Object Detection Using Convolutional Neural Networks for Natural Disaster Recovery

Abstract

Natural disasters cause a great damage to human life. As these disasters occur naturally, no one can able to stop their occurrences. But for recovery there is a team named Disaster management or emergency management which helps in recovery of human loss. As recovering and analyzing the objects is not easy, it will be a tough challenge for Disaster management team to identify and process large amount of data in real-time. To make this simple and easy Convolutional Neural Networks (CNN) models are used for object detection of disaster's aftermath. As there are various types of natural disasters such as hurricanes, tsunamis, floods, earthquakes etc., this study focuses on floods and earthquake images for object detection by using neural networks which has the ability to recognize objects easily. The network is processed on the DISASTER dataset which contains 2423 images out of which 1073 images belong to Flood and 1350 images belong to Earthquake. In this study ResNet50, VGG-16 and VGG-19 pre-trained models are used. These pretrained models are CNN models which have been already trained on some sort of data. By using pre-trained models it will be more easy for object detection of flood and earthquake images. Among the three pre-trained models VGG-19 gets highest accuracy of 94.22%. As this study focused on floods and earthquake images for object detection. In future, by using different dataset and different images object detection will be done which will be helpful for recovery of human loss.

Factors Influencing Natural Disaster Risk Management for Seismic Activity: A Literature Review

“…Within the context of natural disasters, when communities participate in data collection and information sharing, new opportunities arise to better understand urban vulnerabilities, capacities, and risks. Data-driven methods for damage assessment and recovery planning can also be created (Salluri et al, 2020).…”

U-net-based semantic classification for flood extent extraction using SAR imagery and GEE platform: A case study for 2019 central US flooding

“…ResNet is proposed by He et al (2016) based on the idea of residual learning. ResNet50 is a ResNet version with 50 layers and 16 residual bottleneck blocks (Loey et al, 2021) and has also been widely used in studies related to water body extraction (Jain et al, 2020;Quan et al, 2020;Rambour et al, 2020;Salluri et al, 2020).…”

Enhanced Identification of Internal Casting Defects in Vehicle Wheels Using YOLO Object Detection and X-Ray Inspection

“…The advent of enhanced hardware computing power has significantly accelerated computational speed, rendering the feature extraction and data computation of large image samples manageable. Artificial neural networks (ANN) [14] and convolutional neural networks (CNN) [15][16][17] are both have achieved good results in the computer vision field. This has led to the development of artificial intelligence and deep learning for identification and practical application in various related industries.…”