Pub Date : 2021-02-26DOI: 10.12086/OEE.2021.200218
Wang Jinjin, Zhu Qiuhao, Dong Jian-feng
Chiral metasurfaces are ultra-thin metamaterials composed of planar chiral cell structures with specific electromagnetic responses. They have attracted great attention due to their singular ability to control electromagnetic waves at will. With tunable materials incorporated into the metasurfaces design, one can realize tunable/reconfigurable metadevices with functionalities controlled by external stimuli, opening a new platform to dynamically manipulate electromagnetic waves. In this paper, we introduce some theoretical foundations of the electromagnetic properties of tunable/reconfigurable chiral metasurfaces. When a linearly polarized light enters a tunable chiral metasurface, it can be decomposed into left-handed circularly polarized (LCP) wave and right-handed circularly polarized (RCP) wave. By changing the dielectric constant and magnetic permeability of the medium through the external environment, the metadevices can dynamically control the response characteristics to various polarized lights, especially circularly polarized lights such as refractive index, dichroism, optical rotation, asymmetric transmission, etc. According to the properties of negative refractive index, circular dichroism, optical rotation, and asymmetric transmission controlled by the tunable chiral metasurfaces, we review the latest research progress. Finally, we put forward our own opinions on the possible future development directions and existing challenges of the rapidly developing field of the tunable chiral metasurface.
{"title":"Research progress of electromagnetic properties of tunable chiral metasurfaces","authors":"Wang Jinjin, Zhu Qiuhao, Dong Jian-feng","doi":"10.12086/OEE.2021.200218","DOIUrl":"https://doi.org/10.12086/OEE.2021.200218","url":null,"abstract":"Chiral metasurfaces are ultra-thin metamaterials composed of planar chiral cell structures with specific electromagnetic responses. They have attracted great attention due to their singular ability to control electromagnetic waves at will. With tunable materials incorporated into the metasurfaces design, one can realize tunable/reconfigurable metadevices with functionalities controlled by external stimuli, opening a new platform to dynamically manipulate electromagnetic waves. In this paper, we introduce some theoretical foundations of the electromagnetic properties of tunable/reconfigurable chiral metasurfaces. When a linearly polarized light enters a tunable chiral metasurface, it can be decomposed into left-handed circularly polarized (LCP) wave and right-handed circularly polarized (RCP) wave. By changing the dielectric constant and magnetic permeability of the medium through the external environment, the metadevices can dynamically control the response characteristics to various polarized lights, especially circularly polarized lights such as refractive index, dichroism, optical rotation, asymmetric transmission, etc. According to the properties of negative refractive index, circular dichroism, optical rotation, and asymmetric transmission controlled by the tunable chiral metasurfaces, we review the latest research progress. Finally, we put forward our own opinions on the possible future development directions and existing challenges of the rapidly developing field of the tunable chiral metasurface.","PeriodicalId":39552,"journal":{"name":"Guangdian Gongcheng/Opto-Electronic Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84509123","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-02-26DOI: 10.12086/OEE.2021.200069
Li Xun, Li Linpeng, A. Lazovik, Wang Wenjie, W. Xiaohua
An algorithm (Re-CRNN) of image processing is proposed using RGB-D object recognition, which is improved based on a double stream convolutional recursive neural network, in order to improve the accuracy of object recognition. Re-CRNN combines RGB image with depth optical information, the double stream convolutional neural network (CNN) is improved based on the idea of residual learning as follows: top-level feature fusion unit is added into the network, the representation of federation feature is learning in RGB images and depth images and the high-level features are integrated in across channels of the extracted RGB images and depth images information, after that, the probability distribution was generated by Softmax. Finally, the experiment was carried out on the standard RGB-D data set. The experimental results show that the accuracy was 94.1% using Re-CRNN algorithm for the RGB-D object recognition, which was significantly improved compared with the existing image-based object recognition methods.
