Discrimination of residential and industrial buildings using LiDAR data and an effective spatial-neighbor algorithm in a typical urban industrial park

Abstract

The Economic and Technological Development Zone (ETDZ) is a critical urban economic and functional area. Inefficient land exploitation and insufficient supervision have led to a great waste of land resources. The timely and precise extraction of residential and industrial building type, area and density information is urgently needed and essential for sustainable land use development. This study attempted to discriminate residential and industrial buildings by integrating LiDAR data, a lacunarity algorithm, object-based segmentation and a decision tree classifier. All buildings were identified using a normalized digital surface model (nDSM) and object-based segmentation. Lacunarity features and a decision tree classifier were then adopted to discriminate building types. An accuracy assessment indicated that the proposed method can effectively identify residential and industrial buildings. The overall classification accuracy was greater than 85.67% for both of the two test blocks. A comparison with results derived from the nDSM alone showed a significantly improved classification accuracy using the KHAT statistics from a Kappa analysis. The results not only confirmed the applicability and effectiveness of the combined method but also provided fundamental information for evaluating land use in the ETDZ.

Discrimination of Settlement and Industrial Area Using Landscape Metrics in Rural Region

“…However, a specific relationship between the scale parameters and the spatial distribution characteristics of buildings is found in this study. This is in agreement with the study in lacunarity [21], in which the optimum window size was related to the mean building block sizes. However, this relationship still needs to be further validated using independent dataset, and a standard and objective process need to be introduced to determine scale parameter.…”

“…Lacunarity is a measure of "gappiness" or "hole-iness" of a geometric structure and has been used to describe the distribution of the gap sizes in a fractal sequence [43]. Lacunarity algorithm was demonstrated in discriminating land-use types or building types in some urban area [20,21]. In this paper, a lacunarity properties based hierarchical classification was compared with the other two methods.…”

“…Only few studies focused on discrimination of land-use types of rural area or agriculture land. Some articles differentiate LULC types or building types by integrating VHR and normalized Digital Surface Model (nDSM) derived from radar data [21]. However, radar data may meet challenge in coverage of rural area, as the height of factory and settlement buildings are similar, between 3 and 4 floors in typical rural areas of the Yangtze River Delta.…”

“…Lacunarity was used to identify informal settlements from a high resolution binary imagery [20]. Ma [21] successfully discriminated residential and industrial buildings by integrating lacunarity algorithm, object-based segmentation and a decision tree classifier.…”

Rural Settlement Subdivision by Using Landscape Metrics as Spatial Contextual Information

“…Moreover, in the group of geospatial information analysis techniques, spatial autocorrelation metrics, such as Moran's Index and Getis statistic have been used as textural features for image classification [32]. LISA measures [14] and lacunarity [33,34] are also considered important components for OBIA classification procedures. These four categories of spatial contextual techniques make up a large body of related literature: research applying various extraction approaches to generate different kinds of needed contextual information.…”