Segment Optimization and Data-Driven Thresholding for Knowledge-Based Landslide Detection by Object-Based Image Analysis

Abstract

To detect landslides by object-based image analysis using criteria based on shape, color, texture, and, in particular, contextual information and process knowledge, candidate segments must be delineated properly. This has proved challenging in the past, since segments are mainly created using spectral and size criteria that are not consistent for landslides. This paper presents an approach to select objectively parameters for a regiongrowing segmentation technique to outline landslides as individual segments and also addresses the scale dependence of landslides and false positives occurring in a natural landscape. Multiplescale parameters were determined using a plateau objective function derived from the spatial autocorrelation and intrasegment variance analysis, allowing for differently sized features to be identified. While a high-resolution Resourcesat-1 Linear Imaging and Self Scanning Sensor IV (5.8 m) multispectral image was used to create segments for landslide recognition, terrain curvature derived from a digital terrain model based on Cartosat-1 (2.5 m) data was used to create segments for subsequent landslide classification. Here, optimal segments were used in a knowledge-based classification approach with the thresholds of diagnostic parameters derived from K-means cluster analysis, to detect landslides of five different types, with an overall recognition accuracy of 76.9%. The approach, when tested in a geomorphologically dissimilar area, recognized landslides with an overall accuracy of 77.7%, without modification to the methodology. The multiscale classification-based segment optimization procedure was also able to reduce the error of commission significantly in comparison to a single-optimal-scale approach.Index Terms-Disaster support, feature extraction, India, K-means cluster analysis, object-oriented analysis (OOA), segmentation.

Supervised Method of Landslide Inventory Using Panchromatic SPOT5 Images and Application to the Earthquake-Triggered Landslides of Pisco (Peru, 2007, Mw8.0)

“…For these areas, the method must be modified for use with multispectral data. Indeed, multispectral data enable the computation of Normalized Difference Vegetation Index (NDVI) images, and changes of vegetation-cover can be detected between the two acquisitions (e.g., [22]). Therefore, only the change detection step (Section 3.3) would differ.…”

“…These methods often lead to incomplete or biased inventories, due to subjectivity of the operator [5,14]. Therefore, automatic or semi-automatic detection methods have been developed in the past years (e.g., [15][16][17][18][19][20][21][22][23]). These methods are either based on the supervised or unsupervised classification of one satellite image (e.g., [18,24]), or on the detection of new landslides in a pair of images acquired at different dates [20,21].…”

An Efficient Parallel Multi-Scale Segmentation Method for Remote Sensing Imagery

“…It is important to set these parameters properly. There are some methods for a fact-based determination of these parameters, such as estimation of scale parameters (ESP) [30], optimized image segmentation [31], segmentation parameter tuner (SPT) [32], plateau objective function (POF) [33] or the work of Stumpf and Kerle (2011), who optimized segmentation through the optimal use of the derived object features in a random forest framework [34]. In FNEA, the color and the shape parameter work contrarily: The larger the weight of the color is, the better the spectral consistency of the resulting objects.…”

ERN: Edge Loss Reinforced Semantic Segmentation Network for Remote Sensing Images

“…The ever-increasing amount of data places more emphasis on automated interpretation of remote sensing images [2,4]. As an important step towards scene understanding [5], segmentation plays a vital role in many important remote sensing applications [6], such as natural hazards detection [7], urban planning [8,9], land cover mapping [10] and so on. Unlike the classical paradigm in geographic object-based image analysis that unsupervised segmentation is followed by classification [11][12][13][14], semantic segmentation employs a pixel-level supervised style and assigns each pixel with a pre-designed label.…”