristics of a target data set so as to obtain candidate frames of a moving target;
the non-maximum suppression algorithm is used for removing overlapping frames in the candidate frames of the moving target, so that a plurality of moving target detection frames are obtained;
the Kalman filtering algorithm is used for predicting the position and the state of the next frame of the moving target detection frame in the throwing video to obtain the state parameter of the moving target detection frame at the next moment;
and carrying out optimal matching on a plurality of moving object detection frames between two adjacent frames by using the Hungary algorithm to obtain the moving track of the moving object detection frames in the throwing video.
In specific implementation, referring to fig. 4, the landing point detection module performs a landing point detection process by using a circle fitting algorithm, where the circle fitting algorithm includes: an edge detection algorithm, a non-maximum suppression algorithm and a least square fitting algorithm;
acquiring a two-dimensional image of a shot after falling to the ground by a camera, and establishing an x-y coordinate system by taking the upper left corner of the processed image as an origin of coordinates after the computer is processed by a preprocessing module;
the edge detection algorithm is used for acquiring edge characteristics of the moving target in the target data set, so that candidate frames of the moving target are obtained;
the non-maximum suppression algorithm is used for removing overlapping frames in the candidate frames of the moving target, so that a plurality of moving target detection frames are obtained;
the least square fitting algorithm is used for performing circle fitting on the target state parameters in the moving target detection frame to obtain the distance between the landing point of the moving target in the throwing video and the throwing starting line.
Claims (4)
1. The utility model provides a throwing shot score recording system based on artificial intelligence, characterized in that, be provided with preparation district and score district in throwing the place, the preparation district is circular, the score district is fan-shaped, be provided with in the preparation district and throw the initial line, throw the initial line and be one section arc, arc and the fan-shaped arc of score district are concentric arc; 1 camera is arranged in the throwing field; n athletes in the throwing field wear different number plates in sequence according to the order of going out of the field, the front of each athlete is stuck with the number plate with the same number; an industrial personal computer, a display screen and a loudspeaker are arranged on one side of the throwing field;
the industrial personal computer is provided with: the system comprises a data acquisition module, a preprocessing module, a number matching module, a timing module, a personnel position detection module, a personnel gesture detection module, a landing detection module, a violation detection module and a score output module;
after the nth athlete enters the detection area, the data acquisition module acquires a throwing video of the nth athlete by using the camera and sends the throwing video to the preprocessing module;
the preprocessing module cuts the received current n throwing video, extracts video key frames of each frame of the cut video, and cuts and rotates the video key frames to obtain an n target data set;
the number matching module identifies the number of the first frame image in the nth target data set, if the number identification result is the same as the number broadcasted by the loudspeaker, the timing module is triggered, otherwise, the number is misplaced by the loudspeaker;
the timing module is used for counting the time stamp t of the first frame image of the current nth throwing video 0 Starting timing and finishing timing when the falling point detection module detects that the shot falls to the ground, so as to obtain the throwing time of the nth athlete and then clearing;
the personnel position detection module carries out personnel position processing on the nth target data set to obtain the position of the athlete in the current nth throwing video;
the violation detection module judges whether the foot of the sportsman exceeds the throwing line or not when throwing according to the position of the sportsman in the current nth throwing video, if yes, the violation is judged, otherwise, whether the current throwing time of the nth sportsman is overtime or not is judged, if overtime, the violation is judged, otherwise, the timing and detection are continued;
the track detection module carries out track tracking processing on the nth target data set to obtain a moving track of the shot in the current throwing video;
the landing point detection module carries out landing point detection processing on the nth target data set to obtain the landing point of the shot in the current nth throwing video, and calculates the throwing distance between the landing point and the throwing line;
the achievement output module outputs the throwing distance of the nth athlete to the display screen for display according to the number identification result;
the preprocessing module processes the throwing video by adopting a residual dense jumper network and an affine change method;
the residual dense jumper network comprises: the device comprises a shallow feature extraction unit SFE, a dense block unit RDB, a dense feature fusion unit DFF and an image UP-acquisition unit UP;
the shallow feature extraction unit SFE extracts low-frequency information of each frame of image in the throwing video;
the dense block unit RDB performs layered extraction on the low-frequency information to obtain an RDB layer characteristic diagram;
the dense feature fusion unit DFF includes: a global feature fusion unit GFF and a global residual error learning unit GRL;
the global feature fusion unit GFF performs feature extraction on the RDB layer feature map to obtain a global feature map;
the global residual error learning unit GRL performs feature extraction on the RDB layer feature map to obtain a local feature map;
forming an image feature map from the global feature map and the local feature map;
the image UP-acquisition unit UP acquires a super-resolution image after UP-acquisition processing of the image feature image;
and carrying out rotary transformation processing on the super-resolution image line by utilizing affine transformation to obtain the super-resolution image after correcting the angle.
2. The artificial intelligence based shot-making result recording system according to claim 1, wherein the personnel position detection module detects the personnel position by using a Yolo network structure, wherein the Yolo network structure comprises an Input part, a backbox part, a rock part and a Head part;
the Input part enhances the target data set to obtain an image feature map;
the backbox part carries out maximum pooling treatment on the image feature images, and the feature images with different scales are spliced to obtain spliced image feature images;
the Neck part fuses the spliced image feature images in an up-sampling mode to obtain a predicted feature image;
and the Head part judges the prediction frame of the prediction feature map to obtain an optimal prediction frame which is used as the position of the athlete.