{"title":"RGB-D object recognition algorithm based on improved double stream convolution recursive neural network","authors":"Li Xun, Li Linpeng, A. Lazovik, Wang Wenjie, W. Xiaohua","doi":"10.12086/OEE.2021.200069","DOIUrl":"https://doi.org/10.12086/OEE.2021.200069","url":null,"abstract":"An algorithm (Re-CRNN) of image processing is proposed using RGB-D object recognition, which is improved based on a double stream convolutional recursive neural network, in order to improve the accuracy of object recognition. Re-CRNN combines RGB image with depth optical information, the double stream convolutional neural network (CNN) is improved based on the idea of residual learning as follows: top-level feature fusion unit is added into the network, the representation of federation feature is learning in RGB images and depth images and the high-level features are integrated in across channels of the extracted RGB images and depth images information, after that, the probability distribution was generated by Softmax. Finally, the experiment was carried out on the standard RGB-D data set. The experimental results show that the accuracy was 94.1% using Re-CRNN algorithm for the RGB-D object recognition, which was significantly improved compared with the existing image-based object recognition methods.","PeriodicalId":39552,"journal":{"name":"Guangdian Gongcheng/Opto-Electronic Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83868023","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-02-26DOI: 10.12086/OEE.2021.200013
Dong Yindong, R. Fuji, Liu Chunbin
The principal component analysis of linear kernel and XGBoost models are introduced to design electro-encephalogram (EEG) classification algorithm of four emotional states under continuous audio-visual stimulation. In order to reflect universality, the traditional power spectral density (PSD) is used as the feature of EEG signal, and the feature importance measure under the weight index is obtained with XGBoost learning. Then linear kernel principal component analysis is used to process the threshold selected features and send them to XGBoost model for recognition. According to the experimental analysis, gamma-band plays a more important role than other bands in XGBoost model recognition; in addition, for distribution on channels, the central, parietal, and right occipital regions play a more important role than other brain regions. The recognition accuracy of this algorithm is 78.4% and 92.6% respectively under the two recognition schemes of subjects all participation (SAP) and subject single dependent (SSD). Compared with other literature, this algorithm has made a great improvement. The scheme proposed is helpful to improve the recognition performance of brain-computer emotion system under audio-visual stimulation.
{"title":"EEG emotion recognition based on linear kernel PCA and XGBoost","authors":"Dong Yindong, R. Fuji, Liu Chunbin","doi":"10.12086/OEE.2021.200013","DOIUrl":"https://doi.org/10.12086/OEE.2021.200013","url":null,"abstract":"The principal component analysis of linear kernel and XGBoost models are introduced to design electro-encephalogram (EEG) classification algorithm of four emotional states under continuous audio-visual stimulation. In order to reflect universality, the traditional power spectral density (PSD) is used as the feature of EEG signal, and the feature importance measure under the weight index is obtained with XGBoost learning. Then linear kernel principal component analysis is used to process the threshold selected features and send them to XGBoost model for recognition. According to the experimental analysis, gamma-band plays a more important role than other bands in XGBoost model recognition; in addition, for distribution on channels, the central, parietal, and right occipital regions play a more important role than other brain regions. The recognition accuracy of this algorithm is 78.4% and 92.6% respectively under the two recognition schemes of subjects all participation (SAP) and subject single dependent (SSD). Compared with other literature, this algorithm has made a great improvement. The scheme proposed is helpful to improve the recognition performance of brain-computer emotion system under audio-visual stimulation.","PeriodicalId":39552,"journal":{"name":"Guangdian Gongcheng/Opto-Electronic Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82211394","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-01-15DOI: 10.12086/OEE.2021.200072
Ma Lixin, Dou Chenfei, Song Chencan, Yan Tianxiao
In the power system, it is difficult to detect the insulator's deterioration in operation. Aiming at this problem, this thesis applies the convolution neural network algorithm to evaluate the insulator's deterioration degree based on the deep analysis of the principle and structure of the convolution neural network model. Firstly, the power frequency flashover test was conducted on the insulator to produce three states as follows: no discharge, weak discharge, and strong discharge. Moreover, the Ultraviolet imager was applied to collect the insulator's ultraviolet images in different discharge state to establish the ultraviolet images sample library. Subsequently, the VGGNet framework neural network algorithm was applied to perform the classification training and the state-prediction evaluation on the samples so as to eventually achieve the purpose of judging whether the insulator is degraded. From the experimental results, it can be seen that the accuracy rate of the algorithm is as high as 98.4%, which has broad application prospects in the insulator's degradation detection. Furthermore, it provides a mentality for the reliability detection of other power equipments.
