Object-oriented Mapping and Analysis of Wetlands using SPOT 5 Data

Author(s):  
L. Hubert-Moy ◽  
K. Michel ◽  
T. Corpetti ◽  
B. Clement
Keyword(s):  
Land ◽  
2019 ◽  
Vol 8 (12) ◽  
pp. 193
Author(s):  
Ali Alghamdi ◽  
Anthony R. Cummings

The implications of change on local processes have attracted significant research interest in recent times. In urban settings, green spaces and forests have attracted much attention. Here, we present an assessment of change within the predominantly desert Middle Eastern city of Riyadh, an understudied setting. We utilized high-resolution SPOT 5 data and two classification techniques—maximum likelihood classification and object-oriented classification—to study the changes in Riyadh between 2004 and 2014. Imagery classification was completed with training data obtained from the SPOT 5 dataset, and an accuracy assessment was completed through a combination of field surveys and an application developed in ESRI Survey 123 tool. The Survey 123 tool allowed residents of Riyadh to present their views on land cover for the 2004 and 2014 imagery. Our analysis showed that soil or ‘desert’ areas were converted to roads and buildings to accommodate for Riyadh’s rapidly growing population. The object-oriented classifier provided higher overall accuracy than the maximum likelihood classifier (74.71% and 73.79% vs. 92.36% and 90.77% for 2004 and 2014). Our work provides insights into the changes within a desert environment and establishes a foundation for understanding change in this understudied setting.


2012 ◽  
Vol 10 (1) ◽  
pp. 415-424 ◽  
Author(s):  
Jie Liang ◽  
Jianyu Yang ◽  
Chao Zhang ◽  
Xuejiao Du ◽  
Anzhi Yue ◽  
...  

2013 ◽  
Vol 29 (7) ◽  
pp. 792-806 ◽  
Author(s):  
Mustafa Neamah Jebur ◽  
Helmi Zulhaidi Mohd Shafri ◽  
Biswajeet Pradhan ◽  
Mahyat Shafapour Tehrany

2009 ◽  
Vol 75 (9) ◽  
pp. 1069-1081 ◽  
Author(s):  
Kasper Johansen ◽  
Stuart Phinn ◽  
Christian Witte ◽  
Seonaid Philip ◽  
Lisa Newton

2011 ◽  
Vol 33 (11) ◽  
pp. 3557-3579 ◽  
Author(s):  
Wei Su ◽  
Chao Zhang ◽  
Jianyu Yang ◽  
Honggan Wu ◽  
Lei Deng ◽  
...  

FLORESTA ◽  
2010 ◽  
Vol 40 (2) ◽  
Author(s):  
Naíssa Batista da Luz ◽  
Alzir Felippe Buffara Antunes ◽  
João Batista Tavares Júnior

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.


Sign in / Sign up

Export Citation Format

Share Document