State forest inventory (SFI) program has been adopted for obtaining and updating forest inventory data in the territory of the Russian Federation. In the course of SFI, circular permanent sample plots (PSP) of constant radii are laid out. The number of PSP depends on the representation of plantations in the work object. Currently, high resolution satellite images are used within the framework of SFI mainly for updating the cartographic basis of forest inventory. We propose a method for joint processing of multispectral and panchromatic satellite images of high spatial resolution in order to retrieve the species composition and age classes of mixed forest stands. The method consists of several steps. The preprocessing step includes calibration, correction, matching satellite and ground data. The next step is obtaining regional specific training data from PSP measurements. For the retrieval of forest parameters, we propose the recognition method based on the modified ECOC (Error Correcting Output Codes) classifier and regularized stepwise forward feature selection. This allows us to combine spectral and texture features more effectively. The last postprocessing step is the correction of classification results using the methods of mathematical morphology. The proposed method contributes to the automation of updating data on species composition and age classes of forest stands and allows improving the efficiency of SFI works. The accuracy of the retrieval of the species composition of mixed forests using high-resolution satellite images is comparable with the accuracy of the standard archival ground inventory data.
The article presents a model for assessing the information capabilities of multi-, hyperspectral satellite systems for Earth remote sensing in solving forest monitoring problems. The information capabilities of satellite system for Earth remote sensing means the ability to complete assigned tasks in time and quality. Assessment of information capabilities is divided into two parts. The first part is an assessment of the operational capabilities of the satellite system, that is, an expected time to complete the task. The second part is an assessment of solving the problems quality. Assessing of the information capabilities of satellite systems for Earth remote sensing allows to determine the appropriateness of including the task of monitoring territories (for example, forest monitoring) in the flight task for the satellite system, to develop measures to improve information capability in solving the tasks. The article also provides informational capability assessment obtained by the proposed method for the hyperspectral satellite system by NPO «Lepton» and Moscow Institute of Physics and Technology in solving the problem of classifying the species composition of deciduous and coniferous forest on a given territory. Such assessment is valid for similar satellite systems for Earth remote sensing when solving similar problems.
Hyperspectral imaging is up-to-date promising technology widely applied for the accurate thematic mapping. The presence of a large number of narrow survey channels allows us to use subtle differences in spectral characteristics of objects and to make a more detailed classification than in the case of using standard multispectral data. The difficulties encountered in the processing of hyperspectral images are usually associated with the redundancy of spectral information which leads to the problem of the curse of dimensionality. Methods currently used for recognizing objects on multispectral and hyperspectral images are usually based on standard base supervised classification algorithms of various complexity. Accuracy of these algorithms can be significantly different depending on considered classification tasks. In this paper we study the performance of ensemble classification methods for the problem of classification of the forest vegetation. Error correcting output codes and boosting are tested on artificial data and real hyperspectral images. It is demonstrates, that boosting gives more significant improvement when used with simple base classifiers. The accuracy in this case in comparable the error correcting output code (ECOC) classifier with Gaussian kernel SVM base algorithm. However the necessity of boosting ECOC with Gaussian kernel SVM is questionable. It is demonstrated, that selected ensemble classifiers allow us to recognize forest species with high enough accuracy which can be compared with ground-based forest inventory data.
Collecting and updating forest inventory data play an important part in the forest management. The data can be obtained directly by using exact enough but low efficient ground based methods as well as from the remote sensing measurements. We present applications of airborne hyperspectral remote sensing for the retrieval of such important inventory parameters as the forest species and age composition. The hyperspectral images of the test region were obtained from the airplane equipped by the produced in Russia light-weight airborne video-spectrometer of visible and near infrared spectral range and high resolution photo-camera on the same gyro-stabilized platform. The quality of the thematic processing depends on many factors such as the atmospheric conditions, characteristics of measuring instruments, corrections and preprocessing methods, etc. An important role plays the construction of the classifier together with methods of the reduction of the feature space. The performance of different spectral classification methods is analyzed for the problem of hyperspectral remote sensing of soil and vegetation. For the reduction of the feature space we used the earlier proposed stable feature selection method. The results of the classification of hyperspectral airborne images by using the Multiclass Support Vector Machine method with Gaussian kernel and the parametric Bayesian classifier based on the Gaussian mixture model and their comparative analysis are demonstrated.
Some results are given of the airborne applications to recognize forest classes of different species and ages for a test area based on the imaging spectrometer produced in Russia. Optimization techniques are outlined to select the most informative spectral bands for the particular subject area of the forest applications using the improved Bayesian classifier in the pattern recognition supervising procedures. A successive addition method is used in this optimization with the calculation of the probability error of the statistical pattern recognition while collecting the spectral ensembles for the known classes of forest vegetation for different species and ages. The subsequent step up method consists in fixing the level of the probability error that is not improved by adding the channels in the related computational procedures. The best distinguishable classes are recognized at the first stage of these procedures. The analytical technique called “cross-validation” is used for this purpose. The second stage is realized as a stable feature selection method based on the standard stepwise optimization approach, holdout cross-validation and resampling.
Optimization principles of accounting for the most informative spectral channels in hyperspectral remote sensing data
processing serve to enhance the efficiency of the employed high-productive computers. The problem of pattern
recognition of the remotely sensed land surface objects with the accent on the forests is outlined from the point of view
of the spectral channels optimization on the processed hyperspectral images. The relevant computational procedures are
tested using the images obtained by the produced in Russia hyperspectral camera that was installed on a gyro-stabilized
platform to conduct the airborne flight campaigns. The Bayesian classifier is used for the pattern recognition of the
forests with different tree species and age. The probabilistically optimal algorithm constructed on the basis of the
maximum likelihood principle is described to minimize the probability of misclassification given by this classifier. The
classification error is the major category to estimate the accuracy of the applied algorithm by the known holdout cross-validation
method. Details of the related techniques are presented. Results are shown of selecting the spectral channels of
the camera while processing the images having in mind radiometric distortions that diminish the classification accuracy.
The spectral channels are selected of the obtained subclasses extracted from the proposed validation techniques and the
confusion matrices are constructed that characterize the age composition of the classified pine species as well as the
broad age-class recognition for the pine and birch species with the fully illuminated parts of their crowns.
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.