In this study, we present an unsupervised methodology for detecting moving targets using Capella Space’s latest generation SAR sensor. The sensor has the capability to dwell on a target for an extended period of time in its spot-light (SP) mode, which we take advantage of to track moving objects in an acquisition. An approach that combines a signal-processing-based workflow with an image-domain-based one is presented. From one side, the long-dwell SAR image is exploit by doing an interfeometric processing of different azimuth sub-apertures from the long-dwell. From another side, a kernelized cross correlation technique is used. By combining intermediate results from these complementary workflows, a smooth and robust track is obtained on the targets. The algorithm is demonstrated on a long-dwell spotlight obtained over a busy shipping channel with watercraft both small and large successfully tracked.

The ability to automatically detect hard targets is highly beneficial for an imagery analyst. Their initial task in the information gathering process is to identify and interpret these targets in a scene. By automating the detection process, the workflow can be expedited. This paper presents an algorithm for detecting hard targets in long dwell spotlight (SP) Capella Space SAR images. The spectrum of the SP image is divided into non-overlaping sub-bands in order to compute the interferometric coherence between them. The proposed algorithm is tested on real spaceborne Capella SAR data showing the potential to clearly identify hard targets such as buildings, vehicles, and other artificial man-made objects.

This paper presents an innovative approach to archaeological and geological exploration, combining Synthetic Aperture Radar (SAR) imagery, Ground Penetrating Radar (GPR), and advanced robotic algorithms. Utilizing SAR data captured by Capella, the study identifies areas of interest (AOIs) through supervised classification methods. These AOIs are then surveyed by a UAV equipped with GPR, optimized for efficient pathfinding and maximal coverage using robotic exploration algorithms. The survey generates high-resolution radar images, detailed digital elevation models, and orthomosaic images through photogrammetry, providing a comprehensive view of both surface and subsurface features.

In this work we explore the potential of time series of high-resolution radar imagery from Capella Space to enable crop monitoring in areas characterised by very small agricultural fields. Thanks to the spatial resolution provided by the Capella Space SAR images, adjacent fields are well separated in the analysis and, consequently, can be properly monitored and classified. The high-resolution feature complements the all-weather and sun independent operation of radar, hence being an excellent asset for this application.

Floods are among the most common and devastating extreme weather events that cause damage to infrastructure, agricultural lands, transportation and communication systems. To effectively respond to floods, it is important to have accurate information about the depth of floodwater across the affected area, and ground surveys are not always possible in such scenarios. This information can be estimated remotely through the use of spaceborne synthetic aperture radar (SAR) systems, which are equipped to operate under nearly all weather and time conditions. Here, we present a case study of estimating the flood depth using inferred flood extents from the very high resolution (VHR) Capella Space X-band constellation. We have used a publicly available digital elevation model (DEM) with a Python-based implementation of the Floodwater Depth Estimation Tool (FwDET) to determine flood depth from the SAR imagery. We estimated the depth of floods in two major flood events (March 2021 and March 2022) in Hawkesbury Valley, New South Wales, Australia. Furthermore, we explored the utility of these depth maps for rapid flood damage assessments.

Taking advantage of Capella’s ability to dwell on a target for an extended period of time (nominally 30s) in its spotlight (SP) mode, an unsupervised methodology for detecting moving targets in this data is presented in this paper. By colourizing short segments (sub-apertures) of the total imaging time, a colourised sub-aperture image (CSI) can be formed. This can be used in conjunction with well-established computer vision techniques to detect moving targets and track them in the SP image. In essence, the moving target detection problem is transformed from temporal image stack identification to colour segmentation in a single image. The presented detection and tracking are wholly unsupervised. Additionally, computer-vision-based tracking algorithms are demonstrated on detected movers and qualitatively assessed for accuracy of tracking.

Capella Space is the first US commercial company to build, launch, and operate a constellation of synthetic aperture radar satellites capable of collecting very high resolution SAR imagery. All satellites in the constellation carry an X-band radar capable of acquiring imagery in spotlight, sliding spotlight, and stripmap modes. In 2023, Capella will launch the first of a new generation of satellites names Acadia. These satellites will provide high quality imagery and lay the platform for advanced SAR data products, such as interferometric SAR and bistatic imagery.

Satellites are often used to observe, understand, and track movement at the earth’s surface. SAR is an especially powerful tool for such applications due to its persistent viewing capability; it operates day or night and penetrates clouds, smoke, and other particulate cover that can occlude the ground from other instruments, like optical. There are many known techniques specific to determining motion in SAR data. However, this paper will apply an optical flow open source package, like Particle Image Velocimetry (PIV), to determine motion in SAR data provided by Capella Space. Movement will be analyzed across target velocities by implementing this technique on subapertures from a single collection and across a time-series collection over a given Area of Interest (AOI). Sample use cases in this paper include large ice blocks moving through a glacial mélange and moving ships on open water.

