Extracting Tables from Document Images using a Multi-stage Pipeline for Table Detection and Table Structure Recognition

Deploy Computer Vision solutions with a few lines of code.

An AI-powered fitness tracker that uses real-time pose estimation to count reps, monitor form, and provide instant feedback for exercises like squats, push-ups, and bicep curls. Designed for accuracy, motivation, and adaptability

Modern instance segmentation for DJI Tello drones with YOLOv8/Detectron2. Real-time performance, modular design, autonomous tracking.

Access Android camera via WebSocket client API and run AI / computer vision tasks with ease on live camera stream

A hands-on collection of computer vision projects for everyone.

Agentic AI platform transforming passive CCTV into proactive railway safety intelligence. Real-time behavioural detection (suicide risk, pickpocketing) via YOLOv8 + BiLSTM + multi-agent reasoning — zero new hardware, privacy-first, no facial recognition.

Real-time monocular depth estimation for DJI Tello drone collision avoidance. Modern TF2.x implementation with webcam support, comprehensive tests, and autonomous navigation. PyDNet-based with MiDaS support.

This repository details the various methods I have attempted for skin segmentation.

Moving Target Tracking

This project employs computer vision techniques to analyse 8-ball game footage and provide accurate shot predictions to enhance performance.

Automate LinuxCNC with machine vision by detecting and probing holes while reading the dial of a Haimer 3D Sensor

Vídeos, textos e exemplos ensinando o fundamental das mais recentes versões do Python e do OpenCV

Gaze estimation algorithms in C++ using laptop's camera as input and machine learning algorithms for the prediction of gaze's direction.

A comprehensive resource for mastering computer vision, featuring practice problems, code examples, and interview-focused concepts using Python and OpenCV. Covers image processing, object detection, and deep learning models for technical interview success.

Real‑time badminton analytics using YOLOv8‑Pose - skeleton overlay, player stats and trajectory visualisation with OpenCV & MoviePy.

The binary classification problem focused on first IEEE Image forensics challenge-phase 1, to predict the given image is pristine or manipulated/edited/fake. Comparing CNN & Transfer Learning models for the problem and boosting the performance by feature extraction

🚀 专为 Python 自动化打造的高性能截图库 | 180+ FPS | 支持后台/遮挡 | 可暂停 零功耗待机;🚀 High-performance capture library for Python automation | 180+ FPS | Background/Occluded Support | Pausable (Pause/Resume) Zero-Power Standby