Accelerating Ukraine Intelligence Evaluation with Pc Imaginative and prescient on Artificial Aperture Radar Imagery


Determine 1: Airmass measurements (clouds) over Ukraine from February 18, 2022 – March 01, 2022 from the SEVIRI instrument. Information accessed by way of the EUMETSAT Viewer.

Satellite tv for pc imagery is a important supply of data in the course of the present invasion of Ukraine. Army strategists, journalists, and researchers use this imagery to make selections, unveil violations of worldwide agreements, and inform the general public of the stark realities of conflict. With Ukraine experiencing a considerable amount of cloud cowl and assaults typically occuring throughout night-time, many types of satellite tv for pc imagery are hindered from seeing the bottom. Artificial Aperture Radar (SAR) imagery penetrates cloud cowl, however requires particular coaching to interpret. Automating this tedious process would allow real-time insights, however present laptop imaginative and prescient strategies developed on typical RGB imagery don’t correctly account for the phenomenology of SAR. This results in suboptimal efficiency on this important modality. Enhancing the entry to and availability of SAR-specific strategies, codebases, datasets, and pretrained fashions will profit intelligence companies, researchers, and journalists alike throughout this important time for Ukraine.

On this put up, we current a baseline technique and pretrained fashions that allow the interchangeable use of RGB and SAR for downstream classification, semantic segmentation, and alter detection pipelines.


We reside in a quickly altering world, one which experiences pure disasters, civic upheaval, conflict, and all kinds of chaotic occasions which depart unpredictable—and sometimes everlasting—marks on the face of the planet. Understanding this transformation has traditionally been troublesome. Surveyors had been despatched out to discover our new actuality, and their distributed findings had been typically noisily built-in right into a supply of actuality. Sustaining a relentless state of vigilance has been a purpose of mankind since we had been capable of conceive such a thought, all the way in which from when Nadar took the primary aerial {photograph} to when Sputnik 1’s radio indicators had been used to research the ionosphere.

Vigilance, or to the French, surveillance, has been part of human historical past for millenia. As with every instrument, it has been a double-edged sword. Traditionally, surveillance with out checks and balances has been detrimental to society. Conversely, the right and accountable surveillance has allowed us to study deep truths about our world which have resulted in advances within the scientific and humanitarian domains. With the quantity of satellites in orbit at present, our understanding of the atmosphere is up to date nearly day by day. We have now quickly transitioned from having little or no data to now having extra knowledge than we are able to meaningfully extract information from. Storing this data, not to mention understanding, is an engineering problem that’s of rising urgency.

Machine Studying and Distant Sensing

With a whole bunch of terabytes of information being downlinked from satellites to knowledge facilities each day, gaining information and actionable insights from that knowledge with handbook processing has already turn into an unimaginable process. Essentially the most broadly used type of distant sensing knowledge is electro-optical (EO) satellite tv for pc imagery. EO imagery is commonplace—anybody who has used Google Maps or comparable mapping software program has interacted with EO satellite tv for pc imagery.

Machine studying (ML) on EO imagery is utilized in all kinds of scientific and industrial purposes. From bettering precipitation predictions, analyzing human slavery by figuring out brick kilns, to classifying complete cities to enhance site visitors routing, the outputs of ML on EO imagery have been built-in into nearly each aspect of human society.

Determine 2: VHR EO imagery over the Kyiv area as acquired by Maxar on February 28, 2022.

Generally used satellite tv for pc constellations for EO imagery embody the Landsat collection of satellites operated by the USA Geological Survey and the Copernicus Sentinel-2 constellation operated by the European Area Company. These constellations present imagery at resolutions between 10-60 meters which is nice sufficient for a lot of use circumstances, however preclude the remark of finer particulars.

The Creation of Very Excessive Decision, Business Electro-Optical Satellite tv for pc Imagery

Over the previous few years, very excessive decision (VHR) EO imagery has been made out there by a wide range of industrial sources. Starting from between 0.3 – 2.0 meter decision, firms comparable to Planet, Maxar, Airbus, and others are offering extraordinarily exact imagery with excessive revisit charges, imaging the whole planet each day.

Determine 3: An instance of Maxar VHR EO imagery exhibiting floating manufacturing, storage and off-loading items and a tanker.

The elevated decision supplied by VHR imagery allows a litany of downstream use circumstances. Erosion might be detected at finer scales, and the constructing harm might be categorized after pure disasters.

