2D Feature Space for Snow Particle Classification into Snowflake and Graupel

Abstract

SUMMARYThis study presents three image processing systems for snow particle classification into snowflake and graupel. All of them are based on feature classification, yet as a novelty in all cases multiple features are exploited. Additionally, each of them is characterized by a different data flow. In order to compare the performances, we not only consider various features, but also suggest different classifiers. The best achieved results are for the snowflake discrimination method applied before statistical classifier, as the correct classification ratio in this case reaches 94%. In other cases the best results are around 88%.

Feature Analysis and Classification of Particle Data from Two-Dimensional Video Disdrometer

“…In our previous study, we proposed a system for automatically taking particle images by a CCD video camera and classifying them into snowflakes and graupels [7]. Using rich information contained in a large number of grayscale particle images, the system achieved high accuracy of classification (94.14%).…”

Weather measurement system using near‐infrared differential spectroscopy

“…Data used to differentiate between snow and sleet in mountainous areas are needed to estimate precipitation retention, or to understand the phenomenon of snow cover. Commercially available snow sensors use microwave radar [2], or an optical detection system that consists of a light-emitting diode (LED) with an emission wavelength of 800 nm, an optical chopper and a silicon photodiode, whose upper sensitivity limit is at a wavelength of 1000 nm [3]. The absorption band of water has a peak wavelength of about 1400 nm, which is within the wavelength sensitivity range of indium gallium arsenide (InGaAs) photodiodes used for optical communication.…”