Object-oriented ensemble classification for polarimetric SAR Imagery using restricted Boltzmann machines

Qin, Fanglu; Guo, Jiming; Sun, Weidong

doi:10.1080/2150704x.2016.1258128

Cited by 36 publications

(30 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(3) Finally, DBN model was slightly worse than the SVM model when spectral-spatial information was used. Qin et al [60] revealed that the RBM-AdaBoost model performed better than the single and stacked RBM, RBM-based nearest neighbor, RBM-based bagging, minimum distance, nearest neighbor, Wishart, and RF models. In addition, Qin et al [60] demonstrated that the RBM-based nearest neighbor and bagging models performed better than the other models.…”

Section: Effectiveness Of the Multimodal And Multi-model Deep Fusion mentioning

confidence: 99%

“…Qin et al [60] revealed that the RBM-AdaBoost model performed better than the single and stacked RBM, RBM-based nearest neighbor, RBM-based bagging, minimum distance, nearest neighbor, Wishart, and RF models. In addition, Qin et al [60] demonstrated that the RBM-based nearest neighbor and bagging models performed better than the other models. He et al [61] revealed that the DSN-LR model was better than the SVM and single-layer NN-based LR models.…”

Section: Effectiveness Of the Multimodal And Multi-model Deep Fusion mentioning

confidence: 99%

“…Furthermore, Ayhan and Kwan [59] compared the DBN algorithm with a spectral angle mapper (SAM) and SVM. Qin et al [60] developed a combined model based on a restricted Boltzmann machine (RBM, a basic component of a DBN) and an adaptive boosting (AdaBoost) algorithm, called the RBM-AdaBoost model. He et al [61] combined a deep stacking network (DSN) similar to a DBN and LR (DSN-LR).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Multimodal and Multi-Model Deep Fusion for Fine Classification of Regional Complex Landscape Areas Using ZiYuan-3 Imagery

Tang

Chen

et al. 2019

Remote Sensing

View full text Add to dashboard Cite

Land cover classification (LCC) of complex landscapes is attractive to the remote sensing community but poses great challenges. In complex open pit mining and agricultural development landscapes (CMALs), the landscape-specific characteristics limit the accuracy of LCC. The combination of traditional feature engineering and machine learning algorithms (MLAs) is not sufficient for LCC in CMALs. Deep belief network (DBN) methods achieved success in some remote sensing applications because of their excellent unsupervised learning ability in feature extraction. The usability of DBN has not been investigated in terms of LCC of complex landscapes and integrating multimodal inputs. A novel multimodal and multi-model deep fusion strategy based on DBN was developed and tested for fine LCC (FLCC) of CMALs in a 109.4 km 2 area of Wuhan City, China. First, low-level and multimodal spectral–spatial and topographic features derived from ZiYuan-3 imagery were extracted and fused. The features were then input into a DBN for deep feature learning. The developed features were fed to random forest and support vector machine (SVM) algorithms for classification. Experiments were conducted that compared the deep features with the softmax function and low-level features with MLAs. Five groups of training, validation, and test sets were performed with some spatial auto-correlations. A spatially independent test set and generalized McNemar tests were also employed to assess the accuracy. The fused model of DBN-SVM achieved overall accuracies (OAs) of 94.74%± 0.35% and 81.14% in FLCC and LCC, respectively, which significantly outperformed almost all other models. From this model, only three of the twenty land covers achieved OAs below 90%. In general, the developed model can contribute to FLCC and LCC in CMALs, and more deep learning algorithm-based models should be investigated in future for the application of FLCC and LCC in complex landscapes.

show abstract

Section: Effectiveness Of the Multimodal And Multi-model Deep Fusion mentioning

confidence: 99%

Section: Effectiveness Of the Multimodal And Multi-model Deep Fusion mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multimodal and Multi-Model Deep Fusion for Fine Classification of Regional Complex Landscape Areas Using ZiYuan-3 Imagery