Capella's first commercial Synthetic Aperture Radar (SAR) satellite was launched in August 2020. After more than one year of successful operations, Capella plans a continuous growth of both number of satellites and satellite capabilities. New tasking patterns allow the collection of pairs and time series of very high resolution (VHR) SAR images. A novel repeat tasking request pattern will enable SAR applications such as change detection and the exploitation of interferometric SAR (InSAR) techniques. The combination of on-board GPUs and dedicated on-board processing algorithms will be used for rapid target detection and minimized satellite downlink. On-board processing, applicable in many quasi real-time operational scenarios, can also be used for tipping and cueing other satellites to immediately capture a high resolution imagery. Finally, Capella Space Open Data program started in 2021 with new images added each quarter.

The rapid delineation of water extent in a flood-type event can be very beneficial to disaster relief efforts, and Synthetic Aperture Radar (SAR) is a modality ideally suited for such mapping. However, in a rapid-response scenario, it is desirable to produce such maps independent of historical or external data. To this end, we have propose a scheme to produce flood event maps from a single high-resolution StripMap (SM) imagery acquired from the Capella Space X-band VHR SAR constellation. The learning algorithm is solely trained on publicly available ancillary data, without the use of any human generated labels. The flood-maps are validated quantitatively on non-event scenes against water-occurrence data and qualitatively over the course of a flood-event caused by Hurricane Ida's landfall.

Floods are among the most common and destructive extreme weather events in the world. Spaceborne synthetic aperture radar (SAR) systems are well-suited for monitoring flood events given their ability to operate in near all-weather and all-time conditions. We present a case study classifying imagery from both the commercial very high resolution (VHR) Capella Space X-band constellation and the public C-band Sentinel-1 mission. We use inferred flood extents from these disparate sources to investigate the progression of unprecedented inundation over Abbotsford, British Columbia in November - December 2021.

Small-sat systems are providing unprecedented access to remote sensing data and at a cost far lower than traditional spacecraft. This makes them appealing for a range of environmental and humanitarian monitoring applications previously thought unfeasible. In this paper we are demonstrating Capella Space's VHR X-band SAR, high-revisit satellite constellation applied to rice agriculture, glaciology, and a particular focus on urban mapping.

Unmanned Aerial Vehicle (UAV) based aerial mapping has taken over the surveying industry thanks to low costs and ease of use. Although these UAVs have relatively high-resolution imaging systems, there exists a near exponential relationship between the ground sampling distance (GSD) and the number of images required - which is a function of flight altitude. To tackle this, we use a generative network based super-resolution approach to increase the GSD of images which effectively reduces flight time. In this paper we test the efficiency and efficacy of this approach using two multimedia super-resolution implementations. We also provide quantitative results comparing the two using various image processing metrics.

Future PolSAR missions are expected to collect vast quantities of data, which can significantly add to the storage cost of various geospatial cloud driven applications. Data compression techniques like those prescribed by the JPEG2000 (JP2) standard might help counteract this cost. However, it is important to measure the impact on target application performance due to these techniques. In this paper, the impact of JP2 and JPEG compression on classification performance of PolSAR data is studied and it has been found that compression has no significant impact on Deep Neural Network (DNN) classification performance.

Owing to the unique all-weather, day-night imaging capabilities of Synthetic Aperture Radar (SAR) imaging, the modality is advantageous in the detection of anthropogenic activity. In this paper we present a fully unsupervised change detection framework that operates on Very High Resolution (VHR) SAR image pairs to produce a binary change map, without a need for per-image parameter setting. The framework is demonstrated on a pair of Capella-2 VHR X-band imagery acquired over San Diego, USA.

Many applications utilizing SAR data, such as change detection, segmentation and classification, are impaired by the multiplicative speckle interference inherent in the imagery. Thus despeckling of SAR imagery is a often the key to developing robust algorithms for scene understanding. In recent years numerous deep learning-based approaches to speckle reduction have been proposed. However, the performance of these methods has largely failed to meet the expectations of researchers and industry alike. A key reason for this is due to the lack of accurate SAR-based ground truth training data. In this paper we propose the use of very high-resolution (VHR), low speckle aerial imagery and an accurate speckle model, as a ground truth signal for training a despeckling network based on the DnCNN architecture. Furthermore, we investigate modifications to the training formulation and finally demostrate the approach on Capella-2 VHR X-band imagery.

