Search

Urban area mapping is an important application of remote sensing which aims at both estimation and change in land cover under the urban area. A major challenge being faced while analyzing Synthetic Aperture Radar (SAR) based remote sensing data is that there is a lot of similarity between highly vegetated urban areas and oriented urban targets with that of actual vegetation. This similarity between some urban areas and vegetation leads to misclassification of the urban area into forest cover. The present work is a precursor study for the dual-frequency L and S-band NASA-ISRO Synthetic Aperture Radar (NISAR) mission and aims at minimizing the misclassification of such highly vegetated and oriented urban targets into vegetation class with the help of deep learning. In this study, three machine learning algorithms Random Forest (RF), K-Nearest Neighbour (KNN), and Support Vector Machine (SVM) have been implemented along with a deep learning model DeepLabv3+ for semantic segmentation of Polarimetric SAR (PolSAR) data. It is a general perception that a large dataset is required for the successful implementation of any deep learning model but in the field of SAR based remote sensing, a major issue is the unavailability of a large benchmark labeled dataset for the implementation of deep learning algorithms from scratch. In current work, it has been shown that a pre-trained deep learning model DeepLabv3+ outperforms the machine learning algorithms for land use and land cover (LULC) classification task even with a small dataset using transfer learning. The highest pixel accuracy of 87.78% and overall pixel accuracy of 85.65% have been achieved with DeepLabv3+ and Random Forest performs best among the machine learning algorithms with overall pixel accuracy of 77.91% while SVM and KNN trail with an overall accuracy of 77.01% and 76.47% respectively. The highest precision of 0.9228 is recorded for the urban class for semantic segmentation task with DeepLabv3+ while machine learning algorithms SVM and RF gave comparable results with a precision of 0.8977 and 0.8958 respectively. [ABSTRACT FROM AUTHOR]

Oil spills are a potential hazard, causing the deaths of millions of aquatic animals and this leaves a calamitous effect on the marine ecosystem. This research focuses on evaluating the potential of polarimetric parameters in discriminating the oil slick from water and also possible thicker/thinner zones within the slick. For this purpose, L-band UAVSAR quad-pol data of the Gulf of Mexico region is exploited. A total number of 19 polarimetric parameters are examined to study their behavior and ability in distinguishing oil slick from water and its own less or more oil accumulated zones. The simulation of compact-pol data from UAVSAR quad-pol data is carried out which has shown good performance in detection and discrimination of oil slick from water. To know the extent of separation between oil and water classes, a statistical separability analysis is carried out. The outcomes of each polarimetric parameter from separability analysis are then quantified with the radial basis function (RBF) supervised Support Vector Machine classifier followed with an accurate estimation of the results. Moreover, a comparison of the achieved and estimated accuracy has shown a significant drop in accuracy values. It has been observed that the highest accuracy is given by LHV compact-pol decomposition and coherency matrix with a classification accuracy of ~ 94.09% and ~ 94.60%, respectively. The proposed methodology has performed well in discriminating the oil slick by utilizing UAVSAR dataset for both quad-pol and compact-pol simulation. [ABSTRACT FROM AUTHOR]