Abstract
Abstract. Hyperspectral imagery is a rich source of spectral information and plays very important role in discrimination of similar land-cover classes. In the past, several efforts have been investigated for improvement of hyperspectral imagery classification. Recently the interest in the joint use of LiDAR data and hyperspectral imagery has been remarkably increased. Because LiDAR can provide structural information of scene while hyperspectral imagery provide spectral and spatial information. The complementary information of LiDAR and hyperspectral data may greatly improve the classification performance especially in the complex urban area. In this paper feature level fusion of hyperspectral and LiDAR data is proposed where spectral and structural features are extract from both dataset, then hybrid feature space is generated by feature stacking. Support Vector Machine (SVM) classifier is applied on hybrid feature space to classify the urban area. In order to optimize the classification performance, two issues should be considered: SVM parameters values determination and feature subset selection. Bees Algorithm (BA) is powerful meta-heuristic optimization algorithm which is applied to determine the optimum SVM parameters and select the optimum feature subset simultaneously. The obtained results show the proposed method can improve the classification accuracy in addition to reducing significantly the dimension of feature space.
Highlights
With the progress in remote sensing technologies, it is possible to measure different characteristics of objects on the earth such as spectral, height, amplitude and phase information by multispectral/hyperspectral, LiDAR and SAR respectively (Debes et al 2014)
To evaluate the performance of the proposed method, experiments are performed on Compact Airborne Spectrographic Imager (CASI) hyperspectral imagery and LiDAR derived DSM acquired by the NSF-funded Center for Airborne Laser Mapping (NCALM), both at the same spatial resolution (2.5 m)
The hyperspectral imagery consists of 144 spectral bands in the spectral range between 380 nm to 1050 nm and the corresponding co-registered DSM consists of elevation in meters above sea level (Geoid 2012A model)
Summary
With the progress in remote sensing technologies, it is possible to measure different characteristics of objects on the earth such as spectral, height, amplitude and phase information by multispectral/hyperspectral, LiDAR and SAR respectively (Debes et al 2014). Availability of different types of data, provides means of detecting and discriminating of land use land cover in complex urban area (Ramdani, 2013). Hyperspectral imagery provides comprehensive spectral information but classification of complex urban area based on just spectral information has some limitations: same objects with different spectral characteristic don’t classify in a class (e.g. buildings with different roof material/color don’t classify in one class) and different objects with same spectral appearance may classify in same class (e.g. tree and grass/ roof and road). There is a complementary relationship between passive hyperspectral images and active LiDAR data, as they contain very different information (Khodadazadeh et al 2015)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
