6533b828fe1ef96bd12884b7

RESEARCH PRODUCT

Extracting cloud motion from satellite image sequences

Remus BradI.a. Letia

subject

Computer scienceSegmentation-based object categorizationbusiness.industryComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONScale-space segmentationImage processingPattern recognitionImage segmentationThresholdingImage textureMotion estimationComputer visionArtificial intelligencebusinessBlock-matching algorithm

description

This paper present a new technique for the estimation of cloud motion, using a sequence of infrared satellite images. It can be considered a challenging task due to the complexity of phenomena implied, as non-linear events and a non-rigid motion. In this circumstances most motion models are not suitable and new algorithms have to be developed. We propose a novel method, combining an Automatic Multilevel Thresholding for image segmentation, a Block Matching Algorithm (BMA) and a best candidate block search along with a vector median regularization.

yearjournalcountryeditionlanguage
2004-01-237th International Conference on Control, Automation, Robotics and Vision, 2002. ICARCV 2002.
https://doi.org/10.1109/icarcv.2002.1234961