Abstract
Thunderstorm is one of the most dangerous natural phenomenons. Basically clouds can be broadly classified into three types. Among them cumulonimbus cloud is the main ingredient of this type of savage weather. In this paper, we have classified cumulonimbus cloud from natural images of different clouds. We have used watershed transformation to segment only the cloud parts from those images and used two pre-trained convolutional neural network, namely AlexNet and GoogLeNet, to classify them into cumulonimbus and non-cumulonimbus cloud. We have seen that AlexNet is performing much better compared with GoogLeNet in terms of total training time with same parameters for training. We have done simulation on MATLAB and giving promising result of 81.65% accuracy in case of AlexNet.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Chakrabarty D, Biswas HR, Das GK, Kore PA (2008) Observational aspects and analysis of events of severe thunderstorms during April and May 2006 for Assam and adjoining states—a case study on Pilot storm project. vol 59, Issue 4, Mausam, pp 461-478
Galvin JFP (2009) The weather and climate of the tropics: part 8 Mesoscale weather systems. Weather 64(2):32-38
Gonzalez RC, Woods RE (2004) Digital image processing. 2nd edn. Prentice Hall
Hamdi MA (2011) Modified algorithm marker-controlled watershed transform for image segmentation based on curvelet threshold. Can J Image Process Comput Vis 2(8):88–91
Couprie C, Grady L, Najman L, Talbot H (2009) Power watersheds: a new image segmentation framework extending graph cuts random walker and optimal spanning forest. In: Proceedings ICCV, Kyoto, Japan, pp 731–738
Muhammad NA, Ab Nasir A, Ibrahim Z, Sabri N (2018) Evaluation of CNN, alexnet and googlenet for fruit recognition. Indonesian J Electri Eng Comput Sci 12(2):468–475
Krizhevsky A, Sutskever I, Hinton G (2012) Image net classification with deep convolutional neural networks. In: Proceedings advances in neural information processing systems, Lake Tahoe, NV, USA, pp 1097–1105
Pal S, Kumar R, Son LH et al (2019) Novel probabilistic resource migration algorithm for cross-cloud live migration of virtual machines in public cloud. J Supercomput 75:5848–5865
Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Boston, 7–12 June, pp 1–9
Sudha KK, Sujatha P (2019) A qualitative analysis of googlenet and alexnet for fabric defect detection. Int J Recent Technol Eng 8(1):86–92
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Chattopadhyay, S., Pal, S., Acharjya, P.P., Bhattacharyya, S. (2021). A Comparative Study to Classify Cumulonimbus Cloud Using Pre-trained CNN. In: Kumar, R., Quang, N.H., Kumar Solanki, V., Cardona, M., Pattnaik, P.K. (eds) Research in Intelligent and Computing in Engineering. Advances in Intelligent Systems and Computing, vol 1254. Springer, Singapore. https://doi.org/10.1007/978-981-15-7527-3_11
Download citation
DOI: https://doi.org/10.1007/978-981-15-7527-3_11
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-7526-6
Online ISBN: 978-981-15-7527-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)