http://journal.bit.edu.cn/jbit/ JOURNAL OF BEIJING INSTITUTE OF TECHNOLOGY blgywb@bit.edu.cn blgywb@bit.edu.cn en blgywb@bit.edu.cn 1004-0579 http://journal.bit.edu.cn/jbit/article/doi/10.15918/j.jbit1004-0579.2021.012?pageType=en Zhen Ye, Shihao Shi, Zhan Cao, Lin Bai, Cuiling Li, Tao Sun, Yongqiang Xi Hyperspectral image (HSI) contains a wealth of spectral information, which makes fine classification of ground objects possible. In the meanwhile, overly redundant information in HSI brings many challenges. Specifically, the lack of training samples and the high computational cost are the inevitable obstacles in the design of classifier. In order to solve these problems, dimensionality reduction is usually adopted. Recently, graph-based dimensionality reduction has become a hot topic. In this paper, the graph-based methods for HSI dimensionality reduction are summarized from the following aspects. 1) The traditional graph-based methods employ Euclidean distance to explore the local information of samples in spectral feature space. 2) The dimensionality-reduction methods based on sparse or collaborative representation regard the sparse or collaborative coefficients as graph weights to effectively reduce reconstruction errors and represent most important information of HSI in the dictionary. 3) Improved methods based on sparse or collaborative graph have made great progress by considering global low-rank information, local intra-class information and spatial information. In order to compare typical techniques, three real HSI datasets were used to carry out relevant experiments, and then the experimental results were analysed and discussed. Finally, the future development of this research field is prospected. JOURNAL OF BEIJING INSTITUTE OF TECHNOLOGY. 2021 30(2): 91-112. Zhen Ye, Shihao Shi, Zhan Cao, Lin Bai, Cuiling Li, Tao Sun, Yongqiang Xi Hyperspectral image (HSI) contains a wealth of spectral information, which makes fine classification of ground objects possible. In the meanwhile, overly redundant information in HSI brings many challenges. Specifically, the lack of training samples and the high computational cost are the inevitable obstacles in the design of classifier. In order to solve these problems, dimensionality reduction is usually adopted. Recently, graph-based dimensionality reduction has become a hot topic. In this paper, the graph-based methods for HSI dimensionality reduction are summarized from the following aspects. 1) The traditional graph-based methods employ Euclidean distance to explore the local information of samples in spectral feature space. 2) The dimensionality-reduction methods based on sparse or collaborative representation regard the sparse or collaborative coefficients as graph weights to effectively reduce reconstruction errors and represent most important information of HSI in the dictionary. 3) Improved methods based on sparse or collaborative graph have made great progress by considering global low-rank information, local intra-class information and spatial information. In order to compare typical techniques, three real HSI datasets were used to carry out relevant experiments, and then the experimental results were analysed and discussed. Finally, the future development of this research field is prospected. JOURNAL OF BEIJING INSTITUTE OF TECHNOLOGY. 2021 30(2): 91-112. Graph-Based Dimensionality Reduction for Hyperspectral Imagery: A Review Zhen Ye, Shihao Shi, Zhan Cao, Lin Bai, Cuiling Li, Tao Sun, Yongqiang Xi 2021-06-30 Personal use only, all commercial or other reuse prohibited JOURNAL OF BEIJING INSTITUTE OF TECHNOLOGY. 2021 30(2): 91-112. article doi:10.15918/j.jbit1004-0579.2021.012 10.15918/j.jbit1004-0579.2021.012 JOURNAL OF BEIJING INSTITUTE OF TECHNOLOGY 30 2 2021-06-30 http://journal.bit.edu.cn/jbit/article/doi/10.15918/j.jbit1004-0579.2021.012?pageType=en 91 http://journal.bit.edu.cn/jbit/article/doi/10.15918/j.jbit1004-0579.2021.016?pageType=en Chenzhong Gao, Wei Li This paper aims at providing multi-source remote sensing images registered in geometric space for image fusion. Focusing on the characteristics and differences of multi-source remote sensing images, a feature-based registration algorithm is implemented. The key technologies include image scale-space for implementing multi-scale properties, Harris corner detection for keypoints extraction, and partial intensity invariant feature descriptor (PIIFD) for keypoints description. Eventually, a multi-scale Harris-PIIFD image registration algorithm framework is proposed. The experimental results of fifteen sets of representative real data show that the algorithm has excellent, stable performance in multi-source remote sensing image registration, and can achieve accurate spatial alignment, which has strong practical application value and certain generalization ability. JOURNAL OF BEIJING INSTITUTE OF TECHNOLOGY. 