KEYWORDS: High dynamic range imaging, Principal component analysis, Neural networks, Camera shutters, Visualization, Artificial neural networks, Data modeling, Clouds, Cameras, Neurons
The appearance of the sky has a fundamental
effect on the way human beings perceive an
environment. This paper presents a method to
compute synthetic high-dynamic-range fisheye
images from weather parameter data sets. These
images can then be used in global-illumination
systems (e. g. Radiance) to define the lighting
conditions at an arbitrary weather state.
Applications of this technology can be found in
flight simulators and in architectural visualization.
The method combines artificial neural networks
and principal component analysis to associate
the appearance of the sky with the state of a
weather parameter vector. A model is trained
with examples of sky images and weather data
from a period of seven months. This model is
then used to generate artificial sky images
corresponding to a specific weather parameter
vector. This is a novel method which contrary to
many previous methods is able to synthesize a
sky image which varies with the current weather
state. The results show that, although it is not
possible to represent the cloud details, it is
possible to distinguish between different weather
states.
Satellite images are important sources of
information for meteorologists to predict rapid
weather changes, for example storms, now and in
the near-future (Nowcasting). It is not possible to
use traditional numerical weather forecasts for
this purpose since these are computed with a
time-lag of several hours. This means that the
most recent weather changes are not taken into
account.
This paper presents a method to compute
synthetic satellite images from simulated forecast
files. The cloud information in numerical forecast
data sets is of much more interest if it can be
visualized with a well-known representation like
the satellite image.
The proposed method uses artificial neural
network technology to construct a model which is
trained with data from numerical forecasts and
classified satellite data captured at the same
points in time. The cloud cover parameters in the
forecast data set are tied to the cloud
classification in the satellite image using a
point-to-point representation. The results show
that this is a useful method to compute synthetic
satellite images. The level of detail in the
resulting images is lower than in a real satellite
image, but detailed enough to provide information
about the principal features of the cloud cover.
Visualizing a weather prediction data set by actually synthesizing an image of the sky is a difficult problem. In this paper we present a method for synthesizing realistic sky images from weather prediction and climate prediction data. Images of the sky are combined with a number of weather parameters (like pressure and
temperature) to train an artificial neural network (ANN) to predict the appearance of the sky from certain weather parameters. Hourly measurements from a period of eight months are used. The principal component analysis (PCA) method is used to decompose images of the sky into their eigen components -- the eigenskies. In this way
the image information is compressed into a small number of coefficients while still preserving the main information in the image. This means that the fine details of the cloud cover cannot be
synthesized using this method. The PCA coefficients together with measured weather parameters at the same time form a data point
that is used to train the ANN. The results show that the method gives adequate results and although some discrepancies exist, the main appearance is correct. It is possible to distinguish
between different types of weather. A rainy day looks rainy and a sunny day looks sunny.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.