The idea of ‘citizen as sensors’ has gradually become a reality over the past decade. Today, Volunteered Geographic Information (VGI) from citizens is highly involved in acquiring information on natural disasters. In particular, the rapid development of deep learning techniques in computer vision and natural language processing in recent years has allowed more information related to natural disasters to be extracted from social media, such as the severity of building damage and flood water levels. Meanwhile, many recent studies have integrated information extracted from social media with that from other sources, such as remote sensing and sensor networks, to provide comprehensive and detailed information on natural disasters. Therefore, it is of great significance to review the existing work, given the rapid development of this field. In this review, we summarized eight common tasks and their solutions in social media content analysis for natural disasters. We also grouped and analyzed studies that make further use of this extracted information, either standalone or in combination with other sources. Based on the review, we identified and discussed challenges and opportunities.

Object-based convolutional neural networks (OCNNs) have achieved great performance in the field of land-cover and land-use classification. Studies have suggested that the generation of object convolutional positions (OCPs) largely determines the performance of OCNNs. Optimized distribution of OCPs facilitates the identification of segmented objects with irregular shapes. In this study, we propose a morphology-based binary tree sampling (BTS) method that provides a reasonable, effective, and robust strategy to generate evenly distributed OCPs. The proposed BTS algorithm consists of three major steps: 1) calculating the required number of OCPs for each object, 2) dividing a vector object into smaller sub-objects, and 3) generating OCPs based on the sub-objects. Taking the object identification in land-cover and land-use classification as a case study, we compare the proposed BTS algorithm with other competing methods. The results suggest that the BTS algorithm outperforms all other competing methods, as it yields more evenly distributed OCPs that contribute to better representation of objects, thus leading to higher object identification accuracy. Further experiments suggest that the efficiency of BTS can be improved when multi-thread technology is implemented.

Street view imagery such as Google Street View is widely used in people’s daily lives. Many studies have been conducted to detect and map objects such as traffic signs and sidewalks for urban built-up environment analysis. While mapping objects in the horizontal dimension is common in those studies, automatic vertical measuring in large areas is underexploited. Vertical information from street view imagery can benefit a variety of studies. One notable application is estimating the lowest floor elevation, which is critical for building flood vulnerability assessment and insurance premium calculation. In this article, we explored the vertical measurement in street view imagery using the principle of tacheometric surveying. In the case study of lowest floor elevation estimation using Google Street View images, we trained a neural network (YOLO-v5) for door detection and used the fixed height of doors to measure doors’ elevation. The results suggest that the average error of estimated elevation is 0.218 m. The depthmaps of Google Street View were utilized to traverse the elevation from the roadway surface to target objects. The proposed pipeline provides a novel approach for automatic elevation estimation from street view imagery and is expected to benefit future terrain-related studies for large areas.

Various methods have been proposed to detect the base locations of individuals, with their geo-tagged social media data. However, a common challenge relating to base-location detection methods (BDMs) is that, the rare availability of ground-truth data impedes the method assessment of accuracy and robustness, thus undermining research validity and reliability. To address this challenge, we collect users’ information from unstructured online content, and evaluate both the performance and robustness of BDMs. The evaluation consists of two tasks: the detection of base locations and also the differentiation between local residents and tourists. The results show BDMs can achieve high accuracies in base-location detection but tend to overestimate the number of tourists. Evaluation conducted in this study, also shows that BDMs’ accuracy is subject to the intensity of user’s activities and number of countries visited by the user but are insensitive to user’s gender. Temporally, BDMs perform better during weekends and summertime than during other periods, but the best performances appear with datasets that cover the whole time periods (whole day, week, and year). To the best of knowledge, this study is the first work to evaluate the performance and robustness of BDMs at individual level.