Results 1 - 10
of
27
A Multilevel context-based system for classification of very high spatial resolution images
- IEEE Transaction on Geosciences and Remote Sensing
, 2006
"... Abstract—This paper proposes a novel pixel-based system for the supervised classification of very high geometrical (spa-tial) resolution images. This system is aimed at obtaining ac-curate and reliable maps both by preserving the geometrical details in the images and by properly considering the spat ..."
Abstract
-
Cited by 35 (2 self)
- Add to MetaCart
(Show Context)
Abstract—This paper proposes a novel pixel-based system for the supervised classification of very high geometrical (spa-tial) resolution images. This system is aimed at obtaining ac-curate and reliable maps both by preserving the geometrical details in the images and by properly considering the spatial-context information. It is made up of two main blocks: 1) a novel feature-extraction block that, extending and developing some con-cepts previously presented in the literature, adaptively models the spatial context of each pixel according to a complete hierarchical multilevel representation of the scene and 2) a classifier, based on support vector machines (SVMs), capable of analyzing hyperdi-mensional feature spaces. The choice of adopting an SVM-based classification architecture is motivated by the potentially large number of parameters derived from the contextual feature-extraction stage. Experimental results and comparisons with a standard technique developed for the analysis of very high spatial resolution images confirm the effectiveness of the proposed system. Index Terms—Hierarchical feature extraction, hierarchical segmentation, multilevel and multiscale analysis, spatial-context information, support vector machines (SVMs), very high spatial resolution images. I.
Evaluation of remote sensing image segmentation quality – further results and concepts
- Proceedings of the 1 st International Conference on Object-Based Image Analysis
, 2006
"... Primarily due to the progresses in spatial resolution of satellite imagery, the methods of segment-based image analysis for generating and updating geographical information are becoming more and more important. In the studies of Neubert and Meinel (2003) and Meinel and Neubert (2004) the capabilitie ..."
Abstract
-
Cited by 8 (0 self)
- Add to MetaCart
Primarily due to the progresses in spatial resolution of satellite imagery, the methods of segment-based image analysis for generating and updating geographical information are becoming more and more important. In the studies of Neubert and Meinel (2003) and Meinel and Neubert (2004) the capabilities of available segmentation programmes for high resolution remote sensing data were assessed and compared. This paper intends to supplement the preceding studies by considering recently available software. Moreover, a self-implemented optimised segmentation algorithm for the image processing software HALCON is included in the test. The achieved segmentation quality of each programme is evaluated on the basis of an empirical discrepancy method using pansharpened multi-spectral IKONOS data. Furthermore, an overview of further methods for quantitative image segmentation quality evaluation is given. Finally, the qualitative and quantitative outcomes are compared and contrasted to the previously tested software solutions. The stated results provide an approach to determine each programme’s performance and appropriateness for specific segmentation tasks. 1.
The Synthetic Image TEsting Framework (SITEF) for the evaluation of multi-spectral image segmentation algorithms
- IEEE IGARSS 2009, IV
, 2009
"... ABSTRACT One of the most challenging tasks in Remote Sensing at present is how to handle the huge amounts of image data acquired every day by the existing Earth Observation Satellites (EOS). An alternative approach to the standard per-pixel analysis of multi-spectral EOS images has evolved over the ..."
Abstract
-
Cited by 2 (2 self)
- Add to MetaCart
(Show Context)
ABSTRACT One of the most challenging tasks in Remote Sensing at present is how to handle the huge amounts of image data acquired every day by the existing Earth Observation Satellites (EOS). An alternative approach to the standard per-pixel analysis of multi-spectral EOS images has evolved over the last decade. Instead of focusing on individual image pixels, the object-based image analysis approach consists of partitioning an image into meaningful image-objects. One of the reasons for the development of object-based methods has been the dramatic increase in commercially available high resolution digital remote sensing imagery, with spatial resolutions of 5.0 m and finer [1]. Also it has been recognised that the image pixel is not a "natural" element of an image scene. A common element of all object-based image analysis systems is the segmentation stage, where the image is partitioned in a number of objects (or segments), which is clearly a critical stage of the whole process. If the segmentation fails to identify as an object a given element present in the image, the subsequent stages will generally be unable to recognise or to classify this element. An evaluation of the abilities and limitations of the segmentation algorithms used is therefore an important aspect of any object based image analysis system. However, there is no established standard procedure for the evaluation of the segmentation results produced for EOS images The purpose of this work is to present the Synthetic Image TEsting Framework (SITEF), a tool to evaluate the performance of segmentation algorithms on multi-spectral images. The method is based on the production of synthetic images with the spectral characteristics of the image pixels extracted from a signature multi-spectral image The methodology used here is an evolution of the method described in REFERENCES [1] G.J. Hay, G. Castilla, M.A. Wulder, J.R. Ruiz, "An automated object-based approach for the multiscale image segmentation of forest scenes
A Summary of Recent Progresses for Segmentation Evaluation
, 2006
"... This chapter provides a summary of the recent (especially since 2000) progress for the evaluation of image and video segmentation. It is seen that much more effort has been expended on this subject recently than several years ago. A number of works are based on previously proposed principles, and se ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
This chapter provides a summary of the recent (especially since 2000) progress for the evaluation of image and video segmentation. It is seen that much more effort has been expended on this subject recently than several years ago. A number of works are based on previously proposed principles, and several works have made modifications to and improvements on previous techniques as well as presented a few new ideas. The generality and complexity of the evaluation methods and performance criteria used in these works have been thoroughly compared. As the research in this field is still on the rise, some existing problems and several future directions are also highlighted.
