Multiple Sources Data Fusion Via Deep Forest

In this paper, we propose to fuse multiple sources remotely sensed datasets, such as hyperspectral (HS) and Light Detection and Ranging (LiDAR)-derived digital surface model (DSM) using a novel deep learning method. Morphological openings and closings with partial reconstruction are taken into account to model spatial and elevation information for both sources. Then, the stacked features directly input to a deep learning classifier, namely Deep Forest (DF). In particular, Deep Forest can be viewed as the cascade or the ensembles of Rotation Forests (RoF) and Random Forests (RF). We applied the proposed method to the datasets obtained from Tama forest, Japan. Experimental results demonstrate that Deep Forest can achieve better classification results than other approaches. Compared to deep neural networks, deep forest pays little effort in parameter tuning and has a significant reduction in computational complexity.

[1]  Juan José Rodríguez Diez,et al.  Rotation Forest: A New Classifier Ensemble Method , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Ji Feng,et al.  Deep Forest: Towards An Alternative to Deep Neural Networks , 2017, IJCAI.

[3]  Ulugbek Kamilov,et al.  Autocalibration of lidar and optical cameras via edge alignment , 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[4]  Peijun Du,et al.  Spectral–Spatial Classification for Hyperspectral Data Using Rotation Forests With Local Feature Extraction and Markov Random Fields , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[5]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[6]  Naoto Yokoya,et al.  Hyperspectral Tree Species Classification of Japanese Complex Mixed Forest With the Aid of Lidar Data , 2015, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[7]  Peijun Du,et al.  Semi-supervised graph fusion of hyperspectral and lidar data for classification , 2015, 2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).

[8]  Gang Wang,et al.  Deep Learning-Based Classification of Hyperspectral Data , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[9]  Lorenzo Bruzzone,et al.  Fusion of Hyperspectral and LIDAR Remote Sensing Data for Classification of Complex Forest Areas , 2008, IEEE Transactions on Geoscience and Remote Sensing.

[10]  Aleksandra Pizurica,et al.  Classification of Hyperspectral Data Over Urban Areas Using Directional Morphological Profiles and Semi-Supervised Feature Extraction , 2012, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[11]  Nataliia Kussul,et al.  Deep Learning Classification of Land Cover and Crop Types Using Remote Sensing Data , 2017, IEEE Geoscience and Remote Sensing Letters.

[12]  Jocelyn Chanussot,et al.  Rotation-Based Ensemble Classifiers for High-Dimensional Data , 2014, Fusion in Computer Vision.

[13]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[14]  Geoffrey E. Hinton,et al.  Learning to Detect Roads in High-Resolution Aerial Images , 2010, ECCV.

[15]  Xiao Xiang Zhu,et al.  Hyperspectral and LiDAR Data Fusion Using Extinction Profiles and Deep Convolutional Neural Network , 2017, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[16]  Jon Atli Benediktsson,et al.  Classification of Remote Sensing Optical and LiDAR Data Using Extended Attribute Profiles , 2012, IEEE Journal of Selected Topics in Signal Processing.

[17]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[18]  Bernhard Schölkopf,et al.  Nonlinear Component Analysis as a Kernel Eigenvalue Problem , 1998, Neural Computation.

[19]  Yoshua Bengio,et al.  Extracting and composing robust features with denoising autoencoders , 2008, ICML '08.

[20]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.