Automated Detection of Hazards
Hazard Detector
Summary
According to the problem statement, we have created a web app that detects and predicts the impact,radius and gives the details of the hazard and also gives suggestions about what steps should be takennext to minimize the effect of hazard. analysis of remote sensing imageryis imperatives in the domain of environmental and climatemonitoring primarily for the application of detecting andmanaging a natural disaster. Satellite imagery or aerial imagery isbeneficial because it can widely capture the condition of thesurface ground and provides a massive amount of information ina piece of satellite imagery. We propose automatic natural disaster detection particularly byimplementing CNN.
How We Addressed This Challenge
According to the problem statement, we have created a web app that detects and predicts the impact, radius and gives the details of the hazard and also gives suggestions about what steps should be taken next to minimize the effect of hazard. analysis of remote sensing imagery is imperatives in the domain of environmental and climate monitoring primarily for the application of detecting and managing a natural disaster. Satellite imagery or aerial imagery is beneficial because it can widely capture the condition of the surface ground and provides a massive amount of information in a piece of satellite imagery. We propose automatic natural disaster detection particularly by implementing a convolutional neural network (CNN) in extracting the feature of disaster more effectively. CNN is robust to shadow, able to obtain the characteristic of disaster adequately, and most importantly able to overcome misdetection or misjudgment by operators, which will affect the effectiveness of disaster relief. We created training data patches of pre-disaster and post-disaster. Based on the promising results, the proposed method may assist in our understanding of the role of deep learning in disaster detection. For better understanding, we will also do Data Visualization and also ancillary data When our model will be working fine, we will integrate it with the web application by using the rest API server and will upload it to the Heroku.
How We Developed This Project
According to the problem statement, we have created a web app that detects and predicts the impact, radius and gives the details of the hazard and also gives suggestions about what steps should be taken next to minimize the effect of hazard. analysis of remote sensing imagery is imperatives in the domain of environmental and climate monitoring primarily for the application of detecting and managing a natural disaster. Satellite imagery or aerial imagery is beneficial because it can widely capture the condition of the surface ground and provides a massive amount of information in a piece of satellite imagery. We propose automatic natural disaster detection particularly by implementing a convolutional neural network (CNN) in extracting the feature of disaster more effectively. CNN is robust to shadow, able to obtain the characteristic of disaster adequately, and most importantly able to overcome misdetection or misjudgment by operators, which will affect the effectiveness of disaster relief. We created training data patches of pre-disaster and post-disaster. Based on the promising results, the proposed method may assist in our understanding of the role of deep learning in disaster detection. For better understanding, we will also do Data Visualization and also ancillary data When our model will be working fine, we will integrate it with the web application by using the rest API server and will upload it to the Heroku.
How We Used Space Agency Data in This Project
Satellite imagery or aerial imagery is beneficial because it can widely capture the condition of the surface ground and provides a massive amount of information in a piece of satellite imagery. Which I got from
https://drive.google.com/file/d/1NvTyhUsrFbL91E10EPm38IjoCg6E2c6q/view
