[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120429-en":3,"doc-seo-120429-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},120429,1374391974468,"Eden","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",6,"Technology","COURTMETRICS - UNLOCKING TENNIS INSIGHTS WITH MACHINE LEARNING - Overview","COURTMETRICS presents an end-to-end deep learning system for tennis match understanding using video analytics. It combines ball tracking and player tracking with court keypoints detection via a mini-court overlay, then performs player action recognition and action-based insights. Player-vs-player statistics are generated by integrating ATP data and Azure OpenAI services. The solution is deployed on Azure VM with supporting Azure services and uses datasets spanning multiple court surfaces plus a COCO-annotated pose/action dataset.","COURTMETRICS – UNLOCKING TENNIS INSIGHTS WITH MACHINE LEARNING  \nTeam Members:  \nGautham Gali  \nAshutosh Reddy Pochamreddy  \nAtharva Rajendra Sardar  \nLokesh Devendra Satpute  \nProfessor. Soheil Sibdari  \n Overview  \n- Objective:  \n- Enhance tennis video analysis through deep learning-based detection of player actions, ball tracking, and court keypoints to provide comprehensive match insights.  \n- Ball and Player Tracking: Successfully integrated tracking mechanisms for both ball movement and player actions within match videos.  \n- Court Keypoints Detection: Developed a mini-court overlay for enhanced visualization.  \n- Player Action Analysis: Completed player action detection.  \n- Player Statistics Analysis: integrated player vs player statistical analysis using ATP data and Utilized Azure Openai Services.  \n- Deployment & Optimization: Deployed Our Services Using Azure VM and Azure OpenAI service.  \nDataset  \n•Size: 8,841 images (75% training, 25% validation)  \n•Resolution: 1280 × 720  \n•Content: Hard, clay, and grass courts  \n•Source: Semi-automated extraction from YouTube highlights Link:  \n[https://drive.google.com/fi](https://drive.google.com/fi)le/d/1lhAaeQCmk2y440PmagA0KmIVBIysVMwu/view?usp=drive link  \nDataset  \n•Tennis Player Actions Dataset for Human Pose Estimation  \n•Size: 500 images each Resolution: 1280 × 720  \n•Content: The actions in this dataset, the action categories name in COCO-format is in brackets:  \n•1. backhand shot (backhand)  \n•2. forehand shot (forehand)  \n•3. ready position (ready_position)  \n•4. serve (serve)  \nWe use COCO-Annotator to annotating and categorizing human actions  \n•[\"nose\", \"left_eye\", \"right_eye\", \"left_ear\", \"right_ear\", \"left_shoulder\", \"right_shoulder\", \"left_elbow\", \"right_elbow\",\"left_wrist\", \"right_wrist\", \"left_hip\", \"right_hip\", \"left_knee\", \"right_knee\", \"left_ankle\", \"right_ankle\", \"neck\"]  \n• Source: Mendeley Data  \nLink:  \n[https://data.mendeley.com/datasets/nv3rpsxhhk/1](https://data.mendeley.com/datasets/nv3rpsxhhk/1)  \nTools  \n• FrontEnd: HTML, CSS, JS  \n• Backend: Flask, PostgresDB, python, Azure Open AI  \n• ML models: yolov8, Tracknet CNN, ResNet-18  \n• Azure Services: Azure Virtual Machine, Azure Open AI, Azure Virtual net, Azure DNS, Azure Resource groups, Azure public IP  \n• LLM: gpt-4o (version:2024-08-06)  \n• Visualization: seaborn, matplotlib  \n• IDE: Visual Studio Code, Azure OpenAI Service  \n• Other: Trello, kanban, Jira  \n• Communication: zoom, WhatsApp, slack  \n Sprint  \nSprint 1 Achievements  \n•Completed:  \n•Video download/upload feature  \n•Player ranking API and match scheduling API  \n•Backend server setup for video processing  \n•Ongoing:  \n•Player detection models and player vs. player statistics  \n•Video processing framework (Due: Nov 10)  \nSprint 2 Achievements  \n•Completed:  \n• Ball Tracker Integration: Successful tracking and monitoring of ball movement during match videos.  \n• Player Tracker Integration: Accurate tracking of players within match videos for detailed analysis.  \n• Court Keypoints Detection: Mini-court overlay with key points for enhanced match visualization.  \n• Player Action Detection: Completed detection of key player movements.  \n• Player vs Player Statistics Analysis: Integrated ATP data for comprehensive player comparisons.  \n• Ongoing:  \n• Integrating everything  \n• Video processing framework (Due: Nov 20)  \nSprint 3 Achievements  \n•Completed:  \n• Ball Tracker Integration: Successful tracking and monitoring of ball movement during match videos.  \n• Player Tracker Integration: Accurate tracking of players within match videos for detailed analysis.  \n• Court Keypoints Detection: Mini-court overlay with key points for enhanced match visualization.  \n• Player Action Detection: Completed detection of key player movements.  \n• Player vs Player Statistics Analysis: Integrated ATP data for comprehensive player comparisons.  \n• Integrated Azure VM and Deployment.  \nSPRINT RETROSPECTIVE & NEXT STEPS","cbCaieQTAL2fBC32","https://ap.wps.com/l/cbCaieQTAL2fBC32","pdf",3481780,1,33,"English","en",105,"# Overview\n## Objective\n## Dataset\n## Tools\n## Sprint\n## Sprint Retrospective & Next Steps","[{\"question\":\"What is the main objective of COURTMETRICS?\",\"answer\":\"Enhance tennis video analysis using deep learning to detect player actions, track the ball, and identify court keypoints for match insights.\"},{\"question\":\"What capabilities are included in the video analysis pipeline?\",\"answer\":\"Ball and player tracking, court keypoint detection with a mini-court overlay, and player action detection, followed by player vs player statistics analysis.\"},{\"question\":\"Where is the solution deployed and which models are used?\",\"answer\":\"Services are deployed on Azure VM and Azure OpenAI. ML models include YOLOv8, Tracknet CNN, and ResNet-18, with gpt-4o as the LLM.\"}]","COURTMETRICS - UNLOCKING TENNIS INSIGHTS WITH MACHINE LEARNING - Overview | PDF",1785730022,83,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"courtmetrics-unlocking-tennis-insights-with-machine-learning-overview","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/technology/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/courtmetrics-unlocking-tennis-insights-with-machine-learning-overview/120429/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What is the main objective of COURTMETRICS?","Question",{"text":75,"@type":76},"Enhance tennis video analysis using deep learning to detect player actions, track the ball, and identify court keypoints for match insights.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What capabilities are included in the video analysis pipeline?",{"text":80,"@type":76},"Ball and player tracking, court keypoint detection with a mini-court overlay, and player action detection, followed by player vs player statistics analysis.",{"name":82,"@type":73,"acceptedAnswer":83},"Where is the solution deployed and which models are used?",{"text":84,"@type":76},"Services are deployed on Azure VM and Azure OpenAI. ML models include YOLOv8, Tracknet CNN, and ResNet-18, with gpt-4o as the LLM.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,113,118,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":111,"slug":112},50,"technology",{"id":114,"doc_module":4,"doc_module_name":46,"category_name":115,"show_sort_weight":116,"slug":117},7,"Healthcare",40,"healthcare",{"id":119,"doc_module":4,"doc_module_name":46,"category_name":120,"show_sort_weight":121,"slug":122},8,"Research & Report",30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]