2021 30(2): 113-124. Chenzhong Gao, Wei Li This paper aims at providing multi-source remote sensing images registered in geometric space for image fusion. Focusing on the characteristics and differences of multi-source remote sensing images, a feature-based registration algorithm is implemented. The key technologies include image scale-space for implementing multi-scale properties, Harris corner detection for keypoints extraction, and partial intensity invariant feature descriptor (PIIFD) for keypoints description. Eventually, a multi-scale Harris-PIIFD image registration algorithm framework is proposed. The experimental results of fifteen sets of representative real data show that the algorithm has excellent, stable performance in multi-source remote sensing image registration, and can achieve accurate spatial alignment, which has strong practical application value and certain generalization ability. JOURNAL OF BEIJING INSTITUTE OF TECHNOLOGY. 2021 30(2): 113-124. Multi-Scale PIIFD for Registration of Multi-Source Remote Sensing Images Chenzhong Gao, Wei Li 2021-06-29 Personal use only, all commercial or other reuse prohibited JOURNAL OF BEIJING INSTITUTE OF TECHNOLOGY. 2021 30(2): 113-124. article doi:10.15918/j.jbit1004-0579.2021.016 10.15918/j.jbit1004-0579.2021.016 JOURNAL OF BEIJING INSTITUTE OF TECHNOLOGY 30 2 2021-06-29 http://journal.bit.edu.cn/jbit/article/doi/10.15918/j.jbit1004-0579.2021.016?pageType=en 113 http://journal.bit.edu.cn/jbit/article/doi/10.15918/j.jbit1004-0579.2021.003?pageType=en Zhou Fang, Xinrong Wang, Wei Ji, Meng Xu, Yinan Zhang, Yan Li, Longfei Li The evaluation of geometric calibration accuracy of high resolution satellite images has been increasingly recognized in recent years. In order to evaluate geometric accuracy for dual-camera satellite images based on the ground control points (GCP), a rigorous geometric imaging model, which was based on the collinear equation of the probe directional angle and the optimized tri-axial attitude determination (TRIAD) algorithm, is presented. Two reliable test fields in Tianjin and Jinan (China) were utilized for geometric accuracy validation of Pakistan Remote Sensing Satellite-1. The experimental results demonstrate a certain deviation of the on-orbit calibration result from the initial design values of the calibration parameters. Therefore, on-orbit geometric calibration is necessary for optical satellite imagery. Within this research, the geometrical performances including positioning accuracy without/with GCP and band registration of the dual-camera satellite were analyzed in detail, and the results of geometric image quality are assessed and discussed. As a result, it is feasible and necessary to establish such a geometric calibration model to evaluate the geometric quality of dual-camera satellite. JOURNAL OF BEIJING INSTITUTE OF TECHNOLOGY. 2021 30(2): 125-138. Zhou Fang, Xinrong Wang, Wei Ji, Meng Xu, Yinan Zhang, Yan Li, Longfei Li The evaluation of geometric calibration accuracy of high resolution satellite images has been increasingly recognized in recent years. In order to evaluate geometric accuracy for dual-camera satellite images based on the ground control points (GCP), a rigorous geometric imaging model, which was based on the collinear equation of the probe directional angle and the optimized tri-axial attitude determination (TRIAD) algorithm, is presented. Two reliable test fields in Tianjin and Jinan (China) were utilized for geometric accuracy validation of Pakistan Remote Sensing Satellite-1. The experimental results demonstrate a certain deviation of the on-orbit calibration result from the initial design values of the calibration parameters. Therefore, on-orbit geometric calibration is necessary for optical satellite imagery. Within this research, the geometrical performances including positioning accuracy without/with GCP and band registration of the dual-camera satellite were analyzed in detail, and the results of geometric image quality are assessed and discussed. As a result, it is feasible and necessary to establish such a geometric calibration model to evaluate the geometric quality of dual-camera satellite. JOURNAL OF BEIJING INSTITUTE OF TECHNOLOGY. 