An Innovative Salient Object Detection Using Center-Dark Channel Prior

AI-powered retail intelligence platform that converts CCTV footage into footfall analytics, heatmaps, queue intelligence, conversion funnels, anomaly detection, and sales insights using YOLOv8, ByteTrack, FastAPI, and Docker.

🔎 Multiple Object Tracking with Particle Filter

👀 A web app for detecting and counting objects in videos using YOLOv8 for detection and ByteTrack for tracking, with customizable regions of interest (ROIs) function.

A technical prototype to test the posibility of runinng object detection in the browser of your phone or computer

Implement SLAM, a robust method for tracking an object over time and mapping out its surrounding environment using elements of probability, motion models, linear algerbra.

🎨 Simplify rotoscoping with AI in Google Colab, creating high-quality alpha mattes effortlessly to save you time and enhance your workflow.

Automated traffic violation detection and review platform with real-time computer vision, evidence generation, and judge-friendly deployment.

스마트 자율주행 쇼핑카트 with Scout mini ROS

Real-time object tracking using OpenCV and Python

A curated list of object tracking software (includes standalone apps and libraries)

Real-time Rear-Vehicle detection using HAAR Cascade Classifiers and OpenCV Trackers in combination. This project is a part of HPC Research Group from University of Wyoming - Department of Electrical engineering and Computer Science.

Object tracking implementation based on the VOT (Visual Object Tracking) 2017 Challenge. Developed in Python, it includes evaluation scripts, performance reports (Accuracy/Robustness), and benchmark sequences.

🚗 **Speed Estimator** is a Computer Vision-based application developed using Python, Flask, and OpenCV that estimates vehicle speed in real time from video streams. The system detects moving vehicles, tracks their movement across frames, and calculates speed using motion analysis techniques. It provides a live monitoring interface that allows user

Tutorials of the "Mathemagics" behind computer vision before the deep learning era.

AI perception platform for law enforcement. Multi-camera tracking, re-identification, and behavioral analytics across CCTV, drones, bodycams, and city networks.

AI-powered vehicle surveillance system with YOLOv8 detection, DeepOCSORT tracking, license plate recognition, entry/exit classification, and a real-time Flask dashboard backed by MongoDB.

Lucas-Kanade and Matthews-Baker inverse compositional trackers from scratch in MATLAB — Gauss-Newton translation tracking and 6-parameter affine warps with precomputed Jacobian/Hessian, tracking a car across 261 frames. CMPEN 454, The Pennsylvania State University.