Hidden feature extraction for unstructured agricultural environment based on supervised kernel locally linear embedding modeling

An online hidden feature extraction algorithm is proposed for unknown and unstructured agricultural environments based on a supervised kernel locally linear embedding (SKLLE) algorithm. Firstly, an online obtaining method for scene training samples is given to obtain original feature data. Secondly, Bayesian estimation of the a posteriori probability of a cluster center is performed. Thirdly, nonlinear kernel mapping function construction is employed to map the original feature data to hyper-high-dimensional kernel space. Fourthly, the automatic determination of hidden feature dimensions is performed using a local manifold learning algorithm. Then, a low-level manifold computation in hidden space is completed. Finally, long-range scene perception is realized using a 1-NN classifier. Experiments are conducted to show the effectiveness and the influence of parameter selection for the proposed algorithm. The kernel principal component analysis (KPCA), locally linear embedding (LLE), and supervised locally linear embedding (SLLE) methods are compared under the same experimental unstructured agricultural environment scene. Test results show that the proposed algorithm is more suitable for unstructured agricultural environments than other existing methods, and that the computational load is significantly reduced.

[1]  Melba M. Crawford,et al.  Manifold-Learning-Based Feature Extraction for Classification of Hyperspectral Data: A Review of Advances in Manifold Learning , 2014, IEEE Signal Processing Magazine.

[2]  S T Roweis,et al.  Nonlinear dimensionality reduction by locally linear embedding. , 2000, Science.

[3]  Juan Feng,et al.  Location of apples in trees using stereoscopic vision , 2015, Comput. Electron. Agric..

[4]  Urs A. Muller,et al.  Learning long-range vision for autonomous off-road driving , 2009 .

[5]  Martin Andreas Falk Jensen,et al.  In-field and inter-field path planning for agricultural transport units , 2012, Comput. Ind. Eng..

[6]  Warren E. Dixon,et al.  Vision-based localization of a wheeled mobile robot for greenhouse applications: A daisy-chaining approach , 2008 .

[7]  Giulio Reina,et al.  3D reconstruction and classification of natural environments by an autonomous vehicle using multi-baseline stereo , 2014, Intell. Serv. Robotics.

[8]  Larry D. Jackel,et al.  The DARPA LAGR program: Goals, challenges, methodology, and phase I results , 2006, J. Field Robotics.

[9]  Noboru Noguchi,et al.  Development of a master-slave robot system for farm operations , 2004 .

[10]  Sven Fjeldaas,et al.  Computer vision supported by 3D geometric modelling , 2014 .

[11]  Moritz Diehl,et al.  Moving horizon estimation and nonlinear model predictive control for autonomous agricultural vehicles , 2013 .

[12]  Hossein Mousazadeh,et al.  A technical review on navigation systems of agricultural autonomous off-road vehicles , 2013 .

[13]  Steven Lake Waslander,et al.  Three-dimensional Scan Registration using Curvelet Features in Planetary Environments , 2016, J. Field Robotics.

[14]  Ali Jamali,et al.  An automated 3D modeling of topological indoor navigation network , 2017 .

[15]  Michael J. Procopio,et al.  Learning terrain segmentation with classifier ensembles for autonomous robot navigation in unstructured environments , 2009 .

[16]  Marco Bietresato,et al.  Evaluation of a LiDAR-based 3D-stereoscopic vision system for crop-monitoring applications , 2016, Comput. Electron. Agric..

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

[18]  Andrey V. Savkin,et al.  Nonlinear sliding mode control of an unmanned agricultural tractor in the presence of sliding and control saturation , 2013, Robotics Auton. Syst..

[19]  Matti Pietikäinen,et al.  Supervised Locally Linear Embedding , 2003, ICANN.

[20]  Qi Chen,et al.  Long-range terrain perception using convolutional neural networks , 2018, Neurocomputing.

[21]  Soh-Khim Ong,et al.  Novel AR-based interface for human-robot interaction and visualization , 2014 .

[22]  Tadahiro Taniguchi,et al.  Visualization of Driving Behavior Based on Hidden Feature Extraction by Using Deep Learning , 2017, IEEE Transactions on Intelligent Transportation Systems.

[23]  Bernhard Schölkopf,et al.  Kernel Principal Component Analysis , 1997, ICANN.

[24]  T. Stepinski,et al.  Regionalization of multi-categorical landscapes using machine vision methods , 2013 .