Robert De Wulf

Land cover mapping at sub-pixel scales using linear optimization techniques

Mixed pixels result when the sensors instantaneous field-of-view includes more than one land cover class on the ground. For mixed pixels, fuzzy classifiers can be used, which assign a pixel to several land cover classes in proportion to the area of the pixel that each class covers. These fraction values can be assigned to sub-pixels, based on the assumption of spatial dependence and the application of linear optimization techniques. A newly proposed sub-pixel mapping algorithm was first applied to a synthetic data set with a 1-km resolution, derived from a 20-m resolution image. This algorithm yielded land cover maps at 500, 200, and 100 m resolution with accuracies close to 89%. Subsequent mode filtering further increased these values. When applied to a real data set, the accuracy reached 78%. While this study suggests the potential of the proposed technique, there is still ample scope for improvements and extensions.

A sub‐pixel mapping algorithm based on sub‐pixel/pixel spatial attraction models

Soft classification techniques avoid the loss of information characteristic to hard classification techniques when handling mixed pixels. Sub‐pixel mapping is a method incorporating benefits of both hard and soft classification techniques. In this paper an algorithm is developed based on sub‐pixel/pixel attractions. The design of the algorithm is accomplished using artificial imagery but testing is done on artificial as well as real synthetic imagery. The algorithm is evaluated both visually and quantitatively using established classification accuracy indices. The resulting images show increased accuracy when compared to hardened soft classifications.

Extraction of forest stand parameters from panchromatic and multispectral SPOT-1 data

Abstract The main objective of this paper is to determine the extent to which forest structural variables can be estimated from SPOT-1 panchromatic and multispectral radiance. The test site is the state-owned Pynven forest, featuring a large amount of evenly-aged pine stands from which those with Corsican pine (Pinus nigra Am. var. Calabrica Loud.) are selected. Investigated image parameters include waveband, first-order statistics estimators and sample window size. The forest stand parameters are stand density, stand age, average tree diameter, stand basal area, average canopy height and stand volume. Empirical linear models are constructed based on Bartletts three-group method, followed by inversion and validation using an independent test data set. The green and red SPOT-1 waveband are useless for forest stand parameter estimation, and the arithmetic mean of sample window radiance is the only usable estimator from the set of tested statistical measures. Stand density and average canopy height can sati...

Is fitness inheritance useful for real-world applications?

Fitness evaluation in real-world applications often causes a lot of computational overhead. Fitness inheritance has been proposed for tackling this problem. Instead of evaluating each individual, a certain percentage of the individuals is evaluated indirectly by interpolating the fitness of their parents. However, the problems on which fitness inheritance has been tested are very simple and the question arises whether fitness inheritance is really useful for real-world applications. The objective of this paper is to test the performance of average and weighted average fitness inheritance on a well-known test suite of multiple objective optimization problems. These problems have been generated as to constitute a collection of test cases for genetic algorithms. Results show that fitness inheritance can only be applied to convex and continuous problems.

A spatial approach to forest‐management optimization: linking GIS and multiple objective genetic algorithms

Forest‐management decision‐support systems are largely monolithic structures. Spatial details are left out during the optimization process and are elaborated during the operational planning. This might produce misleading results and plans that are impossible to implement. In this paper, a forest‐management spatial decision‐support systems is presented, in which spatial formulation needed for wildlife models is included during the optimization process. To this end, a multiple‐objective genetic algorithm is combined with a geographical information system. An online spatial evaluation of the objective functions is made possible. This is illustrated by a pilot study in Kirkhill forest, Aberdeen.

Remote sensing for wildlife management: Giant panda habitat mapping from LANDSAT MSS images

Abstract Remote sensing is a powerful and accurate means of collecting data for wildlife management, particularly for large areas which are difficult of access and feature delicate ecosystems. Giant panda habitat in the Peoples Republic of China was evaluated by visual interpretation of multitemporal LANDSAT MSS images. The resulting map, combined with ground survey data, provides important information upon which management decisions can be planned. This case study illustrates that remote sensing techniques can make a significant contribution to the management programme for the conservation of a threatened animal species.

