This paper describes research undertaken on the improvement of within-field late season yield forecasting for crops such as wheat using multi-temporal visible/infrared satellite imagery and multi-polarization radar satellite imagery. Experiments have been carried out using ASAR imagery from Envisat combined with nine bands of ASTER imagery from the NASA Terra satellite. An experimental test site in an agricultural area in the county of Lincolnshire, UK, has been used. The satellite imagery has been integrated using artificial neural networks which have been trained as predictors of the spatial distributions of yield per unit area in a variety of fields. Ground truth data in the form of yield maps from GPS-enabled combine harvesters have been used to train the neural networks and to evaluate accuracy. The results show that the combinations of ASTER and ASAR imagery can provide enhanced yield predictions with overall correlations of up to 0.77 between predicted and actual yield patterns. The results also show that the use of dual polarization radar data alone is not sufficient to give reasonable yield predictions even in a multi-temporal mode. It has also been shown that varying the architectures of the neural networks with ensembles can improve the overall results.
Texture features computed from unfiltered ERS-1 SAR imagery have been used as additional features alongside Landsat TM radiances to map Mediterranean land cover. The texture features were normalized to reduce the impact of speckle noise. The classification procedure was carried out with a multilayer perceptron neural network. The results show that the addition of contrast, angular second moment, entropy, and inverse difference moment features from SAR, in addition to TM channels, can give overall accuracy improvement in land cover classification of 2 - 3%. While overall this is not very significant, for particular classes the use of texture leads to greater improvements in accuracy which could be useful in mapping applications. The results of the use of the SAR texture measures were compared using a number of different accuracy measures derived from individual confusion matrices.
A hybrid segmentation method has been developed integrating two segmentation methods, edge detection and region growing in order overcome weaknesses of either method. The segmentation method involves the following: (i) filtering, (ii) edge detection and following (iii) edge fragment linking, and (iv) region growing. In (ii) edge detection is carried out. The resulting edge magnitude values are thresholded and on the thresholded values a thinning operation is performed in order to create one pixel thick edges. In (iii) the resulting edge fragments are linked together where possible by detecting one pixel wide gaps between edge fragments. By connecting the edge fragments closed polygons are formed, dividing the image into a set of sub-images. Edge fragments not belonging to a closed polygon are pruned. In (iv) region growing is carried out within every polygon. Regions are not allowed to grow outside the polygons. The region growing method used is the best merge, which merges per merging scan over the image the pair with a lowest cost value. For merging remaining isolated pixels context rules are defined. Results of the segmentation method are shown for classification of a non-segmented Landsat-TM scene and its segmented counterpart by an artificial neural network. Moreover the use of the segmentation for filtering SAR imagery is indicated.
Unsupervised as well as classification of multi-spectral remote sensing data can be done by statistical as well as by neural network classifiers. Since classifiers are often approached as black boxes, it is not clear why one particular classifier performs better for a certain problem than another. In order to gain some insight in the actual training and classification processes, we implemented a software tool to study these processes in n-dimensional feature space. This tool allows visualization of the data points in feature space, of the individually classified clusters, and of the decision boundaries of the classifier. Image sequences are used to visualize higher-dimensional feature spaces as well as dynamic processes such as the training of neural networks or the effect of this training on an image to be classified. The visualization approach was further extended by allowing interaction with the decision boundaries. Feedback of this interaction is provided by a direct link between the decision boundaries and the classified landuse image. Pushing or pulling a decision boundary is directly reflected by changes to the corresponding classified image. Finally, we give an example of a combined classification scheme where visualization is used in order to validate the approach.
Segmentation methods for images often have cost functions which evaluate the (dis)similarity between pixels or segments. Thresholds on cost values are then used to decide whether or not to grow, join or split segments. The results for a given image critically depend on the selection of the threshold values. In remote sensing, a too low threshold will split up regions of constant ground cover and a too high threshold will join adjacent regions of different ground cover. Optimal thresholds can be determined using different classes of methods: generating cost value distributions from the original image; obtaining statistical distributions from segmented images; comparing a 'true' segmentation with the results of segmentation using a range of thresholds. A so-called 'true' segmentation can be derived from human expert segmentations or from maps obtained by ground surveys or segmentation of higher resolution images. Also artificial images can be generated having the advantage that the segmentation is known to sub-pixel level. Several methods for threshold determination are described for a hybrid segmentation method developed by us. Measures are described for comparison of two segmentations. Results are evaluated using several (parts of) LANDSAT images and artificial generated images.
The classification of remotely sensed satellite data for land surface mapping is a complex pattern recognition problem. Recent work has shown that neural networks often perform better than parametric or statistical classifiers in a large number of cases. Since neural and parametric classifiers are based on very different mathematical models it is appropriate to attempt to integrate them in order to exploit the best aspects of both. A simple method for integrating neural and statistical classifiers effectively is proposed in this paper. This method has been developed with the aim of improving land cover map products derived from multi- sensor data sets. The integration is achieved in a multi-stage process in which two classifiers of different types are initially trained to classify the same multi-sensor training data, and then samples for which the two classifiers are in disagreement are used to train an additional second stage neural classifier. Preliminary results show that significant improvements can be made in overall classification performance compared to using either neural or parametric classifiers alone.
The automatic mapping of land cover from satellite imagery requires optimal classification and spatial generalization procedures. Here we describe the use of functional ink neural networks, based on a flat perceptron net with an augmented feature vector, to generate high accuracy classification products. These can then be trained more rapidly than multi-layer perceptrons. The network output is then used to fix land cover class area statistics which control a low-level generalization procedure based on a combined iterative majority filtering and reduced class growing procedure.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.