Abstract: Now a days UNMANNED AERIAL VEHICLES incorporating image / video segmentation and object detection methods in them for various applications such as reconnaissance, surveillance, tracking, ...

This project implements bounding box detection and semantic segmentation on the CamVid dataset using Mask R-CNN. It includes data preprocessing, model training, and visualization tools.

Prepare train and test images This repository contains train and test images for detection of "UE Roll" blue bluetooth speaker but I will highly recommend you to create your own dataset. Pick up an ...