Selected Publications

A novel physics-based deep learning technique was proposed which overcomes the traditional limitations of training such networks by augmenting the input information from target simulations.
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2013

A novel tensorization framework is proposed, which utilizes the Kronecker product to combine multifrequency polarimetric synthetic aperture radar data in conjunction with an artificial neural network (ANN) for classification. The ANN comprises of two stages, where an unsupervised stochastic sampling autoencoder learns an efficient representation and a supervised feed forward network performs classification. The proposed framework is demonstrated using multifrequency (C-, L-, and P-bands) data sets collected by the AIRSAR system. The classification performance of single tensor product of dual- and triple-band combinations is evaluated. It is observed that the classification accuracy of the tensor products outperforms single, as well as, the simple augmentation of the frequency bands.
IEEE Geoscience and Remote Sensing Letters,2013

Recent Publications

More Publications

. Change detection in polarimetric SAR images using a geodesic distance between scattering mechanisms. IEEE Geoscience and Remote Sensing Letters, 2017.

. Local contrast based adaptive SAR speckle filter. Journal of the Indian Society of Remote Sensing, 2017.

. Predicting the popularity of instagram posts for a lifestyle magazine using deep learning. Communication Systems, Computing and IT Applications (CSCITA), 2017 2nd International Conference on, 2017.

. A learning tool for optical and microwave satellite image processing and analysis. Multispectral, Hyperspectral, and Ultraspectral Remote Sensing Technology, Techniques and Applications VI, 2016.

. An unsupervised hidden markov random field based segmentation of polarimetric SAR images. Geoscience and Remote Sensing Symposium (IGARSS), 2016 IEEE International, 2016.

. A New Target Decomposition Technique for Compact Polarimetric SAR Data. Lunar and Planetary Science Conference, 2015.

. MMSE based seed selection in IDAN speckle filter with point target preservation. International Journal of Imaging and Robotics, 2015.

. Modifying the Yamaguchi four-component decomposition scattering powers using a stochastic distance. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2015.

. Remote estimation of dielectric permittivity of lunar surface regolith using compact polarimetric synthetic aperture radar data. Advances in Space Research, 2015.

. Selection of suitable window size for speckle reduction and deblurring using SOFM in polarimetric SAR images. Journal of the Indian Society of Remote Sensing, 2015.

Recent & Upcoming Talks

Recent Posts

The phrase “it’s not an exact science” often surprises me, mainly because nothing probably is. To an outside observer it may seem to be a craft of precision, but its practitioners know that if anything, science and engineering is fundamentally comprised of abstraction and approximation. The greatest engineering marvels, the most breathtaking scientific breakthroughs are nothing but an approximation with tolerances. A probability, that in all sense of practicality, the stated hypothesis is true. Engineers have a word for the process of approximation inherent in their design process; they call it “eyeballing it”. Slang for approximation a particular measurement that is perhaps too tedious, or too complicated to account for, and can be successfully approximated with little consequence to the overall system.

CONTINUE READING

Projects

Custom Section

This is an example of using the custom widget to create your own homepage section.

To remove this section, either delete content/home/teaching.md or edit the frontmatter of the file to deactivate the widget by setting active = false.

Tags

Contact