2021 30(2): 125-138. Geometric Calibration and Image Quality Assessment of High Resolution Dual-Camera Satellite Zhou Fang, Xinrong Wang, Wei Ji, Meng Xu, Yinan Zhang, Yan Li, Longfei Li 2021-06-29 Personal use only, all commercial or other reuse prohibited JOURNAL OF BEIJING INSTITUTE OF TECHNOLOGY. 2021 30(2): 125-138. article doi:10.15918/j.jbit1004-0579.2021.003 10.15918/j.jbit1004-0579.2021.003 JOURNAL OF BEIJING INSTITUTE OF TECHNOLOGY 30 2 2021-06-29 http://journal.bit.edu.cn/jbit/article/doi/10.15918/j.jbit1004-0579.2021.003?pageType=en 125 http://journal.bit.edu.cn/jbit/article/doi/10.15918/j.jbit1004-0579.2021.013?pageType=en Zhen Ye, Shihao Shi, Tao Sun, Lin Bai As a key technique in hyperspectral image pre-processing, dimensionality reduction has received a lot of attention. However, most of the graph-based dimensionality reduction methods only consider a single structure in the data and ignore the interfusion of multiple structures. In this paper, we propose two methods for combining intra-class competition for locally preserved graphs by constructing a new dictionary containing neighbourhood information. These two methods explore local information into the collaborative graph through competing constraints, thus effectively improving the overcrowded distribution of intra-class coefficients in the collaborative graph and enhancing the discriminative power of the algorithm. By classifying four benchmark hyperspectral data, the proposed methods are proved to be superior to several advanced algorithms, even under small-sample-size conditions. JOURNAL OF BEIJING INSTITUTE OF TECHNOLOGY. 2021 30(2): 139-158. Zhen Ye, Shihao Shi, Tao Sun, Lin Bai As a key technique in hyperspectral image pre-processing, dimensionality reduction has received a lot of attention. However, most of the graph-based dimensionality reduction methods only consider a single structure in the data and ignore the interfusion of multiple structures. In this paper, we propose two methods for combining intra-class competition for locally preserved graphs by constructing a new dictionary containing neighbourhood information. These two methods explore local information into the collaborative graph through competing constraints, thus effectively improving the overcrowded distribution of intra-class coefficients in the collaborative graph and enhancing the discriminative power of the algorithm. By classifying four benchmark hyperspectral data, the proposed methods are proved to be superior to several advanced algorithms, even under small-sample-size conditions. JOURNAL OF BEIJING INSTITUTE OF TECHNOLOGY. 2021 30(2): 139-158. Local Preserving Graphs Using Intra-Class Competitive Representation for Dimensionality Reduction of Hyperspectral Image Zhen Ye, Shihao Shi, Tao Sun, Lin Bai 2021-06-29 Personal use only, all commercial or other reuse prohibited JOURNAL OF BEIJING INSTITUTE OF TECHNOLOGY. 2021 30(2): 139-158. article doi:10.15918/j.jbit1004-0579.2021.013 10.15918/j.jbit1004-0579.2021.013 JOURNAL OF BEIJING INSTITUTE OF TECHNOLOGY 30 2 2021-06-29 http://journal.bit.edu.cn/jbit/article/doi/10.15918/j.jbit1004-0579.2021.013?pageType=en 139 http://journal.bit.edu.cn/jbit/article/doi/10.15918/j.jbit1004-0579.2021.014?pageType=en Zhaoyang Lin, Jianbu Wang, Wei Li, Xiangyang Jiang, Wenbo Zhu, Yuanqing Ma, Andong Wang With the deterioration of the environment, it is imperative to protect coastal wetlands. Using multi-source remote sensing data and object-based hierarchical classification to classify coastal wetlands is an effective method. The object-based hierarchical classification using remote sensing indices (OBH-RSI) for coastal wetland is proposed to achieve fine classification of coastal wetland. First, the original categories are divided into four groups according to the category characteristics. Second, the training and test maps of each group are extracted according to the remote sensing indices. Third, four groups are passed through the classifier in order. Finally, the results of the four groups are combined to get the final classification result map. The experimental results demonstrate that the overall accuracy, average accuracy and kappa coefficient of the proposed strategy are over 94% using the Yellow River Delta dataset. JOURNAL OF BEIJING INSTITUTE OF TECHNOLOGY. 