Machine studying strategies have needed to adapt in response to VHR satellite tv for pc imagery. With an elevated acuity, the quantity of pixels and the quantity of lessons that may be discerned has elevated by orders of magnitude. Pc imaginative and prescient analysis has responded by lowering the computational price to study environment friendly illustration of satellite tv for pc imagery, creating strategies to alleviate the elevated burden on labelers, and even engineering giant software program frameworks to permit laptop imaginative and prescient practitioners to deal with this considerable supply of images.

Basically, current laptop imaginative and prescient strategies on different, non-aerial RGB imagery switch very effectively to satellite tv for pc imagery. This has allowed industrial VHR imagery to be instantly helpful with extremely correct outcomes.

The Downside with Electro-Optical Imagery

For extremely turbulent and dangerous conditions comparable to conflict and pure disasters, having fixed, dependable entry to the Earth is paramount. Sadly, EO imagery can’t remedy all of our surveillance wants. EO can solely detect mild sources throughout daytime, and because it seems, almost 2/3rds of the Earth is roofed by clouds at any given time. Except you care about clouds, this blockage of the floor of the planet is problematic when understanding what occurs on the bottom is of important significance. Machine studying strategies try and sidestep this downside by predicting what the world would appear to be with out clouds. Nonetheless, the lack of data is essentially irrecoverable.

Artificial Aperture Radar Imagery

Artificial aperture radar (SAR) imagery is an lively type of distant sensing during which a satellite tv for pc transmits pulses of microwave radar waves right down to the floor of the Earth. These radar waves mirror off the bottom and any objects on it and are returned again to the satellite tv for pc. By processing these pulses over time and area, a SAR picture is fashioned the place every pixel is the superposition of various radar scatters.

Radar waves penetrate clouds, and for the reason that satellite tv for pc is actively producing the radar waves, it illuminates the floor of the Earth even in the course of the night time. Artificial aperture radar has all kinds of makes use of, getting used to estimate the roughness of the Earth, mapping the extent of flooding over giant areas, and to detect the presence of unlawful fishing vessels in protected waters.

There are a number of SAR satellite tv for pc constellations in operation in the mean time. The Copernicus Sentinel-1 constellation gives imagery to the general public at giant with resolutions starting from 10 – 80 meters (10 meter imagery being the commonest. Most industrial SAR suppliers, comparable to ICEYE and Capella Area, present imagery right down to 0.5 meter decision. In upcoming launches, different industrial distributors purpose to supply SAR imagery with sub-0.5 meter decision with excessive revisit charges as satellite tv for pc constellations develop and authorities rules evolve.

Determine 4: A VHR SAR picture supplied by Capella Area over the Ukraine-Belarus border.

The Wacky World of Artificial Aperture Radar Imagery

Whereas SAR imagery, at a fast look, might look similar to EO imagery, the underlying physics is sort of totally different, which results in many fascinating results within the imagery product which might be counterintuitive and incompatible with trendy laptop imaginative and prescient. Three widespread results are termed polarization, layover, and multi-path results.

Radar antennas on SAR satellites typically transmit polarized radar waves. The route of polarization is the orientation of the wave’s electrical subject. Objects on the bottom exhibit totally different responses to the totally different polarizations of radar waves. Due to this fact, SAR satellites typically function in twin or quad-polarization modes, broadcasting horizontally (H) or vertically (V) polarized waves and studying both polarization again, leading to HH, HV, VH, and VV bands. You may distinction this with RGB bands in EO imagery, however the elementary physics are totally different.

Determine 5: Distinction between VH (left) and VV (proper) polarizations over the identical area in Dnipro, Ukraine from Sentinel-1 radiometric terrain corrected imagery. As seen right here, the radar returns in corresponding native areas might be totally different.

Layover is an impact during which radar beams attain the highest of a construction earlier than they attain the underside, ensuing within the high of the thing being introduced as overlapping with the underside. This occurs when objects are significantly tall. Visually, tall buildings seem as if they’re laying on their aspect, whereas mountains could have their peaks intersecting with their bases.

Determine 6: Instance of layover in Capella’s VHR SAR imagery. The higher portion of the stadium is intersecting, seemingly, with the car parking zone behind it.

Multi-path results happen when radar waves mirror off of objects on the bottom and incur a number of bounces earlier than returning to the SAR sensor. Multi-path results lead to objects showing within the imagery in varied transformations within the ensuing picture. This impact might be seen in all places in SAR imagery, however is especially noticeable in city areas, forests, and different dense environments.

Determine 7: Instance of a multi-path impact on a bridge from indirect SAR imagery.

