scispace - formally typeset
Book ChapterDOI

Bayesian Approach for Landslide Identification from High-Resolution Satellite Images

01 Jan 2018-pp 13-24

TL;DR: A novel method based on object-oriented image analysis using bi-temporal satellite images and DEM that can identify medium- and large-scale landslides efficiently is proposed.

AbstractLandslides are one of the severe natural catastrophes that affect thousands of lives and cause colossal damage to infrastructure from small to region scales. Detection of landslide is a prerequisite for damage assessment. We propose a novel method based on object-oriented image analysis using bi-temporal satellite images and DEM. The proposed methodology involves segmentation, followed by extraction of spatial and spectral features of landslides and classification based on supervised Bayesian classifier. The proposed framework is based on the change detection of spatial features which capture the spatial attributes of landslides. The proposed methodology has been applied for the detection and mapping of landslides of different sizes in selected study sites in Himachal Pradesh and Uttarakhand, India. For this, high-resolution multispectral images from the IRS, LISS-IV sensor and DEM from Cartosat-1 are used in this study. The resultant landslides are compared and validated with the inventory landslide maps. The results show that the proposed methodology can identify medium- and large-scale landslides efficiently.

...read more


Citations
More filters
Journal ArticleDOI
24 Jun 2021
TL;DR: Wang et al. as discussed by the authors proposed a two-phase framework for urban village boundary identification and population estimation based on heterogeneous open government data, which can not only accurately identify the boundaries of urban villages from large-scale satellite imagery by fusing road networks guided patches with bike-sharing drop-off patterns, but also accurately estimate the resident and floating populations of urban village with a proposed multi-view neural network model.
Abstract: Urban villages refer to the residential areas lagging behind the rapid urbanization process in many developing countries. These areas are usually with overcrowded buildings, high population density, and low living standards, bringing potential risks of public safety and hindering the urban development. Therefore, it is crucial for urban authorities to identify the boundaries of urban villages and estimate their resident and floating populations so as to better renovate and manage these areas. Traditional approaches, such as field surveys and demographic census, are time consuming and labor intensive, lacking a comprehensive understanding of urban villages. Against this background, we propose a two-phase framework for urban village boundary identification and population estimation. Specifically, based on heterogeneous open government data, the proposed framework can not only accurately identify the boundaries of urban villages from large-scale satellite imagery by fusing road networks guided patches with bike-sharing drop-off patterns, but also accurately estimate the resident and floating populations of urban villages with a proposed multi-view neural network model. We evaluate our method leveraging real-world datasets collected from Xiamen Island. Results show that our framework can accurately identify the urban village boundaries with an IoU of 0.827, and estimate the resident population and floating population with R2 of 0.92 and 0.94 respectively, outperforming the baseline methods. We also deploy our system on the Xiamen Open Government Data Platform to provide services to both urban authorities and citizens.
Patent
26 Jul 2019
TL;DR: Zhang et al. as mentioned in this paper proposed a remote sensing image landslide mapping method based on a deep neural network, which comprises the steps of preprocessing remote sensing images before and after landslide, carrying out super-pixel segmentation on the landslide image; superposing the super-position region of the post-landslide image and the pre-landslaslide images to obtain a super-pixels region of a pre-landslide region; calculating a change intensity characteristic of an area where each superpixel is located; fusing the superpixel spectral features and the
Abstract: The invention provides a remote sensing image landslide mapping method based on a deep neural network. The remote sensing image landslide mapping method comprises the steps of preprocessing remote sensing images before and after landslide; carrying out super-pixel segmentation on the landslide image; superposing the super-pixel region of the post-landslide image and the pre-landslide image to obtain a super-pixel region of the pre-landslide image; calculating a change intensity characteristic of an area where each superpixel is located; fusing the super-pixel spectral features and the change intensity features before and after the landslide to generate feature vectors; calculating the change intensity characteristics of each pixel, carrying out landslide extraction through an LSELUC algorithm, then superposing the landslide extraction with a superpixel region, calculating the change ratio of each region, and extracting a pseudo sample data set through threshold segmentation to form a landslide extraction initial result; constructing a landslide map deep neural network model, performing training by using the pseudo sample data set, and inputting feature vectors for classification; and fusing the landslide extraction initial result and the model classification result to generate a final landslide mapping result.

References
More filters
Journal ArticleDOI
TL;DR: A landslide is the movement of a mass of rock, earth or debris down a slope as mentioned in this paper, and is defined as the mass of earth, rock, or debris moving along a slope.
Abstract: SummaryA landslide is the movement of a mass of rock, earth or debris down a slope.RésuméUn glissement de terrain est la descente d'une masse de roche, de terre ou de débris le long d'un versant.

