Remote Sensing Image Classification by PSONN
|
Title | Remote Sensing Image Classification by PSONN |
Authors | |
Abstract | Polarimetric synthetic aperture radar has attracted the research interest among numerous scholars and researchers. It plays an important role in either the military or the domestic fields. In this study, we proposed a novel Polarimetric SAR image classification method. We first extract the feature sets including span image, the H/A/α decomposition, and the gray-level co-occurrence matrix based texture features. Afterwards, we used an artificial neural network to construct the classifier and chose the particle swarm optimization method as the training algorithm. The experiments used the San Francisco area as the test data, and compared our PSONN method with traditional IPNN method and SVM method. The results show that our method achieves the best classification accuracy as 96.55%, meanwhile, IPNN and SVM only achieved 96.13% and 96.43% classification accuracy, respectively. Therefore, our method is effective. |
Publisher | World Science Publisher |
Date | 2012-06-06 |
Source | 2167-6372 |
Rights | Copyright NoticeProposed Creative Commons Copyright Notices1. Proposed Policy for Journals That Offer Open AccessAuthors who publish with this journal agree to the following terms:Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work´s authorship and initial publication in this journal.Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal´s published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).Proposed Policy for Journals That Offer Delayed Open AccessAuthors who publish with this journal agree to the following terms:Authors retain copyright and grant the journal right of first publication, with the work [SPECIFY PERIOD OF TIME] after publication simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work´s authorship and initial publication in this journal.Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal´s published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access). |