Pub Date : 2021-06-18DOI: 10.1109/IMCEC51613.2021.9482351
Shuo Ma, Jiajun Chen, Zekai Li, Wei Nai, Y. Xing
Communication based train control (CBTC) system, which has been employed in the train-ground wireless communication scenario of modern train operation and control systems (OCS), can realize fast and accurate information transmission and enhance train operation efficiency and safety. Many companies, especially the ones in those countries with traditional technology advantages in railway system construction and operation, are developing and improving CBTC related technologies, and have applied for huge amount of related innovative patents. By considering that patents can not only help to protect related technologies from their corresponding companies and give related engineers or researchers in rail transit industry valuable methods or ideas for reference, but reflect the development of related techniques as well, in this paper, Alstom, which is a famous and representative company in railway signal industry in not only France but also the whole world and has applied abundant innovative patents during past decades, has been chosen as the research object, a thorough development study has been done on CBTC related techniques based on systematically analyzing granted patents of this company, and some ideas have been summarized and provided on CBTC development and application.
{"title":"Development Study on CBTC Related Techniques Based on Systematically Analyzing Granted Patents of Alstom Company","authors":"Shuo Ma, Jiajun Chen, Zekai Li, Wei Nai, Y. Xing","doi":"10.1109/IMCEC51613.2021.9482351","DOIUrl":"https://doi.org/10.1109/IMCEC51613.2021.9482351","url":null,"abstract":"Communication based train control (CBTC) system, which has been employed in the train-ground wireless communication scenario of modern train operation and control systems (OCS), can realize fast and accurate information transmission and enhance train operation efficiency and safety. Many companies, especially the ones in those countries with traditional technology advantages in railway system construction and operation, are developing and improving CBTC related technologies, and have applied for huge amount of related innovative patents. By considering that patents can not only help to protect related technologies from their corresponding companies and give related engineers or researchers in rail transit industry valuable methods or ideas for reference, but reflect the development of related techniques as well, in this paper, Alstom, which is a famous and representative company in railway signal industry in not only France but also the whole world and has applied abundant innovative patents during past decades, has been chosen as the research object, a thorough development study has been done on CBTC related techniques based on systematically analyzing granted patents of this company, and some ideas have been summarized and provided on CBTC development and application.","PeriodicalId":240400,"journal":{"name":"2021 IEEE 4th Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114232047","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 : 2021-06-18DOI: 10.1109/IMCEC51613.2021.9482021
Zhigang Zhang, Pengfei Yu, Haiyan Li, Hongsong Li
In order to reduce the occurrence of wild mushroom poisoning incidents, and at the same time reduce the impact of the complex background of wild mushroom pictures on the recognition accuracy, this paper uses the Squeeze-and-Excitation attention mechanism and feature pyramid to improve the ResNet50 network. First, in order to increase the correlation between channels, the Squeeze-and-Excitation attention mechanism is added to the residual block of the ResNet50 network. Second, the feature pyramid is used to fuse the features between different layers of the network. Next, send the lowest feature map which fused by FPN to the fully connected layer. At last, the final result is normalized by softmax function and classified. The experimental results show that the accuracy of the method can reach 95.97%, which is 2.71% higher than the unimproved ResNet50 network. The comparison results show that it is better than the three network models of VGG19, DenseNet161 and Iception_v3, the accuracy rates are increased by 6.40%, 6.31% and 2.28% respectively.
