Detection of major changes in satellite images

José Luis LISANI; Jean-Michel MOREL

doi:10.1109/ICIP.2003.1247119

Detection of major changes in satellite images

José Luis LISANI^*
, Jean-Michel MOREL

^*Corresponding author for this work

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Research › peer-review

23 Citations (Scopus)

Abstract

We address in this paper the problem of detecting changes between two photographs of the same scene taken at different dates. Considering that both images are already accurately registered our problem reduces to a) detect changes between corresponding pixels, and b) determine whether these changes are a clue of a major change in the scene. The solution of a) involves the use of spectral invariant features, since we consider the general situation of comparing photographs coming from different spectral channels. The answer to b) implies the computation of an absolute thres-hold above which a region of the image will be detected as having "meaningful changes". In order to do that, we apply a recently introduced method yielding accurate false alarm rates for each detection. We show that this method permits to help significantly photo-interprets in their search for major changes in a scene. This will be illustrated by a striking application, the detection of the explosion of the AZF chemical plant in Toulouse (France) in September 2001.

Original language	English
Title of host publication	Proceedings: 2003 International Conference on Image Processing
Publisher	IEEE
Pages	941-944
Number of pages	4
Volume	1
ISBN (Print)	0780377508
DOIs	https://doi.org/10.1109/ICIP.2003.1247119
Publication status	Published - 2003
Externally published	Yes
Event	2003 International Conference on Image Processing - Barcelona, Spain Duration: 14 Sept 2003 → 17 Sept 2003

Publication series

Name	IEEE International Conference on Image Processing
Publisher	IEEE
ISSN (Print)	1522-4880

Conference

Conference	2003 International Conference on Image Processing
Abbreviated title	ICIP 2003
Country/Territory	Spain
City	Barcelona
Period	14/09/03 → 17/09/03

Bibliographical note

The authors thank Bernard RougC for valuable information, encouragements and comments, and CNES for providing the Toulouse Satellite images

Funding

The first author gratcfUlly acknowledges partial support by ClCYT project, reference TIC99-0266. The second author acknowledges partial support from Centre Na- tional *Etudes Sptrales (Contra1 lnvaiants Sprctraux) and from Office of Naval Research under grant N00014-97-1-0839.

Access to Document

10.1109/ICIP.2003.1247119

Cite this

@inproceedings{4c6a448f4ff6499ebb30d2f1064369eb,

title = "Detection of major changes in satellite images",

abstract = "We address in this paper the problem of detecting changes between two photographs of the same scene taken at different dates. Considering that both images are already accurately registered our problem reduces to a) detect changes between corresponding pixels, and b) determine whether these changes are a clue of a major change in the scene. The solution of a) involves the use of spectral invariant features, since we consider the general situation of comparing photographs coming from different spectral channels. The answer to b) implies the computation of an absolute thres-hold above which a region of the image will be detected as having {"}meaningful changes{"}. In order to do that, we apply a recently introduced method yielding accurate false alarm rates for each detection. We show that this method permits to help significantly photo-interprets in their search for major changes in a scene. This will be illustrated by a striking application, the detection of the explosion of the AZF chemical plant in Toulouse (France) in September 2001.",

author = "LISANI, \{Jos{\'e} Luis\} and Jean-Michel MOREL",

note = "The authors thank Bernard RougC for valuable information, encouragements and comments, and CNES for providing the Toulouse Satellite images; 2003 International Conference on Image Processing, ICIP 2003 ; Conference date: 14-09-2003 Through 17-09-2003",

year = "2003",

doi = "10.1109/ICIP.2003.1247119",

language = "English",

isbn = "0780377508",

volume = "1",

series = "IEEE International Conference on Image Processing",

publisher = "IEEE",

pages = "941--944",

booktitle = "Proceedings: 2003 International Conference on Image Processing",

}

TY - GEN

T1 - Detection of major changes in satellite images

AU - LISANI, José Luis

AU - MOREL, Jean-Michel

N1 - The authors thank Bernard RougC for valuable information, encouragements and comments, and CNES for providing the Toulouse Satellite images

PY - 2003

Y1 - 2003

N2 - We address in this paper the problem of detecting changes between two photographs of the same scene taken at different dates. Considering that both images are already accurately registered our problem reduces to a) detect changes between corresponding pixels, and b) determine whether these changes are a clue of a major change in the scene. The solution of a) involves the use of spectral invariant features, since we consider the general situation of comparing photographs coming from different spectral channels. The answer to b) implies the computation of an absolute thres-hold above which a region of the image will be detected as having "meaningful changes". In order to do that, we apply a recently introduced method yielding accurate false alarm rates for each detection. We show that this method permits to help significantly photo-interprets in their search for major changes in a scene. This will be illustrated by a striking application, the detection of the explosion of the AZF chemical plant in Toulouse (France) in September 2001.

AB - We address in this paper the problem of detecting changes between two photographs of the same scene taken at different dates. Considering that both images are already accurately registered our problem reduces to a) detect changes between corresponding pixels, and b) determine whether these changes are a clue of a major change in the scene. The solution of a) involves the use of spectral invariant features, since we consider the general situation of comparing photographs coming from different spectral channels. The answer to b) implies the computation of an absolute thres-hold above which a region of the image will be detected as having "meaningful changes". In order to do that, we apply a recently introduced method yielding accurate false alarm rates for each detection. We show that this method permits to help significantly photo-interprets in their search for major changes in a scene. This will be illustrated by a striking application, the detection of the explosion of the AZF chemical plant in Toulouse (France) in September 2001.

UR - https://www.scopus.com/pages/publications/0345097428

U2 - 10.1109/ICIP.2003.1247119

DO - 10.1109/ICIP.2003.1247119

M3 - Conference paper (refereed)

AN - SCOPUS:0345097428

SN - 0780377508

VL - 1

T3 - IEEE International Conference on Image Processing

SP - 941

EP - 944

BT - Proceedings: 2003 International Conference on Image Processing

PB - IEEE

T2 - 2003 International Conference on Image Processing

Y2 - 14 September 2003 through 17 September 2003

ER -

Detection of major changes in satellite images

Abstract

Publication series

Conference

Bibliographical note

Funding

Access to Document

Other files and links

Fingerprint

Cite this