Related papers: Nighttime sky/cloud image segmentation
We present a new approach to the sky subtraction for long-slit spectra suitable for low-surface brightness objects based on the controlled reconstruction of the night sky spectrum in the Fourier space using twilight or arc-line frames as…
Image segmentation is a central topic in image processing and computer vision and a key issue in many applications, e.g., in medical imaging, microscopy, document analysis and remote sensing. According to the human perception, image…
Forecasting the formation and development of clouds is a central element of modern weather forecasting systems. Incorrect clouds forecasts can lead to major uncertainty in the overall accuracy of weather forecasts due to their intrinsic…
Haze removal is important for computational photography and computer vision applications. However, most of the existing methods for dehazing are designed for daytime images, and cannot always work well in the nighttime. Different from the…
Graph-based video segmentation methods rely on superpixels as starting point. While most previous work has focused on the construction of the graph edges and weights as well as solving the graph partitioning problem, this paper focuses on…
We consider the reconstruction of the interface of compact, connected "clouds" from satellite or airborne light intensity measurements. In a two dimensional setting, the cloud is modeled by an interface, locally represented as a graph, and…
We describe a system for rapidly measuring the brightness of the night sky using a mosaic of CCD images obtained with a low-cost automated system. The portable system produces millions of independent photometric measurements covering the…
Image segmentation is a key topic in image processing and computer vision with applications such as scene understanding, medical image analysis, robotic perception, video surveillance, augmented reality, and image compression, among many…
Superpixel segmentation aims at dividing the input image into some representative regions containing pixels with similar and consistent intrinsic properties, without any prior knowledge about the shape and size of each superpixel. In this…
Nighttime monitoring of the aerosol content of the lower atmosphere is a challenging task, because appropriate reference natural light sources are lacking. Here we show that the anthropogenic night sky brightness due to city lights can be…
Does radiometry (e.g., signal-to-noise ratio) limit the performance of near-IR subcloud imaging of our sister planet's surface at night? It does not. We compute subcloud radiometry using above-cloud observations, an assumed ground…
Ground-based whole sky cameras are extensively used for localized monitoring of clouds nowadays. They capture hemispherical images of the sky at regular intervals using a fisheye lens. In this paper, we propose a framework for estimating…
Computational photography encompasses a diversity of imaging techniques, but one of the core operations performed by many of them is to compute image differences. An intuitive approach to computing such differences is to capture several…
Shadows are common aspect of images and when left undetected can hinder scene understanding and visual processing. We propose a simple yet effective approach based on reflectance to detect shadows from single image. An image is first…
Image super-resolution is an important research area in computer vision that has a wide variety of applications including surveillance, medical imaging etc. Real-world signal image super-resolution has become very popular now-a-days due to…
In this paper we present a new dynamical systems algorithm for clustering in hyperspectral images. The main idea of the algorithm is that data points are \`pushed\' in the direction of increasing density and groups of pixels that end up in…
We present new deep near-infrared images of dark clouds in the Perseus molecular complex. These images show beautiful extended emission which we model as scattered ambient starlight and name ``cloudshine''. The brightness and color…
Satellite-collected nighttime light provides a unique perspective on human activities, including urbanization, population growth, and epidemics. Yet, long-term and fine-grained nighttime light observations are lacking, leaving the analysis…
Images of spacecraft photographed from other spacecraft operating in outer space are difficult to come by, especially at a scale typically required for deep learning tasks. Semantic image segmentation, object detection and localization, and…
Segmentation, a useful/powerful technique in pattern recognition, is the process of identifying object outlines within images. There are a number of efficient algorithms for segmentation in Euclidean space that depend on the variational…