Coastal wetlands are characterized by complex patterns both in their geomorphlc and ecological teatures. Besides field observations, it is necessary to analyze the land cover of wetlands through the color infrared （...Coastal wetlands are characterized by complex patterns both in their geomorphlc and ecological teatures. Besides field observations, it is necessary to analyze the land cover of wetlands through the color infrared （CIR） aerial photography or remote sensing image. In this paper, we designed an evolving neural network classifier using variable string genetic algorithm （VGA） for the land cover classification of CIR aerial image. With the VGA, the classifier that we designed is able to evolve automatically the appropriate number of hidden nodes for modeling the neural network topology optimally and to find a near-optimal set of connection weights globally. Then, with backpropagation algorithm （BP）, it can find the best connection weights. The VGA-BP classifier, which is derived from hybrid algorithms mentioned above, is demonstrated on CIR images classification effectively. Compared with standard classifiers, such as Bayes maximum-likelihood classifier, VGA classifier and BP-MLP （multi-layer perception） classifier, it has shown that the VGA-BP classifier can have better performance on highly resolution land cover classification.展开更多
The Point-In-Polyhedron problem is to check whether a point is inside or outside of a given polyhedron.When a degenerate case is detected,the traditional ray-crossing algorithms avoid the case by selecting a different...The Point-In-Polyhedron problem is to check whether a point is inside or outside of a given polyhedron.When a degenerate case is detected,the traditional ray-crossing algorithms avoid the case by selecting a different ray or erase the case by perturbing input data.This paper introduces a Threshold-Based Ray-Crossing (TBRC) algorithm for solving the Point-In-Polyhedron problem.The TBRC algorithm copes directly with degenerate cases by checking whether to count the face intersecting with the ray.It is worth mentioning that the TBRC algorithm can handle all degeneracies without extra computation and storage.Moreover,we analyze the basic algorithm and examine how to accelerate it.The experimental results show that TBRC algorithm is highly efficient and robust for the Point-In-Polyhedron problem,compared to a classical tetrahedron-based algorithm without pre-processing.展开更多
文摘Coastal wetlands are characterized by complex patterns both in their geomorphlc and ecological teatures. Besides field observations, it is necessary to analyze the land cover of wetlands through the color infrared （CIR） aerial photography or remote sensing image. In this paper, we designed an evolving neural network classifier using variable string genetic algorithm （VGA） for the land cover classification of CIR aerial image. With the VGA, the classifier that we designed is able to evolve automatically the appropriate number of hidden nodes for modeling the neural network topology optimally and to find a near-optimal set of connection weights globally. Then, with backpropagation algorithm （BP）, it can find the best connection weights. The VGA-BP classifier, which is derived from hybrid algorithms mentioned above, is demonstrated on CIR images classification effectively. Compared with standard classifiers, such as Bayes maximum-likelihood classifier, VGA classifier and BP-MLP （multi-layer perception） classifier, it has shown that the VGA-BP classifier can have better performance on highly resolution land cover classification.
基金the Joint Foundation of Guangdong Province and CAS (No.2009B091300149)
文摘The Point-In-Polyhedron problem is to check whether a point is inside or outside of a given polyhedron.When a degenerate case is detected,the traditional ray-crossing algorithms avoid the case by selecting a different ray or erase the case by perturbing input data.This paper introduces a Threshold-Based Ray-Crossing (TBRC) algorithm for solving the Point-In-Polyhedron problem.The TBRC algorithm copes directly with degenerate cases by checking whether to count the face intersecting with the ray.It is worth mentioning that the TBRC algorithm can handle all degeneracies without extra computation and storage.Moreover,we analyze the basic algorithm and examine how to accelerate it.The experimental results show that TBRC algorithm is highly efficient and robust for the Point-In-Polyhedron problem,compared to a classical tetrahedron-based algorithm without pre-processing.