515 citations

Journal ArticleDOI
TL;DR: Wang et al. as discussed by the authors presented the preliminary results of an extensive study of the mapping the distribution of landslides triggered by the Wenchuan earthquake in Sichuan Province, China, on 12 May 2008.
Abstract: This paper presents the preliminary results of an extensive study of the mapping the distribution of landslides triggered by the Wenchuan earthquake in Sichuan Province, China, on 12 May 2008. An extensive landslide interpretation was carried out using a large set of optical high resolution satellite images (e.g. ASTER, ALOS, Cartosat-1, SPOT-5 and IKONOS) as well as air photos for both the pre- and post-earthquake situation. Landslide scarps were mapped as points using multi-temporal visual image interpretation taking into account shape, tone, texture, pattern, elevation and ridge and valley orientation. Nearly 60,000 individual landslide scarps were mapped. The landslide distribution map was compared with the inventory map that was prepared directly after the earthquake, which contains about 11,000 individual landslide points, through the calculation of normalized landslide isopleths maps. Remarkable differences were observed, as the earlier inventory mapping did not consider the pre-earthquake situation and did not consider all individual landslides. As part of the landslide inventory, landslides were identified that had blocked the drainage and had formed landslide dams. The landslide distribution was compared with a number of aspects, such as the seismic parameters (distance to epicenter, distance to fault rupture, co-seismic fault geometry and co-seismic slip distribution), and geology. The most remarkable correlation found was with the co-seismic slip distribution and the fault geometry. Landslide distribution in the section of the fault that had mainly a thrust component with low angle fault plane was found to be much higher than the sections that had steeper fault angles and a major strike slip component.

380 citations

Journal ArticleDOI
TL;DR: In this paper, a combination of spectral, shape and contextual information was used to detect landslides from false positives, and objects recognised as landslides were subsequently classified based on material type and movement as debris slides, debris flows and rock slides, using adjacency and morphometric criteria.
Abstract: Recognition and classification of landslides is a critical requirement in pre- and post-disaster hazard analysis. This has been primarily done through field mapping or manual image interpretation. However, image interpretation can also be done semi-automatically by creating a routine in object-based classification using the spectral, spatial and morphometric properties of landslides, and by incorporating expert knowledge. This is a difficult task since a fresh landslide has spectral properties that are nearly identical to those of other natural objects, such as river sand and rocky outcrops, and they also do not have unique shapes. This paper investigates the use of a combination of spectral, shape and contextual information to detect landslides. The algorithm is tested with a 5.8 m multispectral data from Resourcesat-1 and a 10 m digital terrain model generated from 2.5 m Cartosat-1 imagery for an area in the rugged Himalayas in India. It uses objects derived from the segmentation of a multispectral image as classifying units for object-oriented analysis. Spectral information together with shape and morphometric characteristics was used initially to separate landslides from false positives. Objects recognised as landslides were subsequently classified based on material type and movement as debris slides, debris flows and rock slides, using adjacency and morphometric criteria. They were further classified for their failure mechanism using terrain curvature. The procedure was developed for a training catchment and then applied without further modification on an independent catchment. A total of five landslide types were detected by this method with 76.4% recognition and 69.1% classification accuracies. This method detects landslides relatively quickly, and hence has the potential to aid risk analysis, disaster management and decision making processes in the aftermath of an earthquake or an extreme rainfall event.

324 citations

Journal ArticleDOI
TL;DR: A change detection-based Markov random field (CDMRF) method is proposed for near-automatic LM from aerial orthophotos, which is the first time CDMRF is used to LM from bitemporal aerial photographs.
Abstract: Landslide mapping (LM) is essential for hazard prevention, mitigation, and vulnerability assessment. Despite the great efforts over the past few years, there is room for improvement in its accuracy and efficiency. Existing LM is primarily achieved using field surveys or visual interpretation of remote sensing images. However, such methods are highly labor-intensive and time-consuming, particularly over large areas. Thus, in this paper a change detection-based Markov random field (CDMRF) method is proposed for near-automatic LM from aerial orthophotos. The proposed CDMRF is applied to a landslide-prone site with an area of approximately 40 km2 on Lantau Island, Hong Kong. Compared with the existing region-based level set evolution (RLSE), it has three main advantages: 1) it employs a more robust threshold method to generate the training samples; 2) it can identify landslides more accurately as it takes advantages of both the spectral and spatial contextual information of landslides; and 3) it needs little parameter tuning. Quantitative evaluation shows that it outperforms RLSE in the whole study area by almost 5.5% in Correctness and by 4% in Quality. To our knowledge, it is the first time CDMRF is used to LM from bitemporal aerial photographs. It is highly generic and has great potential for operational LM applications in large areas and also can be adapted for other sources of imagery data.

60 citations