Related papers: Data downlink prioritization using image classific…

Convolution Neural Networks (CNN) have performed well in many applications such as object detection, pattern recognition, video surveillance and so on. CNN carryout feature extraction on labelled data to perform classification. Multi-label…

In recent years, with the development of aerospace technology, we use more and more images captured by satellites to obtain information. But a large number of useless raw images, limited data storage resource and poor transmission…

As the important component of the Earth observation system, hyperspectral imaging satellites provide high-fidelity and enriched information for the formulation of related policies due to the powerful spectral measurement capabilities.…

On-orbit service is important for maintaining the sustainability of space environment. Space-based visible camera is an economical and lightweight sensor for situation awareness during on-orbit service. However, it can be easily affected by…

This article explores the latest Convolutional Neural Networks (CNNs) for cloud detection aboard hyperspectral satellites. The performance of the latest 1D CNN (1D-Justo-LiuNet) and two recent 2D CNNs (nnU-net and 2D-Justo-UNet-Simple) for…

A common class of problems in remote sensing is scene classification, a fundamentally important task for natural hazards identification, geographic image retrieval, and environment monitoring. Recent developments in this field rely…

Transfer learning has become an essential tool in modern computer vision, allowing practitioners to leverage backbones, pretrained on large datasets, to train successful models from limited annotated data. Choosing the right backbone is…

Deep learning architecture with convolutional neural network (CNN) achieves outstanding success in the field of computer vision. Where U-Net, an encoder-decoder architecture structured by CNN, makes a great breakthrough in biomedical image…

The site conditions that make astronomical observatories in space and on the ground so desirable -- cold and dark -- demand a physical remoteness that leads to limited data transmission capabilities. Such transmission limitations directly…

The idea behind FIRST (Fibered Imager foR a Single Telescope) is to use single-mode fibers to combine multiple apertures in a pupil plane as such as to synthesize a bigger aperture. The advantages with respect to a pure imager are i)…

Satellite-based onboard data processing is crucial for time-sensitive applications requiring timely and efficient rapid response. Advances in edge artificial intelligence are shifting computational power from ground-based centers to…

Although the latest high-end smartphone has powerful CPU and GPU, running deeper convolutional neural networks (CNNs) for complex tasks such as ImageNet classification on mobile devices is challenging. To deploy deep CNNs on mobile devices,…

Real-time visual feedback is essential for tetherless control of remotely operated vehicles, particularly during inspection and manipulation tasks. Though acoustic communication is the preferred choice for medium-range communication…

Convolutional neural networks (CNNs) have been widely used for hyperspectral image classification. As a common process, small cubes are firstly cropped from the hyperspectral image and then fed into CNNs to extract spectral and spatial…

To reduce the storage requirements, remote sensing (RS) images are usually stored in compressed format. Existing scene classification approaches using deep neural networks (DNNs) require to fully decompress the images, which is a…

The Star-Planet Activity Research CubeSat (SPARCS) is a 6U CubeSat under development to monitor the flaring and chromospheric activity of M dwarfs at near-ultraviolet (NUV) and far-ultraviolet (FUV) wavelengths. The spacecraft hosts two…

Earth observation (EO) missions traditionally rely on transmitting raw or minimally processed imagery from satellites to ground stations for computationally intensive analysis. This paradigm is infeasible for CubeSat systems due to…

Semantic segmentation is a critical tool in computer vision, applied in various domains like autonomous driving and medical imaging. This study focuses on aircraft contrail detection in global satellite images to improve contrail models and…

Semantic labeling (or pixel-level land-cover classification) in ultra-high resolution imagery (< 10cm) requires statistical models able to learn high level concepts from spatial data, with large appearance variations. Convolutional Neural…

We have developed a low-cost off-the-shelf component star sensor (StarSense) for use in minisatellites and CubeSats to determine the attitude of a satellite in orbit. StarSense is an imaging camera with a limiting magnitude of 6.5, which…