Several different methods for the fusion of multispectral and panchromatic images based on the wavelet transform have been proposed. The majority provide satisfactory results, but there is one, the à trous algorithm, that presents several advantages over the other fusion methods. Its computation is very simple; it only involves elementary algebraic operations, such as products, differences and convolutions. It yields a better spatial and spectral quality than the other methods. Standard fusion methods do not allow control of the spatial and spectral quality of the fused image; high spectral quality implies low spatial quality and vice versa. This paper proposes a new version of a fusion method based on the wavelet transform, computed through the à trous algorithm, that permits customization of the trade-off between the spectral and spatial quality of the fused image through the evaluation of two quality indices: a spectral index (the ERGAS index) and a spatial one. For the latter, a new spatial index based on ERGAS concepts and translated to the spatial domain has been defined. In addition, several different schemes for the computation of the fusion method investigated have been evaluated to optimize the degradation level of the source image required to perform the fusion process. The performance of the proposed fusion method has been compared with the fusion methods based on wavelet Mallat and filtering in the Fourier domain.
A correct delineation of agricultural parcels is a primary requirement for any parcel-based application such as the estimate of agricultural subsidies. Currently, high-resolution remote-sensing images provide useful spatial information to delineate parcels; however, their manual processing is highly time consuming. Thus, it is necessary to create methods which allow performing this task automatically. In this work, the use of a machine-learning algorithm to delineate agricultural parcels is explored through a novel methodology. The proposed methodology combines superpixels and supervised classification in order to determine which adjacent superpixels should be merged, transforming the segmentation issue into a machine learning matter. A visual evaluation of results obtained by the methodology applied to two areas of a high-resolution satellite image of fragmented agricultural landscape points out that the use of machine-learning algorithm for this task is promising.
Abstract:Very high resolution remotely sensed images are an important tool for monitoring fragmented agricultural landscapes, which allows farmers and policy makers to make better decisions regarding management practices. An object-based methodology is proposed for automatic generation of thematic maps of the available classes in the scene, which combines edge-based and superpixel processing for small agricultural parcels. The methodology employs superpixels instead of pixels as minimal processing units, and provides a link between them and meaningful objects (obtained by the edge-based method) in order to facilitate the analysis of parcels. Performance analysis on a scene dominated by agricultural small parcels indicates that the combination of both superpixel and edge-based methods achieves a classification accuracy slightly better than when those methods are performed separately and comparable to the accuracy of traditional object-based analysis, with automatic approach.
Accurate and up-to-date information on the spatial and geographical characteristics of agricultural areas is an indispensable value for the various activities related to agriculture and research. Most agricultural studies and policies are carried out at the field level, for which precise boundaries are required. Today, high-resolution remote sensing images provide useful spatial information for plot delineation; however, manual processing is time-consuming and prone to human error. The objective of this paper is to explore the potential of deep learning (DL) approach, in particular a convolutional neural network (CNN) model, for the automatic outlining of agricultural plot boundaries from orthophotos over large areas with a heterogeneous landscape. Since DL approaches require a large amount of labeled data to learn, we have exploited the open data from the Land Parcel Identification System (LPIS) from the Chartered Community of Navarre, Spain. The boundaries of the agricultural plots obtained from our methodology were compared with those obtained using a state-of-the-art methodology known as gPb-UCM (global probability of boundary followed by ultrametric contour map) through an error measurement called the boundary displacement error index (BDE). In BDE terms, the results obtained by our method outperform those obtained from the gPb-UCM method. In this regard, CNN models trained with LPIS data are a useful and powerful tool that would reduce intensive manual labor in outlining agricultural plots. INDEX TERMS Convolutional neural network, deep learning, edge extraction, land parcel identification system, parcels delineation.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.