Extraction of Main Urban Roads from High Resolution Satellite Images by Machine Learning || Python

TO PURCHASE OUR PROJECTS IN ONLINE (OR) OFFLINE
CONTACT:VENKAT PROJECTS
NAME: VENKATARAO GANIPISETTY
Mobile & WhatsApp :[phone]
Email :[e-mail]
Website:www.venkatjavaprojects.com
About Project:
In this paper author is using AdaBoost machine learning algorithm to extract road from satellite images. To train AdaBoost author is using QuickBird satellite images dataset and then applying various features extraction technique such Canny Edge Detection, Hough Line and LBP to extract features from images and then this extracted features will be input to AdaBoost for learning or training a model. This AdaBoost trained model can be applied on any test satellite image to extract road as AdaBoost trained on straight lines features so it can predict straight line road from any test images.
To implement this project we have apply following techniques
1) Input images: using this module we will input satellite images
2) Canny Edge Detection: using this method we will extract edges from images
3) Hough Transformation: if extracted edges contains straight line then we got road in input images and then extract features
4) LBP: Extracted features will be input to LBP algorithm to extract out road lines from images
5) AdaBoost Learning: extracted LBP features will be input to AdaBoost algorithm to train a model.
6) Road Extraction: AdaBoost trained model will be applied on test image to get road
To implement this project we have designed following Modules
1) Upload Satellite Images Dataset: using this module we will upload satellite images dataset to application
2) Run Canny, Hough & LBP Features Extraction Algorithms: using this module we will read all images and then extract features using Canny, Hough and LBP
3) Train AdaBoost Algorithm: using this module we will input extracted features to AdaBoost algorithm to train a model
4) Road Extraction from Test Images: using this module we will input test image and then AdaBoost will learn and extract road from given satellite images