Fusion of sensor data, knowledge sources and algorithms for extraction and classification of topographic objects

baltsavias, emmanuel p.

Bibliographic data

Monograph

Persistent identifier:: 856473650

Author:: Baltsavias, Emmanuel P.

Title:: Fusion of sensor data, knowledge sources and algorithms for extraction and classification of topographic objects

Sub title:: Joint ISPRS/EARSeL Workshop ; 3 - 4 June 1999, Valladolid, Spain

Scope:: III, 209 Seiten

Year of publication:: 1999

Place of publication:: Coventry

Publisher of the original:: RICS Books

Identifier (digital):: 856473650

Illustration:: Illustrationen, Diagramme, Karten

Language:: English

Usage licence:: Attribution 4.0 International (CC BY 4.0)

Publisher of the digital copy:: Technische Informationsbibliothek Hannover

Place of publication of the digital copy:: Hannover

Year of publication of the original:: 2016

Document type:: Monograph

Collection:: Earth sciences

Chapter

Title:: TECHNICAL SESSION 1 OVERVIEW OF IMAGE / DATA / INFORMATION FUSION AND INTEGRATION

Document type:: Monograph

Structure type:: Chapter

Chapter

Title:: DEFINITIONS AND TERMS OF REFERENCE IN DATA FUSION. L. Wald

Document type:: Monograph

Structure type:: Chapter

International Archives of Photogrammetry and Remote Sensing, Vol. 32, Part 7-4-3 W6, Valladolid, Spain, 3-4 June, 1999 Int 2 DEFINITIONS AND TERMS OF REFERENCE IN DATA FUSION L. Wald Groupe Télédétection & Modélisation, Ecole des Mines de Paris, BP 207, 06904 Sophia Antipolis cedex, France, lucien. ■wald @ cenerg .cma.fr KEYWORDS: Remote sensing, concept, alignment of information. ABSTRACT The concept of data fusion is easy to understand. However its exact meaning varies from one scientist to another. A working group, set up by the European Association of Remote Sensing Laboratories (EARSeL) and the French Society for Electricity and Electronics (SEE, French affiliate of the IEEE), devoted most of its efforts to establish a lexicon or terms of reference, which is presented in this communication. A new definition of the data fusion is proposed which better fits the remote sensing domain. Data fusion should be seen as a framework, not merely as a collection of tools and means. This definition emphasizes the concepts and the fundamentals in remote sensing. The establishment of a lexicon or terms of reference allows the scientific community to express the same ideas using the same words, and also to disseminate their knowledge towards the industry and 'customers' communities. Moreover it is a sine qua non condition to set up clearly the concept of data fusion and the associated formal framework. Such a framework is mandatory for a better understanding of data fusion fundamentals and of its properties. It allows a better description and formalization of the potentials of synergy between the remote sensing data, and accordingly, a better exploitation of these data. Finally, the introduction of the concept of data fusion into the remote sensing domain should raise the awareness of our colleagues on the whole chain ranging from the sensor to the decision, including the management, assessment and control of the quality of the information. The problem of alignment of the information to be fused is very difficult to tackle. It is a pre-requisite to any fusion process and should be considered with great care. 1. THE NEED FOR CONCEPT AND TERMS OF REFERENCE The concept of data fusion is easy to understand. However its exact meaning varies from one scientist to another. Several words have appeared, such as merging, combination, synergy, integration, etc. All of them appeal more or less to the same concept but are however felt differently. Several times, the word « fusion » is used while « classification » would be more appropriate, given the contents of the publication. There is a need for terms of reference in the remote sensing community, which has been strongly expressed in several meetings. A working group, set up by the European Association of Remote Sensing Laboratories (EARSeL) and the French Society for Electricity and Electronics (SEE, French affiliate of the IEEE), devoted most of its efforts to establish a lexicon or terms of reference, which is presented in this article. This is not the only attempt to set up definitions in data fusion. The remote sensing community should not establish terms which are also used elsewhere with different meanings. Therefore, whenever possible, definitions were adopted which are already widely used in the broad scientific community, especially that dealing with information. Examples of such terms are image, features, symbols, etc. Several lexicons have been already set up which have been established in the framework of the Defence domain (e.g., US Department of Defence, 1991, DSTO, 1994). It was found that it is not easy to translate military terms in meaningful words for the scientific community dealing with Earth observation: this would imply a refinement of the military terms to expand their meaning, with a reference to the time-space scales. It was concluded that using an existing lexicon is not straightforward, and that a new one is required to tackle the specific needs of our community. However, we should benefit from this previous work as much as possible, and, whenever possible, we should use the terms already adopted. 2. A DEFINITION OF DATA FUSION Data fusion means a very wide domain and it is very difficult to provide a precise definition. This large domain cannot be simply defined by restricting it, for example, to specific wavelengths, or specific acquisition means, or specific applications. A fusion process may call upon so many different mathematical tools that it is also impossible to define fusion by these tools. Several definitions can be found in the literature: Hall, Llinas (1997), Klein (1993), Li et al. (1993), Mangolini (1994), Pohl and van Genderen (1998), US Department of Defence (1991). They have been discussed by Wald (1998c, 1999). It was felt that most of these definitions were focusing too much on methods, though paying some attention to quality. As a whole, there is no reference to concept in these definitions, while the need fc scientisi It is oft fusion: 1998; ( van Ge "pixel" informa or «-dii would t though experiei propose mislead fusion p levels. 1 and fus: In Eart (attribui help in provide are mea of a fus: a mixed the cas résolut! better ri bands ( to simu having measure The for allows < to be si presente sensing A searc followii be resti neither should architec concept Buchroi definitie formal : the allia obtainir ‘greater la fusic s’exprir donnée: d’inf on « plus g

Access restriction

Copyright

fullscreen: Fusion of sensor data, knowledge sources and algorithms for extraction and classification of topographic objects

Monograph

Chapter

Chapter

Table of contents

Cite and reuse

Monograph

Chapter

Image

Image fragment

Citation links

Citation recommendation