YOLOv7 Object Tracking Using PyTorch, OpenCV and Sort Tracking

👁 零代码零标注 CV AI 自动化测试工具 🚀 免除大量人工画框和打标签等，直接零代码快速自动化测试 CV 计算机视觉 AI 人工智能图像识别算法：行人检测、动植物分类、人脸识别、OCR 车牌识别、旋转校正、舞蹈姿态、抠图分割 等，还可一键 下载测试报告、导出训练和测试数据集

Multi-stream video inference with Ultralytics YOLO - Display multiple video streams in a grid layout with real-time object detection.

ultralytics_pro 是一堆改過架構的模型大禮包 (包含 v3 ~ v13, RTMDet / RT-DETR, yolact, yoloe, yolo-world, PicoDet / PPyoloE / YoloX, YOLOR / goldyolo / Leyolo / damoyolo / fbrt-yolo / maf-yolo / bgf-yolo / cst-yolo / hyper-yolo / HEYDet / alss-yolo / rcs-yolo / syolo / pst )

work on YOLOv8s-based predator detection for farmland, an ongoing project aimed at detecting and classifying predator species that threaten livestock and crops.

A toolkit for deploying optimized YOLOv8 vision applications container on Advantech edge AI devices with hardware acceleration. Designed specifically for Advantech edge AI devices based on NVIDIA Jetson platforms

Optimize test for ultralytics yolo11. Using OpenVINO, TensorRT, and Hailo-8.

Detect space station safety gear with a click. AI + 3D models make safety inspection intuitive and futuristic.

Adaptive traffic signal management with YOLOv8 + SORT: real‑time vehicle counting, line crossing, and congestion‑aware timing

Successfully developed a real-time soccer player re-identification and tracking system using YOLOv11 and Deep SORT with TorchreID-based embeddings.

RealTimeOCR is a computer vision tool combining YOLO for real-time object detection and PaddleOCR for text recognition in video streams, with customizable ROIs for precise targeting.

Telegram bot for real-time object detection using YOLO. Processes user images and returns annotated images with detection summaries.

Ultralytics YOLO는 실시간 객체 탐지, 분할, 분류를 위한 최첨단 AI 모델입니다.

This project demonstrates a simple yet powerful application of the YOLOv8 (You Only Look Once) object detection model for identifying various traffic-related objects.

Real-time object detection pipeline with YOLOv5 and OpenCV

In order to use the Synthetic SynPlay dataset with YOLO models, it must be converted to a YOLO format. This repository will walk you through the process.

A pipeline for compressing and deploying YOLO models on AWS Lambda for efficient, low-latency inference.

This repository presents an integrated deep-learning pipeline for vehicle detection, Automatic Number Plate Recognition (ANPR), and illegal number-plate font identification. The system improves traffic enforcement, enhances monitoring, and reduces the need for manual verification.

Repository made for my bachelor's thesis.

A fine tuned YOLO11 model up to 100 epochs. This custom dataset based fine tuned yolo11s is down streamed on the task of traffic signals detection in both images, videos. Furthermore, the model has been exported to the ONNX format as well. You may export it to your desired serialization format.