Research Domain
I work with Deep Learning algorithms to extract meaningful information from the images in remote sensing domain; primarily hyperspectral imageries, multispectral imageries and LiDAR.
For my PhD research project, I am working in hyperspectral image analysis and processing using deep learning techniques for several applications. Primarily, the research work is divided into three areas:
Image Classification: Image classification is one of the hottest topics in the remote sensing domain. The idea here is to research on and develop the techniques that can correctly identify the land use/ land cover classes present in the remotely sensed images. However, the problem still remains to be challenging one from different perspectives such as identifying the most suitable features/ bands, getting significantly good classification results with limited training samples, ensure that models are trained within limited time. As a PhD researcher, I am working on mitigating these problems and create more robust classification models. Figure 1 shows the the HSI classification maps from a recent research that uses attention mechanism for classification.
Missing Modality Prediction: Sometimes, it happens in remote sensing domain that while training the classification models, all the the modalities are available. However, during model deployment, a few of the features are not available. In such a scenario, it becomes important that the model is robust enough to handle the missing modality and give accurate predictions. This is another aspect of hyperspectral images that is the focus of PhD research. Here, I am working on the concept of knowledge distillation, using which the features of absent modality could be mimicked during the deployment phase, thus compensating for its absence. Figure 2 presents the components of the modality prediction/distillation framework (from the PhD research), to compensate for the missing bands .
Multimodal Fusion: The goal here is to work simultaneously with multiple sources of remote sensing data such as hyperspectral, multispectral, synthetic aperture radar (SAR), light detection and ranging (LiDAR). This proves to be challenging task because different modalities have different set of unique characteristics which make their simultaneous processing difficult. Furthermore, acquisition of data from different sensors also leads to difficulty in creating a mapping between the two modalities. For my PhD, I am researching on the efficient ways to combine the HSI data with different modalities (primarily LiDAR, because of its inherent elevation information) for better classification performance. A deep learning based HSI-LiDAR fusion framework is proposed as a part of PhD research (see Figure 3).
Key Areas
Remote Sensing, Machine Learning, Deep Learning, Hyperspectral Images, LiDAR, Image Processing