{"title":"Wild Mushroom Recognition Based on Attention Mechanism and Feature Pyramid","authors":"Zhigang Zhang, Pengfei Yu, Haiyan Li, Hongsong Li","doi":"10.1109/IMCEC51613.2021.9482021","DOIUrl":"https://doi.org/10.1109/IMCEC51613.2021.9482021","url":null,"abstract":"In order to reduce the occurrence of wild mushroom poisoning incidents, and at the same time reduce the impact of the complex background of wild mushroom pictures on the recognition accuracy, this paper uses the Squeeze-and-Excitation attention mechanism and feature pyramid to improve the ResNet50 network. First, in order to increase the correlation between channels, the Squeeze-and-Excitation attention mechanism is added to the residual block of the ResNet50 network. Second, the feature pyramid is used to fuse the features between different layers of the network. Next, send the lowest feature map which fused by FPN to the fully connected layer. At last, the final result is normalized by softmax function and classified. The experimental results show that the accuracy of the method can reach 95.97%, which is 2.71% higher than the unimproved ResNet50 network. The comparison results show that it is better than the three network models of VGG19, DenseNet161 and Iception_v3, the accuracy rates are increased by 6.40%, 6.31% and 2.28% respectively.","PeriodicalId":240400,"journal":{"name":"2021 IEEE 4th Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114305997","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 : 2021-06-18DOI: 10.1109/IMCEC51613.2021.9482329
Ming Long, Jun Yang, S. Xia, Xu Wei
In this paper, convolutional neural network (CNN) is used to classificate the rotor blade number of rotor targets micro-motion signal with deep learning’s strong feature extraction ability. Firstly, the scattering point model of the rotor blade echo is used to generate the target echo. Under the condition of different signal-to-noise ratio, time-frequency diagram of the echo with different number of rotor blades is constructed by using short-time Fourier transform, which is used as the test set and training set. Three convolutional neural network models of lenet, alexnet and vggnet are used for training. The performance of the network model is compared, and the recognition performance of the alexnet network model is analyzed under ambiguous, unambiguous and a method of Interpolation to resolve ambiguous. Through experiments, it can be found that the recognition rate of the proposed method can reach 95% under the condition of signal-to-noise ratio of 10dB. It has good recognition performance for classification of rotor blade number, and provides effective data and algorithm support for the rotor target recognition in the future.
{"title":"Classification of rotor blade number of rotor targets micro-motion signal based on CNN","authors":"Ming Long, Jun Yang, S. Xia, Xu Wei","doi":"10.1109/IMCEC51613.2021.9482329","DOIUrl":"https://doi.org/10.1109/IMCEC51613.2021.9482329","url":null,"abstract":"In this paper, convolutional neural network (CNN) is used to classificate the rotor blade number of rotor targets micro-motion signal with deep learning’s strong feature extraction ability. Firstly, the scattering point model of the rotor blade echo is used to generate the target echo. Under the condition of different signal-to-noise ratio, time-frequency diagram of the echo with different number of rotor blades is constructed by using short-time Fourier transform, which is used as the test set and training set. Three convolutional neural network models of lenet, alexnet and vggnet are used for training. The performance of the network model is compared, and the recognition performance of the alexnet network model is analyzed under ambiguous, unambiguous and a method of Interpolation to resolve ambiguous. Through experiments, it can be found that the recognition rate of the proposed method can reach 95% under the condition of signal-to-noise ratio of 10dB. It has good recognition performance for classification of rotor blade number, and provides effective data and algorithm support for the rotor target recognition in the future.","PeriodicalId":240400,"journal":{"name":"2021 IEEE 4th Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC)","volume":"253 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116727424","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 : 2021-06-18DOI: 10.1109/IMCEC51613.2021.9482349
Chen Xiaomao, Liu Chunfei, Fan Yiwei, Guo Ning
In order to solve the demand of time synchronization with GPS satellite clock, a combination of high-precision time interval measurement technology and crystal taming technology is used to realize the taming control of local clock source by using standard 1PPS signal to complete the time synchronization with GPS satellite clock. The interpolation of the delay unit is completed by the internal feed structure of FPGA to measure the time interval smaller than the system clock, which is combined with the pulse counting method to increase the range of the delay unit interpolation measurement. Finally, the FPGA is used to control the DAC7512 output voltage in real time to adjust the output of the local crystal based on the time interval output value. After a long time test, the accuracy of the synchronous 1PPS obtained by this method is better than 700ps compared with the standard 1PPS, and the local crystal can maintain a stable state for a long time.
