Data Fusion for Urban Feature Extraction from LiDAR and Hyperspectral Data

Dr. Seyed Yousef Sadjadia; Omid Aienehb

The main problems of hyperspectral data are the large number of bands, high dependency between them and different signal to noise ratio in each band. In order to reduce the dimensions of the feature space, minimizing noise and spectral dependence between bands, the MNF method has been used for achieving better results in this paper. Finally, by applying this algorithm, the 144 bands of hyperspectral data was reduced to 19 suitable bands. Then from LiDAR data, the image height and intensity of the return signal received from the first and the last pulse of the laser were produced by LiDAR sensor. At last, The 19 spectral bands extracted from hyperspectral data have been fusion with 4 images of LiDAR data at the pixel level to create 23 suitable spectral bands . In order to detect and extract any feature study of the area on 23 spectral bands, seven different SVM method were applied and finally by majority voting in the decision level between 7 obtained results, the class of each pixel was turned out. Then , morphology closing transform for repairing buildings and Hough transform for reconstructing the network effects of the fragmentation of land transportation were used on the results of pixels basis SVM method to disciplined side structure built by man as well as the individual pixels is reduced. The results in this paper indicates the 99.52% overall accuracy and .958 kappa coefficient which compared to the GRSS chosen institution method .06 Kappa coefficient has been improved. The data used in this paper are air-borne LiDAR and hyper-spectral scenes requested and downloaded from the organized of a recent contest in data fusion domain. The data have been gathered and are available from Houston University in 2012 by Geoscience and Remote Sensing Society (GRSS), a branch of IEEE institute.

Select Volume / Issues:

• Volume 6,Issue 6, Nov. 2015

Year:

2015

Type of Publication:

Article

Keywords:

MNF; SVM; LiDAR; Hyperspectral; Majority; Voting; Fusion; Extraction

Journal:

IJECCE

Volume:

6

Number:

6

Pages:

727-732

Month:

November