{"title":"Insulator nondestructive testing based on VGGNet algorithm","authors":"Ma Lixin, Dou Chenfei, Song Chencan, Yan Tianxiao","doi":"10.12086/OEE.2021.200072","DOIUrl":"https://doi.org/10.12086/OEE.2021.200072","url":null,"abstract":"In the power system, it is difficult to detect the insulator's deterioration in operation. Aiming at this problem, this thesis applies the convolution neural network algorithm to evaluate the insulator's deterioration degree based on the deep analysis of the principle and structure of the convolution neural network model. Firstly, the power frequency flashover test was conducted on the insulator to produce three states as follows: no discharge, weak discharge, and strong discharge. Moreover, the Ultraviolet imager was applied to collect the insulator's ultraviolet images in different discharge state to establish the ultraviolet images sample library. Subsequently, the VGGNet framework neural network algorithm was applied to perform the classification training and the state-prediction evaluation on the samples so as to eventually achieve the purpose of judging whether the insulator is degraded. From the experimental results, it can be seen that the accuracy rate of the algorithm is as high as 98.4%, which has broad application prospects in the insulator's degradation detection. Furthermore, it provides a mentality for the reliability detection of other power equipments.","PeriodicalId":39552,"journal":{"name":"Guangdian Gongcheng/Opto-Electronic Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87649171","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-01-15DOI: 10.12086/OEE.2021.200094
Meng Fanjun, Yin Dong
It is far essential to properly recognize the vehicle identification number (VIN) engraved on the car frame for vehicle surveillance and identification. In this paper, we propose an algorithm for recognizing rotational VIN im-ages based on neural network which incorporates two components: VIN detection and VIN recognition. Firstly, with lightweight neural network and text segmentation based on EAST, we attain efficient and excellent VIN detection performance. Secondly, the VIN recognition is regarded as a sequence classification problem. By means of connecting sequential classifiers, we predict VIN characters directly and precisely. For validating our algorithm, we collect a VIN dataset, which contains raw rotational VIN images and horizontal VIN images. Experimental results show that the algorithm we proposed achieves good performance on VIN detection and VIN recognition in real time.
{"title":"Vehicle identification number recognition based on neural network","authors":"Meng Fanjun, Yin Dong","doi":"10.12086/OEE.2021.200094","DOIUrl":"https://doi.org/10.12086/OEE.2021.200094","url":null,"abstract":"It is far essential to properly recognize the vehicle identification number (VIN) engraved on the car frame for vehicle surveillance and identification. In this paper, we propose an algorithm for recognizing rotational VIN im-ages based on neural network which incorporates two components: VIN detection and VIN recognition. Firstly, with lightweight neural network and text segmentation based on EAST, we attain efficient and excellent VIN detection performance. Secondly, the VIN recognition is regarded as a sequence classification problem. By means of connecting sequential classifiers, we predict VIN characters directly and precisely. For validating our algorithm, we collect a VIN dataset, which contains raw rotational VIN images and horizontal VIN images. Experimental results show that the algorithm we proposed achieves good performance on VIN detection and VIN recognition in real time.","PeriodicalId":39552,"journal":{"name":"Guangdian Gongcheng/Opto-Electronic Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88994332","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-01-15DOI: 10.12086/OEE.2021.200062
Zhang Wenming, Li Xiangyang, Li Hai-bin, Liu Ya-qian
In order to solve the problems of low work efficiency and safety caused by the inability of human eyes to accurately determine the position of the grab during the loading and unloading of dry bulk cargo by portal crane, a method of grab detection based on deep learning is proposed for the first time. The improved deep convolution neural network (YOLOv3-tiny) is used to train and test on the data set of grab, and then to learn its internal feature representation. The experimental results show that the detection method based on deep learning can achieve a detection speed of 45 frames per second and a recall rate of 95.78%. It can meet the real-time and accuracy of detection, and improve the safety and efficiency of work in the industrial field.