{"title":"Time synchronization method based on time interval measurement","authors":"Chen Xiaomao, Liu Chunfei, Fan Yiwei, Guo Ning","doi":"10.1109/IMCEC51613.2021.9482349","DOIUrl":"https://doi.org/10.1109/IMCEC51613.2021.9482349","url":null,"abstract":"In order to solve the demand of time synchronization with GPS satellite clock, a combination of high-precision time interval measurement technology and crystal taming technology is used to realize the taming control of local clock source by using standard 1PPS signal to complete the time synchronization with GPS satellite clock. The interpolation of the delay unit is completed by the internal feed structure of FPGA to measure the time interval smaller than the system clock, which is combined with the pulse counting method to increase the range of the delay unit interpolation measurement. Finally, the FPGA is used to control the DAC7512 output voltage in real time to adjust the output of the local crystal based on the time interval output value. After a long time test, the accuracy of the synchronous 1PPS obtained by this method is better than 700ps compared with the standard 1PPS, and the local crystal can maintain a stable state for a long time.","PeriodicalId":240400,"journal":{"name":"2021 IEEE 4th Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117134130","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 : 2021-06-18DOI: 10.1109/IMCEC51613.2021.9482267
Xiaomeng Wu, Zexuan Li
Since the industrial revolution, the application of traditional petrochemical energy has brought a lot of pollution and greenhouse effect to the global environment, and new energy technology, as one of the important ways to solve global environmental problems, has been widely recognized by all countries in the world, and its application has become more and more deep widely. As a majority of distributed photovoltaic projects are integrated into the distribution network to generate electricity, the impact on the distribution network and system stability has become increasingly prominent. Since distributed photovoltaic grid connection is the main form and development trend of photovoltaic power generation in the future, analyzing the impact of its harmonics on the distribution network is particularly important for maintaining the stable operation of the grid system.
{"title":"The Impact of Harmonic Generated by Distributed Photovoltaic Grid-connected Power Generation System","authors":"Xiaomeng Wu, Zexuan Li","doi":"10.1109/IMCEC51613.2021.9482267","DOIUrl":"https://doi.org/10.1109/IMCEC51613.2021.9482267","url":null,"abstract":"Since the industrial revolution, the application of traditional petrochemical energy has brought a lot of pollution and greenhouse effect to the global environment, and new energy technology, as one of the important ways to solve global environmental problems, has been widely recognized by all countries in the world, and its application has become more and more deep widely. As a majority of distributed photovoltaic projects are integrated into the distribution network to generate electricity, the impact on the distribution network and system stability has become increasingly prominent. Since distributed photovoltaic grid connection is the main form and development trend of photovoltaic power generation in the future, analyzing the impact of its harmonics on the distribution network is particularly important for maintaining the stable operation of the grid system.","PeriodicalId":240400,"journal":{"name":"2021 IEEE 4th Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC)","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117171780","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}
In this paper, collected the operation data of a fuel cell vehicle (FCV) at - 30 ℃ by analyzing the vehicle CAN message. Took stack temperature, stack voltage, stack calorific value and battery SOC as the target objects, analyzed the control logic of fast cold start of the fuel cell vehicle stack at low temperature, and summarized the technical highlights of the fuel cell vehicle, which can be used to guide the product development of domestic automobile enterprises.
{"title":"Research on the performance of fuel cell vehicle at cold start of -30 ℃","authors":"Tong Wang, Nanlin Lei, Shaoqing He, Xiaoyu Jia, Qiang Zhang, Feikun Zhou, Wenwen Guo","doi":"10.1109/imcec51613.2021.9481959","DOIUrl":"https://doi.org/10.1109/imcec51613.2021.9481959","url":null,"abstract":"In this paper, collected the operation data of a fuel cell vehicle (FCV) at - 30 ℃ by analyzing the vehicle CAN message. Took stack temperature, stack voltage, stack calorific value and battery SOC as the target objects, analyzed the control logic of fast cold start of the fuel cell vehicle stack at low temperature, and summarized the technical highlights of the fuel cell vehicle, which can be used to guide the product development of domestic automobile enterprises.","PeriodicalId":240400,"journal":{"name":"2021 IEEE 4th Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115770476","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 : 2021-06-18DOI: 10.1109/IMCEC51613.2021.9482153
Bingxin Xu, Rui-xia Liu, Yinglong Wang
ECG is a kind of weak body surface signal that is easily disturbed by noise during the collection process. The traditional ECG signal denoising technology depends on effective filters, which is artificially created by experience. Once the form of the signal is updated, the inherent space may no longer be suitable for this problem. As the deep learning method can learn sparse features from the data without manual intervention. We designed a deep learning process to apply the powerful functions of neural networks to the inference of the ECG sparse noise reduction model, which can also solve the optimization problem in sparse signal processing. By using this method of deep expansion, an optimization strategy is proposed, which turns the iterative optimization problem into constructing a new network framework. In this way, the model parameters can be easily solved through cross-layer. Through experimental verification, our method improves the SNR by 83.29% compared with the current advanced method.
