Study on Multi-Scale Window Determination for GLCM Texture Description in High-Resolution Remote Sensing Image Geo-Analysis Supported by GIS and Domain Knowledge

Abstract

Texture features based on the gray-level co-occurrence matrix (GLCM) can effectively improve classification accuracy in geographical analyses of optical remote sensing (RS) images, with the parameters of scale of the GLCM texture window greatly affecting the validity. By analyzing human visual attention characteristics for geo-texture cognition, it was found that there is a strong correlation between the texture scale parameters and the domain shape knowledge in a specified geo-scene. Therefore, a new approach for quickly determining the multi-scale parameters of the texture with the assistance of a geographic information system (GIS) and domain knowledge is proposed in this paper. First, the validity of domain knowledge from an existing GIS database is measured by spatial data mining algorithms, including spatial partitioning, image segmentation, and space-time system evaluation. Second, the general domain shape knowledge of each category is described by the GIS minimum enclosing rectangle indices and rectangular-degree indices. Then, the corresponding multi-scale texture windows can be quickly determined for each category by a correlation analysis with the shape indices. Finally, the Fisher function is used to evaluate the validity of the scale parameters. The experimental results show that the multi-scale value keeps a one-to-one relationship with the classified objects, and their value ranges are from a few to tens, instead of the smaller values of a traditional analysis; thus, effective texture features at such a scale can be built to identify categories in a geo-scene. In this way, the proposed method can increase the total number of categories for a certain geo-scene and reduce the classification uncertainty, as well as better meet the requirements of large-scale image geo-analysis. It also has as high a calculation efficiency and as good a performance as the traditional enumeration method.

A Survey on Deep Learning-Driven Remote Sensing Image Scene Understanding: Scene Classification, Scene Retrieval and Scene-Guided Object Detection

“…As mentioned above, deep learning has incomparable advantages over traditional algorithms. Scene classification mainly includes artificial features (Grey-Level Co-occurrence Matrix (GLCM) [35], Local binary patterns (LBP) [36], Histogram of Oriented Gradient (HOG) [37], Gist [38]), data-driven supervised classification features, and data-driven unsupervised classification features. Typical deep learning network structures include the deep belief network which needs to vectorize the raw image and can lead to loss of topology information, the stacked autoencoder (SAE) [33], and convolutional neural networks (CNNs).…”

“…As mentioned above, deep learning has incomparable advantages over traditional algorithms. Scene classification mainly includes artificial features (Grey-Level Co-occurrence Matrix (GLCM) [35], Local binary patterns (LBP) [36], Histogram of Oriented Gradient (HOG) [37], Gist [38]), data-driven supervised classification features, and data-driven unsupervised classification features.…”

Delineation of Cocoa Agroforests Using Multi-Season Sentinel-1 SAR Images: Low Grey Level Range Reduces Uncertainties in GLCM Texture-Based Mapping

“…Yet, the authors [34] suggested that an optimum combination of texture features is needed for the specific type of landscape heterogeneity. Land cover classification using GLCM texture extraction have focused on scale or window size [32,[34][35][36][37]. However, the importance of grey level quantization in GLCM texture analysis has been emphasized [38][39][40].…”

Leading Progress in Digital Terrain Analysis and Modeling

“…Generally, the term surface roughness is used as an expression of the variability of elevation of a topographic surface at a given scale, where the scale of analysis is determined by the size of the landforms or geomorphic features of interest, either local or regional. In this SI, two works deal with the influence of scale in roughness analysis but from different points of view: to identify the optimal wavelength of lidar data [27], and to derive gray-level co-occurrence matrices focus on the roughness spectrum [27,28], a derivative of digital terrain models (DTMs) that is used as a surface roughness descriptor in many geomorphological and physical models. Their work assesses differences in such spectra due to different sources of lidar point clouds or due to different processing of the same point cloud.…”

“…From a textural perspective, [28] refer to roughness by the use of the gray-level co-occurrence matrix. Their work proposes a new approach for quickly determining the multi-scale parameters of such texture, with the assistance of a geographic information system and domain knowledge.…”