scholarly journals CNN-BASED MULTI-SCALE HIERARCHICAL LAND USE CLASSIFICATION FOR THE VERIFICATION OF GEOSPATIAL DATABASES

2021 ◽  
Vol XLIII-B2-2021 ◽  
pp. 495-502
Author(s):  
C. Yang ◽  
F. Rottensteiner ◽  
C. Heipke
Keyword(s):  
Land Use ◽  
Classification Performance ◽  
Land Use Classification ◽  
Multi Scale ◽  
Input Size ◽  
New Strategy ◽  
Joint Prediction ◽  
Fixed Input ◽  
Geospatial Databases

Abstract. Land use is an important piece of information with many applications. Commonly, land use is stored in geospatial databases in the form of polygons with corresponding land use labels and attributes according to an object catalogue. The object catalogues often have a hierarchical structure, with the level of detail of the semantic information depending on the hierarchy level. In this paper, we extend our prior work for the CNN (Convolutional Neural Network)-based prediction of land use for database objects at multiple semantic levels corresponding to different levels of a hierarchical class catalogue. The main goal is the improvement of the classification accuracy for small database objects, which we observed to be one of the largest problems of the existing method. In order to classify large objects using a CNN of a fixed input size, they are split into tiles that are classified independently before fusing the results to a joint prediction for the object. In this procedure, small objects will only be represented by a single patch, which might even be dominated by the background. To overcome this problem, a multi-scale approach for the classification of small objects is proposed in this paper. Using this approach, such objects are represented by multiple patches at different scales that are presented to the CNN for classification, and the classification results are combined. The new strategy is applied in combination with the earlier tiling-based approach. This method based on an ensemble of the two approaches is tested in two sites located in Germany and improves the classification performance up to +1.8% in overall accuracy and +3.2% in terms of mean F1 score.

scholarly journals Land Use and Its Suitability to the Spatial Pattern in Batam City

2020 ◽  
Vol 4 (2) ◽  
pp. 363-366
Author(s):  
Novika Dora ◽  
Arif Roziqin
Keyword(s):  
Land Use ◽  
Spatial Pattern ◽  
City Government ◽  
Land Use Classification ◽  
Class Iii ◽  
Human Needs ◽  
Bare Land ◽  
The Government ◽  
Land Use Maps

Land use continues to grow as population increases in an area, various activities and human needs require land. Land use will affect the suitability of the spatial pattern determined by the Government stipulated in the laws and regulations governing spatial patterns. The purpose of this research is to identify land use that occurred in Batam City in 2019 and determine the suitability of the land use of the Batam City spatial pattern. In this study, the spatial pattern used is the spatial pattern obtained from BP Batam, this is because the spatial pattern originating from the Batam City Government has not yet been approved. The research method used is the method of Classification of Multispectral Maximum Likelihood and Overlay. The results of the map show the class of land use classifications totaling 11 classes in accordance with the class III land use classification class specified by Malingreau, which consists of lakes, forests, industry, pool, bare land, mangroves, ports, plantations, settlements, airports, and livestock. The results of the suitability of land use maps to the spatial pattern of Batam City indicate that the area of the area that is in accordance with the spatial pattern is 30986.77 Ha and the area that is not suitable is 34554.29 Ha.

scholarly journals AN ITERATIVE INFERENCE PROCEDURE APPLYING CONDITIONAL RANDOM FIELDS FOR SIMULTANEOUS CLASSIFICATION OF LAND COVER AND LAND USE

2015 ◽  
Vol II-3/W5 ◽  
pp. 369-376 ◽  
Author(s):  
L. Albert ◽  
F. Rottensteiner ◽  
C. Heipke
Keyword(s):  
Land Use ◽  
Land Cover ◽  
Random Fields ◽  
Conditional Random Fields ◽  
Main Idea ◽  
Aerial Images ◽  
Land Use Classification ◽  
Inference Procedure ◽  
Cover Layer

Land cover and land use exhibit strong contextual dependencies. We propose a novel approach for the simultaneous classification of land cover and land use, where semantic and spatial context is considered. The image sites for land cover and land use classification form a hierarchy consisting of two layers: a <i>land cover layer</i> and a <i>land use layer</i>. We apply Conditional Random Fields (CRF) at both layers. The layers differ with respect to the image entities corresponding to the nodes, the employed features and the classes to be distinguished. In the land cover layer, the nodes represent super-pixels; in the land use layer, the nodes correspond to objects from a geospatial database. Both CRFs model spatial dependencies between neighbouring image sites. The complex semantic relations between land cover and land use are integrated in the classification process by using contextual features. We propose a new iterative inference procedure for the simultaneous classification of land cover and land use, in which the two classification tasks mutually influence each other. This helps to improve the classification accuracy for certain classes. The main idea of this approach is that semantic context helps to refine the class predictions, which, in turn, leads to more expressive context information. Thus, potentially wrong decisions can be reversed at later stages. The approach is designed for input data based on aerial images. Experiments are carried out on a test site to evaluate the performance of the proposed method. We show the effectiveness of the iterative inference procedure and demonstrate that a smaller size of the super-pixels has a positive influence on the classification result.

Sign in / Sign up

Export Citation Format

Share Document