Selecting change image for efficient change detection

Abstract Change detection (CD) is a fundamental problem that aims at detecting changed objects from two observations. Previous CNN‐based CD methods detect changes through multi‐scale deep convolutional features extracted from two images. However, we find that change always occurs in the ‘Query’ imag...

Full description

Saved in:
Bibliographic Details
Main Authors: Rui Huang, Ruofei Wang, Yuxiang Zhang, Yan Xing, Wei Fan, Kai Leung Yung
Format: Article
Language:English
Published: Wiley 2022-05-01
Series:IET Signal Processing
Subjects:
Online Access:https://doi.org/10.1049/sil2.12095
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850166207019220992
author Rui Huang
Ruofei Wang
Yuxiang Zhang
Yan Xing
Wei Fan
Kai Leung Yung
author_facet Rui Huang
Ruofei Wang
Yuxiang Zhang
Yan Xing
Wei Fan
Kai Leung Yung
author_sort Rui Huang
collection DOAJ
description Abstract Change detection (CD) is a fundamental problem that aims at detecting changed objects from two observations. Previous CNN‐based CD methods detect changes through multi‐scale deep convolutional features extracted from two images. However, we find that change always occurs in the ‘Query’ image for fixed cameras. This condition means that changes can be detected in advance from a single image with a coarse change. In this paper, we propose an efficient CD method to detect precise changes from the change image. First, a change image selector is designed to identify the image containing changes. Second, a coarse change prior map generator is proposed to generate coarse change prior to indicate the position of changes. Then, we introduce a simple multi‐scale CD module to refine the coarse change detection. As only one image is used in the multi‐scale CD module, our method is more efficient in training and testing than other compared methods. Numerous experiments have been conducted to analyse the effectiveness of the proposed method. Experimental results show that the proposed method achieves superior detection performance and higher speed than other compared CD methods.
format Article
id doaj-art-dda35e6a88f8422cbb9fdf7fdb4cf45a
institution OA Journals
issn 1751-9675
1751-9683
language English
publishDate 2022-05-01
publisher Wiley
record_format Article
series IET Signal Processing
spelling doaj-art-dda35e6a88f8422cbb9fdf7fdb4cf45a2025-08-20T02:21:30ZengWileyIET Signal Processing1751-96751751-96832022-05-0116332733910.1049/sil2.12095Selecting change image for efficient change detectionRui Huang0Ruofei Wang1Yuxiang Zhang2Yan Xing3Wei Fan4Kai Leung Yung5College of Computer Science and Technology Civil Aviation University of China Tianjin ChinaCollege of Computer Science and Technology Civil Aviation University of China Tianjin ChinaCollege of Computer Science and Technology Civil Aviation University of China Tianjin ChinaCollege of Computer Science and Technology Civil Aviation University of China Tianjin ChinaCollege of Computer Science and Technology Civil Aviation University of China Tianjin ChinaDepartment of Industrial and Systems Engineering The Hong Kong Polytechnic University Hung Hom Hong KongAbstract Change detection (CD) is a fundamental problem that aims at detecting changed objects from two observations. Previous CNN‐based CD methods detect changes through multi‐scale deep convolutional features extracted from two images. However, we find that change always occurs in the ‘Query’ image for fixed cameras. This condition means that changes can be detected in advance from a single image with a coarse change. In this paper, we propose an efficient CD method to detect precise changes from the change image. First, a change image selector is designed to identify the image containing changes. Second, a coarse change prior map generator is proposed to generate coarse change prior to indicate the position of changes. Then, we introduce a simple multi‐scale CD module to refine the coarse change detection. As only one image is used in the multi‐scale CD module, our method is more efficient in training and testing than other compared methods. Numerous experiments have been conducted to analyse the effectiveness of the proposed method. Experimental results show that the proposed method achieves superior detection performance and higher speed than other compared CD methods.https://doi.org/10.1049/sil2.12095change detectionchange image selectorefficient change detectionmulti‐scale change detection
spellingShingle Rui Huang
Ruofei Wang
Yuxiang Zhang
Yan Xing
Wei Fan
Kai Leung Yung
Selecting change image for efficient change detection
IET Signal Processing
change detection
change image selector
efficient change detection
multi‐scale change detection
title Selecting change image for efficient change detection
title_full Selecting change image for efficient change detection
title_fullStr Selecting change image for efficient change detection
title_full_unstemmed Selecting change image for efficient change detection
title_short Selecting change image for efficient change detection
title_sort selecting change image for efficient change detection
topic change detection
change image selector
efficient change detection
multi‐scale change detection
url https://doi.org/10.1049/sil2.12095
work_keys_str_mv AT ruihuang selectingchangeimageforefficientchangedetection
AT ruofeiwang selectingchangeimageforefficientchangedetection
AT yuxiangzhang selectingchangeimageforefficientchangedetection
AT yanxing selectingchangeimageforefficientchangedetection
AT weifan selectingchangeimageforefficientchangedetection
AT kaileungyung selectingchangeimageforefficientchangedetection