In: Wagner W., Székely, B. (eds.): ISPRS TC VII Symposium - 100 Years ISPRS, Vienna, Austria, July 5-7, 2010, IAPRS, Vol. XXXVIII, Part 7B 
213 
TARGETED CHANGE DETECTION: 
A NOVEL SENSOR-INDEPENDENT PARTIALLY-SUPERVISED APPROACH 
D. Femandez-Prieto a , M. Marconcini a ’ * 
a Dept, of Earth Observation Science, Applications and Future Technologies, European Space Agency, ESA-ESRIN, 
Via Galileo Galilei, 00044, Frascati, Rome, Italy - (diego.femandez, mattia.marconcini)@esa.int 
KEY WORDS: Change Detection, Land Cover, Satellite, Multitemporal, Multispectral, Hyperspectral 
ABSTRACT: 
In several real-world applications (e.g., forestry, agriculture), the objective of change detection is actually limited to one (or few) 
specific “targeted” land-cover transition(s) affecting a certain area in a given time period. In such cases, ground-truth information is 
generally available for the only land-cover classes of interest at the two dates, which limits (or hinders) the possibility of success 
fully employing standard supervised approaches. Moreover, even unsupervised change-detection methods cannot be effectively 
used, as they allow identifying all the areas experiencing any type of change, but not discriminating where specific land-cover tran 
sitions of interest occur. In this paper, we present a novel technique capable of addressing this challenging issue (formulated in terms 
of a compound decision problem) by exploiting the only ground truth available for the targeted land-cover classes at the two dates. 
In particular, the proposed method relies on a partially-supervised approach and jointly exploits the Expectation-Maximization (EM) 
algorithm and an iterative labelling strategy based on Markov random fields (MRF) accounting for spatial and temporal correlation 
between the two images. Moreover, it also allows handling images acquired by different sensors at the two investigated times. Ex 
perimental results on different multi-temporal and multi-sensor data sets confirmed the effectiveness and the reliability of the pro 
posed technique, which provided change-detection accuracies comparable with those obtained by fully-supervised methods. 
1. INTRODUCTION 
Detecting changes occurring on the Earth’s surface represents 
one of the main applications of satellite remote sensing. Indeed, 
in a variety of different fields and applications (e.g., urban 
planning, forestry, agriculture, disaster management, etc.) the 
employment of multi-temporal satellite data has become essen 
tial for identifying where and (when possible) which types of 
transitions have occurred between two given dates (Jensen, 
2009). 
Generally, change-detection methods are categorized as either 
supervised or unsupervised, depending on the availability of 
suitable prior information (Coppin et al., 2004; Duda et al., 
2000; Lu et al., 2004; Radke et al., 2005; Singh, 1989). 
When an exhaustive multi-temporal ground truth characterizing 
all the land-cover classes over the area of interest at both times 
is available, then, supervised approaches can be applied. These 
types of techniques are generally robust and effective, and al 
low identifying all the land-cover transitions occurred between 
the two considered dates. In this framework, three main ap 
proaches are generally employed: post-classification compari 
son (PCC), supervised direct multi-data classification (DMC) 
and compound classification (Duda et al., 2000; Lu et al., 2004; 
Singh, 1989). 
When no ground truth is available, instead, unsupervised tech 
niques must be used, which allow detecting areas experiencing 
changes (being even capable of separating land-cover transi 
tions of different nature and characterizing their distribution), 
but are unable to provide information on the specific type of 
changes occurred. Several unsupervised change-detection tech 
niques have been presented so far in the literature. Most of them 
are based on image differencing, image ratioing, image regres 
sion, change vector analysis (CVA) and principal component 
analysis (PCA), which all require the selection of proper thresh 
olds for determining changed regions (Coppin et al., 2004; Lu 
et al., 2004; Radke et al., 2005). 
It is worth noting that, in the above described framework, su 
pervised methods represent an ideal approach to change- 
detection analysis, since they permit both to identify areas ex 
periencing changes, as well as to reliably determine the associ 
ated land-cover transitions. Nevertheless, their range of appli 
cability is significantly limited by the difficulties in gathering 
exhaustive and accurate ground-truth information for all the 
land-cover classes characterizing each date under analysis. In 
deed, such a requirement is costly, time consuming and not 
always possible or feasible to satisfy. 
However, in several operational change-detection problems the 
main objective is not to characterize all the land-cover transi 
tions occurred in the investigated area, but rather to identify a 
single (or few) targeted land-cover transition(s) of interest. This 
is typical for instance in agriculture, urban planning, or forestry 
applications. In such circumstances, when only one (or few) 
specific land-cover transitions need to be identified, it is rea 
sonable to assume that the collection of ground-truth informa 
tion associated with the only (or few) land-cover class(es) of 
interest at the two considered dates is highly simplified. How 
ever, under this assumption, neither supervised nor unsuper 
vised change-detection techniques can be effectively employed. 
Let us consider for instance the case of two images acquired 
over the same area at different times U and h , where the objec 
tive is to identify all the patterns experiencing the targeted land- 
cover transitions from class “A” (e.g., forest) to “B” (e.g., urban 
area) under the hypothesis that a ground truth for class “A” at 
U and for class “B” at h is available (or can be easily retrieved 
by an operator), respectively. In this context, on the one hand, 
supervised techniques cannot be used, since the lack of an ex 
haustive ground truth characterizing all the land-cover classes at 
the two dates under consideration will not allow a successful 
training of the classifiers. On the other hand, unsupervised 
techniques may allow identifying all the areas experiencing any 
type of change, but not discriminating where specific targeted 
land-cover transitions of interest occur. In this latter case, a 
comparison (e.g., trough a significance-testing approach (Jeon 
and Landgrebe, 1999)) of the labelled samples available for the