Mahesh Pal

Achala Shakya, Mantosh Biswas, Mahesh Pal

SAR (VV and VH polarization) and optical data are widely used in image fusion to use the complimentary information of each other and to obtain the better-quality image (in terms of spatial and spectral features) for the improved classification results. This paper uses anisotropic diffusion with PCA for the fusion of SAR and optical data and patch-based SVM Classification with LBP (LBP-PSVM). Fusion results with VV polarization performed better than VH polarization using considered fusion method. For classification, the performance of LBP-PSVM using S1 (VV) with S2, S1 (VH) with S2 is compared with SVM classifier (without patch) and PSVM classifier (with patch), respectively. Classification results suggests that the LBP-PSVM classifier is more effective in comparison to SVM and PSVM classifiers for considered data.

Mahesh Pal, Akshay, B. Charan Teja

We proposes a simple deep learning architecture combining elements of Inception, ResNet and Xception networks. Four new datasets were used for classification with both small and large training samples. Results in terms of classification accuracy suggests improved performance by proposed architecture in comparison to Bayesian optimised 2D-CNN with small training samples. Comparison of results using small training sample with Indiana Pines hyperspectral dataset suggests comparable or better performance by proposed architecture than nine reported works using different deep learning architectures. In spite of achieving high classification accuracy with limited training samples, comparison of classified image suggests different land cover classes are assigned to same area when compared with the classified image provided by the model trained using large training samples with all datasets.

Mahesh Pal, Akshay, Himanshu Rohilla et al.

Pixel based algorithms including back propagation neural networks (NN) and support vector machines (SVM) have been widely used for remotely sensed image classifications. Within last few years, deep learning based image classifier like convolution neural networks (2D-CNN) are becoming popular alternatives to these classifiers. In this paper, we compare performance of patch based SVM and NN with that of a deep learning algorithms comprising of 2D-CNN and fully connected layers. Similar to CNN which utilise image patches to derive features for further classification, we propose to use patches as an input in place of individual pixel with both SVM and NN classifiers. Two datasets, one multispectral and other hyperspectral data was used to compare the performance of different classifiers. Results with both datasets suggest the effectiveness of patch based SVM and NN classifiers in comparison to state of art 2D-CNN classifier.

Mahesh Pal

With the advancement in computing power over last decades, deep neural networks (DNN), consisting of two or more hidden layers with large number of nodes, are being suggested as an alternate to commonly used single-hidden-layer neural networks (ANN). DNN are found to be flexible models with a very large number of parameters, thus making them capable of modelling very complex and highly nonlinear relationships existing between inputs and outputs. This paper investigates the potential of a DNN consisting of 3 hidden layers (100, 80 and 50 nodes) to predict the local scour around bridge piers using field data. To update the weights and bias of DNN, an adaptive learning rate optimization algorithm was used. The dataset consists of 232 pier scour measurements, out of which a total of 154 data were used to train whereas remaining 78 data to test the created model. A correlation coefficient value of 0.957 (root mean square error = 0.306m) was achieved by DNN in comparison to 0.938 (0.388m) by ANN, indicating an improved performance by DNN for scour depth perdition. Encouraging performance on the used dataset in the work suggests the need of more studies on the use of DNN for various civil engineering applications.