{"title":"The detection method for grab of portal crane based on deep learning","authors":"Zhang Wenming, Li Xiangyang, Li Hai-bin, Liu Ya-qian","doi":"10.12086/OEE.2021.200062","DOIUrl":"https://doi.org/10.12086/OEE.2021.200062","url":null,"abstract":"In order to solve the problems of low work efficiency and safety caused by the inability of human eyes to accurately determine the position of the grab during the loading and unloading of dry bulk cargo by portal crane, a method of grab detection based on deep learning is proposed for the first time. The improved deep convolution neural network (YOLOv3-tiny) is used to train and test on the data set of grab, and then to learn its internal feature representation. The experimental results show that the detection method based on deep learning can achieve a detection speed of 45 frames per second and a recall rate of 95.78%. It can meet the real-time and accuracy of detection, and improve the safety and efficiency of work in the industrial field.","PeriodicalId":39552,"journal":{"name":"Guangdian Gongcheng/Opto-Electronic Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90914990","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-01-15DOI: 10.12086/OEE.2021.200068
Wang Ye, Liu Qiang, Qin Linbo, Qizhi Teng, X. He
This paper proposes a correlation filter tracking algorithm based on adaptive spatial regularization and aberrance repression aiming at the problem that the spatial regularization weight of the background-aware correlation filter is fixed and does not adapt to the change of the target, and the problem that enlarging search area may introduce background noise, decreasing the discrimination ability of filters. First, FHOG features, CN features, and gray features are extracted to enhance the algorithm's ability to express the target. Second, aberrance repression terms are added to the target function to constrain the response map of the current frame, and to enhance the filter's discrimination ability to alleviate the filter model degradation. Finally, adaptive spatial regularization terms are added to the objective function to make the spatial regularization weights being updated as the objective changes, so that the filter can make full use of the target's diversity information. This paper involves experiments on the public data sets OTB-2013, OTB-2015 and VOT2016 to evaluate the proposed algorithm. The experimental results show that the speed of the algorithm used in this paper is 20 frames/s, evaluation indicators such as distance accuracy and success rate are superior to comparison algorithms, and it has good robustness in a variety of complex scenarios such as occlusion, background interference, and rotation changes.
{"title":"Learning adaptive spatial regularization and aberrance repression correlation filters for visual tracking","authors":"Wang Ye, Liu Qiang, Qin Linbo, Qizhi Teng, X. He","doi":"10.12086/OEE.2021.200068","DOIUrl":"https://doi.org/10.12086/OEE.2021.200068","url":null,"abstract":"This paper proposes a correlation filter tracking algorithm based on adaptive spatial regularization and aberrance repression aiming at the problem that the spatial regularization weight of the background-aware correlation filter is fixed and does not adapt to the change of the target, and the problem that enlarging search area may introduce background noise, decreasing the discrimination ability of filters. First, FHOG features, CN features, and gray features are extracted to enhance the algorithm's ability to express the target. Second, aberrance repression terms are added to the target function to constrain the response map of the current frame, and to enhance the filter's discrimination ability to alleviate the filter model degradation. Finally, adaptive spatial regularization terms are added to the objective function to make the spatial regularization weights being updated as the objective changes, so that the filter can make full use of the target's diversity information. This paper involves experiments on the public data sets OTB-2013, OTB-2015 and VOT2016 to evaluate the proposed algorithm. The experimental results show that the speed of the algorithm used in this paper is 20 frames/s, evaluation indicators such as distance accuracy and success rate are superior to comparison algorithms, and it has good robustness in a variety of complex scenarios such as occlusion, background interference, and rotation changes.","PeriodicalId":39552,"journal":{"name":"Guangdian Gongcheng/Opto-Electronic Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75223799","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-01-15DOI: 10.12086/OEE.2021.200124
Ren Yu, Luo Yihan, Xu Shaoxiong, Ma Hao-Tong, Tan Yi
Non-line-of-sight location is an active detection technology which is used to detect the position of objects out of sight by extracting the time of flight. It is a research hotspot in recent years. In order to study the performance differences of mean filter, median filter and Gaussian filter in extracting time of flight, firstly, the energy changing model of photon flight model is optimized by photometry, and then the parameters of the three filtering methods are optimized and analyzed. After that, the adaptability of these three extraction methods to the maximum value judgment method and probability threshold weighted judgment method is analyzed. Finally, the accuracy and stability of these three time extraction algorithms are compared by using the positions of devices and invisible object as variables. The simulation results show that the median filter is suitable for a narrow environment and it has the high accuracy in positioning; the locations with Gaussian filter have good positioning stability and there is a wider selection range of filtering parameters when the signal is processed with Gaussian filter.
