Assessing household damages using multi-model deep learning pipeline
European Mechanical Science · 2022
DOI: 10.26701/ems.1031595 ↗Kurz gefasst
Fachartikel in der Zeitschrift European Mechanical Science, 2022. Verfasst von Fatih KIYIKÇI und 5 weiteren Autor:innen. Die Arbeit nennt 13 Literaturangaben.
Abstract (Originalsprache)
Since the beginning of the pandemic, the home insurance sector has suffered from various difficulties. One of the most important difficulties was assessing the damages in the insurance owners’ homes. Due to the current pandemic, letting the experts assess the damages in place is a life-threatening risk. Therefore, the idea of automatically assessing the damage is born. This study aims to create a full report for home damages using Convolutional Neural Network (CNN) and various large deep learning model architectures such as EfficientNet, ResNet, U-Net, or Feature Pyramid Network (FPN). Multiple models for tasks such as binary classification and instance segmentation were developed to create an end-to-end reporting pipeline. In more detail, the pipeline consists of two binary classification models and a segmentation model. Binary classification models are responsible for detecting if the picture is indoors and if there is a wall in the picture, whereas the instance segmentation model is responsible for segmenting the damaged parts of the wall class. The effectiveness of the pipeline was measured using different metrics for each task, including accuracy, F1, dice, and Intersection over Union (IoU) scores. The data for each task is labeled by hand and fed to models. The results show that the constructed pipeline can successfully classify and segment the given images according to the needs of our project. The project will affect the home insurance assessment procedure and time spent tremendously by automatizing these repetitive processes.
Zitieren
APA
KIYIKÇI, F., CUNEDİOĞLU, H. O., KOŞAR, E., BEKİN, M. E., ABUT, F., & AKAY, F. (2022). Assessing household damages using multi-model deep learning pipeline. European Mechanical Science. https://doi.org/10.26701/ems.1031595
Vancouver
KIYIKÇI F, CUNEDİOĞLU HO, KOŞAR E, BEKİN ME, ABUT F, AKAY F. Assessing household damages using multi-model deep learning pipeline. European Mechanical Science. 2022. doi:10.26701/ems.1031595
BibTeX
@article{KIYIKI2022,
author = {KIYIKÇI, Fatih and CUNEDİOĞLU, Hilal Onur and KOŞAR, Enes and BEKİN, Mehmet Eren and ABUT, Fatih and AKAY, Fatih},
title = {Assessing household damages using multi-model deep learning pipeline},
journal = {European Mechanical Science},
year = {2022},
doi = {10.26701/ems.1031595}
}
EUVIMED