%0 Conference Proceedings
%T Detection of Flooded Regions from Satellite Images Using Modified UNET
%+ Vellore Institute of Technology (VIT)
%+ Sri Venkateshwara University, Gajraula, J. P. Nagar, Uttar Pradesh, India
%A Jaisakthi, S., M.
%A Dhanya, P., R.
%A Jitesh Kumar, S.
%Z Part 1: Machine Learning (ML), Deep Learning (DL), Internet of Things (IoT)
%< avec comité de lecture
%( IFIP Advances in Information and Communication Technology
%B 4th International Conference on Computational Intelligence in Data Science (ICCIDS)
%C Chennai, India
%Y Vallidevi Krishnamurthy
%Y Suresh Jaganathan
%Y Kanchana Rajaram
%Y Saraswathi Shunmuganathan
%I Springer International Publishing
%3 Computational Intelligence in Data Science
%V AICT-611
%P 167-174
%8 2021-03-18
%D 2021
%R 10.1007/978-3-030-92600-7_16
%K Flooded region segmentation
%K Convolutional neural network (CNN)
%K UNET
%Z Computer Science [cs]Conference papers
%X It is necessary to analyze the accessibility of flood-affected regions for better planning of response. Flood level detection using remotely sensed images could minimize costs and can also allow taking adequate preparation for fast recovery. MediaEval 2017 multimedia satellite task dataset is used for flood detection in satellite images. The image segmentation technique on satellite images using the modified UNET convolutional neural network is applied after pre-processing to analyze flood-affected regions and compared them to the corresponding segmented regions during the period of a flood event. Initially, all images were segmented using conventional segmentation methods like the Mean shift clustering algorithm. It is observed that the U-Net model produced a good measure for Intersection over Union (IoU) as 99.46% with 99.41% accuracy. The segmented images are then considered for further conventional processing to get meaningful information of flooded regions from satellite imagery.
%G English
%Z TC 12
%2 https://inria.hal.science/hal-03772928/document
%2 https://inria.hal.science/hal-03772928/file/512058_1_En_16_Chapter.pdf
%L hal-03772928
%U https://inria.hal.science/hal-03772928
%~ IFIP-LNCS
%~ IFIP
%~ IFIP-AICT
%~ IFIP-TC
%~ IFIP-TC12
%~ IFIP-ICCIDS
%~ IFIP-AICT-611