Paper Infomation
Comparison of Different LiDAR and Hypespectral Data Fusion Strategies Using SVM and ABNet
Full Text(PDF, 385KB)
Author: Pengyu Hao, Zheng Niu
Abstract: The objective of this paper is to compare two LiDAR data and hyperspectral data fusion strategies, band extension and hierarchical classification using two newly proposed classification algorithms SVM and ABNet, and test the sensitivity of different classification method to sample size. The result showed that the fusion data increased the SVM classification accuracy by 10%, but did not improve the ABNet result apparently. And the hierarchical classification strategy performed better than band extension strategy. In addition, the sensitivity test indicated that both hyperspectral solely and fusion data applying ABNet algorithms were more robust when training samples contain more than 60% of original size.
Keywords: Hyperspectral; LiDAR; fusion; SVM; ABNet; remote sensing
References:
[1] Weng, Qihao, Hu, Xuefei and Lu, Dengsheng "Extracting impervious surfaces from medium spatial resolution multispectral and hyperspectral imagery: a comparison". International Journal of Remote Sensing, 29. (2008): 3209-3232
[2] Du, Peijun, Xia, Junshi, Cao, Wen and Wang, Xiaoling Extraction of urban impervious surface from hyperspectral remote sensing image. IEEE Computer Society, City, 2010
[3] Weng, Qihao "Remote sensing of impervious surfaces in the urban areas: Requirements, methods, and trends". Remote Sensing of Environment, 117. (2012): 34-49
[4] Heiden, Uta, Segl, Karl, Roessner, Sigrid and Kaufmann, Hermann "Determination of robust spectral features for identification of urban surface materials in hyperspectral remote sensing data". Remote Sensing of Environment, 111. (2007): 537-552
[5] Im, Jungho, Lu, Zhenyu, Rhee, Jinyoung and Jensen, John R. "Fusion of feature selection and optimized immune networks for hyperspectral image classification of urban landscapes". Geocarto International, 27. (2012a): 373-393
[6] Kamandar, Mehdi and Ghassemian, Hassan "Linear Feature Extraction for Hyperspectral Images Based on Information Theoretic Learning". Ieee Geoscience and Remote Sensing Letters, 10. (2013): 702-706
[7] Pedergnana, Mattia, Marpu, Prashanth Reddy, Mura, Mauro Dalla, Benediktsson, Jon Atli and Bruzzone, Lorenzo "Classification of Remote Sensing Optical and LiDAR Data Using Extended Attribute Profiles". Ieee Journal of Selected Topics in Signal Processing, 6. (2012): 856-865
[8] Meng, Xuelian, Currit, Nate and Zhao, Kaiguang "Ground Filtering Algorithms for Airborne LiDAR Data: A Review of Critical Issues". Remote Sensing, 2. (2010): 833-860
[9] Lee, Dong Hyuk, Lee, Kyoung Mu and Lee, Sang Uk "Fusion of lidar and imagery for reliable building extraction". Photogrammetric Engineering and Remote Sensing, 74. (2008): 215-225
[10] Meng, Xuelian, Currit, Nate, Wang, Le and Yang, Xiaojun "Detect Residential Buildings from Lidar and Aerial Photographs through Object-Oriented Land-Use Classification". Photogrammetric Engineering and Remote Sensing, 78. (2012): 35-44
[11] Chaplot, Vincent, Darboux, Frederic, Bourennane, Hocine, Leguedois, Sophie, Silvera, Norbert and Phachomphon, Konngkeo "Accuracy of interpolation techniques for the derivation of digital elevation models in relation to landform types and data density". Geomorphology, 77. (2006): 126-141
[12] Anderson, E. S., Thompson, J. A., Crouse, D. A. and Austin, R. E. "Horizontal resolution and data density effects on remotely sensed LIDAR-based DEM". Geoderma, 132. (2006): 406-415
[13] Germaine, Kreh A. and Hung, Ming-Chih "Delineation of Impervious Surface from Multispectral Imagery and Lidar Incorporating Knowledge Based Expert System Rules". Photogrammetric Engineering and Remote Sensing, 77. (2011): 75-85
[14] Im, J., Lu, Z. Y., Rhee, J. and Quackenbush, L. J. "Impervious surface quantification using a synthesis of artificial immune networks and decision/regression trees from multi-sensor data". Remote Sensing of Environment, 117. (2012b): 102-113
[15] Mountrakis, Giorgos, Im, Jungho and Ogole, Caesar "Support vector machines in remote sensing: A review". ISPRS Journal of Photogrammetry and Remote Sensing, 66. (2011): 247-259
[16] Zhong, Yanfei and Zhang, Liangpei "An Adaptive Artificial Immune Network for Supervised Classification of Multi-/Hyperspectral Remote Sensing Imagery". IEEE Transactions on Geoscience and Remote Sensing, 50. (2012): 894-909
[17] Zhong, Y. F., Zhang, L. P., Gong, J. Y. and Li, P. X. "A supervised artificial immune classifier for remote-sensing imagery". Ieee Transactions on Geoscience and Remote Sensing, 45. (2007): 3957-3966
[18] Zhong, Y. F., Zhang, L. P., Huang, B. and Li, P. X. "An unsupervised artificial immune classifier for multi/hyperspectral remote sensing imagery". Ieee Transactions on Geoscience and Remote Sensing, 44. (2006): 420-431
[19] Zhong, Y. F., Zhang, L. P. and Gong, W. "Unsupervised remote sensing image classification using an artificial immune network". International Journal of Remote Sensing, 32. (2011): 5461-5483
[20] 2013 IEEE GRSS Data Fusion Contest, Online: http://www.grss-ieee.org/community/technical-committees/data-fusion/"
[21] Chang, C. C. and Lin, C. J. "LIBSVM: A Library for Support Vector Machines". Acm Transactions on Intelligent Systems and Technology, 2. (2011)
[22] Im, Jungho, Lu, Zhenyu, Rhee, Jinyoung and Quackenbush, Lindi J. "Impervious surface quantification using a synthesis of artificial immune networks and decision/regression trees from multi-sensor data". Remote Sensing of Environment, 117. (2012c): 102-113