Trackers gives you clean, modular re-implementations of leading multi-object tracking algorithms released under the permissive Apache 2.0 license. You combine them with any detection model you already use.

BoT-SORT + YOLOX implemented using only onnxruntime, Numpy and scipy, without cython_bbox and PyTorch. Fast human tracker. OSNet is not used.

Хакатон компании Ренью

SOTA Multi Object Tracker in Cpp

AI CUP 2024

ZoneGuard - Real-time perimeter security system using YOLO11 for detecting persons entering restricted zones. Tracks movement with distance, speed, and duration analytics.

An AI-driven Adaptive Traffic Signal Control System (ATSCS) that replaces static timers with dynamic green-light phases. Utilizes YOLOv8 for real-time vehicle density estimation and multi-class classification, achieving 96.4% mAP. Optimized for low-latency inference (>30 FPS) on edge devices to reduce urban congestion and commuter wait times.

A complete computer vision pipeline for soccer video understanding. It combines YOLO11, BoT-SORT, and HSV pitch filtering for robust player tracking, alongside tactical behavior analysis via ROI presence estimation

ExplainableTrack — an explainable, interpretable toolkit for object tracking with visualizations.

A Machine Vision pipeline that automates feeding of fishes by detecting, tracking and scheduling feeding interval.

A complete computer vision pipeline for soccer video understanding. It combines YOLO11, BoT-SORT and HSV pitch filtering for robust player tracking, alongside tactical behavior analysis via ROI presence estimation.

An intelligent traffic monitoring system using YOLOv8 for real-time vehicle tracking, perspective-based speed estimation, and Automatic License Plate Recognition (ALPR).

👤 Conditional diffusion model for 64x64 face generation on CelebA, conditioned on gender, smile, and age attributes. Implements a DDPM-based architecture for controllable face synthesis and attribute-guided sampling.