Scene 1 (0s)
SMART INDIA HACKATHON 2025 Team Details and Problem Statement 1 SMART INDIA - HACKATHON 2025 SIH • Problem Statement ID — 25073 • Problem Statement Title - A1-Powered Mobile Platform for Democratizing Sports Talent Assessment • Theme - Fitness & Sports • PS Category - Software • Team ID - [Yet to be given] AthletiQ A1 • Team Name - 01010 101010 SIH.
Scene 2 (13s)
AthletlQ IDEA: IDEA & APPROACH DETAILS 1 SIH SMART INDIA - HACKATHON 2025 To create an A1-powered mobile platform that democratizes sports talent assessment across India by enabling athletes - especially from rural and remote areas - to easily perform, record, and get instant feedback on standard fitness tests, thereby overcoming infrastructure and accessibility barriers. APPROACH: Mobile app for video recording and fitness assessment Record videos of vertical jumps, shuttle runs Prescribed fitness tests accessible via app Offline and low-bandwidth support • Performs analysis on-device without internet • Works on entry-level smartphones & low connectivity Performance benchmarking and instant feedback Benchmarks against age/gender standards Real-time feedback to motivate improvement On-device AllML analysis and verification Automatically detects and segments performance clips A1 verifies video accuracy and authenticity • Includes cheat detection for fairness Secure data submission Transmits verified results securely to SAI Ensures data privacy and security Gamified user experience Progress badges and leaderboards • Interactive, reward-based engagement.
Scene 3 (46s)
AthletlQ TECHNICAL APPROACH 1 SIH Record Performance Athlete records fitness test videos (jump, run, sit-ups, etc.) SMART INDIA - HACKATHON 2025 TECHNOLOGY STACK: React JS Tailwind CSS web development, one drop at a time Chart.js s Instant Feedback Athlete receives ben- chmarking reedback based on age/gender Download App Athlete downloads the app on their smartphone FLOW DIAGRAM Secure Data Submission Verified data is uploaded to Sports Authority of India servers On-Device Analysis AI/ML processes video data directly on the device.
Scene 4 (1m 5s)
AthletlQ FEASIBILITY AND VIABILITY 1 SIH SMART INDIA - HACKATHON 2025 Analysis of the feasibility of the idea: Why the idea is practical and achievable Widespread smartphone access (even in rural areas) Feasible offline processing via lightweight A1 models Camera-based analysis eliminates need for physical test centres Existing A1 tools available for motion tracking, rep counting Secure and scalable backend Potential challenges and risks: What could go wrong Low bandwidth areas may hinder data uploads Device hardware limitations (low RAM/CPU in entry-level phones) Incorrect video angles or poor lighting User adoption — athletes may not trust tech-based assessment Cheating attempts (fake recordings, external help) Strategies for overcoming these challenges: How we'll solve or avoid issues On-device video compression to reduce upload size Optimized A1 models for low- spec devices In-app guidance overlay to ensure proper video framing A1-based anomaly & cheat detection Gamified UX to boost engagement and trust Benchmark-based feedback to help athletes self-assess instantly.
Scene 5 (1m 35s)
AthletlQ Target Audience: IMPACT AND BENEFITS 1 SIH SMART INDIA - HACKATHON 2025 Aspiring athletes from rural & urban India Coaches and sports academies Sports Authority of India (SAI) and talent scouts Potential Impact: Inclusivity: Talent from remote areas can participate without needing to travel Early Identification: Promotes youth entry into professional training earlier Solution Benefits: Social Benefits Enables athletes from remote/rural areas to participate fairly. Boosts engagement via badges, leaderboards, and instant feedback. Economic Benefits No need for physical infrastructure or in-person testing logistics. Reduces travel, equipment, and administrative Data-Driven Talent Discovery: Brings objectivity expenses. to selection Scalability & Sustainability Increased Awareness: Encourages fitness and Can handle thousands of users with lightweight self-evaluation culture cloud and on-device tech. Fully digital approach reduces carbon emissions from travel..
Scene 6 (2m 5s)
AthletlQ RESEARCH AND REFERENCES Research Sources: Pose Estimation — MediaPipe Sports Analytics — SportsAnalytics.org Mobile Frameworks — Flutter Dataset References: Public sports datasets Open video datasets for pose training Articles / Reports: A1 in Sports Training (IEEE Papers) Government sports schemes & programs Additional Links: SIH Portal Guidelines Hackathon Documentation 1 SIH SMART INDIA - HACKATHON 2025.