Full text: Papers accepted on the basis of peer-reviewed abstracts (Part B)

In: Wagner W., Székely, B. (eds.): ISPRS TC VII Symposium - 100 Years ISPRS, Vienna, Austria, July 5-7, 2010, IAPRS, Vol. XXXVIII, Part 7B 
389 
a Royal Military Academy -RMA, Department of Communication and Information Systems & Sensors - CISS, 
Rue Hobbema 8, 1000, Brussels, Belgium - (nada, dclosson)@elec.rma.ac.be 
b Télécom Paris Tech, CNRS LTCI, 46 rue Barrault, 75013, Paris, France - isabelle.bloch@telecom-paristech.ff 
The technique of coherent change detection in repeat-pass Synthetic Aperture Radar imagery has the potential to detect very subtle 
scene changes such as changes in man-made targets or potential human activities. In this paper, we propose a simple method for 
detecting temporal changes in a scene possibly caused by human activities, such as building up areas of hard surface on a terrain that 
was previously a part of a desert. This method is based on comparison of coherence change detection results obtained in successive 
time frames. In order to cover a wide range of applications and situations, the proposed method is intentionally designed so that it 
does not need any specific knowledge source about the terrain. However, once coherent change detection results are obtained, 
various knowledge sources can be taken into account in order to improve the final interpretation. These knowledge sources can be 
related to the sensors, such as their operational principles, or to the situation at hand, referring to the context - terrain type, land-use, 
historical background etc. A way to include them in the reasoning process is discussed here too. In addition, in order to further 
improve the quality of the obtained output, usefulness of applying a spatial regularization technique is tested as well. The method is 
illustrated and validated using ALOS PALSAR multi-temporal data related to a real situation - works performed in building up 
additional runways of an airport. The results are in concordance with the ground-truth information, showing that the presented 
method is promising. 
nous proposons une méthode simple pour détecter les changements temporels dans une scène qui ont pu être causés par les activités 
humaines, telles que la construction de zones de surface dure sur un terrain qui était auparavant un désert. Cette méthode repose sur 
la détection des changements obtenus à partir d’images de cohérence successives. Afin de couvrir un large éventail d'applications et 
de situations, la méthode proposée est volontairement conçue de sorte qu'elle n'ait besoin d'aucune source de connaissances 
connaissances diverses peuvent être prises en compte, si elles sont disponibles, afin d'améliorer l'interprétation finale. Ces sources de 
connaissances peuvent concerner les capteurs et leurs principes de fonctionnement, ou la situation observée et son contexte - type de 
terrain, utilisation des terres, contexte historique ... Nous discutons de la manière d'inclure de telles informations dans le processus 
DETECTING HUMAN-INDUCED SCENE CHANGES USING 
COHERENT CHANGE DETECTION IN SAR IMAGES 
N. Milisavljevié a ’ *, D. Closson a , I. Bloch b 
Technical Commission VII Symposium 2010 
KEY WORDS: Land Use, Change Detection, Combination, SAR, Scene, Temporal 
ABSTRACT: 
RÉSUMÉ: 
La technique de détection de changements cohérents en imagerie radar à ouverture synthétique permet de détecter des changements 
fins dans la scène observe, comme les objets artificiels et les activités humaines, au cours de passages successifs. Dans cet article, 
spécifiques sur le terrain. Cependant, une fois que des résultats de détection des changements cohérents sont obtenus, les sources de 
de raisonnement. Enfin la qualité du résultat peut être encore améliorée par une régularisation spatiale. La méthode est illustrée et 
validée à l'aide de données multi-temporelles ALOS PALSAR correspondant à une situation réelle - travaux effectués pour la 
construction de pistes supplémentaires d'un aéroport. Les résultats sont en accord avec la vérité terrain, et montrent que la méthode 
présentée est prometteuse. 
1. INTRODUCTION 
such two images acquired at different times (Scheuchl, Ullmann 
and Koudogbo, 2009). 
Change detection is an application for which Synthetic Aperture 
Radar (SAR) is particularly well suited as this type of sensors 
can consistently produce high-quality well-calibrated imagery 
with good geo-location accuracy (Price and Stacy, 2006). Two 
forms of change detection in repeat-pass SAR imagery may be 
considered, namely coherent and incoherent change detection 
(Price and Stacy, 2006). While incoherent methods compare the 
backscatter of two images acquired using the same imaging 
parameters, coherent methods exploit the coherence between 
Detection of temporal changes in an area of interest using 
coherent change detection (CCD) in repeat-pass (SAR) imagery 
(Touzi et al., 1999) is presented in this paper, as a follow-up of 
the method introduced in (Milisavljevic, Closson and Bloch, 
2010). The CCD technique has the potential to detect subtle 
scene changes (Price and Stacy, 2006), e.g. changes in man 
made targets (Wright et al., 2005) or potential human activities. 
Nevertheless, urban areas represent a potential problem (Fanelli 
et al., 2000; Matikainen, Hyyppa and Engdahl, 2006) for the 
* 
Corresponding author.
	        
Waiting...

Note to user

Dear user,

In response to current developments in the web technology used by the Goobi viewer, the software no longer supports your browser.

Please use one of the following browsers to display this page correctly.

Thank you.