YoloV8 for a bare Raspberry Pi 4 or 5

A lightweight C++ implementation of YoloV8 running on NVIDIAs TensorRT engine

This project implements a Wrinkle Detection application using YOLOv8 for segmentations. The application is built with Streamlit and allows users to upload images for wrinkle detection of human faces. Segmentation using YOLOv8s (small) finetuned model.

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).

A computer vision desktop application for automated insect phenotyping using YOLOv8, FastAPI, React and Tauri to detect and count insect embryos in high‑resolution microscopy images.

This repository provides a fully containerized microservice for object detection using YOLOv8 and FastAPI. With Docker and Docker Compose, developers can easily set up, run, and integrate advanced object recognition capabilities into their applications.

Advanced real-time object detection with YOLOv8s, counter, dynamic colors, and HD fullscreen display Topics: python yolo computer-vision object-detection opencv deep-learning real-time yolov8s object-counting

detect football player, ball, goalkeeper, refree with custom trained yolo wieghts

Real-time underwater trash detection using YOLOv8s trained on the TrashCan dataset

An advanced YOLOv8 object detection pipeline trained on mixed BDD100k & RDD datasets. Features custom stratification, live spatial mapping, and a three-tier risk assessment classifier optimized

Traffic Sign Recognition (TSR) vison model for Advanced Driver Assitance System (ADAS) using YOLO-based object detection, trained on a custom Indian traffic sign dataset aligned with Indian Road Congress (IRC:67-2022) standards.

Low-light pedestrian detection via visible-infrared pixel fusion + YOLOv8s fine-tuning on the LLVIP benchmark dataset

A wearable AI-powered sling bag that assists visually impaired users through real-time obstacle detection, text reading, and voice-based guidance using YOLOv8s and Phi-2 LLM.

Face Recognition of individuals using YOLOv8 + ArcFace

This project focuses on the comparative analysis of machine learning models for the task of violence detection in images or videos. Violence detection is a crucial application with various real-world use cases, including surveillance, content moderation, and public safety.

This project analyzes tennis match videos by detecting players, tracking their movement, reading the scoreboard, and generating heatmaps that visualize player positioning and point dynamics.

A React frontend uploads a face image, a YOLOv8 model extracts eye features (brightness, openness, symmetry), stores them in Firebase, and a Flask backend retrieves and displays them.