Automatic building detection and land use classification in urban areas using multispectral high-spatial resolution imagery and LiDAR data

A abordagem de classificação orientada a objetos representa um novo paradigma no processamento de imagens de alta resolução espacial. A utilização de descritores espectrais e de forma, oriundos da segmentação, permitem uma melhor discriminação seletiva entre os objetos. Funções de pertinência fuzzy podem ser construídas a partir das propriedades dos objetos segmentados. Atualmente, o estado do Paraná vem realizando atualização dos mapas de uso da terra em escala 1:50.000 por meio de ortorretificação de imagens Spot 5. Pretende-se neste trabalho elaborar o mapa de uso da terra por meio de técnicas de segmentação multiresolução e classificação contextualizada (lógica fuzzy). Descritores dos objetos foram selecionados por estatística multivariada, métodos das componentes principais e de discriminantes, determinando-se aqueles com maior potencial de separabilidade entre as classes. Testes de classificação sucessivos foram realizados aplicando-se funções de pertinência fuzzy aos descritores selecionados, procedendo-se à classificação final da imagem. O mapa de uso da terra, abrangendo uma área de aproximadamente 218,75 km2, resultou em um valor de acurácia Kappa em torno de 80% (utilizando-se os objetos selecionados como amostras de treinamento), demonstrando o potencial dessa ferramenta, embora posteriores adaptações metodológicas devam ser implementadas. Palavras-chave: Imagem de alta resolução espacial; lógica fuzzy; hierarquia de classes; rede semântica. Abstract Multiresolution segmentation, object-oriented classification and Spot-5 imagery land use mapping. The object oriented classification approach represents a new paradigm to the high spatial resolution imagery processing. The use of spectral and form properties originated from the segmentation procedure allows better discrimination between objects. Fuzzy membership functions are generated from the segmented objects descriptors. The State of Parana has been currently updating its 1:50.000 land use maps by means of Spot 5 orthorectified imagery. The objective of this paper is to develop a methodology to the elaboration of land use maps by means of multi-resolution segmentation techniques and image contextual classification with the aid of fuzzy logic. In order to identify which descriptors could provide better class separability, multivariate statistic, principal components and discriminant analysis techniques were used, as a result potential descriptors were selected. Finally the classification process was achieved using those descriptors to create the fuzzy sets and the membership functions. The Land Use Map generated, including an area of 218,75 km2, reached a Kappa index near to 80%, indicating the potential application of this technique nevertheless subsequent methodological adaptation might be implemented.Keywords: High spatial resolution imagery; object oriented classification; fuzzy logic; land use mapping.

Download Full-text

Performance Evaluation of Object-based and Pixel-based Building Detection Algorithms from Very High Spatial Resolution Imagery

Photogrammetric Engineering & Remote Sensing ◽

10.14358/pers.80.6.519-528 ◽

2014 ◽

Vol 80 (6) ◽

pp. 519-528 ◽

Cited By ~ 9

Author(s):

Iman Khosravi ◽

Mehdi Momeni ◽

Maryam Rahnemoonfar

Keyword(s):

Performance Evaluation ◽

Spatial Resolution ◽

High Spatial Resolution ◽

Building Detection ◽

Detection Algorithms ◽

Object Based ◽

Very High Spatial Resolution ◽

Very High ◽

High Spatial Resolution Imagery

Download Full-text

Development of Land Use Regression Model for Seasonal Variation of Nitrogen Dioxide (NO2) in Lahore, Pakistan

Sustainability ◽

10.3390/su13094933 ◽

2021 ◽

Vol 13 (9) ◽

pp. 4933

Author(s):

Saimar Pervez ◽

Ryuta Maruyama ◽

Ayesha Riaz ◽

Satoshi Nakai

Keyword(s):