Tang

Chen

et al. 2019

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The proposed network is based on sparse filtering 378 , and the proposed network performs a minimization on the output L 1 norm to enforce sparsity. Qin et al 178 performed object-oriented classification of polarimetric SAR data using a RBM and built an adaptive boosting framework (AdaBoost 379 ) vice a stacked DBN in order to handle small training data. They also put forth the RBM-AdaBoost algorithm.…”

Section: Non-traditional Heterogeneous Data Sourcesmentioning

confidence: 99%

Comprehensive survey of deep learning in remote sensing: theories, tools, and challenges for the community

Ball

Anderson

Chan

2017

J. Appl. Remote Sens

541

331

View full text Add to dashboard Cite

Abstract. In recent years, deep learning (DL), a rebranding of neural networks (NNs), has risen to the top in numerous areas, namely computer vision (CV), speech recognition, and natural language processing. Whereas remote sensing (RS) possesses a number of unique challenges, primarily related to sensors and applications, inevitably RS draws from many of the same theories as CV, e.g., statistics, fusion, and machine learning, to name a few. This means that the RS community should not only be aware of advancements such as DL, but also be leading researchers in this area. Herein, we provide the most comprehensive survey of state-of-the-art RS DL research. We also review recent new developments in the DL field that can be used in DL for RS. Namely, we focus on theories, tools, and challenges for the RS community. Specifically, we focus on unsolved challenges and opportunities as they relate to (i) inadequate data sets, (ii) human-understandable solutions for modeling physical phenomena, (iii) big data, (iv) nontraditional heterogeneous data sources, (v) DL architectures and learning algorithms for spectral, spatial, and temporal data, (vi) transfer learning, (vii) an improved theoretical understanding of DL systems, (viii) high barriers to entry, and (ix) training and optimizing the DL. © The Authors.Published by SPIE under a Creative Commons Attribution 3.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.

show abstract

“…Besides, a Wishart-DBN [31] is proposed to classify different land-covers by employing the prior knowledge of polarimetric SAR images. To release the inadequate effect of data volume, an RBM [32] based adaptive boosting model is proposed for object-oriented classification of polarimetric SAR imagery. Meanwhile, a discriminant deep belief network [33] is proposed to learning high-level features for SAR images classification, in which the discriminant informations are captured by combing ensemble learning with a deep belief network in an unsupervised manner.…”

Section: Introductionmentioning

confidence: 99%

The Generalized Gamma-DBN for High-Resolution SAR Image Classification

et al. 2018

View full text Add to dashboard Cite

With the increase of resolution, effective characterization of synthetic aperture radar (SAR) image becomes one of the most critical problems in many earth observation applications. Inspired by deep learning and probability mixture models, a generalized Gamma deep belief network (gΓ-DBN) is proposed for SAR image statistical modeling and land-cover classification in this work. Specifically, a generalized Gamma-Bernoulli restricted Boltzmann machine (gΓB-RBM) is proposed to capture high-order statistical characterizes from SAR images after introducing the generalized Gamma distribution. After stacking the gΓB-RBM and several standard binary RBMs in a hierarchical manner, a gΓ-DBN is constructed to learn high-level representation of different SAR land-covers. Finally, a discriminative neural network is constructed by adding an additional predict layer for different land-covers over the constructed deep structure. Performance of the proposed approach is evaluated via several experiments on some high-resolution SAR image patch sets and two large-scale scenes which are captured by ALOS PALSAR-2 and COSMO-SkyMed satellites respectively.

show abstract

Object-oriented ensemble classification for polarimetric SAR Imagery using restricted Boltzmann machines

Cited by 36 publications

References 12 publications

Multimodal and Multi-Model Deep Fusion for Fine Classification of Regional Complex Landscape Areas Using ZiYuan-3 Imagery

Multimodal and Multi-Model Deep Fusion for Fine Classification of Regional Complex Landscape Areas Using ZiYuan-3 Imagery

Comprehensive survey of deep learning in remote sensing: theories, tools, and challenges for the community

The Generalized Gamma-DBN for High-Resolution SAR Image Classification

Contact Info

Product

Resources

About