Article Full Hierarchic Versus Non-Hierarchic Classification Approaches for Mapping Sealed Surfaces at the Rural-Urban Fringe Using High-Resolution Satellite Data
, 2009
"... sensors ..."
Article Feature Learning Based Approach for Weed Classification Using High Resolution Aerial Images from a Digital Camera Mounted
, 2014
"... remote sensing ..."
(Show Context)
Towards Large Scale Land-cover Recognition of Satellite Images
"... Abstract—The entire Earth surface has been documented with satellite imagery. The amount of data continues to grow as higher resolutions and temporal information become available. With this increasing amount of surface and temporal data, recognition, segmentation, and event detection in satellite im ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
(Show Context)
Abstract—The entire Earth surface has been documented with satellite imagery. The amount of data continues to grow as higher resolutions and temporal information become available. With this increasing amount of surface and temporal data, recognition, segmentation, and event detection in satellite images with a highly scalable system becomes more and more desirable. In this paper, a semantic taxonomy is constructed for the land-cover classification of satellite images. Both the training and running of the classifiers are implemented in a distributed Hadoop computing platform. Publicly available high resolution datasets were collected and divided into tiles of fixed dimensions as training data. The training data was manually indexed into the semantic taxonomy categories, such as ”Vegetation”, ”Building”, and ”Pavement”. A scalable modeling system implemented in the Hadoop MapReduce framework is used for training the classifiers and performing subsequent image classification. A separate larger test dataset of the San Diego region, acquired from Microsoft BING Maps, was used to demonstrate the efficacy of our system at large scale. The presented methodology of land-cover recognition provides a scalable solution for automatic satellite imagery analysis, especially when GIS data is not readily available, or surface change may occur due to catastrophic events such as flooding, hurricane, and snow storm, etc. I.
unknown title
, 2008
"... www.elsevier.com/locate/isprsjprs A framework of region-based spatial relations for non-overlapping features and its application in object based image analysis ..."
Abstract
- Add to MetaCart
(Show Context)
www.elsevier.com/locate/isprsjprs A framework of region-based spatial relations for non-overlapping features and its application in object based image analysis
Segmentation: The Achilles ’ heel of object–based image analysis?
"... Much of the background material on geo-object-based image analysis (GEOBIA) begins with a description of image segmentation and suggest it as the first stage of the process. Although this approach may be reasonable in some cases, the crucial first step should be more generically defined as obtaining ..."
Abstract
- Add to MetaCart
(Show Context)
Much of the background material on geo-object-based image analysis (GEOBIA) begins with a description of image segmentation and suggest it as the first stage of the process. Although this approach may be reasonable in some cases, the crucial first step should be more generically defined as obtaining a set of objects which represent the features of interest in the image. In the context of land cover mapping these objects will be fields, lakes and patches of woodland etc. The application of image segmentation might be considered a ‘black art’, due to it dependence on the image data and the limited amount of control available to the user. The resulting segments reflect the spectral structure of the image rather than the presence of true boundary features in the landscape. For instance, two adjacent fields with the same crop could be combined into a single object even though they may be owned by different farmers. Conversely, single fields containing natural and acceptable variability may give multiple objects per field. Segments also retain the inherent area sampling of the original image. This lack of a direct one-to-one relationship between real world objects and segments has prevented GEOBIA reaching its full potential. Rarely today is any environmental analysis begun on a blank canvas, but in the context of existing mapping of some form, often in digital format. In regions of the world with high quality large scale cartographic mapping an obvious question is why this information is not used to control the GEOBIA process? Much of the earlier GEOBIA work was within the raster processing domain and only recently have fully structured digital vector cartography datasets and the necessary software tools become available. It is proposed that the GEOBIA process be made more generic to use the best existing real world feature datasets as the starting point for the process before segmentation is considered. Such an approach would increase