2021 30(2): 159-171. Zhaoyang Lin, Jianbu Wang, Wei Li, Xiangyang Jiang, Wenbo Zhu, Yuanqing Ma, Andong Wang With the deterioration of the environment, it is imperative to protect coastal wetlands. Using multi-source remote sensing data and object-based hierarchical classification to classify coastal wetlands is an effective method. The object-based hierarchical classification using remote sensing indices (OBH-RSI) for coastal wetland is proposed to achieve fine classification of coastal wetland. First, the original categories are divided into four groups according to the category characteristics. Second, the training and test maps of each group are extracted according to the remote sensing indices. Third, four groups are passed through the classifier in order. Finally, the results of the four groups are combined to get the final classification result map. The experimental results demonstrate that the overall accuracy, average accuracy and kappa coefficient of the proposed strategy are over 94% using the Yellow River Delta dataset. JOURNAL OF BEIJING INSTITUTE OF TECHNOLOGY. 2021 30(2): 159-171. OBH-RSI: Object-Based Hierarchical Classification Using Remote Sensing Indices for Coastal Wetland Zhaoyang Lin, Jianbu Wang, Wei Li, Xiangyang Jiang, Wenbo Zhu, Yuanqing Ma, Andong Wang 2021-06-29 Personal use only, all commercial or other reuse prohibited JOURNAL OF BEIJING INSTITUTE OF TECHNOLOGY. 2021 30(2): 159-171. article doi:10.15918/j.jbit1004-0579.2021.014 10.15918/j.jbit1004-0579.2021.014 JOURNAL OF BEIJING INSTITUTE OF TECHNOLOGY 30 2 2021-06-29 http://journal.bit.edu.cn/jbit/article/doi/10.15918/j.jbit1004-0579.2021.014?pageType=en 159 http://journal.bit.edu.cn/jbit/article/doi/10.15918/j.jbit1004-0579.2021.017?pageType=en Huifang Li, Jianghang Huang, Jingwei Huang, Senchun Chai, Leilei Zhao, Yuanqing Xia Industrial Internet of Things (IoT) connecting society and industrial systems represents a tremendous and promising paradigm shift. With IoT, multimodal and heterogeneous data from industrial devices can be easily collected, and further analyzed to discover device maintenance and health related potential knowledge behind. IoT data-based fault diagnosis for industrial devices is very helpful to the sustainability and applicability of an IoT ecosystem. But how to efficiently use and fuse this multimodal heterogeneous data to realize intelligent fault diagnosis is still a challenge. In this paper, a novel Deep Multimodal Learning and Fusion (DMLF) based fault diagnosis method is proposed for addressing heterogeneous data from IoT environments where industrial devices coexist. First, a DMLF model is designed by combining a Convolution Neural Network (CNN) and Stacked Denoising Autoencoder (SDAE) together to capture more comprehensive fault knowledge and extract features from different modal data. Second, these multimodal features are seamlessly integrated at a fusion layer and the resulting fused features are further used to train a classifier for recognizing potential faults. Third, a two-stage training algorithm is proposed by combining supervised pre-training and fine-tuning to simplify the training process for deep structure models. A series of experiments are conducted over multimodal heterogeneous data from a gear device to verify our proposed fault diagnosis method. The experimental results show that our method outperforms the benchmarking ones in fault diagnosis accuracy. JOURNAL OF BEIJING INSTITUTE OF TECHNOLOGY. 