Pattern recognition techniques for the identification of cloud and cloud systems

Pankiewicz, G. S.

doi:10.1002/met.5060020309

Cited by 60 publications

(25 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The choice of these features is based on their Fisher Distances F x ij , a selection criterion used in cloud classification work relating to satellite imagery (Pankiewicz, 1995). It is defined as…”

Section: Features Usedmentioning

confidence: 99%

Automatic cloud classification of whole sky images

2010

View full text Add to dashboard Cite

Abstract.The recently increasing development of whole sky imagers enables temporal and spatial high-resolution sky observations. One application already performed in most cases is the estimation of fractional sky cover. A distinction between different cloud types, however, is still in progress. Here, an automatic cloud classification algorithm is presented, based on a set of mainly statistical features describing the color as well as the texture of an image. The k-nearestneighbour classifier is used due to its high performance in solving complex issues, simplicity of implementation and low computational complexity. Seven different sky conditions are distinguished: high thin clouds (cirrus and cirrostratus), high patched cumuliform clouds (cirrocumulus and altocumulus), stratocumulus clouds, low cumuliform clouds, thick clouds (cumulonimbus and nimbostratus), stratiform clouds and clear sky. Based on the Leave-One-Out CrossValidation the algorithm achieves an accuracy of about 97%. In addition, a test run of random images is presented, still outperforming previous algorithms by yielding a success rate of about 75%, or up to 88% if only "serious" errors with respect to radiation impact are considered. Reasons for the decrement in accuracy are discussed, and ideas to further improve the classification results, especially in problematic cases, are investigated.

show abstract

Section: Features Usedmentioning

confidence: 99%

Automatic cloud classification of whole sky images

2010

View full text Add to dashboard Cite

show abstract

“…E-mail: d.kerr@lboro.ac.uk texture, size, shape, organization and shadow effects. Cloud spectral properties may change but their texture properties are unique to a given cloud type, according to Lamei et al (1994) and Pankiewicz (1995). Texture analysis of visible wavelength images of clouds obtained from ground-based observations has been demonstrated by different authors.…”

Section: Introductionmentioning

confidence: 99%

Field trial of an automated ground‐based infrared cloud classification system

Rumi

Kerr

Sandford

et al. 2015

Meteorological Applications

View full text Add to dashboard Cite

Automated classification of cloud types using a ground-based infrared (IR) imager can provide invaluable high-resolution and localized information for air traffic controllers. Observations can be made consistently, continuously in real time and accurately during both day and night operation. Details of a field trial of an automated, ground-based IR cloud classification system are presented. The system was designed at Campbell Scientific Ltd. in collaboration with Loughborough University, UK. The main objective of the trial was to assess the performance of an automated IR camera system with a lightning detector in classifying several types of clouds, specifically cumulonimbus and towering cumulus, during continuous day and night operation. Results from the classification system were compared with those obtained from Meteorological Aerodrome Reports (METAR) and with data generated by the UK Meteorological Office from their radarand sferics-automated cloud reports system. In comparisons with METAR data, a probability of detection of up to 82% was achieved, together with a minimum probability of false detection of 18%.

show abstract

“…Clouds are a persistent problem in solar forecasting [1], due to extreme variety in shape, thickness, size and sky coverage. Another factor in their problematic effects is the visual similarity between clouds, and although they can be classified by experts, it is costly and time-consuming to do so in large datasets of cloud images [2] In order to predict the type of a cloud many tools can be used, radiometer, thermometer, ceilometer, etc. However the most basic and intuitive is a ground based, whole-sky camera, which is economic and flexible for cloud-related problems [3].…”

Section: Introductionmentioning

confidence: 99%

Genetic programming to extract features from the whole-sky camera for cloud type classification

Huertas¹,

Rodríguez-Benítez²,

Pozo³

et al. 2024

RE&PQJ

View full text Add to dashboard Cite

In the automatic cloud classification problem it is very important to extract relevant features from the cloud images that can be used as inputs to the classifiers. Typically, sets of hand-designed features, based on the red, green, and blue channels, are used. For instance, spectral and textural, among other characteristics, are commonly extracted from cloud images. Genetic Programming is a powerful tool that has been used to automatically generate functions in a variety of problems. In this work, it is proposed to use Genetic Programming to automatically construct image features for cloud classification. Specifically, the constructed function aims to transform an image, pixel by pixel, and then computing the mean and the standard deviation of the transformed image. The performance of this method is measured against a set of expertdefined features. Experiments have been carried out on a database of whole-sky cloud images. Results show that the proposed method is able to achieve a similar accuracy as the 4 most important features from the expert feature-set.

show abstract

Pattern recognition techniques for the identification of cloud and cloud systems

Cited by 60 publications

References 31 publications

Automatic cloud classification of whole sky images

Automatic cloud classification of whole sky images

Field trial of an automated ground‐based infrared cloud classification system

Genetic programming to extract features from the whole-sky camera for cloud type classification

Contact Info

Product

Resources

About