Land Use ◽

Air Pollution ◽

Regression Model ◽

Urban Areas ◽

Industrial Development ◽

Ambient Air ◽

Ambient Air Pollution ◽

Land Use Classification ◽

Land Use Regression ◽

Air Exposure

Ambient air pollution and its exposure has been a worldwide issue and can increase the possibility of health risks especially in urban areas of developing countries having the mixture of different air pollution sources. With the increase in population, industrial development and economic prosperity, air pollution is one of the biggest concerns in Pakistan after the occurrence of recent smog episodes. The purpose of this study was to develop a land use regression (LUR) model to provide a better understanding of air exposure and to depict the spatial patterns of air pollutants within the city. Land use regression model was developed for Lahore city, Pakistan using the average seasonal concentration of NO2 and considering 22 potential predictor variables including road network, land use classification and local specific variable. Adjusted explained variance of the LUR models was highest for post-monsoon (77%), followed by monsoon (71%) and was lowest for pre-monsoon (70%). This is the first study conducted in Pakistan to explore the applicability of LUR model and hence will offer the application in other cities. The results of this study would also provide help in promoting epidemiological research in future.

Download Full-text

Land-Use/Land-Cover Change Detection Based on Class-Prior Object-Oriented Conditional Random Field Framework for High Spatial Resolution Remote Sensing Imagery

IEEE Transactions on Geoscience and Remote Sensing ◽

10.1109/tgrs.2020.3034373 ◽

2020 ◽

pp. 1-16

Author(s):

Sunan Shi ◽

Yanfei Zhong ◽

Ji Zhao ◽

Pengyuan Lv ◽

Yinhe Liu ◽

...

Keyword(s):

Remote Sensing ◽

Land Use ◽

Random Field ◽

Land Cover Change ◽

Spatial Resolution ◽

High Spatial Resolution ◽

Conditional Random Field ◽

Object Oriented ◽

Land Use Land Cover ◽

Land Cover Change Detection

Download Full-text

Combination of GF-2 high spatial resolution imagery and land surface factors for predicting soil salinity of muddy coasts

CATENA ◽

10.1016/j.catena.2021.105304 ◽

2021 ◽

Vol 202 ◽

pp. 105304

Author(s):

Yufeng Li ◽

Cheng Wang ◽

Alan Wright ◽

Hongyu Liu ◽

Huabing Zhang ◽

...

Keyword(s):

Spatial Resolution ◽

Soil Salinity ◽

Land Surface ◽

High Spatial Resolution ◽

High Spatial Resolution Imagery

Download Full-text

Mapping Urban Functional Zones by Integrating Very High Spatial Resolution Remote Sensing Imagery and Points of Interest: A Case Study of Xiamen, China

Remote Sensing ◽

10.3390/rs10111737 ◽

2018 ◽

Vol 10 (11) ◽

pp. 1737 ◽

Cited By ~ 19

Author(s):

Jinchao Song ◽

Tao Lin ◽

Xinhu Li ◽

Alexander V. Prishchepov

Keyword(s):

Remote Sensing ◽

Land Use ◽

Spatial Resolution ◽

High Spatial Resolution ◽

Remote Sensing Images ◽

Remote Sensing Imagery ◽

Points Of Interest ◽

Very High Spatial Resolution ◽

Functional Zones ◽

Very High

Fine-scale, accurate intra-urban functional zones (urban land use) are important for applications that rely on exploring urban dynamic and complexity. However, current methods of mapping functional zones in built-up areas with high spatial resolution remote sensing images are incomplete due to a lack of social attributes. To address this issue, this paper explores a novel approach to mapping urban functional zones by integrating points of interest (POIs) with social properties and very high spatial resolution remote sensing imagery with natural attributes, and classifying urban function as residence zones, transportation zones, convenience shops, shopping centers, factory zones, companies, and public service zones. First, non-built and built-up areas were classified using high spatial resolution remote sensing images. Second, the built-up areas were segmented using an object-based approach by utilizing building rooftop characteristics (reflectance and shapes). At the same time, the functional POIs of the segments were identified to determine the functional attributes of the segmented polygon. Third, the functional values—the mean priority of the functions in a road-based parcel—were calculated by functional segments and segmental weight coefficients. This method was demonstrated on Xiamen Island, China with an overall accuracy of 78.47% and with a kappa coefficient of 74.52%. The proposed approach could be easily applied in other parts of the world where social data and high spatial resolution imagery are available and improve accuracy when automatically mapping urban functional zones using remote sensing imagery. It will also potentially provide large-scale land-use information.

Download Full-text