My First Project in Computer Vision: Cityscape Semantic Segmentation Using UNet

When I first heard of computer vision, I was only familiar with Object Detection and Classification, but that’s not all there is to Image Semantic Segmentation. Image Segmentation is the process of partitioning a digital image into multiple image segments also known as image regions or image objects (sets of pixels). The goal of segmentation is to simplify and/or change the representation of an image into something that is more representative and easier to analyze. Image segmentation is often used to locate objects and boundaries.

Background

A common problem in many big cities in the world is traffic jams and the high number of accidents. One of the factors that play a major role in the occurrence of this incident is the negligence of the driver.

Read More