Matthieu Molinier

Detecting Man-Made Structures and Changes in Satellite Imagery With a Content-Based Information Retrieval System Built on Self-Organizing Maps

The increasing amount and resolution of satellite sensors demand new techniques for browsing remote sensing image archives. Content-based querying allows an efficient retrieval of images based on the information they contain, rather than their acquisition date or geographical extent. Self-organizing maps (SOMs) have been successfully applied in the PicSOM system to content-based image retrieval in databases of conventional images. In this paper, we investigate and extend the potential of PicSOM for the analysis of remote sensing data. We propose methods for detecting man-made structures, as well as supervised and unsupervised change detection, based on the same framework. In this paper, a database was artificially created by splitting each satellite image to be analyzed into small images. After training the PicSOM on this imagelet database, both interactive and off-line queries were made to detect man-made structures, as well as changes between two very high resolution images from different years. Experimental results were both evaluated quantitatively and discussed qualitatively, and suggest that this new approach is suitable for analyzing very high resolution optical satellite imagery. Possible applications of this work include interactive detection of man-made structures or supervised monitoring of sensitive sites

Polarimetric SAR Data in Land Cover Mapping in Boreal Zone

This paper compares ALOS PALSAR fully polarimetric and dual-polarized data in the application area of land cover mapping. To assure versatile comparison of the data, different classification methods and different features of data are used. Two of the classification methods used are based on supervised classification and two on unsupervised classification. Polarimetric data are used in three ways: (1) as fully polarimetric data; (2) features calculated from fully polarimetric data; and (3) intensity data of selected channels. Combinations of six (water, field, sparse forest, dense forest, peat land, and urban areas), five, four, and three classes were used for classification. Fully polarimetric data gave better results (87.5%-84.7% with three classes; open land areas, forest, and water) than intensity data only (83.6%-78.6%), but the differences in the overall accuracies between the methods were not more than 7.6%. Kappa coefficients of agreement are moderate for all the classifications. Supervised classification can be expected to perform better than unsupervised classification, given that the training areas can be selected accurately. Dual polarization data were found to be an attractive alternative in cases where fully polarimetric data are not available or it is of low resolution. With intensities of selected polarimetric features, it was possible to obtain a high classification accuracy as with fully polarimetric data. This also opens possibilities for nonspecialist users to benefit from polarimetric information in classification.

Ortho-rectification and terrain correction of polarimetric SAR data applied in the ALOS/Palsar context

Methods for terrain correction of polarimetric SAR data were studied and developed. Ortho-rectification resampling and amplitude correction utilized Stokes matrix data. The Stokes matrix of thermal noise was subtracted before amplitude normalization. Application of an azimuth-slope correction algorithm resulted in slightly narrower distribution of orientation angles compared to input data.

Relasphone—Mobile and Participative In Situ Forest Biomass Measurements Supporting Satellite Image Mapping

Due to the high cost of traditional forest plot measurements, the availability of up-to-date in situ forest inventory data has been a bottleneck for remote sensing image analysis in support of the important global forest biomass mapping. Capitalizing on the proliferation of smartphones, citizen science is a promising approach to increase spatial and temporal coverages of in situ forest observations in a cost-effective way. Digital cameras can be used as a relascope device to measure basal area, a forest density variable that is closely related to biomass. In this paper, we present the Relasphone mobile application with extensive accuracy assessment in two mixed forest sites from different biomes. Basal area measurements in Finland (boreal zone) were in good agreement with reference forest inventory plot data on pine ( R 2 = 0 . 75 , R M S E = 5 . 33 m 2 /ha), spruce ( R 2 = 0 . 75 , R M S E = 6 . 73 m 2 /ha) and birch ( R 2 = 0 . 71 , R M S E = 4 . 98 m 2 /ha), with total relative R M S E ( % ) = 29 . 66 % . In Durango, Mexico (temperate zone), Relasphone stem volume measurements were best for pine ( R 2 = 0 . 88 , R M S E = 32 . 46 m 3 /ha) and total stem volume ( R 2 = 0 . 87 , R M S E = 35 . 21 m 3 /ha). Relasphone data were then successfully utilized as the only reference data in combination with optical satellite images to produce biomass maps. The Relasphone concept has been validated for future use by citizens in other locations.

