SPIRO, Spiro, project for student, student projects
A RESEARCH & DEVELOPMENT ORGANIZATION

For Project Enquiry +91 9962 067 067

Slideshow Image 1
Post Your concept Get Project
Guidance
It is purposely dedicated for innovative students. Here we encourage students who have new concepts and projects in various domains.

For Project Title


Project Zone > Electronics > Image Processing

Social share: Facebook SPIRO Google Plus

Unsupervised Detection of Earthquake-Triggered Roof-Holes From UAV Images Using Joint Color and Shape Features

Category : Image Processing


Sub Category : SATELLITE


Project Code : IMP14


Project Abstract

Many methods have been developed to detect damaged buildings due to earthquake. However, little attention has been paid to analyze slightly affected buildings. In this letter, an unsupervised method is presented to detect earthquake-triggered “roof-holes” on rural houses from unmanned aerial vehicle (UAV) images. First, both orthomosaic and gradient images are generated from a set of UAV images. Then, a modified Chinese restaurant franchise model is used to learn an unsupervised model of the geo-object classes in the area by fusing both over segmented orthomosaic and gradient images. Finally, “roof-holes” on rural houses are detected using the learned model.

 

EXISTING SYSTEM

PROPOSED SYSTEM

EXISTING CONCEPT:

          A detailed investigation of the characteristics of the areas damaged due to the Bam earthquake in terms of the differences in the backscattering coefficient and the correlation coefficient of the pre- and post-event Envisat/ASAR images was conducted in order to raise the precision of damage detection.

          Finally, the damage-mapping scheme was revised to present the distribution of damaged areas in Bam.

PROPOSED CONCEPT:

          An unsupervised method is presented to detect earthquake-triggered “roof-holes” on rural houses from unmanned aerial vehicle (UAV) images. First, both orthomosaic and gradient images are generated from a set of UAV images.

 

 

          Finally, “roof-holes” on rural houses are detected using the learned model.

EXISTING  TECHNIQUE :

          A DAMAGE DETECTION METHOD

PROPOSED ALGORITHM:

          ROOF-HOLE DETECTION

TECHNIQUE DEFINITION:

          Two multi-looked intensity images taken before and after an earthquake were prepared. It is desirable that the acquisition dates are as close as possible to the day of the earthquake and that the observation conditions are similar. However, the method was successful in damage detection for the Kobe example, although the image pair had vastly different observation orbits before and after the earthquake. After co-registering the pre- and post-event images, each image was filtered using a Lee filter with a 21_21 pixel window.

ALGORITHM DEFINITION:

          It is done by comparing the distribution of each segment in the clustering result and distribution of “roof-hole” segments in the ground truth. The similarity between two distributions is calculated based on Kullback–Leibler (KL) divergence. For each “roof-hole” segment in the ground truth, all of the segments in the clustering result can be sorted according to their scores computed byKLdivergence. Then, themost representative segments with high scores can be selected as the detected roof-holes.

DRAWBACKS:

          The detection of earthquake by detecting the collapsed building didn’t gave us accuracy due to some surface problems in that method.

          The detection based on shadows is having some drawbacks, because it requires supervision regularly.

           In the existing methods there is no unsupervised earthquake detection system.

ADVANTAGES:

          Many of the myriad tactical uses of EEW - stopping surgery, trains, airport take-offs and landing, closing vulnerable bridges, opening critical doors, warning school kids, and the population in general, and quick tsunami warning input - will prove valuable.

           The reassurance that the populace does not need to interpret every bump in the night as potentially apocalyptic, i.e., that most noticeable earthquakes are not going to be damaging.


 
 
MILE STONES
GUARANTEES
CONTACT US
 
Training and Developemet, Engg Projects
So far we have provided R&D training for more than 1,00,000 engineering Students.
Latest Projects 2012, Latest Technologiy Project
Had conducted seminars in the recent trends of technology at various colleges.
Our research projects had been presented in various National & International Conferences.
Most of our projects were identified by the industries as suitable for their needs.
Our n-number of students got research scholarship to extend our assisted projects for further development.
   
   
Training and Developemt, Project Development in Chennai
SPIRO guarantees small class sizes.
Final Year Projects
SPIRO guarantees quality instructors.
Student Projects, Stupros
SPIRO guarantees competence.
Projects, student projects
SPIRO guarantees that training from SPIRO will be more cost-effective than training from any other source.
Final Year Projects, Projects, student projects
SPIRO guarantees that students in open-enrollment classes are protected against cancellations and will be able to receive desired training at the cost they expect and in the time frame they have planned.
Projects for student
SPIRO guarantees overall quality with a 100% money-back guarantee. If you're not totally satisfied for any reason, simply withdraw before the second day of any class. Notify the instructor and return all course materials and you will receive a 100% refund.
SPIRO SOLUTIONS PRIVATE LIMITED
For ECE,EEE,E&I, E&C & Mechanical,Civil, Bio-Medical
#1, C.V.R Complex, Singaravelu St, T.Nagar, Chennai - 17,
(Behind BIG BAZAAR)Tamilnadu,India
Mobile : +91-9962 067 067, +91-9176 499 499
Landline : 044-4264 1213
Email: info@spiroprojects.com

For IT, CSE, MSC, MCA, BSC(CS)B.COM(cs)
#78, 3rd Floor, Usman Road, T.Nagar, Chennai-17.
(Upstair Hotel Saravana Bhavan) Tamilnadu,India
Mobile: +91-9791 044 044, +91-9176 644 044
E-Mail: info1@spiroprojects.com
About Us | Project Training | Privacy policy | Disclaimer | Contact Us

Copyright © 2015-2016 Stupros All rights reserved.