Cover Image

A framework for multiple moving objects detection in aerial videos

Aerial videos captured using dynamic cameras commonly require background remodeling at every frame. In addition, camera motion and the movement of multiple objects present an unstable imaging environment with varying motion patterns. This makes detecting multiple moving objects a difficult task. In...

Full description

Saved in:
Bibliographic Details
Main Authors: Kalantar, Bahareh, Abdul Halin, Alfian, Al-Najjar, Husam Abdulrasool H., Mansor, Shattri, Genderen, John L. Van, M. Shafri, Helmi Zulhaidi, Zand, Mohsen
Format: Book Section
Language:English
Published: Elsevier 2019
Online Access:http://psasir.upm.edu.my/id/eprint/78645/1/A%20framework%20for%20multiple%20moving%20objects%20detection%20in%20aerial%20videos.pdf
http://psasir.upm.edu.my/id/eprint/78645/
https://www.sciencedirect.com/science/article/pii/B9780128152263000260#!
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.upm.eprints.78645
record_format eprints
spelling my.upm.eprints.786452021-01-03T00:17:44Z http://psasir.upm.edu.my/id/eprint/78645/ A framework for multiple moving objects detection in aerial videos Kalantar, Bahareh Abdul Halin, Alfian Al-Najjar, Husam Abdulrasool H. Mansor, Shattri Genderen, John L. Van M. Shafri, Helmi Zulhaidi Zand, Mohsen Aerial videos captured using dynamic cameras commonly require background remodeling at every frame. In addition, camera motion and the movement of multiple objects present an unstable imaging environment with varying motion patterns. This makes detecting multiple moving objects a difficult task. In this chapter, a two-step framework, termed the motion differences of matched region-based features (MDMRBF), is presented. Firstly, each frame goes through super-pixel segmentation to produce regions where each frame is then represented as a region adjacency graph structure of visual appearance and geometric properties. This representation is important for correspondence discovery between consecutive frames based on multigraph matching. Ultimately, each region is labeled as either a background or foreground (object) using a proposed graph-coloring algorithm. Two datasets, namely (1) the DARPA-VIVID dataset and (2) self-captured videos using an unmanned aerial vehicle-mounted camera, have been used to validate the feasibility of MDMRBF. Comparison is also done with three existing detection algorithms where experiments show promising results with precision at 94%, and recall at 89%. Elsevier 2019 Book Section PeerReviewed text en http://psasir.upm.edu.my/id/eprint/78645/1/A%20framework%20for%20multiple%20moving%20objects%20detection%20in%20aerial%20videos.pdf Kalantar, Bahareh and Abdul Halin, Alfian and Al-Najjar, Husam Abdulrasool H. and Mansor, Shattri and Genderen, John L. Van and M. Shafri, Helmi Zulhaidi and Zand, Mohsen (2019) A framework for multiple moving objects detection in aerial videos. In: Spatial Modeling in GIS and R for Earth and Environmental Sciences. Elsevier, United States, 573 - 588. ISBN 9780128152263 https://www.sciencedirect.com/science/article/pii/B9780128152263000260#! 10.1016/B978-0-12-815226-3.00026-0
institution Universiti Putra Malaysia
building UPM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Putra Malaysia
content_source UPM Institutional Repository
url_provider http://psasir.upm.edu.my/
language English
description Aerial videos captured using dynamic cameras commonly require background remodeling at every frame. In addition, camera motion and the movement of multiple objects present an unstable imaging environment with varying motion patterns. This makes detecting multiple moving objects a difficult task. In this chapter, a two-step framework, termed the motion differences of matched region-based features (MDMRBF), is presented. Firstly, each frame goes through super-pixel segmentation to produce regions where each frame is then represented as a region adjacency graph structure of visual appearance and geometric properties. This representation is important for correspondence discovery between consecutive frames based on multigraph matching. Ultimately, each region is labeled as either a background or foreground (object) using a proposed graph-coloring algorithm. Two datasets, namely (1) the DARPA-VIVID dataset and (2) self-captured videos using an unmanned aerial vehicle-mounted camera, have been used to validate the feasibility of MDMRBF. Comparison is also done with three existing detection algorithms where experiments show promising results with precision at 94%, and recall at 89%.
format Book Section
author Kalantar, Bahareh
Abdul Halin, Alfian
Al-Najjar, Husam Abdulrasool H.
Mansor, Shattri
Genderen, John L. Van
M. Shafri, Helmi Zulhaidi
Zand, Mohsen
spellingShingle Kalantar, Bahareh
Abdul Halin, Alfian
Al-Najjar, Husam Abdulrasool H.
Mansor, Shattri
Genderen, John L. Van
M. Shafri, Helmi Zulhaidi
Zand, Mohsen
A framework for multiple moving objects detection in aerial videos
author_facet Kalantar, Bahareh
Abdul Halin, Alfian
Al-Najjar, Husam Abdulrasool H.
Mansor, Shattri
Genderen, John L. Van
M. Shafri, Helmi Zulhaidi
Zand, Mohsen
author_sort Kalantar, Bahareh
title A framework for multiple moving objects detection in aerial videos
title_short A framework for multiple moving objects detection in aerial videos
title_full A framework for multiple moving objects detection in aerial videos
title_fullStr A framework for multiple moving objects detection in aerial videos
title_full_unstemmed A framework for multiple moving objects detection in aerial videos
title_sort framework for multiple moving objects detection in aerial videos
publisher Elsevier
publishDate 2019
url http://psasir.upm.edu.my/id/eprint/78645/1/A%20framework%20for%20multiple%20moving%20objects%20detection%20in%20aerial%20videos.pdf
http://psasir.upm.edu.my/id/eprint/78645/
https://www.sciencedirect.com/science/article/pii/B9780128152263000260#!
_version_ 1688549434982400000
score 13.211869

Similar Items