An Efficient Approach For Taxi And Surfboard Detection Using Faster R-CNN

Object Detection has been becoming trending in recent years because it allows us to detect objects within an image or video.Object detection has been broken down into machine learning-based approaches and deep learning-based approaches.As deep learning methods have become state-of-the-art approaches to object detection,we study the problem of object detection in this thesis.This research aims to detect taxis on roads and surfboards in water environments using deep learning algorithms,which can,in turn,reduce the deaths caused due to any incidents on-road and accidental drowning.This study first investigates to find the suitable deep learning algorithms used to detect objects with high accuracy and efficient time.Then,an experiment is performed with the chosen algorithm to state the possibility of detecting taxis and surfboards and then evaluating the algorithm’s performance.Firstly,a Literature review is used to find suitable deep learning algorithms,and then based on the finding,an experiment is performed to evaluate the chosen deep learning algorithms.The literature review showed evidence that Faster RCNN is the suitable algorithm and the experimental results showed that Faster RCNN performed better.In this thesis,We will be using Faster R-CNN to detect cars and surfboards.Analyzing the results obtained and considering the real-world scenario this thesis aims at,it can be concluded that Faster RCNN is the algorithm of choice to detect taxis and surfboards.