Back to Project List
Intelligent Swimming Detection and Tracking
2020•✅ Completed
Implementation
Diagram
Flow AI
Project Overview
Sponsored by MOST Taiwan
Problem
Traditional lifeguard monitoring relied heavily on manual observation, making it difficult to detect drowning incidents and track multiple swimmers in real time.
Approach
Developed an AI-based intelligent swimming detection and tracking system using UAV video streams, Tiny-YOLOv4, DeepSORT, ConvLSTM, and swimmer re-identification models
Key Results & Impact
- ✓Delivered a real-time swimmer monitoring system capable of drowning detection, swimming style recognition, swimmer tracking, and drone-based safety surveillance with real-time performance.
Technologies Used
PythonDrone DJIComputer VisionWearablesMachine LearningDeep Learning
Additional Information
CategoryApplied Machine Learning / AI
Year2020
StatusCompleted
Related Projects
Intelligent Sootblower
Optimization of Sootblower Operation Using Machine Learning for Reducing Sootblower Steam Consumption
Multi-task AI Model for Swimmer Tracking and Action Recognition
Design And Implementation Of A Lightweight Multi-task Deep Neural Network For Swimmer Action Recognition And Re-identification
Sensor-Based Human Action Recognition
A wearable AI action recognition system using smartphone and smartwatch sensors for real-time activity detection, sponsored by MOST Taiwan.