Detecting changes in polarimetric SAR data with content-based image retrieval

In this study, we extended the potential of a Content- Based Image Retrieval (CBIR) system based on Self-Organizing Maps (SOMs), for the analysis of remote sensing data. A database was artificially created by splitting each image to be analyzed into small images (or imagelets). Content-based image retrieval was applied to fully polarimetric airborne SAR data, using a selection of polarimetric features. After training the system on this imagelet database, automatic queries could detect changes. Results were encouraging on airborne SAR data and may be more useful for spaceborne polarimetric data.

3D-Connected components analysis for traffic monitoring in image sequences acquired from a helicopter

The aim of the study was to develop methods for moving vehicle tracking in aerial image sequences taken over urban areas. The first image of the sequence was manually registered to a map. Corner points were extracted semi-automatically, then tracked along the sequence, to enable video stabilisation by homography estimation. Moving objects were detected by means of adaptive background subtraction. The vehicles were identified among many stabilisation artifacts and tracked, with a simple tracker based on spatiotemporal connected components analysis. While the techniques used were basic, the results turned out to be encouraging, and several improvements are under scrutiny.

Traffic monitoring and modeling for Intersection Safety

The INTERSAFE-2 project aims to develop and demonstrate a Cooperative Intersection Safety System that is able to significantly reduce injury and fatal accidents at intersections. The cooperative sensor data fusion is based on state-of-the-art and advanced on-board sensors for object recognition and relative localisation, a standard navigation map and information from other road users, infrastructure sensors and traffic lights. We created a traffic safety model for the INTERSAFE-2 system. The system incorporates a high level fusion module and local dynamic maps database that store static intersection topology. Furthermore, risk assessment from the infrastructure side has been performed in order to detect potentially dangerous situations, and to determine when the system should give a warning in order to prevent a possible collision. To evaluate the safety algorithm, video sequences of two intersections in Helsinki are used, which were processed with a generic tool for image processing and traffic monitoring.

Water quality analysis using an inexpensive device and a mobile phone

BackgroundWater transparency is one indicator of water quality. High water transparency is an indication of clean water. A common method for measuring water transparency is Secchi depth. In this paper, we present an approach to water quality (Secchi depth and turbidity) monitoring using mobile phones and a small device designed for water quality measurements.ResultsThe water quality parameters were analysed automatically from the images taken using mobile phone cameras. During the summer of 2012, we conducted a field trial in which 100 test users gathered 1,146 observations using the system. The results of the automatic Secchi3000 depth analysis were compared against reference measurements, and they indicate that our approach can be used for quantitative water quality measurements.ConclusionsResults show that overall the system performs well. Both Secchi depth and turbidity are estimated with excellent or good accuracy when the measurements are taken with care.

Comparison and evaluation of polarimetric change detection techniques in aerial SAR data

This article aims at providing a comparison of polarimetric change detection indices from a practical point of view. Six polarimetric change detection indices were tested on L band EMISAR data over Norway. Tests included quantitative evaluation of change maps compared to a ground truth of changes, and qualitative evaluation by visual inspection. Contrast ratio and the Wishart test gave the best results among the tested indices.

Binary patterns encoded convolutional neural networks for texture recognition and remote sensing scene classification

Abstract Designing discriminative powerful texture features robust to realistic imaging conditions is a challenging computer vision problem with many applications, including material recognition and analysis of satellite or aerial imagery. In the past, most texture description approaches were based on dense orderless statistical distribution of local features. However, most recent approaches to texture recognition and remote sensing scene classification are based on Convolutional Neural Networks (CNNs). The de facto practice when learning these CNN models is to use RGB patches as input with training performed on large amounts of labeled data (ImageNet). In this paper, we show that Local Binary Patterns (LBP) encoded CNN models, codenamed TEX-Nets, trained using mapped coded images with explicit LBP based texture information provide complementary information to the standard RGB deep models. Additionally, two deep architectures, namely early and late fusion, are investigated to combine the texture and color information. To the best of our knowledge, we are the first to investigate Binary Patterns encoded CNNs and different deep network fusion architectures for texture recognition and remote sensing scene classification. We perform comprehensive experiments on four texture recognition datasets and four remote sensing scene classification benchmarks: UC-Merced with 21 scene categories, WHU-RS19 with 19 scene classes, RSSCN7 with 7 categories and the recently introduced large scale aerial image dataset (AID) with 30 aerial scene types. We demonstrate that TEX-Nets provide complementary information to standard RGB deep model of the same network architecture. Our late fusion TEX-Net architecture always improves the overall performance compared to the standard RGB network on both recognition problems. Furthermore, our final combination leads to consistent improvement over the state-of-the-art for remote sensing scene classification.