You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
A simpler (and working) notebook and repo for convinient use of YOLO-NAS-POSE, a human pose estimation model by Deci AI. Aims to run in a less resource intensive manner, by eliminating real-time capture and playback, and instead reading from and writing to permanent image and video files.
Third year university dissertation. Continuous Assessment for ECM3401 - Individual Literature Review and Project. Involves the implementation of a human pose estimation computer vision model to detect two combat athletes, and a machine learning algorithm to identify their grappling position.
This project is completed as a fulfilment for the CDS590 Consultancy Project & Practicum provided by School of Computer Sciences, USM as part of their Masters of Science in Data Science and Analytics program.
Repository containing implemetation and documentation of master's thesis Object detection and segmentation in historical encrypted manuscripts at at Faculty of Electrical Engineering and Information Technology of Slovak University of Technology in Bratislava (FEI STU).
About YOLO_NAS is an architecture for object detection that automatically searches for optimal neural network structures, while Segment Anything Model is a versatile model for segmenting various objects in images.
This repository contains a Streamlit web application for vehicle tracking using different SOTA object detection models. The app offers two options: YOLO-NAS with SORT tracking and YOLOv8 with ByteTrack and Supervision tracking. It enables users to upload a video file, set confidence levels, and visualize the tracking results in real-time.