This project leverages Convolutional Neural Networks (CNNs) to perform real-time audio classification in rainforest environments, detecting sounds such as chainsaws, truck engines, and storms. Audio data, sourced from UrbanSound8K and rainforest recordings, is preprocessed into spectrograms using Librosa, while synthetic soundscapes are generated w

Real-time wildlife detection and telescope collision prevention system using YOLOX + iNaturalist on NVIDIA A30

🖍️ This project achieves some functions of image identification for Self-Driving Cars. First, use yolov5 for object detection. Second, image classification for traffic light and traffic sign. Furthermore, the GUI of this project makes it more user-friendly for users to realize the image identification for Self-Driving Cars.

Real-time vehicle detection and counting system using YOLOv8 and OpenCV. Detects cars, motorcycles, buses, and trucks from video footage, counts them per frame, and outputs annotated video results. Ideal for traffic monitoring, smart city projects, and computer vision portfolios.

Real-time traffic object detection system using YOLOv3 and OpenCV’s DNN module. Detects vehicles, pedestrians, and road objects in live or recorded video streams, with FPS overlay and scene IoU analysis.

Machine vision project for real-time US coin detection and counting using Python, OpenCV, Roboflow, and an Android phone running the IP Webcam app.

[DEIMv2] Real Time Object Detection Meets DINOv3

AI-powered computer vision system for real-time workplace safety monitoring. Detects people and PPE compliance (helmets, vests) using YOLO models with intelligent tracking and MP4 output.

🎮 Production-ready real-time Rock-Paper-Scissors gesture recognition system using MediaPipe & OpenCV. Features: instant hand tracking (30+ FPS), 95% accuracy, fuzzy matching, TDD methodology with 95% test coverage. Bilingual (EN/繁中). Perfect for CV learning & interactive apps.

🎓 End-to-end tutorial project for beginners: From data preparation to real-time application with YOLOv8. Perfect for learning! (🎓 面向初学者的端到端教程项目：从数据准备到YOLOv8实时应用，非常适合学习！)

Real-time yoga pose accuracy detector using MediaPipe and OpenCV. Classifies poses from webcam input with KNN and provides feedback on duration and accuracy, built with Python and scikit-learn.

🎯 A real-time object detection web app built with PyTorch and YOLOv5, featuring live webcam detection and image upload support.

A small VLM that sees everything

Car recognition and license plate reading, along with recognition of the place where the license plate was issued, car color recognition and Iranian car names, accident detection and warning notification.

[ECCV 2024] PyTorch implementation of Rethinking Features-Fused-Pyramid-Neck for Object Detection

Enhances construction site safety using YOLO for object detection, identifying hazards like workers without helmets or safety vests, and proximity to machinery or vehicles. HDBSCAN clusters safety cone coordinates to create monitored zones. Post-processing algorithms improve detection accuracy.

A project showcasing the use of machine learning in detecting and classifying electrical faults

A real-time sign language recognition system using CNNs and MediaPipe for hand landmark detection.

Real-time violence and weapon detection system using MoBiLSTM and YOLOv8, with optional Telegram alerts.

A real-time Sign Language Detection application built with Python, OpenCV, and TensorFlow. This project uses computer vision and a custom-trained Convolutional Neural Network (CNN) to recognize and interpret hand gestures from a live webcam feed.