High-spectral-resolution hyperspectral data are acquired by sensors that gather images from hundreds of narrow and contiguous bands of the electromagnetic spectrum. These data offer unique opportunities for characterization and precise land surface recognition in urban areas. So far, few studies have been conducted with these data to automatically detect and estimate areas of photovoltaic panels, which currently constitute an important part of renewable energy systems in urban areas of developed countries. In this paper, two hyperspectral-unmixing-based methods are proposed to detect and to estimate surfaces of photovoltaic panels. These approaches, related to linear spectral unmixing (LSU) techniques, are based on new nonnegative matrix factorization (NMF) algorithms that exploit known panel spectra, which makes them partial NMF methods. The first approach, called Grd-Part-NMF, is a gradient-based method, whereas the second one, called Multi-Part-NMF, uses multiplicative update rules. To evaluate the performance of these approaches, experiments are conducted on realistic synthetic and real airborne hyperspectral data acquired over an urban region. For the synthetic data, obtained results show that the proposed methods yield much better overall performance than NMF-unmixing-based methods from the literature. For the real data, the obtained detection and area estimation results are first confirmed by using very high-spatial-resolution ortho-images of the same regions. These results are also compared with those obtained by standard NMF-unmixing-based methods and by a one-class-classification-based approach. This comparison shows that the proposed approaches are superior to those considered from the literature.
Land use and land cover (LULC) mapping is often undertaken by national mapping agencies, where these LULC products are used for different types of monitoring and reporting applications. Updating of LULC databases is often done on a multi-year cycle due to the high costs involved, so changes are only detected when mapping exercises are repeated. Consequently, the information on LULC can quickly become outdated and hence may be incorrect in some areas. In the current era of big data and Earth observation, change detection algorithms can be used to identify changes in urban areas, which can then be used to automatically update LULC databases on a more continuous basis. However, the change detection algorithm must be validated before the changes can be committed to authoritative databases such as those produced by national mapping agencies. This paper outlines a change detection algorithm for identifying construction sites, which represent ongoing changes in LU, developed in the framework of the LandSense project. We then use volunteered geographic information (VGI) captured through the use of mapathons from a range of different groups of contributors to validate these changes. In total, 105 contributors were involved in the mapathons, producing a total of 2778 observations. The 105 contributors were grouped according to six different user-profiles and were analyzed to understand the impact of the experience of the users on the accuracy assessment. Overall, the results show that the change detection algorithm is able to identify changes in residential land use to an adequate level of accuracy (85%) but changes in infrastructure and industrial sites had lower accuracies (57% and 75 %, respectively), requiring further improvements. In terms of user profiles, the experts in LULC from local authorities, researchers in LULC at the French national mapping agency (IGN), and first-year students with a basic knowledge of geographic information systems had the highest overall accuracies (86.2%, 93.2%, and 85.2%, respectively). Differences in how the users approach the task also emerged, e.g., local authorities used knowledge and context to try to identify types of change while those with no knowledge of LULC (i.e., normal citizens) were quicker to choose ‘Unknown’ when the visual interpretation of a class was more difficult.
A cartography of vineyards is required by many mapping agencies, both to draw topographic maps and to complete the "vineyard" layer of large scale land cover databases. In this paper, two distinct approaches are proposed and tested to achieve a (semi-)automatic detection of vineyards task out of 50cm ground resolution ortho-images. Both are object based approaches relying on image texture analysis in homogeneous land cover regions. Therefore, the first step (common to both approaches) is a segmentation of the image into homogeneous land cover regions. These regions can then be classified as vineyards or not by the next approaches. A first approach consists in a frequency analysis of the image texture in each region. A semi-variogram is first calculated from the ortho-image for each region of the segmentation. A Fourier transform (FFT) of this semi-variogram of the image is then considered. If a periodic signal with a high frequency (i.e. of which the frequency is upper than a threshold) is identified, the region is labelled as a vineyard. The second approach is a supervised (per region) land cover classification one. It uses texture indexes calculated from ortho-images as input image information. In particular, some texture indexes derived from SIFT descriptors calculated from ortho-images have been used in the experiments, giving good results.
6 June 2016 in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
An energetical approach is proposed for classification decision fusion in urban areas using multispectral and hyperspectral imagery at distinct spatial resolutions. Hyperspectral data provides a great ability to discriminate land-cover classes while multispectral data, usually at higher spatial resolution, makes possible a more accurate spatial delineation of the classes. Hence, the aim here is to achieve the most accurate classification maps by taking advantage of both data sources at the decision level: spectral properties of the hyperspectral data and the geometrical resolution of multispectral images. More specifically, the proposed method takes into account probability class membership maps in order to improve the classification fusion process. Such probability maps are available using standard classification techniques such as Random Forests or Support Vector Machines. Classification probability maps are integrated into an energy framework where minimization of a given energy leads to better classification maps. The energy is minimized using a graph-cut method called quadratic pseudo-boolean optimization (QPBO) with α-expansion. A first model is proposed that gives satisfactory results in terms of classification results and visual interpretation. This model is compared to a standard Potts models adapted to the considered problem. Finally, the model is enhanced by integrating the spatial contrast observed in the data source of higher spatial resolution (i.e., the multispectral image). Obtained results using the proposed energetical decision fusion process are shown on two urban multispectral/hyperspectral datasets. 2-3% improvement is noticed with respect to a Potts formulation and 3-8% compared to a single hyperspectral-based classification.
26 April 2013 in The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Keywords: Image classification, Land cover extraction, Data fusion, Change detection, Satellite, DSM Submetric satellite imagery (Pleiades, GeoEye) offers advantages for map update purposes, e.g. an interesting ground resolution, a good reactivity and the ability to capture wide areas. Experiments on the use of such stereoscopic images for 2D change detection among building objects of GIS topographic database are presented in this paper. Two approaches have been tested. The first one extracts land cover from satellite ortho-images and additional information (correlation DSM-DTM, database) and compares building objects of this classification to those of the database. The second one creates a pseudo-DSM from height information of database building objects combined with a DTM and compares it to a correlation DSM computed from satellite images. Obtained results are quite encouraging even if the correctness rate remains too low for an operational use.