bytetracker

An object tracking project with YOLOv8 and ByteTrack, speed up by C++ and TensorRT.

Анализ трафика на круговом движении с использованием компьютерного зрения

Integration of YOLOv9 with ByteTracker

A "gstreamer-like" C++ framework for ffmpeg/libav graphs with support of async processing and lock-free queue

A thread safe implementation of ByteTrack with (COCO) labels.

A fully functional traffic counter on a bare Raspberry Pi 4 with MQTT and remote live viewer

Official implementation repository for the paper "Beyond the Survey: A Systematic Empirical Study of Detection and Association in Visual MOT", accepted for publication in Artificial Intelligence Review. We also provide source code for paper "Adaptive Confidence Threshold for ByteTrack in Multi-Object Tracking"

🚗 Car Counter: A real-time application for vehicle counting and classification using advanced algorithms like YOLOv8 and ByteTrack. Features a user-friendly dashboard with Streamlit. Collaboratively developed by Richard Zimmermann and Moritz von Angern.

A high-performance multi-object tracking system utilizing a quantized YOLOv11 model deployed on the Triton Inference Server, integrated with a CUDA-accelerated particle filter for robust tracking mutiple objects.

A fully functional traffic counter on a bare RK3588 with MQTT and remote live viewer

Football Analysis system for football matches

The Fashion Trend Analyzer is designed to identify and record seasonal costume patterns among different age groups and genders.

In computer vision, this project meticulously constructs a dataset for precise 'Shoe' tracking using YOLOv8 models. Emphasizing detailed data organization, advanced training, and nuanced evaluation, it provides comprehensive insights. A final project for the Computer Vision cousre on Ottawa Master's in (2023).

Vehicle detection and lane-wise traffic analysis on prerecorded videos using YOLOv8 and ByteTrack

YOLOv8 · ByteTrack · OpenCows2020 · ROI Counting Trained on the OpenCows2020 dataset (University of Bristol) 11,779 overhead images of Holstein-Friesian cattle. Detects, tracks, and counts cows crossing a virtual ROI line in real-time CCTV footage.

Прототип SmartMekeme

This demo is a simple software that I created using my studies and courses. It's designed for real-time object detection and tracking in video streams, using YOLOv8 for detection and ByteTrack for multi-object tracking. It is suitable for tracking objects in video footage, and can run on both GPU and CPU.

An AI-powered CCTV monitoring system for restaurants that tracks table occupancy and waiter visits using YOLO, ByteTrack, and spatiotemporal behavioral inference.

ShelfSense transforms retail CCTV footage and POS data into real-time store intelligence—visitor tracking, conversion funnels, heatmaps, queue analytics, anomalies, and live dashboards powered by YOLOv8, FastAPI, PostgreSQL, and React.

DRISHTI is a deep-learning based drone intelligence system that goes beyond detection to provide persistent tracking and predictive movement analysis. Using YOLO11, ByteTrack, and LSTM, it detects drones, maintains their identities, extracts movement trajectories, and predicts their next five positions.