Large, pretrained models are commonly finetuned with imagery that is heavily augmented to mimic different conditions and scales, with the resulting models used for various tasks with imagery from a range of spatial scales. Such models overlook scale-specific information in the data for scale-dependent domains, such as remote sensing. In this paper, we present Scale-MAE, a pretraining method that explicitly learns relationships between data at different, known scales throughout the pretraining process. Scale-MAE pretrains a network by masking an input image at a known input scale, where the area of the Earth covered by the image determines the scale of the ViT positional encoding, not the image resolution. Scale-MAE encodes the masked image with a standard ViT backbone, and then decodes the masked image through a bandpass filter to reconstruct low/high frequency images at lower/higher scales. We find that tasking the network with reconstructing both low/high frequency images leads to robust multiscale representations for remote sensing imagery. Scale-MAE achieves an average of a $2.4 - 5.6\%$ non-parametric kNN classification improvement across eight remote sensing datasets compared to current state-of-the-art and obtains a $0.9$ mIoU to $1.7$ mIoU improvement on the SpaceNet building segmentation transfer task for a range of evaluation scales.

Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning

Remote radiation monitoring device

—Multispectral Sentinel-2 images are a valuable source of Earth observation data, however spatial resolution of their spectral bands limited to 10m, 20m, and 60m ground sam- pling distance remains insufﬁcient in many cases. This problem can be addressed with super-resolution, aimed at reconstructing a high-resolution image from a low-resolution observation. For Sentinel-2, spectral information fusion allows for enhancing the 20m and 60m bands to the 10m resolution. Also, there were attempts to combine multitemporal stacks of individual Sentinel- 2 bands, however these two approaches have not been combined so far. In this paper, we introduce DeepSent—a new deep network for super-resolving multitemporal series of multispectral Sentinel-2 images. It is underpinned with information fusion per- formed simultaneously in the spectral and temporal dimensions to generate an enlarged multispectral image. In our extensive ex- perimental study, we demonstrate that our solution outperforms other state-of-the-art techniques that realize either multitemporal or multispectral data fusion. Furthermore, we show that the advantage of DeepSent results from how these two fusion types are combined in a single architecture, which is superior to performing such fusion in a sequential manner. Importantly, we have applied our method to super-resolve real-world Sentinel-2 images, enhancing the spatial resolution of all the spectral bands to 3.3m nominal ground sampling distance, and we compare the outcome with very high-resolution WorldView-2 images. We will publish our implementation upon paper acceptance, and we expect it will increase the possibilities of exploiting super-resolved Sentinel-2 images in real-life applications.

Multitemporal and multispectral data fusion for super-resolution of Sentinel-2 images

The article presents a proposal to improve the system of radioactive monitoring in the territory of St Petersburg using an unmanned aerial vehicle equipped with a radiation detector This radiation remote sensing device is essential to ensure environmental safety The use of unmanned aerial vehicles equipped with sensors will make it possible to effectively obtain data on the radioactive contamination of the earth's surface and airspace An un-manned aerial vehicle with a radiation sensor will allow you to receive data in real time In the event of a potentially hazardous situation, this device will measure fluctuations in the dose rate distribution on the ground and can be used for radiation monitoring For this purpose, an improved mobile radiation monitoring system has been created The system consists of models whose functionality allows you to measure dose rates and create radiation pollution maps without the need for human personnel to be present at the measurement site The convenience of the radiation monitoring system is the rapid deployment of unmanned monitoring devices to reduce the radiation burden on the population The system can be used in any place where a source of ionizing radiation may be present Before this system can be used in real-world conditions, its components are calibrated based on certified measuring equipment and state-of-the-art modelling tools

/pdf/development-elements-of-the-information-and-measurement-dhik99fi81.pdf

Development elements of the information and measurement systems of mobile environmental monitoring

Multi-image super-resolution consists in fusing multiple images of the same scene to generate an image of higher spatial resolution. Recently, it has been demonstrated that for remotely sensed multispectral Sentine1-2 images, fusion performed in both spectral and temporal dimensions improves the reconstruction quality. However, the deep networks elaborated for this purpose are quite large and influence of the input data is difficult to interpret. In this paper, we show how to exploit transformer-based image fusion to reduce the number of trainable parameters by 30% and allow for increased interpretability with means of attention rollout. The reported experimental results performed over simulated and real-world data indicate that this does not affect the reconstruction quality, while at the same time the visualization tools may help in developing techniques for input data selection and preprocessing.