{"title":"A comparative study of time of flight extraction methods in non-line-of-sight location","authors":"Ren Yu, Luo Yihan, Xu Shaoxiong, Ma Hao-Tong, Tan Yi","doi":"10.12086/OEE.2021.200124","DOIUrl":"https://doi.org/10.12086/OEE.2021.200124","url":null,"abstract":"Non-line-of-sight location is an active detection technology which is used to detect the position of objects out of sight by extracting the time of flight. It is a research hotspot in recent years. In order to study the performance differences of mean filter, median filter and Gaussian filter in extracting time of flight, firstly, the energy changing model of photon flight model is optimized by photometry, and then the parameters of the three filtering methods are optimized and analyzed. After that, the adaptability of these three extraction methods to the maximum value judgment method and probability threshold weighted judgment method is analyzed. Finally, the accuracy and stability of these three time extraction algorithms are compared by using the positions of devices and invisible object as variables. The simulation results show that the median filter is suitable for a narrow environment and it has the high accuracy in positioning; the locations with Gaussian filter have good positioning stability and there is a wider selection range of filtering parameters when the signal is processed with Gaussian filter.","PeriodicalId":39552,"journal":{"name":"Guangdian Gongcheng/Opto-Electronic Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84058411","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-01-15DOI: 10.12086/OEE.2021.200045
Sun Rui, Zhang Han, Zhi Cheng, Xudong Zhang
In recent years, infrared imaging technology has developed rapidly and has been increasingly used in military reconnaissance, security surveillance, and medical imaging. However, in the process of infrared image imaging or transmission, it is affected by many factors such as environment and equipment. The infrared image often has a low resolution, which greatly reduces the amount of information contained in the infrared image and restricts the application value of the infrared image. Therefore, how to obtain high-resolution and high-information infrared images has become an issue that people urgently need to solve. In recent years, the development of deep learning technology has made rapid progress, and super-resolution methods based on deep learning have begun to appear. However, if A super-resolution reconstruction method of infrared images based on channel attention and transfer learning was proposed to solve the problems of low resolution and low quality of infrared images. In this method, a deep convolutional neural network is designed to enhance the learning ability of the network by introducing the channel attention mechanism, and the residual learning method is used to mitigate the problem of gradient explosion or disappearance and to accelerate the convergence of the network. Because high-quality infrared images are difficult to collect and insufficient in number, so this method is divided into two steps: the first step is to use natural images to pre-train the neural network model, and the second step is to use transfer learning knowledge to fine-tune the pre-trained model’s parameters with a small number of high-quality infrared images to make the model better in reconstructing the infrared image. Finally, a multi-scale detail boosting filter is added to improve the visual effect of the reconstructed infrared image. Experiments on Set5 and Set14 datasets as well as infrared images show that the deepening network depth and introducing channel attention mechanism can improve the effect of super-resolution reconstruction, transfer learning can well solve the problem of insufficient number of infrared image samples, and multi-scale detail boosting filter can improve the details and increase the amount of information of the reconstruction image.these convolutional neural networks are directly applied to the infrared image field, there are some problems: SRCNN, FSRCNN, and ESPCN have fewer network convolutional layers and insufficient network depth, and the learning features will be relatively single, ignoring the differences between image features. The mutual relationship makes it difficult to extract the deep-level information of the infrared image, and SRGAN may generate super-resolution images that are not close to the original image in certain details, which is not conducive to the application of infrared images in military, medical and surveillance. Another problem that needs to be overcome is that it is difficult to collect a sufficie
{"title":"Super-resolution reconstruction of infrared image based on channel attention and transfer learning","authors":"Sun Rui, Zhang Han, Zhi Cheng, Xudong Zhang","doi":"10.12086/OEE.2021.200045","DOIUrl":"https://doi.org/10.12086/OEE.2021.200045","url":null,"abstract":"In recent years, infrared imaging technology has developed rapidly and has been increasingly used in military reconnaissance, security surveillance, and medical imaging. However, in the process of infrared image imaging or transmission, it is affected by many factors such as environment and equipment. The infrared image often has a low resolution, which greatly reduces the amount of information contained in the infrared image and restricts the application value of the infrared image. Therefore, how to obtain high-resolution and high-information infrared images has become an issue that people urgently