Signal and Image Center

Brussels, Belgium

Signal and Image Center

Brussels, Belgium
SEARCH FILTERS
Time filter
Source Type

Lopez J.-F.,Signal and Image Center | Shimoni M.,Signal and Image Center | Grippa T.,Analyse Geospatiale ANAGEO
2017 Joint Urban Remote Sensing Event, JURSE 2017 | Year: 2017

This research assesses the use of SENTINEL-1 SAR data for the extraction of human settlements and the morphological analysis of African cities. Textural features from single polarization amplitude image and dual polarization decomposition products were extracted for this assessment and compared to urban morphological map. The results show that SENTINEL-1 textural features may be useful in the separation between different African types of cities while the dual polarization decomposition products are more useful for inner-urban analysis. © 2017 IEEE.


Moser G.,University of Genoa | Tuia D.,University of Zürich | Shimoni M.,Signal and Image Center
IEEE Geoscience and Remote Sensing Magazine | Year: 2015

The 2015 Data Fusion Contest, organized by the Image Analysis and Data Fusion Technical Committee (IADF TC) of the IEEE Geoscience and Remote Sensing Society (GRSS), aims at providing a challenging image analysis opportunity, including multiresolution and multisensor fusion at extremely high resolution. The 2015 Contest involves two datasets acquired simultaneously by passive and active sensors. The passive data is a 5cm-resolution color ortho-photo acquired in the visible wavelength range. The active data source is a 65 pts/m2 LiDAR 3D point cloud that is provided both as raw 3D coordinates (ASCII format) and as a Digital Surface Model (DSM) with a point spacing of about 10 cm. The laser scan rate, angle, and frequency were 125 Hz, 20°, and 49 Hz, respectively. The LiDAR data include the first, last and one intermediate return. © 2013 IEEE.


Shimoni M.,Signal and Image Center | Lopez J.,Signal and Image Center | Forget Y.,Biological Control and Spatial Ecology LUBIES | Wolff E.,Analyse Geospatiale ANAGEO | And 4 more authors.
International Geoscience and Remote Sensing Symposium (IGARSS) | Year: 2015

The forecast of human population distribution in Africa is limited by the lack of spatial urban expansion model and the quality of its data sources. One way to overcome this shortcoming is to integrate multi-source and multi-temporal data for improving the delineation and the characterization of human settlements. This paper presents a fully automatic fusion processing scheme of multi-temporal SAR and optical data for improving the segmentation of African urban areas. © 2015 IEEE.


Shimoni M.,Signal and Image Center | Tolt G.,Swedish Defence Research Agency | Perneel C.,Royal Military Academy | Ahlberg J.,Swedish Defence Research Agency
International Geoscience and Remote Sensing Symposium (IGARSS) | Year: 2011

In an effort to overcome the limitations of small target detection in complex urban scene, complementary data sets are combined to provide additional insight about a particular scene. This paper presents a method based on shape/spectral integration (SSI) decision level fusion algorithm to improve the detection of vehicles in semi and deep shadow areas. A four steps process combines high resolution LIDAR and hyperspectral data to classify shadow areas, segment vehicles in LIDAR data, detect spectral anomalies and improves vehicle detection. The SSI decision level fusion algorithm was shown to outperform detection using a single data set and the utility of shape information was shown to be a way to enhance spectral target detection in complex urban scenes. © 2011 IEEE.


Tolt G.,Swedish Defence Research Agency | Shimoni M.,Signal and Image Center | Ahlberg J.,Swedish Defence Research Agency
International Geoscience and Remote Sensing Symposium (IGARSS) | Year: 2011

In this paper, a shadow detection method combining hyperspectral and LIDAR data analysis is presented. First, a rough shadow image is computed through line-of-sight analysis on a Digital Surface Model (DSM), using an estimate of the position of the sun at the time of image acquisition. Then, large shadow and non-shadow areas in that image are detected and used for training a supervised classifier (a Support Vector Machine, SVM) that classifies every pixel in the hyperspectral image as shadow or non-shadow. Finally, small holes are filled through image morphological analysis. The method was tested on data including a 24 band hyperspectral image in the VIS/NIR domain (50 cm spatial resolution) and a DSM of 25 cm resolution. The results were in good accordance with visual interpretation. As the line-of-sight analysis step is only used for training, geometric mismatches (about 2 m) between LIDAR and hyperspectral data did not affect the results significantly, nor did uncertainties regarding the position of the sun. © 2011 IEEE.


