Spatial shape feature descriptors in classification of engineered objects using high spatial resolution remote sensing d
- PDF / 2,020,030 Bytes
- 14 Pages / 595.276 x 790.866 pts Page_size
- 67 Downloads / 204 Views
ORIGINAL PAPER
Spatial shape feature descriptors in classification of engineered objects using high spatial resolution remote sensing data Rubeena Vohra1,2 · K. C. Tiwari2 Received: 8 September 2018 / Accepted: 14 February 2019 © Springer-Verlag GmbH Germany, part of Springer Nature 2019
Abstract Spatial and spectral features are two important attributes that form the knowledge based database, useful in classification of engineered objects, using remote sensing data. Spectral features alone may be insufficient to identify buildings and roads in urban areas due to spectral homogeneity and similarity exhibited by them. This has led researchers to explore the spatial features described in terms of shape descriptors to improve accuracy of classification of engineered objects. This paper discusses the parameters of spatial shape features and the method for implementing these features for improving the extraction of engineered objects, using the support vector machine (SVM). SVM classified results obtained using spatial shape features is compared with gray level co-occurrence statistical features in which the former has shown better classification accuracy for buildings and roads. The classification accuracy is also calculated using spectral features of buildings and roads by classifiers such as spectral angle mapper and spectral information divergence. The analysis shows that spatial shape features improve the classification results of buildings and roads in urban areas. Keywords Spatial shape features · Support vector machine · Spectral angle mapper · Spectral information divergence · Connected component analysis · Spatial and spectral resolution
1 Introduction Research in analysing geographical regions of Earth’s surface with the availability of spatial, spectral, temporal and radiometric resolution remote sensing data has increased manifolds. The resolution of remote sensing data defines the resolving power which not only includes the capability of identifying the various objects but also, provides the information for analyzing the properties of those objects. Spectral resolution statistics is the medium of remotely sensed image for land cover classification applications (Gu et al. 2018; Weng 2012). Temporal resolution helps in generating land cover maps for environmental planning, land use change detection and transportation planning (Usman et al. 2015). * Rubeena Vohra [email protected]; [email protected] K. C. Tiwari [email protected] 1
Electronics andCommunication, Bharatividyapeeth’s College of Engineering, Paschim Vihar, New Delhi 110063, India
Civil Engineering, Delhi Technological University, Shahbad Daulatpur, New Delhi 110042, India
2
Spatial resolution influences the accuracy of the ground objects in urban land cover applications (Small 2016). Urban land cover is one of the major regions of the Earth’s surface that leads to various physical, socio-economical and environmental phenomenon’s; therefore, high resolution remote sensing data plays a vital role in classifying diverse an
Data Loading...
