YoloV8 for a bare Raspberry Pi 4 or 5
🐕 Quadruped manipulator planner and controller using MPC and WBC based on OCS2: Unitree AlienGo + Z1
YoloV8 NPU for the RK3566/68/88
Dart Sense is an automatic dart scoring application. It uses a sophisticated deep learning-based computer vision model to predict the positions of the darts, all while calibrating the board automatically to compute scores. Includes Python app app which can score a game of darts in real time using video streamed from a smartphone.
Many yolov8 model are trained on the VisDrone dataset.
Welcome to the YOLOv8 Human Detection Beginner's Repository – your entry point into the exciting world of object detection! This repository is tailored for beginners, providing a straightforward implementation of YOLOv8 for human detection in images and videos.
An example of using OpenCV dnn module with YOLOv8, YOLOv5u, YOLOv9, YOLOv11, YOLOv12. (ObjectDetection, Segmentation, Classification, PoseEstimation)
Local-first manga translator with AI-powered bubble detection, OCR, automatic translation, an editable web reader, browser extension, and local persistence.
Real-time object detection on Raspberry Pi 5 with the AI Camera (Sony IMX500): export YOLO to IMX, package to .rpk, and run the Picamera2 demo.
Real-time cardboard box defect detection using Blender synthetic data + YOLOv8 (Sim-to-Real, 93% hit / 0% FP)
The project is a Dockerized microservice utilizing YOLO for object detection, managed with Docker Compose. It exposes a REST API for detection tasks, ensuring scalability and ease of deployment. Developed with FastAPI, it accurately detects and reports objects within images, prioritizing code quality, containerization efficiency, and clear document
Bachelor's Final Year Project an FPGA-based FP16 CNN accelerator for real-time YOLOv8n object detection on Xilinx Zynq UltraScale+ (ZCU104). Features a reconfigurable multi-engine architecture with on-chip dynamic retiling, achieving scalable throughput for edge AI applications.
PCBQualityControl uses the latest segmentation models to solve this problem of void detection. This solution trained Yolov8 on the target to automatically select (bounding box). SAM then uses the output of YOLO to segment the image, exposing the void and component areas. A quality control report is generated based on the voids to components ratio.
real-time cpu only eye-tracking. yolov8n face detection model + custom finetuned yolov8n-pose model for eyes
Lightweight UAV-SAR perception system for aerial human detection, monocular GPS geolocation, and automated rescue alerting using standard UAV telemetry and edge AI.
Use an image classifier to predict audio file labels.
Object detection on Custom Dataset using YOLOv8. The dataset has been created by me.
To associate your repository with the yolov8n topic, visit your repo's landing page and select "manage topics."