Polarimetric SAR (PolSAR) is uniquely able to capture structural and compositional properties of targets leading to improved performance in various classification applications over traditional single-polarization SAR. To aid in the interpretation of the return scatter, several decomposition techniques have been developed that attempt to classify the scene by presenting the return power as a combination of pre-determined canonical targets. For most decomposition techniques, these relationships are derived from the physics of radar scatter, and thus the results of the segmentation are explainable in terms of observable physical phenomena. Recently, Deep Neural Networks (DNNs) have emerged as a leading strategy for classifying PolSAR data. While effective, these techniques are dependent on discovering relationships between the data and provided supervised labels during an exploratory phase of the algorithm called “training”. The inter-dependencies are embedded into the weights of the network and are subsequently used to perform classification of the unlabeled data samples. Since the entire process is data-driven, it can be difficult to explain the outcomes of the algorithm physically. In this paper, we begin to explore the relationship between radar physics and the latent space embedded in the networks during supervised training. The goal is to explore current and future possibilities of explaining the results of deep neural networks and relating their outputs to radar physics. This can help improve confidence in the outputs of DNNs and potentially illuminate strategies to further improve their performance by embedding physical constraints in their training and classification.

RISAT-1 data is acquired over Mumbai in hybrid and linear dual polarizations. The mean and standard deviation of backscattering coefficients ( σ0) are computed and have been analyzed for various land features. Classification accuracy between RISAT-1 hybrid and dual polarimetric data has been compared. The effect of different multilook on the classification accuracy is also studied. Wishart supervised and Support Vector Machine (SVM) classifiers are used for this study. It has been observed that the classification accuracy can be improved by using m-δ or m-χ decomposition along with Circular Polarization Ratio (CPR) and SPAN of hybrid polarimetric data.

Information from polarimetric synthetic aperture radar (PolSAR) imagery has been used for detecting built-up targets in classification problems, whereas it has been poorly exploited for change detection in multitemporal images. In this letter, we proposed an unsupervised approach for the detection of built-up changed areas from multitemporal full-polSAR images. The approach is based on the automatic thresholding of a novel change index based on the joint use of polarimetric span and average-alpha multitemporal information. The index is proposed for highlighting both constructed and demolished built-up elements. The experimental results on multitemporal UAVSAR images demonstrate that the proposed approach provides high detection accuracy and effectively separates among different types of changes, which is not the case with standard methods.

This paper presents a novel framework for snow cover mapping with multi-basis Poincare sphere parameters obtained from full-polarimetric SAR images in conjunction with an Auto-Encoder neural network. The neural network comprises of two stages where an unsupervised stochastic sampling Auto-Encoder (AE) learns a summarized representation of multi-basis polarimetric SAR data, and a supervised Feed Forward (FF) network performs classification. The proposed algorithm is demonstrated for snow-cover mapping using the Radarsat-2 (FQ-28) C-band full-polarimetric SAR datasets acquired over the Manali-Dhundi region of Himachal Pradesh, India. The results are visualized along with the NDSI-based snow cover map derived from the LANDSAT-8 imagery for the region.

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.

Urban change detection is an important part of monitoring operations and disaster relief efforts. However, often sufficient ground truth data is not available to use traditional supervised machine learning techniques. In this paper, a novel Deep Learning based weakly-supervised framework for urban change detection using multi-temporal polarimetric SAR data is proposed. A modified unsupervised stacked auto-encoder stage is used to learn an efficient representation of the multi-temporal polarimetric information. Then a label aggregation is performed in the feature space before classification by a multi-layer perceptron. The proposed methodology is validated on a L-band UAVSAR dataset acquired over Los Angeles, CA and performs accurately and effectively with a low false alarm rate.

Change detection in large urban areas is an application with increasing relevance. In this domain, Polarimetric SAR (PolSAR) sensors are receiving more attention recently. The enhanced polarimetric information provides useful features which can describe multi-temporal changes. In this work, we aim at introducing an approach for unsupervised change detection with focus on built-up areas that relies on the polarimetric information. This approach is based on the analysis of the multi-temporal α feature obtained from the Cloude-Pottier eigenvalue/eigenvector decomposition. Large differences in the α values can be associated to changes in the dominant scattering mechanism. These are likely to be associated to buildings when built-up areas are considered. Changes are detected according to an automatic and unsupervised approach. Validation is conducted on a pair of UAVSAR images acquired over Los Angeles, USA. Preliminary results highlight the effectiveness of proposed approach.

