Skip navigation
Please use this identifier to cite or link to this item: http://repository.iitr.ac.in/handle/123456789/15422
Title: A cognitive method for object detection from aerial image
Authors: Chandra N.
Sharma A.
Ghosh, Jayanta Kumar
Swaroop A.
Singh M.
Astya P.N.
Sharma V.
Published in: Proceeding of IEEE International Conference on Computing, Communication and Automation, ICCCA 2016
Abstract: Aerial images are rich sources of data for extracting geo-spatial information. A deeper understanding of human cognitive processes is necessary to automate the mechanism of information extraction from aerial images. The objective of this research work is to emulate human cognitive capacities for extracting the geospatial information from an urban area. Firstly, preliminary knowledge about the sequence of cognitive processes which human's image cognition system utilizes during object detection is collected. Secondly, rule based approach is used for the representation of the knowledge which is obtained from the visual interpretation of image by the human beings. Thirdly, defined rules are used to detect the buildings in the aerial image using two different algorithms. ¬© 2016 IEEE.
Citation: Proceeding of IEEE International Conference on Computing, Communication and Automation, ICCCA 2016, (2017), 327- 330
URI: https://doi.org/10.1109/CCAA.2016.7813738
http://repository.iitr.ac.in/handle/123456789/15422
Issue Date: 2017
Publisher: Institute of Electrical and Electronics Engineers Inc.
Keywords: Cognitive
Knowledge
Mixture Tuned Matched Filtering
Spectral Angle Mapper
ISBN: 9.78151E+12
Author Scopus IDs: 57191964249
57210974678
34968946700
Author Affiliations: Chandra, N., Civil Engineering Department, Indian Institute of Technology, Roorkee, India
Sharma, A., Civil Engineering Department, Indian Institute of Technology, Roorkee, India
Ghosh, J.K., Civil Engineering Department, Indian Institute of Technology, Roorkee, India
Appears in Collections:Conference Publications [CE]

Files in This Item:
There are no files associated with this item.
Show full item record


Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.