Earth observation (EO) plays a crucial role in creating and sustaining a resilient and prosperous society that has far reaching consequences for all life and the planet itself. Remote sensing platforms like satellites, airborne platforms, and more recently dones and UAVs are used for EO. They collect large amounts of data and this needs to be downlinked to Earth for further processing and analysis. Bottleneck for such high throughput acquisition is the downlink bandwidth. Data-centric solutions to image compression is required to address this deluge. In this work, semantic compression is studied through a compressed learning framework that utilizes only fast and sparse matrix-vector multiplication to encode the data. Camera noise and a communication channel are the considered sources of distortion. The complete semantic communication pipeline then consists of a learned low-complexity compression matrix that acts on the noisy camera output to generate onboard a vector of observations that is downlinked through a communication channel, processed through an unrolled network and then fed to a deep learning model performing the necessary downstream tasks; image classification is studied. Distortions are compensated by unrolling layers of NA-ALISTA with a wavelet sparsity prior. Decoding is thus a plug-n-play approach designed according to the camera/environment information and downstream task. The deep learning model for the downstream task is jointly fine-tuned with the compression matrix and the unrolled network through the loss function in an end-to-end fashion. It is shown that addition of a recovery loss along with the task dependent losses improves the downstream performance in noisy settings at low compression ratios.
Forests are an integral part of the natural environment providing social, economic, and environmental benefits. Though storms are an important part of natural forest dynamics, large magnitude storms can lead to uprooting of trees, known as windthrows. Post-storm management relies on proper and fast detection of windthrows. In this work, we study the detection of windthrows due to storm David in the coniferous forests of southern Lower-Saxony, Germany as an image segmentation problem. Two deep learning methods, previously researched U-Nets and current state-of-the-art DeepLabv3+ are compared. Often storm damaged forests are surveyed many months later under good weather conditions, however, we study a winter storm surveyed in winter conditions 19 days after the storm. Moreover, we generate a detailed prediction map by segmenting the input scenery into four classes, namely, no forest, forest with no windthrows, forests with windthrows, and cleared areas. The data consists of four spectral channels and we study different 3-channel combinations and input image tile sizes to obtain the best configuration for windthrow detection. DeepLabv3+ is found to outperform U-Net with a prediction accuracy of 86.27% for windthrows, with best accuracy of 95.03% across all classes, and a class IoU of 0.7440 compared to a prediction accuracy of 78.66% and class IoU of 0.6892 for U-Nets. Deeplabv3+ was able to process 2048 × 2048 mosaics with input image tile size of 512 × 512 in nearly 889ms. Thus, a fast and well performing windthrow detection model based on DeepLabv3+ is developed.
Traditional compressed sensing matrices like the Gaussian random matrices and Bernoulli matrices are signal structure agnostic due to their adherence to the Restricted Isometry Property (RIP). However, practical measurement operators like the Walsh measurement matrix do not posses RIP and their reconstruction quality can be improved when the measurements are adapted to the signal structure. Sparsity in natural images decay in an asymptotic manner with dense low spatial frequency subbands and sparser higher frequency subbands. Existing methods use decaying power laws to generate a probability map that mimics this sparsity behaviour. Specifying the subbands to sample and the number of measurements to sample in each subband is difficult in such methods. Also generating frequency selective maps is difficult. We propose a sampling pattern design procedure that adheres to the asymptotic sparsity principle but allows selection of the spatial frequency subbands. Bounds are provided such that maximum measurements are allocated to low spatial frequencies. Through experiments on airborne imagery we show that the proposed method works at-par with existing methods for regular imaging requirements. In an unknown environment the proposed method ensures acquisition of spatial frequencies as- sociated with maximum energy and allows easy and flexible design of sampling patterns for frequency selective imaging in specialized scenarios.
Imaging in deep infrared and terahertz region of the electromagnetic spectrum is difficult due to the unavailability of large sensor arrays. This can be mitigated by using single pixel detectors or radiometers along with a spatial light modulator. A framework for design and analysis of such imaging radiometer systems is presented. Remote exploration systems in space, deep ocean or disaster situations have limited power and computational resources. This puts a cap on the measurement budget of such systems. Apart from being power limited the exploration system must act on its own without external help. A three step sampling procedure involving image segmentation and compressive sampling is proposed which assigns the measurement budget based on coarse reconstructions of the scene. The sampling procedure is simulated using the framework and the effect of various system parameters on the final data output is analyzed. Simulations are performed to illustrate the capability of the framework to design such imaging systems and to study the trade offs between the optical, electrical and software domain.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.