A novel technique to generate the difference image (DI) in change detection analysis for polarimetric SAR (PolSAR) data is proposed. Unlike the standard methods, viz., band difference or intensity/amplitude ratioing, the proposed technique utilizes the full vector nature of multitemporal PolSAR data. In this data, a pixel is characterized by a 4 × 4 Kennaugh matrix. The geodesic distance (GD) on an unit sphere is utilized to define the distance between the Kennaugh matrices of the three elementary targets (trihedral, dihedral, and 45° rotated dihedral about the radar line of sight) producing canonical scattering mechanisms and the observed Kennaugh matrix. Three absolute differences of the GD from respective elementary targets are obtained for time instants t1and t2. The DI is then the maximum among the three quantities. The proposed technique is applied to two scenes obtained from the L-band UAVSAR data characterizing changes due to urbanization. The principal component analysis with k-means clustering proposed by Celik is used to obtain the binary change map. The proposed differencing method performs better than the single-channel intensity band ratio and the total power ratio for time instants t1and t2. The detection rate with the proposed technique is 6% and 20% better than the ratio methods for the two data sets, respectively, with the higher κ value as a measure of performance evaluation.

This paper proposes an iterative unsupervised Markov Random Field (MRF) based segmentation technique for polarimetric Synthetic Aperture Radar (SAR) image using the optimized scattering mechanism similarity parameters. Parameter estimation for the MRF model is generally performed from the available training data in order to perform tasks including semantic image segmentation. Since the current scenario is entirely unsupervised, the parameter estimation is performed iteratively using the Expectation Maximization (EM) technique considering the classes are distributed according to Gaussian functions. Further, we model the pairwise potential of the MRF cost function using a weighted combination of the similarity parameters. Results obtained on a fully polarimetric SAR data establishes the potential of such unsupervised random field models for analyzing SAR data effectively.

The urban classification of PolSAR images is made difficult by the characteristic of a rotated target to exhibit volume scattering. In this paper we use a deep learning technique in conjunction with some statistical parameters to learn to classify urban areas irrespective of the rotation. The learning algorithm was trained to differentiate urban from non-urban areas and was able to achieve a 8.5834% validation accuracy and 6.554% test accuracy.

The angle of rotation (θ) of any object about the line of sight (LOS) is known as the polarization orientation angle (OA). The OA is found to be non-zero for undulating terrains and man-made targets oriented away from the radar LOS. This effect is more pronounced at lower frequencies (eg. L- and P-bands). The OA shift is not only induced by azimuthal slope but also by range slope. The OA shift increases the cross-polarization (HV) intensity and subsequently the co-variance or the coherency matrix becomes reflection asymmetric. Compensating this OA prior to any model-based decomposition technique for geophysical parameter estimation or classification is crucial. In this paper a new method has been proposed for OA estimation based on a stochastic distance. The OA is estimated by maximizing the Hellinger distance between the un-rotated and rotated diagonal elements of the coherency matrix.

In this paper, a new snow wetness estimation methodology is proposed for dual-coherent polarimetric Synthetic Aperture Radar (SAR) data. Surface and volume are the dominant scattering components in the wet-snow conditions. These components, with a limit of penetration depth of high frequency SAR, have been taken into account to estimate the snow-pack wetness. In this new methodology, snow surface wetness has been estimated using the IEM scattering model and snow volume wetness has been estimated under the Rayleigh scattering assumption. The estimated snow wetness is validated using the in-situ field measurements, which were collected synchronous with the satellite pass. In this study we have used dual-coherent TerraSAR-X data acquired over Solang, on 23 January 2009, Himachal Pradesh, India. Typically the snow wetness ranges from 0% to 15% by volume. On comparison with ground measurements, the proposed method shows that the mean absolute error in snow wetness inferred from the SAR imagery was 1.63% by volume.

In this paper we have classified Polarimetric Synthetic Aperture Radar (PolSAR) data using the Random Forest (RF) classifier. The variables were ranked using the mean decrease in accuracy permutation method for each terrain class. RADARSAT-2 (RS-2) data acquired over Mumbai, India was used in this study. This technique is able to efficiently classify the dataset, as well as rank the parameters used in that classifier.

The launch of RISAT-1 Indian remote sensing satellite on 26thApril 2012, made it possible to collect hybrid polarimetric data from a space-borne sensor. The RISAT-1 C-band compact polarimetry data acquired over Mumbai is analyzed and assessed for classification of various land features and also compared with other fully polarimetric spaceborene SAR data sets. For better comparison, RISAT-1 C-band and RADARSAT-2 C-band simulated compact polarimetric data is classified and compared.