Multisource Remote Sensing Data Classification Using Deep Hierarchical Random Walk Networks
作者： Xudong Zhao , Ran Tao , Wei Li
DOI: 10.1109/ICASSP.2019.8683032
关键词: Boundary (topology) 、 Hyperspectral imaging 、 Data classification 、 Random walk 、 Computer science 、 Remote sensing 、 Similarity (network science)
摘要: Collaborative classification of hyperspectral imagery (HSI) and light detection ranging (LiDAR) data is investigated using effective hierarchical random walk networks, denoted as HRWN. The proposed HRWN jointly optimizes dual-tunnel CNN, pixelwise affinity seeds map via a novel layer, which enforces spatial consistency in the deepest layers network. In designed predicted distribution CNN serves global prior while reflects local similarity pixel pairs, preserves boundary localization well. Experimental results validated with two real multisource remote sensing demonstrate that can significantly outperform other state-of-art methods.
sci-hub.se 参考文章(13)
Mahdi Khodadadzadeh, Jun Li, Saurabh Prasad, Antonio Plaza, Fusion of Hyperspectral and LiDAR Remote Sensing Data Using Multiple Feature Learning IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. ,vol. 8, pp. 2971- 2983 ,(2015) , 10.1109/JSTARS.2015.2432037
Craig A. Laben, Bernard V. Brower, Process for enhancing the spatial resolution of multispectral imagery using pan-sharpening ,(1998)
Jinha Jung, Edoardo Pasolli, Saurabh Prasad, James C. Tilton, Melba M. Crawford, A Framework for Land Cover Classification Using Discrete Return LiDAR Data: Adopting Pseudo-Waveform and Hierarchical Segmentation IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. ,vol. 7, pp. 491- 502 ,(2014) , 10.1109/JSTARS.2013.2292032
L. Grady, Random Walks for Image Segmentation IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 28, pp. 1768- 1783 ,(2006) , 10.1109/TPAMI.2006.233
Wei Li, Eric W. Tramel, Saurabh Prasad, James E. Fowler, Nearest Regularized Subspace for Hyperspectral Classification IEEE Transactions on Geoscience and Remote Sensing. ,vol. 52, pp. 477- 489 ,(2014) , 10.1109/TGRS.2013.2241773
L. Grady, Multilabel random walker image segmentation using prior models computer vision and pattern recognition. ,vol. 1, pp. 763- 770 ,(2005) , 10.1109/CVPR.2005.239
Xingping Dong, Jianbing Shen, Ling Shao, Luc Van Gool, Sub-Markov Random Walk for Image Segmentation IEEE Transactions on Image Processing. ,vol. 25, pp. 516- 527 ,(2016) , 10.1109/TIP.2015.2505184
Wei Li, Guodong Wu, Fan Zhang, Qian Du, Hyperspectral Image Classification Using Deep Pixel-Pair Features IEEE Transactions on Geoscience and Remote Sensing. ,vol. 55, pp. 844- 853 ,(2017) , 10.1109/TGRS.2016.2616355
Pedram Ghamisi, Bernhard Hofle, Xiao Xiang Zhu, Hyperspectral and LiDAR Data Fusion Using Extinction Profiles and Deep Convolutional Neural Network IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. ,vol. 10, pp. 3011- 3024 ,(2017) , 10.1109/JSTARS.2016.2634863
Behnood Rasti, Pedram Ghamisi, Richard Gloaguen, Hyperspectral and LiDAR Fusion Using Extinction Profiles and Total Variation Component Analysis IEEE Transactions on Geoscience and Remote Sensing. ,vol. 55, pp. 3997- 4007 ,(2017) , 10.1109/TGRS.2017.2686450