Zixuan Chen; Xuewen Wang; Zekai Xu; WenguangHou
July 2016
International Archives of the Photogrammetry, Remote Sensing & S;2016, Vol. 41 Issue B3, p247
Academic Journal
DEM super resolution is proposed in our previous publication to improve the resolution for a DEM on basis of some learning examples. Meanwhile, the nonlocal algorithm is introduced to deal with it and lots of experiments show that the strategy is feasible. In our publication, the learning examples are defined as the partial original DEM and their related high measurements due to this way can avoid the incompatibility between the data to be processed and the learning examples. To further extent the applications of this new strategy, the learning examples should be diverse and easy to obtain. Yet, it may cause the problem of incompatibility and unrobustness. To overcome it, we intend to investigate a convolutional neural network based method. The input of the convolutional neural network is a low resolution DEM and the output is expected to be its high resolution one. A three layers model will be adopted. The first layer is used to detect some features from the input, the second integrates the detected features to some compressed ones and the final step transforms the compressed features as a new DEM. According to this designed structure, some learning DEMs will be taken to train it. Specifically, the designed network will be optimized by minimizing the error of the output and its expected high resolution DEM. In practical applications, a testing DEM will be input to the convolutional neural network and a super resolution will be obtained. Many experiments show that the CNN based method can obtain better reconstructions than many classic interpolation methods.


Related Articles

  • Biologically inspired load balancing mechanism in neocortical competitive learning. Tal, Amir; Peled, Noam; Siegelmann, Hava T. // Frontiers in Neural Circuits;Mar2014, Vol. 8, p1 

    A unique delayed self-inhibitory pathway mediated by layer 5 Martinotti Cells was studied in a biologically inspired neural network simulation. Inclusion of this pathway along with layer 5 basket cell lateral inhibition caused balanced competitive learning, which led to the formation of neuronal...

  • Digit Recognition System by using Back Propagation Algorithm. Kapoor, V.; Gupta, Priyanka // International Journal of Computer Applications;Dec2013, Vol. 83, p33 

    An artificial neural network is configured for a specific application, such as pattern recognition or data classification, through a learning process. Just like biological systems involves adjustments to the synaptic connections that exist between the neurons, artificial neural network also...

  • The Application of BP Neural Network Optimized by Genetic Algorithm in Students' Comprehensive Quality Evaluation. Ren Rongrong; Fu Jia; Chao Jinboi; Yuan Huilin; Li Jing // International Journal of Simulation -- Systems, Science & Techno;2016, Vol. 17 Issue 2, p3.1 

    This paper evaluates students' comprehensive quality by using a number of indicators. The students' comprehensive quality indicators are nonlinearity which influence each other. The BP network model is good at solving nonlinear problem, so a BP neural network assessment model optimized by...

  • A novel recovery algorithm of time encoded signals. Florescu, Dorian; Coca, Daniel // BMC Neuroscience;2013, Vol. 14 Issue Suppl 1, p1 

    An abstract of the article "A novel recovery algorithm of time encoded signals" by Dorian Florescu and Daniel Coca is presented.

  • Synaptic plasticity: taming the beast. Abbott, L. F.; Nelson, Sacha B. // Nature Neuroscience;Nov2000 Supplement, Vol. 3 Issue 11, p1178 

    Synaptic plasticity provides the basis for most models of learning, memory and development in neural circuits. To generate realistic results, synapse-specific Hebbian forms of plasticity, such as long-term potentiation and depression, must be augmented by global processes that regulate overall...

  • Learning Logic Programming in Radial Basis Function Network via Genetic Algorithm. Hamadneh, Nawaf; Sathasivam, Saratha; Tilahun, Surafel Luleseged; Ong Hong Choon // Journal of Applied Sciences;2012, Vol. 12 Issue 9, p840 

    Neural-symbolic systems are based on both logic programming and artificial neural networks. A neural network is a black box that clearly learns the internal relations of unknown systems. Radial Basis Function Neural Network (RBFNN) is a commonly-used type of feed forward neural network....

  • On the Relationships between Generative Encodings, Regularity, and Learning Abilities when Evolving Plastic Artificial Neural Networks. Tonelli, Paul; Mouret, Jean-Baptiste // PLoS ONE;Nov2013, Vol. 8 Issue 11, p1 

    A major goal of bio-inspired artificial intelligence is to design artificial neural networks with abilities that resemble those of animal nervous systems. It is commonly believed that two keys for evolving nature-like artificial neural networks are (1) the developmental process that links genes...

  • Statistical and Electrical Features Evaluation for Electrical Appliances Energy Disaggregation. Schirmer, Pascal A.; Mporas, Iosif // Sustainability (2071-1050);Jun2019, Vol. 11 Issue 11, p3222 

    In this paper we evaluate several well-known and widely used machine learning algorithms for regression in the energy disaggregation task. Specifically, the Non-Intrusive Load Monitoring approach was considered and the K-Nearest-Neighbours, Support Vector Machines, Deep Neural Networks and...

  • Novel high intrinsic dimensionality estimators. Rozza, A.; Lombardi, G.; Ceruti, C.; Casiraghi, E.; Campadelli, P. // Machine Learning;Oct2012, Vol. 89 Issue 1/2, p37 

    Recently, a great deal of research work has been devoted to the development of algorithms to estimate the intrinsic dimensionality ( id) of a given dataset, that is the minimum number of parameters needed to represent the data without information loss. id estimation is important for the...


Other Topics