All of the Landsat 7 data collected after 2003 contains missing pixels in the form of unsightly stripes across the images. To recover missing data of a Landsat image, different methods may be used. However, the gap fi...All of the Landsat 7 data collected after 2003 contains missing pixels in the form of unsightly stripes across the images. To recover missing data of a Landsat image, different methods may be used. However, the gap filling process creates inconsistencies on pixel intensity values. The incongruous pixel numbers are anomolous observations and their classification in the reference specter is challenging. In an effort to contribute to this need, we propose a reliable robust approach to classify inconsistent pixels after the gap filling process. To estimate multivariate location-scale parameters a new robust DMVV （depth minimum vector variance estimator） is presented. The DMVV algorithm does not require any matrix inversion for its calculation, consequently its computational time is highly reduced. The results show that it has a high breakdown point and is very efficient for large data set. Landsat remote sensing data of Jakarta Province across years 2002 and 2010 are used as case study.展开更多
An extended self-organizing map for supervised classification is proposed in this paper. Unlike other traditional SOMs, the model has an input layer, a Kohonen layer, and an output layer. The number of neurons in the ...An extended self-organizing map for supervised classification is proposed in this paper. Unlike other traditional SOMs, the model has an input layer, a Kohonen layer, and an output layer. The number of neurons in the input layer depends on the dimensionality of input patterns. The number of neurons in the output layer equals the number of the desired classes. The number of neurons in the Kohonen layer may be a few to several thousands, which depends on the complexity of classification problems and the classification precision. Each training sample is expressed by a pair of vectors ： an input vector and a class codebook vector. When a training sample is input into the model, Kohonen＇s competitive learning rule is applied to selecting the winning neuron from the Kohouen layer and the weight coefficients connecting all the neurons in the input layer with both the winning neuron and its neighbors in the Kohonen layer are modified to be closer to the input vector, and those connecting all the neurons around the winning neuron within a certain diameter in the Kohonen layer with all the neurons in the output layer are adjusted to be closer to the class codebook vector. If the number of training sam- ples is sufficiently large and the learning epochs iterate enough times, the model will be able to serve as a supervised classifier. The model has been tentatively applied to the supervised classification of multispectral remotely sensed data. The author compared the performances of the extended SOM and BPN in remotely sensed data classification. The investigation manifests that the extended SOM is feasible for supervised classification.展开更多
基金the Knowledge Innovation Program of the Chinese Academy of Sciences (No.kzcx2-yw-313)the National High Technology Research and Development Program of China (No. 2007AA12Z157)
文摘All of the Landsat 7 data collected after 2003 contains missing pixels in the form of unsightly stripes across the images. To recover missing data of a Landsat image, different methods may be used. However, the gap filling process creates inconsistencies on pixel intensity values. The incongruous pixel numbers are anomolous observations and their classification in the reference specter is challenging. In an effort to contribute to this need, we propose a reliable robust approach to classify inconsistent pixels after the gap filling process. To estimate multivariate location-scale parameters a new robust DMVV （depth minimum vector variance estimator） is presented. The DMVV algorithm does not require any matrix inversion for its calculation, consequently its computational time is highly reduced. The results show that it has a high breakdown point and is very efficient for large data set. Landsat remote sensing data of Jakarta Province across years 2002 and 2010 are used as case study.
基金Supported by National Natural Science Foundation of China (No. 40872193)
文摘An extended self-organizing map for supervised classification is proposed in this paper. Unlike other traditional SOMs, the model has an input layer, a Kohonen layer, and an output layer. The number of neurons in the input layer depends on the dimensionality of input patterns. The number of neurons in the output layer equals the number of the desired classes. The number of neurons in the Kohonen layer may be a few to several thousands, which depends on the complexity of classification problems and the classification precision. Each training sample is expressed by a pair of vectors ： an input vector and a class codebook vector. When a training sample is input into the model, Kohonen＇s competitive learning rule is applied to selecting the winning neuron from the Kohouen layer and the weight coefficients connecting all the neurons in the input layer with both the winning neuron and its neighbors in the Kohonen layer are modified to be closer to the input vector, and those connecting all the neurons around the winning neuron within a certain diameter in the Kohonen layer with all the neurons in the output layer are adjusted to be closer to the class codebook vector. If the number of training sam- ples is sufficiently large and the learning epochs iterate enough times, the model will be able to serve as a supervised classifier. The model has been tentatively applied to the supervised classification of multispectral remotely sensed data. The author compared the performances of the extended SOM and BPN in remotely sensed data classification. The investigation manifests that the extended SOM is feasible for supervised classification.