3. The artificial intelligence based shot-making result recording system according to claim 1, wherein the track detection module performs track tracking processing on the target data set by using Deep Sort algorithm;
the Deep Sort algorithm includes: YOLOv5 target detection algorithm, non-maximum suppression algorithm, kalman filter algorithm and hungarian algorithm;
the YOLOv5 target detection algorithm is used for extracting depth characteristics of a target data set so as to obtain candidate frames of a moving target;
the non-maximum suppression algorithm is used for removing overlapping frames in the candidate frames of the moving target, so that a plurality of moving target detection frames are obtained;
the Kalman filtering algorithm is used for predicting the position and the state of the next frame of the moving target detection frame in the throwing video to obtain the state parameter of the moving target detection frame at the next moment;
and the Hungary algorithm optimally matches a plurality of moving object detection frames between two adjacent frames to obtain the moving track of the moving object detection frames in the throwing video.
4. The artificial intelligence based shot-delivery performance recording system of claim 1, wherein the landing detection module performs a landing detection process using a circle fitting algorithm comprising: an edge detection algorithm, a non-maximum suppression algorithm and a least square fitting algorithm;
the edge detection algorithm is used for acquiring edge characteristics of a moving object in the object data set so as to obtain candidate frames of the moving object;
the non-maximum suppression algorithm is used for removing overlapping frames in the candidate frames of the moving target, so that a plurality of moving target detection frames are obtained;
the least square fitting algorithm is used for performing circle fitting on the target state parameters in the moving target detection frame to obtain the distance between the landing point of the moving target in the throwing video and the throwing starting line.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111527737.5A CN114187171B (en) | 2021-12-14 | 2021-12-14 | System for recording throwing shot score based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111527737.5A CN114187171B (en) | 2021-12-14 | 2021-12-14 | System for recording throwing shot score based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114187171A CN114187171A (en) | 2022-03-15 |
| CN114187171B true CN114187171B (en) | 2024-04-12 |
Family
ID=80604989
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111527737.5A Active CN114187171B (en) | 2021-12-14 | 2021-12-14 | System for recording throwing shot score based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114187171B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110689054A (en) * | 2019-09-10 | 2020-01-14 | 华中科技大学 | Worker violation monitoring method |
| CN113489893A (en) * | 2020-07-31 | 2021-10-08 | 深圳技术大学 | Real-time target object tracking and positioning method and real-time target object tracking and positioning device |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102015002677B3 (en) * | 2015-03-04 | 2016-05-19 | Nils Bühring | Exercise device arrangement for improving ball control |
| CN109978756B (en) * | 2019-03-18 | 2021-03-09 | 腾讯科技（深圳）有限公司 | Target detection method, system, device, storage medium and computer equipment |
-
2021
- 2021-12-14 CN CN202111527737.5A patent/CN114187171B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110689054A (en) * | 2019-09-10 | 2020-01-14 | 华中科技大学 | Worker violation monitoring method |
| CN113489893A (en) * | 2020-07-31 | 2021-10-08 | 深圳技术大学 | Real-time target object tracking and positioning method and real-time target object tracking and positioning device |
Non-Patent Citations (1)
| Title |
|---|
| 铅球投掷角度和最大成绩的函数关系;代利琴;重庆大学学报(自然科学版);20020430(第04期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114187171A (en) | 2022-03-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110223302A (en) | A kind of naval vessel multi-target detection method extracted based on rotary area | |
| CN104820998B (en) | A kind of human testing based on unmanned motor platform and tracking and device | |
| CN104902265B (en) | A kind of video camera method for detecting abnormality and system based on background edge model | |
| US9361520B2 (en) | Method and system for tracking objects | |
| CN109344690B (en) | People counting method based on depth camera | |
| CN110738150B (en) | Camera linkage snapshot method and device and computer storage medium | |
| CN111325048B (en) | Personnel gathering detection method and device | |
| CN105141885A (en) | Method for video monitoring and device | |
| CN110796819B (en) | Detection method and system for platform yellow line invasion border crossing personnel | |
| CN103824070A (en) | Rapid pedestrian detection method based on computer vision | |
| CN113435336B (en) | Running intelligent timing system and method based on artificial intelligence | |
| CN113903081A (en) | Visual identification artificial intelligence alarm method and device for images of hydraulic power plant | |
| CN109871799A (en) | A kind of driver based on deep learning plays the detection method of mobile phone behavior | |
| CN103996203A (en) | Method and device for detecting whether face in image is sheltered | |
| CN110838230B (en) | Mobile video monitoring method, monitoring center and system | |
| CN111460924B (en) | Gate ticket-evading behavior detection method based on target detection | |
| CN110298860A (en) | A kind of high bar silk ball detection number system based on machine vision | |
| CN112270253A (en) | High-altitude parabolic detection method and device | |
| CN111310736A (en) | Rapid identification method for unloading and piling of vehicles in protected area | |
| CN114187171B (en) | System for recording throwing shot score based on artificial intelligence | |
| CN105631900B (en) | A kind of wireless vehicle tracking and device | |
| CN114170272A (en) | Accident reporting and storing method based on sensing sensor in cloud environment | |
| KR102434154B1 (en) | Method for tracking multi target in traffic image-monitoring-system | |
| CN112464765A (en) | Safety helmet detection algorithm based on single-pixel characteristic amplification and application thereof | |
| CN114913323B (en) | Charging pile area night open fire detection method |
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 |