Search

This paper presents a novel method of landslide detection by exploiting the Mask R-CNN capability of identifying an object layout by using a pixel-based segmentation, along with transfer learning used to train the proposed model. A data set of 160 elements is created containing landslide and non-landslide images. The proposed method consists of three steps: (i) augmenting training image samples to increase the volume of the training data, (ii) fine tuning with limited image samples, and (iii) performance evaluation of the algorithm in terms of precision, recall and F1 measure, on the considered landslide images, by adopting ResNet-50 and 101 as backbone models. The experimental results are quite encouraging as the proposed method achieves Precision equals to 1.00, Recall 0.93 and F1 measure 0.97, when ResNet-101 is used as backbone model, and with a low number of landslide photographs used as training samples. The proposed algorithm can be potentially useful for land use planners and policy makers of hilly areas where intermittent slope deformations necessitate landslide detection as prerequisite before planning., Comment: 9 pages, 8 figures, 6 tables, submitted to JSTARS special issue on Cultural Heritage

Lossy JPEG compression is a widely used compression technique. Normally the JPEG standard technique uses three process mapping reduces interpixel redundancy, quantization, which is lossy process and entropy encoding, which is considered lossless process. In this paper, a new technique has been proposed by combining the JPEG algorithm and Symbol Reduction Huffman technique for achieving more compression ratio. The symbols reduction technique reduces the number of symbols by combining together to form a new symbol. As a result of this technique the number of Huffman code to be generated also reduced. It is simple fast and easy to implement. The result shows that the performance of standard JPEG method can be improved by proposed method. This hybrid approach achieves about 20% more compression ratio than the Standard JPEG., Comment: 11 pages,9 figures, SIP 2012 held on 3-4 January 2012,at Bangalore,India. arXiv admin note: text overlap with standard references on JPEG without attribution

The time decay of the thermoremanent magnetization(TRM) of the $\mbox{Fe}_{80-\mbox{x}}\mbox{Ni}_{\mbox{x}}\mbox{Cr}_{20}$ ($14\leq \mbox{x} \leq 30$) alloys has been measured for four different magnetic phases within the fcc $\mbox{$\gamma$}$-phase using a SQUID magnetometer. In the spin-glass phase(SG)(X=19) very distinct ageing effects are observed where M(t) can be described as $M(t)=M_0(t/t_{w})^{-\gamma}\exp[-(t/\tau)^{1-n}]$ for the entire time domain. In the reentrant spin-glass(RSG)(X= 23 and 26), M(t) can be better represented by the stretched exponential with an addition of a constant term which can be well explained by the Gabay-Toulouse(GT) model. We have also measured the linear and non-linear ac susceptibilities for the sample X=23 and confirmed the presence of the ferromagnetic(FM) ordering down to the lowest temperature. In the RSG(X=23), the TRM shows a minimum near T$_{\mbox{c}}$ and a local maximum just above T$_{\mbox{c}}$. In the FM phase (X=30) the popular prediction of the power law decay of the TRM is observed. The latter is indistinguishable from the stretched exponential in the antiferromagnetic(AF) phase (X=14)., Comment: Figures available upon request