Manuel Grizonnet

Stable Mean-Shift Algorithm and Its Application to the Segmentation of Arbitrarily Large Remote Sensing Images

Segmentation of real-world remote sensing images is challenging because of the large size of those data, particularly for very high resolution imagery. However, a lot of high-level remote sensing methods rely on segmentation at some point and are therefore difficult to assess at full image scale, for real remote sensing applications. In this paper, we define a new property called stability of segmentation algorithms and demonstrate that piece- or tile-wise computation of a stable segmentation algorithm can be achieved with identical results with respect to processing the whole image at once. We also derive a technique to empirically estimate the stability of a given segmentation algorithm and apply it to four different algorithms. Among those algorithms, the mean-shift algorithm is found to be quite unstable. We propose a modified version of this algorithm enforcing its stability and thus allowing for tile-wise computation with identical results. Finally, we present results of this method and discuss the various trends and applications.

Large-Scale Feature Selection With Gaussian Mixture Models for the Classification of High Dimensional Remote Sensing Images

A large-scale feature selection wrapper is discussed for the classification of high dimensional remote sensing. An efficient implementation is proposed based on intrinsic properties of Gaussian mixtures models and block matrix. The criterion function is split into two parts:one that is updated to test each feature and one that needs to be updated only once per feature selection. This split saved a lot of computation for each test. The algorithm is implemented in C++ and integrated into the Orfeo Toolbox. It has been compared to other classification algorithms on two high dimension remote sensing images. Results show that the approach provides good classification accuracies with low computation time.

A Scalable Tile-Based Framework for Region-Merging Segmentation

Processing large very high-resolution remote sensing images on resource-constrained devices is a challenging task because of the large size of these data sets. For applications such as environmental monitoring or natural resources management, complex algorithms have to be used to extract information from the images. The memory required to store the images and the data structures of such algorithms may be very high (hundreds of gigabytes) and therefore leads to unfeasibility on commonly available computers. Segmentation algorithms constitute an essential step for the extraction of objects of interest in a scene and will be the topic of the investigation in this paper. The objective of the present work is to adapt image segmentation algorithms for large amounts of data. To overcome the memory issue, large images are usually divided into smaller image tiles, which are processed independently. Region-merging algorithms do not cope well with image tiling since artifacts are present on the tile edges in the final result due to the incoherencies of the regions across the tiles. In this paper, we propose a scalable tile-based framework for region-merging algorithms to segment large images, while ensuring identical results, with respect to processing the whole image at once. We introduce the original concept of the stability margin for a tile. It allows ensuring identical results to those obtained if the whole image had been segmented without tiling. Finally, we discuss the benefits of this framework and demonstrate the scalability of this approach by applying it to real large images.

Orfeo ToolBox: open source processing of remote sensing images

Orfeo ToolBox is an open-source project for state-of-the-art remote sensing, including a fast image viewer, applications callable from command-line, Python or QGIS, and a powerful C++ API. This article is an introduction to the Orfeo ToolBox’s flagship features from the point of view of the two communities it brings together: remote sensing and software engineering.

Synergy of Sentinel-1 and Sentinel-2 imagery for wetland monitoring information extraction from continuous flow of sentinel images applied to water bodies and vegetation mapping and monitoring

Wetlands, very sensitive and valuable ecosystem can be monitored in terms of water surfaces dynamics as well as vegetation characterisation and monitoring exploiting satellite data. The synergy between the recently launched Sentinel1 and Sentinel2 satellites have been investigated over the Poyang and Anhui lakes in PR China. Results highlight the gain in terms of operationality with a very high revisit exploiting the two systems, as well as for a thematic point of view with no was not yet reach at this resolution for water bodies and terrestrial, floating and submerged vegetation mapping and monitoring.

Supervised re-segmentation for very high-resolution satellite images

In this paper, we proposed a supervised methodology to enhance an existing segmentation in which we assume that objects of interest are mainly fragmented. We used a SVM classifier to classify edges from the adjacency graph of the initial segmentation, described with features on the pair of segments and their relationship. Pairs of segments are then merged sequentially according to the classifier decision. We also proposed three methods for efficient supervision by the end user.

Large scale region-merging segmentation using the local mutual best fitting concept

Large scale segmentation remains a challenging task because of time and memory consuming. A usual strategy to process efficiently a large volume of data is to divide into chunks to be processed separately, either sequentially to reduce memory footprint or in parallel in order to speed up the computation. In image processing in general this boils down to dividing the input image into tiles. However, for image segmentation, the tile splitting usually leads incoherent segments on the borders of the tiles even when some overlap between the tiles is applied. In this paper we propose a new strategy making possible the tiling for image segmentation algorithms while maintaining the accuracy of the final results. Specifically, we focus on iterative region merging methods but the strategy can be extended to any segmentation algorithm. The introduction of the local mutual best fitting concept and the area of influence of a segment allows to establish a new methodology of segmentation based on three phases: the tile-based reduction, the iterative reduction and the completion of the segmentation. This new methodology was applied on a large Pleiades HR image with success proving the feasibility of the approach.

The ORFEO acompaniment program and ORFEO ToolBox

Launched last December 17, 2011, the first satellite of the Pleiades system allows of very high resolution images acquisition. This system is made of two “small satellites” (mass of one ton) offering a spatial resolution at nadir of 0.7 meters and a field of view of 20 kilometers. The second satellite will be launched mid-2013. The great agility of those two satellites enables a daily access all over the world, which is a critical need for defence and civil security applications, and a coverage capacity necessary for the cartographic applications at scales better than those accessible to SPOT satellites family. Moreover, Pleiades have very high stereoscopic acquisition capacity to meet the fine cartography needs, notably in urban regions, and to bring information complementary to aerial photography.

State of the Orfeo Toolbox

Orfeo Toolbox (OTB), is a remote sensing image processing library developed by CNES, the French Space Agency since 2006. OTB is distributed as Open Source software and is therefore available for any remote sensing scientist or processing chain developer. This paper describes the key components of the software, the main features recently added to OTB and the expected evolutions in the future.

Mean shift based segmentation of full VHR imagery with limited resources: An exact solution

This paper adresses the problem of piecewise computation of a segmentation algorithm for large images, without creating any artifacts in the results. We first define a property of segmentation algorithms called stability, and show that the well-known MeanShift algorithm can be derived to be stable. We then propose a segmentation methodology that allows for piecewise segmentation of large images with a stable segmentation algorithm, with the guarantee of identical results with respect to full processing at once. Finally, we introduce two examples of applications: large-scale object based classification, and large-scale object counting.