Present laptop imaginative and prescient strategies which can be constructed on conventional RGB imagery will not be constructed with these results in thoughts. Object detectors skilled on EO satellite tv for pc imagery assume {that a} distinctive object will solely seem as soon as, or that the thing will seem comparatively comparable in several contexts, somewhat than doubtlessly mirrored or scattered or interwoven with surrounding objects. The very nature of occlusion and the imaginative and prescient rules underlying the assumptions of occlusion in EO imagery don’t switch to SAR. Taken collectively, current laptop imaginative and prescient strategies can switch to SAR imagery, however with decreased efficiency and a set of systematic errors that may be addressed by SAR-specific methodology.

Pc Imaginative and prescient on SAR Imagery for Ukraine

Imagery analysts are at the moment counting on each EO and SAR imagery the place out there over Ukraine. When EO imagery is on the market, current laptop imaginative and prescient tooling constructed for that modality is used to expedite the method of intelligence gathering. Nonetheless, when solely SAR imagery is on the market, these toolchains can’t be used. Imagery analysts need to resort to handbook evaluation which is time consuming and might be liable to errors. This subject is being explored by another establishments internationally, nevertheless, it nonetheless stays an understudied space with respect to the quantity of information out there.

At Berkeley AI Analysis, now we have created an preliminary set of strategies and fashions which have realized sturdy representations for RGB, SAR, and co-registered RGB + SAR imagery from the publicly launched BigEarthNet-MM dataset and the information from Capella’s Open Information, which consists of each RGB and SAR imagery. As such, utilizing our fashions, imagery analysts are capable of interchangeably use RGB, SAR, or co-registered RGB+SAR imagery for downstream duties comparable to picture classification, semantic segmentation, object detection, or change detection.

Provided that SAR is a phenomenologically totally different knowledge supply than EO imagery, now we have discovered that the Imaginative and prescient Transformer (ViT) is a very efficient structure for illustration studying with SAR because it removes the dimensions and shift invariant inductive biases constructed into convolutional neural networks. Our high performing technique, MAERS, for illustration studying on RGB, SAR, and co-registered RGB + SAR builds upon the Masked Autoencoder (MAE) lately launched by He et. al., the place the community learns to encode the enter knowledge by taking a masked model of the information as enter, encoding the information, after which studying to decode the information in such a means that it reconstructs the unmasked enter knowledge.

Opposite to fashionable lessons of contrastive studying strategies, the MAE doesn’t presuppose sure augmentation invariances within the knowledge that could be incorrect for SAR options. As an alternative, it solely depends on reconstructing the unique enter, which is agnostic to RGB, SAR, or co-registered modalities. As proven in Determine 8, MAERS additional extends MAE by studying impartial enter projection layers for RGB, SAR, and RGB+SAR channels, encoding the output of those projected layers utilizing a shared ViT, after which decoding to the RGB, SAR, or RGB+SAR channels utilizing impartial output projection layers. The enter projection layers and shared ViT can then be transferred to downstream duties, comparable to object detection or change detection, the place the enter encoder can then take RGB, SAR, or RGB+SAR as enter.

Determine 8: (high) A visualization of MAERS to study a joint illustration and encoder that can be utilized for a (backside) downstream process, comparable to object detection on both, or each, modalities.

Studying representations for RGB, SAR, and co-registered modalities can profit a spread of downstream duties, comparable to content-based picture retrieval, classification, segmentation, and detection. To display the effectiveness of our realized representations, we carry out experiments on the well-established benchmarks of 1) multi-label classification of co-registered EO and SAR scenes from the BigEarthNet-MM dataset, and a pair of) semantic segmentation on the VHR EO and SAR SpaceNet 6 dataset.

Multi-Label Classification on BigEarth-MM

Determine 9: (left) co-registered Sentinel-2 EO and Sentinel-1 SAR imagery are patchified and used to carry out a multi-label classification process as specified by the BigEarth-MM problem. A linear layer is added to our multi-modal encoder after which fine-tuned end-to-end.

MAERS is initialized with a set of ImageNet weights for a ViT-Base encoder, adopted by pretraining on the BigEarthNet-MM dataset for 20 epochs with RGB, SAR, and RGB+SAR imagery. We append a single linear layer to the MAERS encoder and study the multi-label classification process by fine-tuning the whole mannequin for 20 epochs (linear probing experiments get hold of comparable outcomes, as we’ll present in our upcoming paper). Our outcomes are proven in Desk 1. MAERS with fine-tuning outperforms one of the best RGB+SAR outcomes as introduced within the BigEarthNet-MM paper, and present that adapting the State-of-the-Artwork MAE structure for illustration studying for RGB, SAR, and RGB+SAR enter modalities results in State-of-the-Artwork outcomes.

