Lionel Valet

Combining Airborne Photographs and Spaceborne SAR Data to Monitor Temperate Glaciers: Potentials and Limits

Monitoring temperate glacier activity has become more and more necessary for economical and security reasons and as an indicator of the local effects of global climate change. Remote sensing data provide useful information on such complex geophysical objects, but they require specific processing techniques to cope with the difficult context of moving and changing features in high-relief areas. This paper presents the first results of a project involving four laboratories developing and combining specific methods to extract information from optical and synthetic aperture radar (SAR) data. Two different information sources are processed, namely: 1) airborne photography and 2) spaceborne C-band SAR interferometry. The difficulties and limitations of their processing in the context of Alpine glaciers are discussed and illustrated on two glaciers located in the Mont-Blanc area. The results obtained by aerial triangulation techniques provide digital terrain models with an accuracy that is better than 30 cm, which is compatible with the computation of volume balance and useful for precise georeferencing and slope measurement updating. The results obtained by SAR differential interferometry using European Remote Sensing Satellite images show that it is possible to measure temperate glacier surface velocity fields from October to April in one-day interferograms with approximately 20-m ground sampling. This allows to derive ice surface strain rate fields required to model the glacier flow. These different measurements are complementary to results obtained during the summer from satellite optical data and ground measurements that are available only in few accessible points

A statistical overview of recent literature in information fusion

The objective of this paper is to make a picture of the recent articles published on information fusion. Indeed, a great number of documents dealing with this technique are available in the literature. A classification scheme including application fields, fusion goals, fusion system architecture and mathematical tools is proposed. This overview of the last three years allows one to compute the article distribution in each class. Finally, some elements of a preliminary analysis of this classification are drawn.

Seismic image segmentation by fuzzy fusion of attributes

To know the subsoil organization, geophysicists try to interpret seismic images acquired by sending acoustic waves into the soil. This paper presents a method for the segmentation of these images in geological regions in order to help interpreters in their study. Information fusion of image attributes provides a solution to part of this complex problem. To realize aggregation, the fuzzy subset theory is an appropriate tool to code interpreter knowledge by a set of rules. The results obtained are promising and show the necessity to evaluate their quality more thoroughly.

An Attribute Fusion System Based on the Choquet Integral to Evaluate the Quality of Composite Parts

This paper presents an information fusion system based on the Choquet integral for the quality evaluation of composite material parts. The application deals with the detection of typical regions inside parts with the help of images. For this purpose, several attributes related to texture homogeneity and intensity gradient orientation are extracted from the X-ray images of composite material parts. These attributes are transformed into region detection degrees expressed under the form of similarity maps. To improve the detection of the typical regions, a fusion system based on the 2-additive Choquet integral is applied on the similarity maps to take the interactions between attributes into account. An unsupervised learning algorithm is used to estimate the Choquet integral parameters from the reference regions pointed out by experts. The results are compared to those obtained by a previous fusion approach based on the ldquoDecision Templatesrdquo.

Leaf Species Classification Based on a Botanical Shape Sub-classifier Strategy

Within the framework of a smartphone-based application, helping people to identify plant species in the wild, a sub-classifier strategy has been introduced. It aims at recognizing the botanical properties of a leaf, relatively to various global and local shape criteria used in flora books. A decision function is applied on these classified shape categories to produce a final decision on the species of the leaf. In this paper, the fusion strategy and its corresponding Random-Forest-based sub-classifiers are described. The results of these algorithms for botanical leaf shape recognition demonstrate that our classification algorithm can achieve good performance on leaf species identification while providing the user with relevant information for educational purposes.

Local versus global evaluation of a cooperative fusion system for 3D image interpretation

Information fusion approaches are more and more used in complex applications in which there is a real need to take into account several kinds of information simultaneously. Fusion systems become complex because they involve all the information treatment chain steps (from the extraction to the decision). A global evaluation of the fused result does not allow the end-users to adjust the numerous parameters and to efficiency interact with the system. This paper proposes a local approach to evaluate the mission completeness of each subpart of the fusion systems. For this, the main mission of each subpart needs to be well formulated and then, a mission achievement measurement will allow to quantify the performance of the subpart according to its objective and independently to the method used inside the subparts. The proposed measurement is based on an histograms comparison and the approach is then illustrated on a real cooperative fusion system devoted to 3D tomographic image interpretation.

Data fusion approach for change detection in multi-temporal ERS-SAR images

This paper presents a new method to detect changes in multi-temporal satellite SAR images. The proposed approach consists in an extraction step-specific change measures reveal the presence of changing features-followed by a fusion step where these measures and a priori information such as geographical map are merged to detect changes. The method is applied to the detection of deforested areas in tropical rain forest of French Guiana. Results obtained with SAR images from satellites ERS 1/2 are presented at two different scales: on a macroscopic scale for the detection of zones presenting a strong deforestation probability and on a microscopic scale for a segmentation of the main deforested parcels.

Sub-classification strategies for tree species recognition

In the context of tree species recognition, botanists knowledge was used in different works specially when recognising tree species through leaves. In this paper, two sub-classification strategies for tree species recognition are proposed. For each sub-classification strategy, Basic belief assignment (Bba) was determined and obtained data were fused thanks to a totally adaptive fusion system implemented in the general framework of belief functions.

Quality evaluation of insulating parts by fusion of classifiers issued from tomographic images

The industrial manufacturing of insulating parts must meet strict requirements in order to be used in disturbed environments. Experts know that the moulding process has an impact on the final product quality. However, the phenomenon is so complicated that the relation between the manufacturing process and the product quality is difficult to identify. Some non-destructive methods are nowadays used in the industry to obtain information from inside the parts. In this paper, 3D tomographic acquisitions are used in order to analyse the parts. From the huge set of data obtained, several attributes have been computed to characterize images. A fusion system based on the Decision Templates method is proposed in this paper. Adaptations of the initial method are proposed to be more effective for image segmentation. The fusion approach capabilities are analysed on real data in the context of insulating part analysis.

Choquet Integral Parameter Optimization for a Fusion System Devoted to Image Interpretation

Parameter adjustment of a fusion system for 3D image interpretation is often a difficult task that is emphasized by the non-understandability of the parameters by the end-users. Moreover, such fusion systems are complex because they involve a complete information treatment chain (from the information extraction to the decision). The sub-parts of the system concern also different scientific areas which add some additional difficulties. Some parameters cannot be easily set empirically and their adjustments are made by trials and errors. This paper studies an optimization of a generalized Choquet Integral parameters by means of genetic algorithms. Fuzzy measures are first learnt thanks to the reference data given by experts and then the best importance coefficients are searched around the initial ones. The approach is illustrated on a cooperative fusion system based on Choquet Integral and devoted to 3D image interpretation.