Over the past decade, using Interferometric Synthetic Aperture Radar (InSAR) remote sensing technology for ground displacement detection has become very successful. However, during the acquisition stage, microwave signals reflected from the ground and received by the satellite are contaminated, for example, due to undesirable material reflectance and atmospheric factors, and there is no clean ground truth to discriminate these noises, which adversely affect InSAR phase computation. Accurate InSAR phase filtering and coherence estimation are crucial for subsequent processing steps. Current methods require expert supervision and expensive runtime to evaluate the quality of intermediate outputs, limiting the usability and scalability in practical applications, such as wide area ground displacement monitoring and predication. We propose a deep convolutional neural network based model DeepInSAR to intelligently solve both phase filtering and coherence estimation problems. We demonstrate our model’s performance using simulated and real data. A teacher-student framework is introduced to handle the issue of missing clean InSAR ground truth. Quantitative and qualitative evaluations show that our teacher-student approach requires less input but can achieve better results than its stack-based teacher method even on new unseen data. The proposed DeepInSAR also outperforms three other top non-stack based methods in time efficiency without human supervision.

Interferometric Synthetic Aperture Radar (InSAR) imagery for estimating ground movement, based on microwaves reflected off ground targets is gaining increasing importance in remote sensing. However, noise corrupts microwave reflections received at satellite and contaminates the signal's wrapped phase. We introduce Convolutional Neural Networks (CNNs) to this problem domain and show the effectiveness of autoencoder CNN architectures to learn InSAR image denoising filters in the absence of clean ground truth images, and for artefact reduction in estimated coherence through intelligent preprocessing of training data. We compare our results with four established methods to illustrate superiority of proposed method.

Abstract-No reference image quality assessment(NR-IQA) on true High Dynamic Range (HDR) images is an unexplored and interesting research topic that has become relevant with the current boom in HDR technology. We first conduct a study on the performance of existing algorithms for NR-IQA, originally developed for Low Dynamic Range images(LDR), on HDR data. Using the results of our investigation, we then propose a new convolutional architecture for NR-IQA achieving state of the art performance in terms of correlation to human judgment on quality. The proposed model disentangles perceptual effects exhibited by the distorted image from the noise present in the image and is capable of extracting perceptually relevant features without the necessity of handcrafting the features. Our architecture predicts the amount and location of the visual errors present in the distorted images without the reference image and performs comparably to the state of the art Full Reference Image Quality assessment(FR-IQA) algorithms.

No abstract

Image Quality Assessment (IQA) algorithms evaluate the perceptual quality of an image using evaluation scores that assess the similarity or difference between two images. We propose a new low level feature based IQA technique, which applies filter-bank decomposition and center-surround methodology. Differing from existing methods, our model incorporates color intensity adaptation and frequency scaling optimization at each filter-bank level and spatial orientation to extract and enhance perceptually significant features. Our computational model exploits the concept of object detection and encapsulates characteristics proposed in other IQA algorithms in a unified architecture. We also propose a systematic approach to review the evolution of IQA algorithms using unbiased test datasets, instead of looking at individual scores in isolation. Experimental results demonstrate the feasibility of our approach.