Traffic Sign Detection and Warning System in real time with Custom Dataset & YOLOV8.

Fire detection using YOLOv8 involves utilizing a state-of-the-art object detection model to accurately identify fire in images or video feeds in real-time, leveraging its advanced capabilities to enhance early warning systems.

Machine Learning model

Detect football players in videos using YOLOv5 for training and YOLOv8 for inference. The dataset is sourced from Roboflow and includes 663 annotated images. The project involves pre-processing, augmentation, and model training for accurate player detection.

The road sign recognition system of the Russian Federation, which uses an already prepared model for object detection and image segmentation in real time to improve road safety

This project focuses on leveraging the YOLO-NAS model for Smoke Detection.

Custom Yolov8x-cls edge model deployment and training to classify trash vs recycling.

This project implements a YOLOv8 model to detect and classify various skin diseases from images. The model is trained on a dataset of labeled images and can identify different types of skin conditions in real-time.

From a selection of data from the Roboflow file https://universe.roboflow.com/landy-aw2jb/fracture-ov5p1/dataset/1, which represents a reduced but homogeneous version of that file, a model is obtained based on yolov10 with that custom dataset to indicate fractures in x-rays.

Use machine learning to identify players, refs and football field markings.

A football analysis system built using YOLOv5, Supervision, OpenCV in Python.

This research work introduced various aspects from dataset preparation techniques to image pre-processing, model comparison, and performance analysis on the detection & instance segmentation of three microalgae class namely Chlorella vulgaris FSP-E, Chlamydomonas reinhardtii, and Spirulina platensis.

Contribution for Traffic Sign Detection and Warning System in real time with Custom Dataset & YOLOv8.

Deep learning project is designed to detect small-sized rooftop photovoltaic (PV) panels using satellite imagery

From dataset https://universe.roboflow.com/drone-detection-pexej/drone-detection-data-set-yolov7/dataset/1# a model is obtained, based on ML (SVR), with that custom dataset, to indicate drones detection

Soccer analysis using YOLOv8 & Supervision ByteTrack

From dataset https://universe.roboflow.com/drone-detection-pexej/drone-detection-data-set-yolov7/dataset/1 a model is obtained, based on yolov10 to detect drones in images. Predictions from several models are used in cascade to obtain the optimal result.

From dataset https://universe.roboflow.com/roboflow-100/bone-fracture-7fylg a model is obtained, based on ML (SVR), with that custom dataset, to indicate fractures in x-rays.

From dataset https://universe.roboflow.com/test-svk7h/brain-tumors-detection/dataset/2 a model is obtained, based on yolov10 to indicate tumors in images of brains.

A computer Vision project for avoiding potholes on road.