Transformer-based spectro-temporal fusion for Sentinel-2 super-resolution

—Insufﬁcient spatial resolution of satellite imagery, including Sentinel-2 data, is a serious limitation in many practical use cases. To mitigate this problem, super-resolution recon- struction is receiving considerable attention from the remote sensing community. When it is performed from multiple images captured at subsequent revisits, it may beneﬁt from information fusion, leading to enhanced reconstruction accuracy. One of the obstacles in multi-image super-resolution consists in the scarcity of real-life benchmark datasets—most of the research was performed for simulated data which do not fully reﬂect the operating conditions. In this letter, we introduce a new MuS2 benchmark for multi-image super-resolution reconstruction of Sentinel-2 images, with WorldView-2 imagery used as the high- resolution reference. Within MuS2, we publish the ﬁrst end-to-end evaluation procedure for this problem which we expect to help the researchers in advancing the state of the art in multi-image super-resolution for Sentinel-2 imagery.

MuS2: A Benchmark for Sentinel-2 Multi-Image Super-Resolution

Abstract Commercially available drone type unmanned aerial vehicles (UAV), as well as parts and subsystems enabling the assemble of UAVs, are becoming more and more widely available, and their performance is constantly improving. The current possibilities of a drone assembled by a hobbyist predispose are not only to be used as a reconnaissance tool but also as a guided missile. The use of a camera with a video stream transmitter simultaneously with virtual reality goggles and video stream receiver gives the pilot an impression of being on the drone, which makes it possible to control it with extreme precision, even at high speeds. The article presents research aimed at determining the extent and type of damage made on exemplary racer drone caused by intense microwave field radiations.

/pdf/investigations-of-the-susceptibility-of-unmanned-aerial-2ose015x9f.pdf

Investigations of the susceptibility of unmanned aerial vehicles on intensive microwave radiation

One of the crucial issues regarding turbine maintenance is registering blade vibrations. These vibrations can cause serious damage to the engine. Turbine blade vibrations were measured during nominal speed as well as during run up and run down. A new, low cost Blade Tip Timing (BTT) is presented in this paper. It composes of two main modules: the FPGA unit and PC unit. The system is based on the TerasIC DE0-CV development board controlled by the Cyclone V 5CEBA4F23C7 chip. Units communicate via an Ethernet interface. The system measures a signal for every revolution as well as up to three signals coming from independent rotor blade sensors. The PC unit records these data in .csv files. The system can be adapted to process the signals of additional sensors. The measurements of the 1st stage compressor blade vibrations in an SO-3 engine prove that the system works correctly, with no data loss during transmission between system units, and compares well with other measurement systems as well as numerical results.

/pdf/new-blade-tip-timing-system-for-measuring-rotor-blade-40hgju60s7.pdf

New blade tip-timing system for measuring rotor blade vibration of steam and gas turbines

Fast Fourier transform-based method of neural network training for human re-rendering

Insufﬁcient image spatial resolution is a serious limitation in many practical scenarios, especially when acquiring images at a ﬁner scale is infeasible or brings higher costs. This is inherent to remote sensing, including Sentinel-2 satellite images that are available free of charge at a high revisit frequency, but whose spatial resolution is limited to 10m ground sampling distance. The resolution can be increased with super-resolution algorithms, in particular when performed from multiple images captured at subsequent revisits of a satellite, taking advantage of information fusion that leads to enhanced reconstruction accuracy. One of the obstacles in multi-image super-resolution consists in the scarcity of real-world benchmarks—commonly, simulated data are exploited which do not fully reﬂect the operating conditions. In this paper, we introduce a new MuS2 benchmark for super-resolving multiple Sentinel-2 images, with WorldView-2 imagery used as the high-resolution reference. Within MuS2, we publish the ﬁrst end-to-end evaluation procedure for this problem which we expect to help the researchers in advancing the state of the art in multi-image super-resolution.

Paweł Kowaleczko

Papers

MuS2: A Benchmark for Sentinel-2 Multi-Image Super-Resolution

Investigations of the susceptibility of unmanned aerial vehicles on intensive microwave radiation

New blade tip-timing system for measuring rotor blade vibration of steam and gas turbines

Fast Fourier transform-based method of neural network training for human re-rendering

MuS2: A Real-World Benchmark for Sentinel-2 Multi-Image Super-Resolution