Abstract
The recognition of postearthquake scenes plays an important role in postearthquake rescue and reconstruction. To overcome the over-reliance on expert visual interpretation and the poor recognition performance of traditional machine learning in postearthquake scene recognition, this paper proposes a postearthquake multiple scene recognition (PEMSR) model based on the classical deep learning Single Shot MultiBox Detector (SSD) method. In this paper, a labeled postearthquake scenes dataset is constructed by segmenting acquired remote sensing images, which are classified into six categories: landslide, houses, ruins, trees, clogged and ponding. Due to the insufficiency and imbalance of the original dataset, transfer learning and a data augmentation and balancing strategy are utilized in the PEMSR model. To evaluate the PEMSR model, the evaluation metrics of precision, recall and F1 score are used in the experiment. Multiple experimental test results demonstrate that the PEMSR model shows a stronger performance in postearthquake scene recognition. The PEMSR model improves the detection accuracy of each scene compared with SSD by transfer learning and data augmentation strategy. In addition, the average detection time of the PEMSR model only needs 0.4565s, which is far less than the 8.3472s of the traditional Histogram of Oriented Gradient + Support Vector Machine (HOG+SVM) method.
Highlights
Earthquakes are one of the most harmful types of natural disasters in the world
The average detection times of both the Single Shot MultiBox Detector (SSD) and postearthquake multiple scene recognition (PEMSR) methods are shorter than 0.5s; these methods are much faster than the traditional Histogram of Gradient (HOG)+Support Vector Machine (SVM) recognition method
It is believed that the optimal recognition performance has been approached or realized on the ruins samples; the best recognition performance is realized by the PEMSR model, and it is difficult to improve via data augmentation
Summary
Earthquakes are one of the most harmful types of natural disasters in the world. Five million earthquakes occur every year worldwide, of which about a dozen or twenty have caused serious harm to humanity, resulting in incalculable environmental damage and loss of life and wealth. The quick and accurate collection of damage information in earthquake-stricken areas is of substantial significance for the timely rescue of trapped people and postearthquake reconstruction [3,4]. In seismic emergency rescue work, the most traditional method is onsite investigation by relevant experts [5,6]; the workload is extremely large, and the efficiency is low due to the large extent and variety of disaster areas [7]. Due to low efficiency and uncertainty, it is not currently possible to satisfy the application requirements of rapid assessment and postearthquake rescue
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
