Pouya Ahmadi; Tayebe Managhebi; Hamid Ebadi; Behnam Asghari
Abstract
With the development of remote sensing science, the use of hyperspectral images is becoming more widespread. Classification is one of the most popular topics in hyperspectral remote sensing. In the last two decades, a number of methods have been proposed to address the problem of hyperspectral data classification.In ...
Read More
With the development of remote sensing science, the use of hyperspectral images is becoming more widespread. Classification is one of the most popular topics in hyperspectral remote sensing. In the last two decades, a number of methods have been proposed to address the problem of hyperspectral data classification.In the present study, a structure based on learning capsule networks has been used to classify hyperspectral images, so that the network structure can have the most optimal generation of features by using a convolution layer and a capsule layer, and at the same time Avoid overfitting the on training data. The obtained results show the high quality of production features in the proposed structure. With the development of remote sensing science, the use of hyperspectral images is becoming more widespread. Classification is one of the most popular topics in hyperspectral remote sensing. In the last two decades, a number of methods have been proposed to address the problem of hyperspectral data classification.In the present study, a structure based on learning capsule networks has been used to classify hyperspectral images, so that the network structure can have the most optimal generation of features by using a convolution layer and a capsule layer, and at the same time Avoid overfitting the on training data. The obtained results show the high quality of production features in the proposed structure.In order to improve the classification accuracy, the feature extraction approach through the designed network and the classification by the Extreme Gradient Boosting was compared with the classification method by the global deep network. The proposed capsule approach consists of 3 basic layers: 1) Prime caps, which are capsules of size 8 and 32 with 9 × 9 filters and movement step 2, 2) Digitcaps with 10 16-dimensional capsules, and 3) fully connected layer. The results of examining two approaches for deep networking as well as combining capsule networks with XGBoost reinforcement tree algorithm were compared. Approaches such as SVM, RF-200, LSTM, GRU and GRU-Pretanh were considered to compare the proposed approach based on the configurations mentioned in their research.Up in addition to the study and quality measurement of production vector deep features by the proposed method in different classifiers, the ability of deep global networks in the application of classification should also be examined. The results of examining two approaches for deep network and also combining CapsNet with XGBoost show that by using the proposed combined method, images are classified with 99% accuracy on training data and 97.5% accuracy on test data.Up in addition to the study and quality measurement of production vector deep features by the proposed method in different classifiers, the ability of deep global networks in the application of classification should also be examined.The results of examining two approaches for deep network and also combining CapsNet with XGBoost show that by using the proposed combined method, images are classified with 99% accuracy on training data and 97.5% accuracy on test data.
T Managhebi; Y Maghsoudi; M.J Valadan Zoej
Volume 9, Issue 4 , May 2017, , Pages 59-72
Abstract
This paper provides an advanced method to improve results of three stage inversion algorithm using polarimetric synthetic aperture radar interferometry (PolInSAR) technique based on Random Volume over Ground model. In conventional three stage method, the ground phase, extinction coefficient and volume ...
Read More
This paper provides an advanced method to improve results of three stage inversion algorithm using polarimetric synthetic aperture radar interferometry (PolInSAR) technique based on Random Volume over Ground model. In conventional three stage method, the ground phase, extinction coefficient and volume layer is estimated in a geometrical way without the need for a prior information or separate reference DEM. The extinction and volume height estimation is done in the third stage by searching in the two dimension area. In the proposed algorithm, defining a new geometrical index, based on signal penetration in the forest, imposes a limited range for the extinction coefficient. The new index, as an axillary data, help search in a more appropriate space. The proposed algorithm was applied on L-band ESAR single baseline single frequency polarimetric SAR interferometry data. As a result of applying this restriction in the extinction range, a 2.5 meter improvement was observed in the RMSE of proposed algorithm compared to the three stage method.