Designing protected areas for giant pandas in China

The familiar black and white giant panda is famous throughout China and the world as a symbol of the plight of endangered species. Fossil remains show that the giant panda was formerly distributed over a much larger area than today, reaching Burma, northern Vietnam, and much of eastern and southern China. Historical records in China also demonstrate that it was formerly much more widespread than today. Figure 8.1 shows this declining range of the giant panda.

Variability of operator performance in remote-sensing image interpretation: the importance of human and external factors

This study tackles a common, yet underrated problem in remote-sensing image analysis: the fact that human interpretation is highly variable among different operators. Despite current technological advancements, human perception and interpretation are still vital components of the map-making process. Consequently, human errors can considerably bias both mapping and modelling results. In our study, we present a web-based tool to quantify operator variability and to identify the human and external factors affecting this variability. Human operators were given a series of images and were asked to hand-digitize different point, line, and polygon objects. The quantification of performance variability was achieved using both thematic and positional accuracy measures. Subsequently, a series of questions related to demographics, experience, and personality were asked, and the answers were also quantified. Correlation and regression analysis was then used to explain the variability in operator performance. From our study, we conclude that: (1) humans were seldom perfect in visual interpretation; (2) some geographic objects were more complex to accurately digitize than others; (3) there was a high degree of variability among image interpreters when hand-digitizing the same objects; and (4) operator performance was mainly determined by demographic, non-cognitive, and cognitive personality factors, whereas external and technical factors influenced operator performance to a lesser extent. Finally, the results also indicated a gradual decline in performance over time, mimicking classical mental fatigue effects.

Influence of different topographic correction strategies on mountain vegetation classification accuracy in the Lancang Watershed, China

Mapping of vegetation using remote sensing in mountainous areas is considerably hampered by topographic effects on the spectral response pattern. A variety of topographic normalization techniques have been proposed to correct these illumination effects due to topography. The purpose of this study was to compare six different topographic normalization methods (Cosine correction, Minnaert correction, C-correction, Sun-canopy-sensor correction, two-stage topographic normalization, and slope matching technique) for their effectiveness in enhancing vegetation classification in mountainous environments. Since most of the vegetation classes in the rugged terrain of the Lancang Watershed (China) did not feature a normal distribution, artificial neural networks (ANNs) were employed as a classifier. Comparing the ANN classifications, none of the topographic correction methods could significantly improve ETM+ image classification overall accuracy. Nevertheless, at the class level, the accuracy of pine forest could be increased by using topographically corrected images. On the contrary, oak forest and mixed forest accuracies were significantly decreased by using corrected images. The results also showed that none of the topographic normalization strategies was satisfactorily able to correct for the topographic effects in severely shadowed areas.

Tourism: An Alternative to Development? Reconsidering Farming, Tourism, and Conservation Incentives in Northwest Yunnan Mountain Communities

Abstract In the last decade, tourism has developed rapidly in the mountainous areas of northwest Yunnan. This growth has led to substantial economic and social changes, with resulting environmental consequences. This article uses a case study to illustrate how local farmers involved in tourism changed their agricultural practices as a result of the transformations that took place in the area. The aim was to examine tourisms expected benefits of poverty alleviation and conservation incentives. Tourism investments were found to have been adopted only by households with available cash and labor, whereas they remained inaccessible for the poor, small landowners who most needed a new source of income and used their land more exhaustively. Relatively rich, large landowners did not take the opportunity to reduce their agricultural activities. Instead, they used supplementary incomes earned from tourism to hire external labor to cultivate their land more intensely. Tourism development failed to generate real incentives for mountain farmers to adopt more conservation measures and prevent soil erosion and nonpoint source agricultural water pollution, which currently constitute serious environmental problems for mountain environments in Yunnan. This article presents recommendations based on the conclusions of the study.