Emmanuel Christophe

Decision Fusion for the Classification of Hyperspectral Data: Outcome of the 2008 GRS-S Data Fusion Contest

The 2008 Data Fusion Contest organized by the IEEE Geoscience and Remote Sensing Data Fusion Technical Committee deals with the classification of high-resolution hyperspectral data from an urban area. Unlike in the previous issues of the contest, the goal was not only to identify the best algorithm but also to provide a collaborative effort: The decision fusion of the best individual algorithms was aiming at further improving the classification performances, and the best algorithms were ranked according to their relative contribution to the decision fusion. This paper presents the five awarded algorithms and the conclusions of the contest, stressing the importance of decision fusion, dimension reduction, and supervised classification methods, such as neural networks and support vector machines.

Quality criteria benchmark for hyperspectral imagery

Hyperspectral data appear to be of a growing interest over the past few years. However, applications for hyperspectral data are still in their infancy as handling the significant size of the data presents a challenge for the user community. Efficient compression techniques are required, and lossy compression, specifically, will have a role to play, provided its impact on remote sensing applications remains insignificant. To assess the data quality, suitable distortion measures relevant to end-user applications are required. Quality criteria are also of a major interest for the conception and development of new sensors to define their requirements and specifications. This paper proposes a method to evaluate quality criteria in the context of hyperspectral images. The purpose is to provide quality criteria relevant to the impact of degradations on several classification applications. Different quality criteria are considered. Some are traditionally used in image and video coding and are adapted here to hyperspectral images. Others are specific to hyperspectral data. We also propose the adaptation of two advanced criteria in the presence of different simulated degradations on AVIRIS hyperspectral images. Finally, five criteria are selected to give an accurate representation of the nature and the level of the degradation affecting hyperspectral data.

Remote Sensing Processing: From Multicore to GPU

As the amount of data and the complexity of the processing rise, the demand for processing power in remote sensing applications is increasing. The processing speed is a critical aspect to enable a productive interaction between the human operator and the machine in order to achieve ever more complex tasks satisfactorily. Graphic processing units (GPU) are good candidates to speed up some tasks. With the recent developments, programming these devices became very simple. However, one source of complexity is on the frontier of this hardware: how to handle an image that does not have a convenient size as a power of 2, how to handle an image that is too big to fit the GPU memory? This paper presents a framework that has proven to be efficient with standard implementations of image processing algorithms and it is demonstrated that it also enables a rapid development of GPU adaptations. Several cases from the simplest to the more complex are detailed and illustrate speedups of up to 400 times.

Multi-Modal Change Detection, Application to the Detection of Flooded Areas: Outcome of the 2009–2010 Data Fusion Contest

The 2009-2010 Data Fusion Contest organized by the Data Fusion Technical Committee of the IEEE Geoscience and Remote Sensing Society was focused on the detection of flooded areas using multi-temporal and multi-modal images. Both high spatial resolution optical and synthetic aperture radar data were provided. The goal was not only to identify the best algorithms (in terms of accuracy), but also to investigate the further improvement derived from decision fusion. This paper presents the four awarded algorithms and the conclusions of the contest, investigating both supervised and unsupervised methods and the use of multi-modal data for flood detection. Interestingly, a simple unsupervised change detection method provided similar accuracy as supervised approaches, and a digital elevation model-based predictive method yielded a comparable projected change detection map without using post-event data.

Hyperspectral Image Compression: Adapting SPIHT and EZW to Anisotropic 3-D Wavelet Coding

Hyperspectral images present some specific characteristics that should be used by an efficient compression system. In compression, wavelets have shown a good adaptability to a wide range of data, while being of reasonable complexity. Some wavelet-based compression algorithms have been successfully used for some hyperspectral space missions. This paper focuses on the optimization of a full wavelet compression system for hyperspectral images. Each step of the compression algorithm is studied and optimized. First, an algorithm to find the optimal 3-D wavelet decomposition in a rate-distortion sense is defined. Then, it is shown that a specific fixed decomposition has almost the same performance, while being more useful in terms of complexity issues. It is shown that this decomposition significantly improves the classical isotropic decomposition. One of the most useful properties of this fixed decomposition is that it allows the use of zero tree algorithms. Various tree structures, creating a relationship between coefficients, are compared. Two efficient compression methods based on zerotree coding (EZW and SPIHT) are adapted on this near-optimal decomposition with the best tree structure found. Performances are compared with the adaptation of JPEG 2000 for hyperspectral images on six different areas presenting different statistical properties.

The Orfeo Toolbox remote sensing image processing software

Orfeo Toolbox, OTB, is a remote sensing image processing library developed by CNES, the French Space Agency. OTB is distributed as Open Source software and is therefore available for any remote sensing scientist or processing chain developer. This paper describes the main features of OTB, how it can be used and the expected evolutions in the coming months.

Robust Road Extraction for High Resolution Satellite Images

Automatic road extraction is a critical feature for an efficient use of remote sensing imagery in most contexts. This paper proposes a robust geometric method to provide a first step extraction level. These results can be used as an initialization for other algorithms or as a starting point for manual road extraction. Results of the extraction are vectorized for GIS integration and for a better interaction with human experts that can refine the results. The algorithm is fast, has very few parameters and is only slightly affected by the image properties (resolution, noise). The algorithm is available in the open-source Orfeo toolbox.

Hyperspectral Data Compression Tradeoff

Hyperspectral data are a challenge for data compression. Several factors make the constraints particularly stringent and the challenge exciting. First is the size of the data: as a third dimension is added, the amount of data increases dramatically making the compression necessary at different steps of the processing chain. Also different properties are required at different stages of the processing chain with variable tradeoff. Second, the differences in spatial and spectral relation between values make the more traditional 3D compression algorithms obsolete. And finally, the high expectations from the scientists using hyperspectral data require the assurance that the compression will not degrade the data quality. All these aspects are investigated in the present chapter and the different possible tradeoffs are explored. In conclusion, we see that a number of challenges remain, of which the most important is to find an easier way to qualify the different algorithm proposals.

Best Anisotropic 3-D Wavelet Decomposition in a Rate-Distortion Sense

Hyperspectral sensors have been of a growing interest over the past few decades for Earth observation as well as deep space exploration. However, the amount of data provided by such sensors requires an efficient compression system which is yet to be defined. It is hoped that the particular statistical properties of such images can be used to obtain very efficient compression algorithms. This paper proposes a method to find the most suitable wavelet decomposition for hyperspectral images and introduces the possibility of non isotropic decomposition. The decomposition is made by choosing the decomposition that provides an optimal rate-distortion trade-off. The obtained decomposition exhibits better performances in terms of rate-distortion curves compared to isotropic decomposition for high bitrates as well as for low bitrates

Performance evaluation of building detection and digital surface model extraction algorithms: Outcomes of the PRRS 2008 Algorithm Performance Contest

This paper presents the initial results of the algorithm performance contest that was organized as part of the 5th IAPR Workshop on Pattern Recognition in Remote Sensing (PRRS 2008). The focus of the 2008 contest was automatic building detection and digital surface model (DSM) extraction. A QuickBird data set with manual ground truth was used for building detection evaluation, and a stereo Ikonos data set with a highly accurate reference DSM was used for DSM extraction evaluation. Nine submissions were received for the building detection task, and three submissions were received for the DSM extraction task. We provide an overview of the data sets, the summaries of the methods used for the submissions, the details of the evaluation criteria, and the results of the initial evaluation.