Cargando…

Multi-Model Estimation Based Moving Object Detection for Aerial Video

With the wide development of UAV (Unmanned Aerial Vehicle) technology, moving target detection for aerial video has become a popular research topic in the computer field. Most of the existing methods are under the registration-detection framework and can only deal with simple background scenes. They...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhang, Yanning, Tong, Xiaomin, Yang, Tao, Ma, Wenguang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2015
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4431192/
https://www.ncbi.nlm.nih.gov/pubmed/25856330
http://dx.doi.org/10.3390/s150408214
_version_ 1782371294757519360
author Zhang, Yanning
Tong, Xiaomin
Yang, Tao
Ma, Wenguang
author_facet Zhang, Yanning
Tong, Xiaomin
Yang, Tao
Ma, Wenguang
author_sort Zhang, Yanning
collection PubMed
description With the wide development of UAV (Unmanned Aerial Vehicle) technology, moving target detection for aerial video has become a popular research topic in the computer field. Most of the existing methods are under the registration-detection framework and can only deal with simple background scenes. They tend to go wrong in the complex multi background scenarios, such as viaducts, buildings and trees. In this paper, we break through the single background constraint and perceive the complex scene accurately by automatic estimation of multiple background models. First, we segment the scene into several color blocks and estimate the dense optical flow. Then, we calculate an affine transformation model for each block with large area and merge the consistent models. Finally, we calculate subordinate degree to multi-background models pixel to pixel for all small area blocks. Moving objects are segmented by means of energy optimization method solved via Graph Cuts. The extensive experimental results on public aerial videos show that, due to multi background models estimation, analyzing each pixel’s subordinate relationship to multi models by energy minimization, our method can effectively remove buildings, trees and other false alarms and detect moving objects correctly.
format Online
Article
Text
id pubmed-4431192
institution National Center for Biotechnology Information
language English
publishDate 2015
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-44311922015-05-19 Multi-Model Estimation Based Moving Object Detection for Aerial Video Zhang, Yanning Tong, Xiaomin Yang, Tao Ma, Wenguang Sensors (Basel) Article With the wide development of UAV (Unmanned Aerial Vehicle) technology, moving target detection for aerial video has become a popular research topic in the computer field. Most of the existing methods are under the registration-detection framework and can only deal with simple background scenes. They tend to go wrong in the complex multi background scenarios, such as viaducts, buildings and trees. In this paper, we break through the single background constraint and perceive the complex scene accurately by automatic estimation of multiple background models. First, we segment the scene into several color blocks and estimate the dense optical flow. Then, we calculate an affine transformation model for each block with large area and merge the consistent models. Finally, we calculate subordinate degree to multi-background models pixel to pixel for all small area blocks. Moving objects are segmented by means of energy optimization method solved via Graph Cuts. The extensive experimental results on public aerial videos show that, due to multi background models estimation, analyzing each pixel’s subordinate relationship to multi models by energy minimization, our method can effectively remove buildings, trees and other false alarms and detect moving objects correctly. MDPI 2015-04-08 /pmc/articles/PMC4431192/ /pubmed/25856330 http://dx.doi.org/10.3390/s150408214 Text en © 2015 by the authors; licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Zhang, Yanning
Tong, Xiaomin
Yang, Tao
Ma, Wenguang
Multi-Model Estimation Based Moving Object Detection for Aerial Video
title Multi-Model Estimation Based Moving Object Detection for Aerial Video
title_full Multi-Model Estimation Based Moving Object Detection for Aerial Video
title_fullStr Multi-Model Estimation Based Moving Object Detection for Aerial Video
title_full_unstemmed Multi-Model Estimation Based Moving Object Detection for Aerial Video
title_short Multi-Model Estimation Based Moving Object Detection for Aerial Video
title_sort multi-model estimation based moving object detection for aerial video
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4431192/
https://www.ncbi.nlm.nih.gov/pubmed/25856330
http://dx.doi.org/10.3390/s150408214
work_keys_str_mv AT zhangyanning multimodelestimationbasedmovingobjectdetectionforaerialvideo
AT tongxiaomin multimodelestimationbasedmovingobjectdetectionforaerialvideo
AT yangtao multimodelestimationbasedmovingobjectdetectionforaerialvideo
AT mawenguang multimodelestimationbasedmovingobjectdetectionforaerialvideo