2021 30(2): 172-185. Huifang Li, Jianghang Huang, Jingwei Huang, Senchun Chai, Leilei Zhao, Yuanqing Xia Industrial Internet of Things (IoT) connecting society and industrial systems represents a tremendous and promising paradigm shift. With IoT, multimodal and heterogeneous data from industrial devices can be easily collected, and further analyzed to discover device maintenance and health related potential knowledge behind. IoT data-based fault diagnosis for industrial devices is very helpful to the sustainability and applicability of an IoT ecosystem. But how to efficiently use and fuse this multimodal heterogeneous data to realize intelligent fault diagnosis is still a challenge. In this paper, a novel Deep Multimodal Learning and Fusion (DMLF) based fault diagnosis method is proposed for addressing heterogeneous data from IoT environments where industrial devices coexist. First, a DMLF model is designed by combining a Convolution Neural Network (CNN) and Stacked Denoising Autoencoder (SDAE) together to capture more comprehensive fault knowledge and extract features from different modal data. Second, these multimodal features are seamlessly integrated at a fusion layer and the resulting fused features are further used to train a classifier for recognizing potential faults. Third, a two-stage training algorithm is proposed by combining supervised pre-training and fine-tuning to simplify the training process for deep structure models. A series of experiments are conducted over multimodal heterogeneous data from a gear device to verify our proposed fault diagnosis method. The experimental results show that our method outperforms the benchmarking ones in fault diagnosis accuracy. JOURNAL OF BEIJING INSTITUTE OF TECHNOLOGY. 2021 30(2): 172-185. Deep Multimodal Learning and Fusion Based Intelligent Fault Diagnosis Approach Huifang Li, Jianghang Huang, Jingwei Huang, Senchun Chai, Leilei Zhao, Yuanqing Xia 2021-06-29 Personal use only, all commercial or other reuse prohibited JOURNAL OF BEIJING INSTITUTE OF TECHNOLOGY. 2021 30(2): 172-185. article doi:10.15918/j.jbit1004-0579.2021.017 10.15918/j.jbit1004-0579.2021.017 JOURNAL OF BEIJING INSTITUTE OF TECHNOLOGY 30 2 2021-06-29 http://journal.bit.edu.cn/jbit/article/doi/10.15918/j.jbit1004-0579.2021.017?pageType=en 172 http://journal.bit.edu.cn/jbit/article/doi/10.15918/j.jbit1004-0579.2021.022?pageType=en Lei Shi, Zhen Huang, Xuefeng Feng A novel efficient partial sharing channelization structure with odd and even stacking is designed and implemented. There are two special designs in the proposed structure. Firstly, by the intensive channel overlap design, for non-cooperative wideband signals, the proposed structure can achieve good parameter estimation accuracy and high probability of complete interception. Secondly, based on the partial sharing design developed in this paper, the computation burden of the proposed structure can be greatly reduced compared with the traditional directly implemented structures. Experiments and numerical simulations are conducted to evaluate the proposed structure, which shows its improvements over traditional methods in terms of field programmable gate arrays (FPGA) resource consumption and parameter estimation accuracy. JOURNAL OF BEIJING INSTITUTE OF TECHNOLOGY. 2021 30(2): 186-193. Lei Shi, Zhen Huang, Xuefeng Feng A novel efficient partial sharing channelization structure with odd and even stacking is designed and implemented. There are two special designs in the proposed structure. Firstly, by the intensive channel overlap design, for non-cooperative wideband signals, the proposed structure can achieve good parameter estimation accuracy and high probability of complete interception. Secondly, based on the partial sharing design developed in this paper, the computation burden of the proposed structure can be greatly reduced compared with the traditional directly implemented structures. Experiments and numerical simulations are conducted to evaluate the proposed structure, which shows its improvements over traditional methods in terms of field programmable gate arrays (FPGA) resource consumption and parameter estimation accuracy. JOURNAL OF BEIJING INSTITUTE OF TECHNOLOGY. 2021 30(2): 186-193. Design and Implementation of Partial Shared Digital Channelized Receiver Lei Shi, Zhen Huang, Xuefeng Feng 2021-06-29 Personal use only, all commercial or other reuse prohibited JOURNAL OF BEIJING INSTITUTE OF TECHNOLOGY. 2021 30(2): 186-193. article doi:10.15918/j.jbit1004-0579.2021.022 10.15918/j.jbit1004-0579.2021.022 JOURNAL OF BEIJING INSTITUTE OF TECHNOLOGY 30 2 2021-06-29 http://journal.bit.edu.cn/jbit/article/doi/10.15918/j.jbit1004-0579.2021.022?pageType=en 186

map