Shimoni M.,Signal and Image Center | Haelterman R.,Royal Military Academy | Perneel C.,Royal Military Academy
International Geoscience and Remote Sensing Symposium (IGARSS) | Year: 2013

Thermal hyperspectral imaging (THI) extends the activities of automatic spectral based target detection to the thermal infrared spectral range. This imaging technique which allows the detection of targets regardless of illumination, unfortunately, frequently suffers from high false alarm rates due to the high noise contained in the image. This study develops a new Normalised Difference Thermal Index NDTIMM which allows the physics -based segmentation of Man-Made objects in the scene. This index produces quick and efficient separation of man-made objects containing silicate minerals from other natural and man-made materials. The change detectors are spatially adapted to segments which present different NDTIMM ratios. As a result, the scene is enhanced and the performances of change detection methods which are based on NDTIMM segments distance are significantly improved. © 2013 IEEE.


Shimoni M.,Signal and Image Center | Perneel C.,Royal Military Academy
International Geoscience and Remote Sensing Symposium (IGARSS) | Year: 2012

The results present in this paper, show the improvement of 15%-17% in the accuracy for most of the classes while applying SEM-S method. © 2012 IEEE.


Shimoni M.,Signal and Image Center | Heremans R.,Signal and Image Center | Perneel C.,Royal Military Academy
International Geoscience and Remote Sensing Symposium (IGARSS) | Year: 2010

Based on the results presented in this paper, the following conclusions can be drawn: • QCE Change detection based clustering method improves the detection with respect to the CE method; • Bi-direction clustering method was found to be a good change detection method for TIR hyperspectral; • Clustering based methods demonstrated an improvement in change detection when applied using the WDS method on combined wavelengths data sets with respect to the single-wavelength hyperspectral data set. © 2010 IEEE.


Shimoni M.,Signal and Image Center | Perneel C.,Royal Military Academy | Gagnon J.-P.,Telops Inc.
2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2010 - Workshop Program | Year: 2010

Automatic detection of occluded targets from a sequence of images is an interesting area of research for defense related application. In this paper, change detection methods are investigated for the detection of buried improvised explosive devices (IED) using temporal thermal hyperspectral scenes. Specifically, the paper assesses the detection of buried small aluminium plates using the TELOPS Hyper-Cam sensor and by applying two change detection algorithms: multivariate statistical based method (Cross-Covariance (CC)) and class-conditional change detector (QCC). It was found that spectral based change detection is a good method for the detection of buried IED under disturbed soil. Moreover, the Cross-Covariance (CC)) and the class-conditional (QCC) change detector were able to detect changes using short temporal sequences as long temporal sequences pairs. ©2010 IEEE.


Closson D.,Signal and Image Center | Karaki N.A.,University of Jordan | Milisavljevic N.,Signal and Image Center | Hallot F.,Signal and Image Center | Acheroy M.,Signal and Image Center
Geodinamica Acta | Year: 2010

This paper discusses the interpretation of ground motions detected in the dried up Lynch Strait, Dead Sea area, by applying radar interferometric techniques to ALOS Falsar Synthetic Aperture Radar images. Four ALOS scenes spanning from. December 15, 2007 to May 17, 2008 have been processed leading to the generation of five interferograms. Three ground deformation zones have been detected. One of them shows surface displacement which could be related to an earthquake (ML 3.1) that took place on April. 13, 2008. High rates of subsidence have been measured in the northern Lynch Strait. They suggest that these subsidence phenomena follow the same trend of rapid, increase as sinkholes. Additional measurements should be earned out in order to refine this observation. The comparison between sinkholes' distributions in the Lynch Strait with that of Ghor Al Haditha, six kilometers eastward, supports the idea that the earthquake that hit the southern Dead Sea on April 23, 1979 (M 5.1) reactivated faults and fractures in the Lynch Strait triggering the development of sinkholes and subsidence in the frame of the Dead Sea recession. © 2010 Lavoisier SAS. All rights reserved.

Loading Signal and Image Center collaborators
Loading Signal and Image Center collaborators