International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Volume XXXIX-B7, 2012 
XXII ISPRS Congress, 25 August — 01 September 2012, Melbourne, Australia 
    
LAND COVER CLASSIFICATION OF MULTI-SENSOR IMAGES BY DECISION 
FUSION USING WEIGHTS OF EVIDENCE MODEL 
Peijun Li * and Bengin Song 
Institute of Remote Sensing and GIS, Peking University, Beijing 100871, P R China 
Emails: pjli@pku.edu.cn, sbq43031@126.com 
Commission VIL, WG VII/4 
KEY WORDS: weights of evidence, multi-sensor, land cover classification, decision fusion 
ABSTRACT: 
This paper proposed a novel method of decision fusion based on weights of evidence model (WOE). The probability rules from 
classification results from each separate dataset were fused using WOE to produce the posterior probability for each class. The final 
classification was obtained by maximum probability. The proposed method was evaluated in land cover classification using two 
examples. The results showed that the proposed method effectively combined multisensor data in land cover classification and 
obtained higher classification accuracy than the use of single source data. The weights of evidence model provides an effective 
decision fusion method for improved land cover classification using multi-sensor data. 
1. INTRODUCTION 
With the increasing availability of digital images acquired by 
different sensors, it is crucially important to effectively process 
and analyze these multisensor data sets in diverse applications, 
since these data provide complementary information for 
improved land cover mapping and monitoring. The development 
of new and effective image fusion methods has been one of the 
important topics in remote sensing information processing and 
applications. This study proposes a novel decision fusion method 
based on the weights of evidence model (Good, 1985; 
Spiegelhalter and Knill-Jones, 1983) to combine multi-sensor 
data for improved land cover classification. 
2. METHODS 
The proposed method can be summarized as follows. The land 
cover classification was first separately conducted on each 
dataset using a supervised classifier. The obtained classification 
results from different datasets were then fused using the weights 
of evidence model. 
2.1 Weight of evidence model 
The weights of evidence model is a data integration method. The 
model was originally developed for medical diagnosis based on 
presence or absence of a set of symptoms (Good, 1985; 
Spiegelhalter and Knill-Jones, 1983), and was subsequently 
adopted for mineral potential mapping (Bonham-Carter et al., 
1988, 1989). 
The weights of evidence method used in this study is derived 
from those used in medical diagnostics. Suppose that there are 
E.i=12,..0 
multiple source of evidence. Let , be the ith 
binary evidence which is related to the occurrence of a class, i.e. 
  
* Corresponding author. 
an event D. E and E denote the presence and absence of the 
evidence, respectively. The probability of the occurrence of a 
class in a location (pixel), given the presence and absence of the 
evidence E; can be given by the following conditional 
probabilities: 
P(DNE;) P(E, | D) 
PAR EN ( EY 
gj. PonE) | 5E 1D) 
A I EE], 
i 
(D 
These two equations can be also expressed in terms of the odd: 
(DE) - o0). 
olpiE)- otn 
: (2) 
Where O(D |E ;) and O(D | E 3 are ratio of the posterior 
probabilities of D given the absence and presence of the 
evidence E. : 
The weights for evidence E ; in a WOE model are calculated 
ran £1») 
P(E,|D) 
i Fl? |p) 
; P(E | D) "