Desk 1: Reported per-class F2 scores on the check set of BigEarthNet-MM.

Semantic Segmentation on VHR EO and SAR SpaceNet 6

We additional experimented with switch studying for a well timed process that may help imagery analysts aiming to grasp the destruction in Ukraine: semantic segmentation of buildings footprints, which is a precursor process to performing constructing harm evaluation. Constructing harm evaluation is of direct curiosity to authorities officers, journalists, and human rights organizations aiming to grasp the scope and severity of Russia’s assaults in opposition to infrastructure and civilian populations.

Determine 10: Instance of constructing SAR-based MAERS segmentation taken from SpaceNet6, the place the picture on the left reveals the RGB picture, and the picture on the best reveals the SAR picture with overlaid segmentation outcomes. The SAR picture is displayed in false shade with VV, VH, and VV/VH bands.

For this experiment, we used the SpaceNet 6 dataset as an open and public benchmark for example the effectiveness of our realized representations for constructing footprint detection with VHR SAR from Capella Area. We used this encoder in tandem with the UperNet structure for semantic segmentation. Determine 11 reveals the IoU efficiency of segmenting constructing footprints in a held-out validation element of the SpaceNet 6 with solely SAR enter imagery, on a segmentation mannequin that was skilled to make use of both SAR or RGB imagery. The MAERS pretrained mannequin results in a ~13 level enchancment in comparison with coaching the RGB+SAR mannequin from scratch or adapting ImageNet weights with the very same structure.

This demonstrates that MAERS can study sturdy RGB+SAR representations that permit a practitioner to make use of EO or SAR imagery interchangeably to perform downstream duties. It is very important notice that the phenomenology of SAR imagery isn’t absolutely conducive for constructing segmentation and that utilizing EO imagery for this process results in IoU scores > 90. This leaves a considerable hole but to be coated by SAR strategies, one thing we hope to cowl in our following paper. Nonetheless, getting this efficiency out of SAR is important when environmental circumstances will not be conducive to EO imagery seize.

Determine 11: Constructing segmentation IoU on the SpaceNet 6 Problem, utilizing an UperNet segmentation mannequin with a ViT spine. MAERS pretraining results in ~13 level achieve in IoU efficiency in comparison with coaching from scratch or adapting ImageNet pretrained weights.

These outcomes are preliminary, however compelling. We are going to comply with up this effort with a publication with an in depth set of experiments and benchmarks. Moreover, we’ll help within the transition of our fashions to our humanitarian companions to allow them to carry out change detection over residential and different civilian areas to allow higher monitoring of conflict crimes being dedicated in Ukraine.

These fashions are created with the purpose of accelerating the efficacy of organizations concerned in humanitarian missions which can be conserving a watchful eye on the conflict in Ukraine. Nonetheless, as with all expertise, it’s our accountability to grasp how this expertise could possibly be misused. Due to this fact, now we have designed these fashions with enter from companions who carry out intelligence and imagery evaluation in humanitarian settings. By taking into consideration their ideas, feedback, and critiques, we’re releasing a functionality we’re assured will probably be used for the nice of humanity and with processes which dictate their secure and accountable use.

Name to Motion

As residents of free democracies who develop applied sciences which assist us make sense of the difficult, chaotic, and counter-intuitive world that we reside in, now we have a accountability to behave when acts of injustice happen. Our colleagues and pals in Ukraine are going through excessive uncertainties and hazard. We possess abilities within the cyber area that may help within the combat in opposition to Russian forces. By focusing our time and efforts, whether or not that be by focused analysis or volunteering our time in serving to preserve observe of processing instances at border crossings, we are able to make a small dent in an in any other case troublesome scenario.

We urge our fellow laptop scientists to accomplice with authorities and humanitarian organizations and hearken to their wants as troublesome instances persist. Easy issues could make giant variations.

Mannequin and Weights

The fashions will not be being made publicly accessible presently. We’re releasing our fashions to certified researchers and companions by this type. Full distribution will comply with as soon as now we have accomplished a radical evaluation of our fashions.


Thanks to Gen. Steve Butow and Dr. Nirav Patel on the Division of Protection’s Protection Innovation Unit for reviewing this put up and offering their experience on the way forward for industrial SAR constellations.


Please enter your comment!
Please enter your name here