- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
Multiple deep-belief-network-based spectral-spatial classification of hyperspectral images
摘要： A deep-learning-based feature extraction has recently been proposed for HyperSpectral Images (HSI) classification. A Deep Belief Network (DBN), as part of deep learning, has been used in HSI classification for deep and abstract feature extraction. However, DBN has to simultaneously deal with hundreds of features from the HSI hyper-cube, which results into complexity and leads to limited feature abstraction and performance in the presence of limited training data. Moreover, a dimensional-reduction-based solution to this issue results in the loss of valuable spectral information, thereby affecting classification performance. To address the issue, this paper presents a Spectral-Adaptive Segmented DBN (SAS-DBN) for spectral-spatial HSI classification that exploits the deep abstract features by segmenting the original spectral bands into small sets/groups of related spectral bands and processing each group separately by using local DBNs. Furthermore, spatial features are also incorporated by first applying hyper-segmentation on the HSI. These results improved data abstraction with reduced complexity and enhanced the performance of HSI classification. Local application of DBN-based feature extraction to each group of bands reduces the computational complexity and results in better feature extraction improving classification accuracy. In general, exploiting spectral features effectively through a segmented-DBN process and spatial features through hyper-segmentation and integration of spectral and spatial features for HSI classification has a major effect on the performance of HSI classification. Experimental evaluation of the proposed technique on well-known HSI standard data sets with different contexts and resolutions establishes the efficacy of the proposed techniques, wherein the results are comparable to several recently proposed HSI classification techniques.
关键词： hyperspectral image classification,support vector machine,deep belief network,segmentation
更新于2025-09-23 15:23:52
-
Unsupervised Change Detection of Multispectral Imagery Using Multi Level Fuzzy Based Deep Representation
摘要： Change detection in remote sensing images provides useful information for various applications. This paper proposes a robust methodology for the analysis of multispectral imagery using Deep belief network (DBN) and Fuzzy interference system (FIS). Initially Euclidean distance and cosine angle distance features are extracted from the image. Deep learning is a robust machine learning method in which the extracted features are processed through set linear mapping and the changes are detected. However, the coarse spatial resolution indicating the intensity of modifications in class proportion instead of accounting for the change using discrete land covers classes is used in fuzzy image classification. Hence, the FIS is combined with DBN which allows defining our own rules to detect the changes accurately. It uses triangular membership function to plot the changes. The experimental results show that the proposed method enhanced the change detection by improving the performance parameters.
关键词： Change detection,Fuzzy interference system,Multi spectral imagery.,Deep belief network
更新于2025-09-19 17:15:36
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - PolSAR Image Classification Based on DBN and Tensor Dimensionality Reduction
摘要： This paper proposes a new semi-supervised PolSAR image classification method using deep belief network (DBN) and tensor dimensionality reduction, which uses multilinear principle component analysis (MPCA) to reduce the dimension of tensor form PolSAR data, and regards the multiple features of PolSAR data as the input of DBN. In order to take full advantage of neighborhood information of each pixel of PolSAR data, we take each pixel and its neighborhood as tensor form. For PolSAR data, simple feature has been proven not to be able to effectively classify complex terrains. Therefore, we combine multiple features of PolSAR data to obtain more abundant information, which can reflect some spatial structure of PolSAR data. The experimental results show that the overall classification accuracy based on the proposed method outperforms the traditional classification strategies.
关键词： deep belief network,image classification,PolSAR,tensor dimensionality reduction
更新于2025-09-09 09:28:46
-
[IEEE 2018 Condition Monitoring and Diagnosis (CMD) - Perth, WA (2018.9.23-2018.9.26)] 2018 Condition Monitoring and Diagnosis (CMD) - Classification of Partial Discharge Images within DC XLPE Cables Based on Convolutional Deep Belief Network
摘要： The classification of partial discharge is of significance to diagnose the defects in high voltage cable insulation defect classification systems. To accuracy at DC cross linked polyethylene(XLPE) cables, a new method used images classification based on convolutional deep belief network (CDBN) is proposed in this paper. Firstly, four kinds of defects in XLPE cables are designed and tested under DC voltage. The q-Δt-n image is constructed based on PD signal collected by HFCT. Then the diagnostic CDBN model is constructed to extract the high-level detailed feature of q-Δt-n images with Gaussian visible units. Finally, classification experiments with CDBN, deep belief network(DBN), support vector machine(SVM) and back- propagation neural network(BPNN) is conducted. The experiment results show that the proposed method has higher classification accuracy of insulation defect diagnosis.
关键词： PD image,insulation defect,feature extraction,convolutional deep belief network(CDBN),DC cable
更新于2025-09-09 09:28:46