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

College

Gokongwei College of Engineering

Department/Unit

Manufacturing Engineering and Management

Document Type

Article

Source Title

International Journal of Advances in Intelligent Informatics

Volume

5

Issue

3

First Page

193

Last Page

205

Publication Date

11-1-2019

Abstract

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.

html

Digitial Object Identifier (DOI)

10.26555/ijain.v5i3.426

Disciplines

Manufacturing

Keywords

Aerial surveillance; Image converters; Image processing—Digital techniques

Upload File

wf_yes

This document is currently not available here.

Share

COinS