need to solve. In recent years, the development of deep learning technology has made rapid progress, and super-resolution methods based on deep learning have begun to appear. However, if A super-resolution reconstruction method of infrared images based on channel attention and transfer learning was proposed to solve the problems of low resolution and low quality of infrared images. In this method, a deep convolutional neural network is designed to enhance the learning ability of the network by introducing the channel attention mechanism, and the residual learning method is used to mitigate the problem of gradient explosion or disappearance and to accelerate the convergence of the network. Because high-quality infrared images are difficult to collect and insufficient in number, so this method is divided into two steps: the first step is to use natural images to pre-train the neural network model, and the second step is to use transfer learning knowledge to fine-tune the pre-trained model’s parameters with a small number of high-quality infrared images to make the model better in reconstructing the infrared image. Finally, a multi-scale detail boosting filter is added to improve the visual effect of the reconstructed infrared image. Experiments on Set5 and Set14 datasets as well as infrared images show that the deepening network depth and introducing channel attention mechanism can improve the effect of super-resolution reconstruction, transfer learning can well solve the problem of insufficient number of infrared image samples, and multi-scale detail boosting filter can improve the details and increase the amount of information of the reconstruction image.these convolutional neural networks are directly applied to the infrared image field, there are some problems: SRCNN, FSRCNN, and ESPCN have fewer network convolutional layers and insufficient network depth, and the learning features will be relatively single, ignoring the differences between image features. The mutual relationship makes it difficult to extract the deep-level information of the infrared image, and SRGAN may generate super-resolution images that are not close to the original image in certain details, which is not conducive to the application of infrared images in military, medical and surveillance. Another problem that needs to be overcome is that it is difficult to collect a sufficie","PeriodicalId":39552,"journal":{"name":"Guangdian Gongcheng/Opto-Electronic Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76583935","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-01-15DOI: 10.12086/OEE.2021.200112
Haiyong Chen, Zhao Peng, Haowei Yan
The background of the EL image of a photovoltaic cell under electroluminescence (EL) presents complex non-uniform texture features, and there are grain pseudo-defects similar to cracks. At the same time, the cracks appear as multi-scale features with various shapes. The above mentioned difficulties have presented great chal-lenges for the detection task. Therefore, this paper proposes a multi-scale Faster-RCNN model that integrates at-tention. On the one hand, an improved feature pyramid network is used to obtain multi-scale advanced semantic feature maps to improve the network's feature expression ability of multi-scale crack defects. On the other hand, an improved attention region proposal network A-RPN is adopted to increase the model's attention to crack defects and suppress the characteristics of complex background and grain pseudo-defects. At the same time, in the RPN network training process, a loss function Focal loss is used to reduce the proportion of simple samples in the training process, so that the model pays more attention to the samples that are difficult to distinguish. Experimental results show that this algorithm improves the accuracy of crack defect detection in EL images, reaching nearly 95%.
{"title":"Crack detection based on multi-scale Faster RCNN with attention","authors":"Haiyong Chen, Zhao Peng, Haowei Yan","doi":"10.12086/OEE.2021.200112","DOIUrl":"https://doi.org/10.12086/OEE.2021.200112","url":null,"abstract":"The background of the EL image of a photovoltaic cell under electroluminescence (EL) presents complex non-uniform texture features, and there are grain pseudo-defects similar to cracks. At the same time, the cracks appear as multi-scale features with various shapes. The above mentioned difficulties have presented great chal-lenges for the detection task. Therefore, this paper proposes a multi-scale Faster-RCNN model that integrates at-tention. On the one hand, an improved feature pyramid network is used to obtain multi-scale advanced semantic feature maps to improve the network's feature expression ability of multi-scale crack defects. On the other hand, an improved attention region proposal network A-RPN is adopted to increase the model's attention to crack defects and suppress the characteristics of complex background and grain pseudo-defects. At the same time, in the RPN network training process, a loss function Focal loss is used to reduce the proportion of simple samples in the training process, so that the model pays more attention to the samples that are difficult to distinguish. Experimental results show that this algorithm improves the accuracy of crack defect detection in EL images, reaching nearly 95%.","PeriodicalId":39552,"journal":{"name":"Guangdian Gongcheng/Opto-Electronic Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89582475","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：