Object-based image analysis of remote sensing data

Veljanovski, Tatjana; Kanjir, Urša; Oštir, Krištof

doi:10.15292/geodetski-vestnik.2011.04.641-664

Cited by 15 publications

(18 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This high-resolution data has caused a substantial change in the relationship between the pixel size and the size of the object of interest. 2 The main problems when using a pixel-based classification on highresolution data is that too much detail produces inconsistent results and the extracted "objects" do not match the object of interest in the way we expected. 3 The increased spatial resolution demands a new method for image analysis when deriving objects made of several pixels.…”

Section: Introductionmentioning

confidence: 88%

See 1 more Smart Citation

Investigating the impact of spatial and spectral resolution of satellite images on segmentation quality

Mesner

Oštir

2014

J. Appl. Remote Sens

Self Cite

View full text Add to dashboard Cite

Abstract. Segmentation, the first step of object-based classification, is crucial to the quality of the final classification results. A poor quality of the segmentation leads directly to a low quality of the classification. Therefore, it is very important to evaluate the segmentation results using quantitative methods and to know how to obtain the best results. To obtain the best possible segmentation results, it is important to choose the right input data resolution as well as the best algorithm and its parameters for a specific remote sensing application. The impact of the segmentation algorithm, the parameter settings, as well as the spatial and spectral resolution of the data is investigated. To describe these impacts, we performed more than 70 segmentations of a Worldview-2 image. The impact of the spectral resolution was tested with 10 combinations of data on different spectral channels, and the impact of the spatial resolution was tested on an original and downsampled test image to four different spatial resolutions. We investigated these impacts on the segmentation of objects that belong to the classes urban, forest, bare soil, vegetation, and water. The impacts on the segmentation are described using a common methodology for the evaluation of segmentation.

show abstract

Section: Introductionmentioning

confidence: 88%

“…2 In our analysis, we included one from each group, both of them integrated in Definiens Developer software (Ref. 15): the edge-based contrast split 15 and the region-growing multiresolution algorithm.…”

Section: Impact Of the Segmentation Algorithmmentioning

confidence: 99%

Investigating the impact of spatial and spectral resolution of satellite images on segmentation quality

Mesner

Oštir

2014

J. Appl. Remote Sens

Self Cite

View full text Add to dashboard Cite

show abstract

“…The inability of C and X-band radar to penetrate vegetation canopies, and backscattering from rooftops and water surfaces, can result in over-estimation of elevation [40,66,249]. Optical imagery applications can be hampered by atmospheric conditions and spatial resolution [250], while one of the core deficiencies of radar images is the inconsistency in delineating floods in urban and forested areas [251].…”

Section: Synthesismentioning

confidence: 99%

Applications of Open-Access Remotely Sensed Data for Flood Modelling and Mapping in Developing Regions

Ekeu-wei

Blackburn

2018

Hydrology

View full text Add to dashboard Cite

Flood modelling and mapping typically entail flood frequency estimation, hydrodynamic modelling and inundation mapping, which require specific datasets that are often unavailable in developing regions due to financial, logistical, technical and organizational challenges. This review discusses fluvial (river) flood modelling and mapping processes and outlines the data requirements of these techniques. This paper explores how open-access remotely sensed and other geospatial datasets can supplement ground-based data and high-resolution commercial satellite imagery in data sparse regions of developing countries. The merits, demerits and uncertainties associated with the application of these datasets, including radar altimetry, digital elevation models, optical and radar images, are discussed. Nigeria, located within the Niger river basin of West Africa is a typical data-sparse country, and it is used as a case study in this review to evaluate the significance of open-access datasets for local and transboundary flood analysis. Hence, this review highlights the vital contribution that open access remotely sensed data can make to flood modelling and mapping and to support flood management strategies in developing regions.

show abstract

“…In this regard, it is clear that OBIA process depends on a correct delineation of the image-objects that are critical to recognizing geographical entities during the analysis phase. Veljanovski et al, 2011).…”

Section: Phases Involve In Object-based Image Analysismentioning

confidence: 99%

“…The basic input data is represented by a multispectral RS image. However in accordance with the aim of the analysis, other ancillary data layers can be included in order to refine the process of sorting segments into object classes (Veljanovski et al, 2011). Furthermore, ancillary data can be also used in other subsequent parts of the analysis process, e.g., for characterizing image-objects.…”

Section: Object Class Thematic Classmentioning

confidence: 99%

Spatio-temporal Analysis of Agricultural Landscape Images: A Superpixel-based Approach

Pedrero¹,

Adolfo²

View full text Add to dashboard Cite

In the last hundred years, the world population has tripled and is still growing dramatically but resources have remained the same, causing changes in food supply outlook. According to the Food and Agriculture Organization (FAO), global food production will need to grow by 70% in order to satisfy the food and feed demand of a population of 9 billion people by 2050. In the current scenario, with limited arable lands and water scarcity, this means a greater pressure than ever before on productive land; thus today's main challenge is to put agriculture on a more sustainable and productive long-term path. In this context, the study of the variability within plots represents an opportunity for improving agricultural management. For most farmers, agricultural plots are variable which implies that not all areas within them require the same management; for example: some areas have specific needs of water, fertilizers, or pesticides in order to be more profitable. Therefore, adjusting the management of the plots based on the variability within them opens a route to a variable farm management able to improve cost/yield relationship.New generation of optical remote sensors placed on aircraft, satellite platforms and drones, offers accessible and useful data of very-high resolution for monitoring and determining spatial variability of agricultural fields at plot level. However, the landscape complexity makes the manual analysis of the variability within an agricultural plot a highly time-consuming and expensive task. At the same time, it hinders considerably the monitoring of a high number of agricultural plots simultaneously. Moreover this very-high spatial resolution represents a challenge for traditional approaches of analysis based on pixels, unable to handle the withinclass spectral variability, intrinsic to this type of images. Therefore, it exists a critical need to develop methodologies for efficiently and automatically extracting and analyzing information from very-high resolution images, that would allow stakeholders to enable variable farm management. In this context, it is of particular interest to automatically detect region dynamics within the agricultural plots.The aim of this work is the development of a methodology for automatic generation of spatial and temporal information on the dynamics of agricultural land, particularly at plot level. In this sense, the study of agricultural scenes has been addressed through an object-based approach, exploring superpixel methods, which are seen as a link between the pixels of the image and objects of interest. To this end a superpixel method for multi-spectral images has been proposed. This method has been exploited in different applications at three different scales of interest:vii (i) to analyze fragmented agricultural scenes, (ii) to delineate agricultural plots, and (iii) to capture the internal variability of agricultural plots.The analysis of fragmented agricultural scenes has been approached by two methodologies. The first one focuses on providing a fram...

show abstract

Object-based image analysis of remote sensing data

Abstract: IZVLEČEK

Cited by 15 publications

References 24 publications

Investigating the impact of spatial and spectral resolution of satellite images on segmentation quality

Investigating the impact of spatial and spectral resolution of satellite images on segmentation quality

Applications of Open-Access Remotely Sensed Data for Flood Modelling and Mapping in Developing Regions

Spatio-temporal Analysis of Agricultural Landscape Images: A Superpixel-based Approach

Contact Info

Product

Resources

About