Radial greed algorithm with rectified chromaticity for anchorless region proposal applied in aerial surveillance

In aerial images, human figures are often rendered at low resolution and in relatively small sizes compared to other objects in the scene, or resemble likelihood to other non-human objects. The localization of trust regions for possible containment of the human figure becomes difficult and computati...

Full description

Saved in:
Bibliographic Details
Main Authors: De Ocampo, Anton Louise Pernez, Dadios, Elmer P.
Format: text
Published: Animo Repository 2019
Subjects:
Online Access:https://animorepository.dlsu.edu.ph/faculty_research/1441
https://animorepository.dlsu.edu.ph/context/faculty_research/article/2440/type/native/viewcontent
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: De La Salle University
id oai:animorepository.dlsu.edu.ph:faculty_research-2440
record_format eprints
spelling oai:animorepository.dlsu.edu.ph:faculty_research-24402021-06-28T06:45:58Z Radial greed algorithm with rectified chromaticity for anchorless region proposal applied in aerial surveillance De Ocampo, Anton Louise Pernez Dadios, Elmer P. In aerial images, human figures are often rendered at low resolution and in relatively small sizes compared to other objects in the scene, or resemble likelihood to other non-human objects. The localization of trust regions for possible containment of the human figure becomes difficult and computationally exhaustive. The objective of this work is to develop an anchorless region proposal which can emphasize potential persons from other objects and the vegetative background in aerial images. Samples are taken from different angles, altitudes and environmental factors such as illumination. The original image is rendered in rectified color space to create a pseudo-segmented version where objects of close chromaticity are combined. The geometric features of segments formed are then calculated and subjected to Radial-Greed Algorithm where segments resembling human figures are selected as the proposed regions for classification. The proposed method achieved 96.76% less computational cost against brute sliding window method and hit rate of 95.96%. In addition, the proposed method achieved 98.32 % confidence level that it can hit target proposals at least 92% every time. © 2019, Universitas Ahmad Dahlan. All rights reserved. 2019-11-01T07:00:00Z text text/html https://animorepository.dlsu.edu.ph/faculty_research/1441 https://animorepository.dlsu.edu.ph/context/faculty_research/article/2440/type/native/viewcontent Faculty Research Work Animo Repository Aerial surveillance Image converters Image processing—Digital techniques Manufacturing
institution De La Salle University
building De La Salle University Library
continent Asia
country Philippines
Philippines
content_provider De La Salle University Library
collection DLSU Institutional Repository
topic Aerial surveillance
Image converters
Image processing—Digital techniques
Manufacturing
spellingShingle Aerial surveillance
Image converters
Image processing—Digital techniques
Manufacturing
De Ocampo, Anton Louise Pernez
Dadios, Elmer P.
Radial greed algorithm with rectified chromaticity for anchorless region proposal applied in aerial surveillance
description In aerial images, human figures are often rendered at low resolution and in relatively small sizes compared to other objects in the scene, or resemble likelihood to other non-human objects. The localization of trust regions for possible containment of the human figure becomes difficult and computationally exhaustive. The objective of this work is to develop an anchorless region proposal which can emphasize potential persons from other objects and the vegetative background in aerial images. Samples are taken from different angles, altitudes and environmental factors such as illumination. The original image is rendered in rectified color space to create a pseudo-segmented version where objects of close chromaticity are combined. The geometric features of segments formed are then calculated and subjected to Radial-Greed Algorithm where segments resembling human figures are selected as the proposed regions for classification. The proposed method achieved 96.76% less computational cost against brute sliding window method and hit rate of 95.96%. In addition, the proposed method achieved 98.32 % confidence level that it can hit target proposals at least 92% every time. © 2019, Universitas Ahmad Dahlan. All rights reserved.
format text
author De Ocampo, Anton Louise Pernez
Dadios, Elmer P.
author_facet De Ocampo, Anton Louise Pernez
Dadios, Elmer P.
author_sort De Ocampo, Anton Louise Pernez
title Radial greed algorithm with rectified chromaticity for anchorless region proposal applied in aerial surveillance
title_short Radial greed algorithm with rectified chromaticity for anchorless region proposal applied in aerial surveillance
title_full Radial greed algorithm with rectified chromaticity for anchorless region proposal applied in aerial surveillance
title_fullStr Radial greed algorithm with rectified chromaticity for anchorless region proposal applied in aerial surveillance
title_full_unstemmed Radial greed algorithm with rectified chromaticity for anchorless region proposal applied in aerial surveillance
title_sort radial greed algorithm with rectified chromaticity for anchorless region proposal applied in aerial surveillance
publisher Animo Repository
publishDate 2019
url https://animorepository.dlsu.edu.ph/faculty_research/1441
https://animorepository.dlsu.edu.ph/context/faculty_research/article/2440/type/native/viewcontent
_version_ 1703981055271239680