On Line Segment Detection in IRS Images.

Date of Submission

December 1992

Date of Award

Winter 12-12-1993

Institute Name (Publisher)

Indian Statistical Institute

Document Type

Master's Dissertation

Degree Name

Master of Technology

Subject Name

Computer Science


Electronics and Communication Sciences Unit (ECSU-Kolkata)


Majumder, D. Dutta (ECSU-Kolkata; ISI)

Abstract (Summary of the Work)

This Report Provides the Results of applying Various Line Detecting Algorithms on I.r.s (Indian Remote Sensing Satellite) Images. With the Resolution 36.25 X 36.25 Sg.mt of Irs Images the Linear Features of Interest to us as Roads, Such Railway lines are in General One, Two or Three Pixels Wide.There are Many Algorithms in Literature for Detecting line Segments Such as Simple Thresholding[5], Linear and Non-Linear line Detecting Operators(51, Using a Pair of Edges(2].This Report Deals with the Detection of line Segments Using Three Earlier Methods in Relation to two new Methods. The results are Provided in the Report. The Images Under Cosideration for Analysis are I.r.s Images of Calcutta & Bombay.One Pixel width line Segments are Detected byline Tracing line Segments Upto Three Pixels Width are Detected Using the 'classification'results of the Images. The Classification has Been Done According to the Land Cover Type.


ProQuest Collection ID: http://gateway.proquest.com/openurl?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:dissertation&res_dat=xri:pqm&rft_dat=xri:pqdiss:28843478

Control Number


Creative Commons License

Creative Commons Attribution 4.0 International License
This work is licensed under a Creative Commons Attribution 4.0 International License.



This document is currently not available here.