Find Jobs
Hire Freelancers

Detecing Voulme of Fault in an Image

₹12500-37500 INR

Closed
Posted over 6 years ago

₹12500-37500 INR

Paid on delivery
Automatic detection of damaged buildings from aerial and satellite images is an important problem for rescue planners and military personnel. A method for detecting the buildings from high resolution color aerial images is proposed in this paper. The aim is to extract the buildings from high resolution color aerial images using color invariance property and canny edge detection technique. The buildings on the aerial images are 2-dimentional structures which are mostly made up of regions having borders being straight line which depicts edges in the images. The color information in the aerial image using a specific color index is extracted. The green area is separated by vegetation green from color aerial image.
Project ID: 15616248

About the project

5 proposals
Remote project
Active 6 yrs ago

Looking to make some money?

Benefits of bidding on Freelancer

Set your budget and timeframe
Get paid for your work
Outline your proposal
It's free to sign up and bid on jobs
5 freelancers are bidding on average ₹23,444 INR for this job
User Avatar
Expertise in MATLAB with a substantial background in image processing and computer vision. I can provide you your complete task in decided time frame with quality work. We can discuss further details in the message
₹14,444 INR in 7 days
4.9 (102 reviews)
5.5
5.5
User Avatar
I can assist you to implement your project which I believe is using the normalized difference indices to detect buildings and other land features from satellite imagery. Relevant Skills and Experience I have experience using R and to a smaller extent Matlab to process satellite imagery. I wrote and maintain the Rsatellite package that extracts nightlight data from nightlight satellite imagery. Proposed Milestones ₹33333 INR - On completion
₹33,333 INR in 10 days
4.6 (13 reviews)
5.3
5.3
User Avatar
Hello! You've an interesting theory, but in practical you've not mentioned how exactly you wish to detect damaged structures/buildings using just 2D information? I speak with experience of working with LIDAR data for the exact same purpose during cloud bursts few years ago in India. What you're correct with? Segmentation of the building and vegetation area, however if considering the geometry and their edge maps, most vegetation area should be eliminated anyway. Okay, with color information, more can be done, things can be slightly better. Where you're still unclear? How do you prove a broken edge is in fact a damaged structure? Kindly elaborate more of this part, so that I can get a good idea of the time it will take for the implementation. About me: Am a research assistant in image processing and machine learning field, so if you like me to work on any algorithm changes, I can help you with it. However, it will be additional to the implementation costs. Perhaps, we can discuss in more details, if you're interested. Approach: On a brief note, we shall divide it into 2 to 3 milestone payments, for update tracking and delivery. Tools: Matlab, Python Kindly leave your queries and clarifications even if I'm not online, and I shall revert back ASAP. Thanks!
₹25,000 INR in 11 days
4.9 (17 reviews)
4.3
4.3

About the client

Flag of INDIA
Mumbai, India
5.0
1
Member since Oct 30, 2017

Client Verification

Thanks! We’ve emailed you a link to claim your free credit.
Something went wrong while sending your email. Please try again.
Registered Users Total Jobs Posted
Freelancer ® is a registered Trademark of Freelancer Technology Pty Limited (ACN 142 189 759)
Copyright © 2024 Freelancer Technology Pty Limited (ACN 142 189 759)
Loading preview
Permission granted for Geolocation.
Your login session has expired and you have been logged out. Please log in again.