{"title":"An ECG Sparse Noise Reduction Method based on Deep Unfolding Network","authors":"Bingxin Xu, Rui-xia Liu, Yinglong Wang","doi":"10.1109/IMCEC51613.2021.9482153","DOIUrl":"https://doi.org/10.1109/IMCEC51613.2021.9482153","url":null,"abstract":"ECG is a kind of weak body surface signal that is easily disturbed by noise during the collection process. The traditional ECG signal denoising technology depends on effective filters, which is artificially created by experience. Once the form of the signal is updated, the inherent space may no longer be suitable for this problem. As the deep learning method can learn sparse features from the data without manual intervention. We designed a deep learning process to apply the powerful functions of neural networks to the inference of the ECG sparse noise reduction model, which can also solve the optimization problem in sparse signal processing. By using this method of deep expansion, an optimization strategy is proposed, which turns the iterative optimization problem into constructing a new network framework. In this way, the model parameters can be easily solved through cross-layer. Through experimental verification, our method improves the SNR by 83.29% compared with the current advanced method.","PeriodicalId":240400,"journal":{"name":"2021 IEEE 4th Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115006413","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 : 2021-06-18DOI: 10.1109/IMCEC51613.2021.9482055
Yueming Wang
Arbitrary style transfer means that stylized images can be generated from a set of arbitrary input image pairs of content images and style images. Recent arbitrary style transfer algorithms lead to distortion of content or incompletion of style transfer because network need to make a balance between the content structure and style. In this paper, we introduce a dual attention network based on style attention and channel attention, which can flexibly transfer local styles, pay more attention to content structure, keep content structure intact and reduce unnecessary style transfer. Experimental results show that the network can synthesize high quality stylized images while maintaining real-time performance.
{"title":"An Arbitrary Style Transfer Network based on Dual Attention Module","authors":"Yueming Wang","doi":"10.1109/IMCEC51613.2021.9482055","DOIUrl":"https://doi.org/10.1109/IMCEC51613.2021.9482055","url":null,"abstract":"Arbitrary style transfer means that stylized images can be generated from a set of arbitrary input image pairs of content images and style images. Recent arbitrary style transfer algorithms lead to distortion of content or incompletion of style transfer because network need to make a balance between the content structure and style. In this paper, we introduce a dual attention network based on style attention and channel attention, which can flexibly transfer local styles, pay more attention to content structure, keep content structure intact and reduce unnecessary style transfer. Experimental results show that the network can synthesize high quality stylized images while maintaining real-time performance.","PeriodicalId":240400,"journal":{"name":"2021 IEEE 4th Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC)","volume":"58 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123131802","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 : 2021-06-18DOI: 10.1109/IMCEC51613.2021.9482222
Bakun Zhu, Weigang Zhu, Wei Li, Tianhao Gao
Real-time and accurate evaluation of jamming effect is the key to implement intelligent jamming decision. The existing evaluation method of jamming effect based on radar side is too rough to serve the problem of radar jamming intelligent decision. Based on the syntactic model, a four-layers multi-functional radar signal mode (FMRSM) is proposed in this paper. By analyzing the behavior rules of multi-functional radar(MFR) in the process of radar countermeasure, an online evaluation model of multifunctional radar jamming effect is proposed in combination with FMRSM. The effectiveness of the jamming effect evaluation method is proved by experimental simulation under the background of aircraft penetration.
{"title":"An On-line Evaluation Method of Multi-Functional Radar Jamming Effect","authors":"Bakun Zhu, Weigang Zhu, Wei Li, Tianhao Gao","doi":"10.1109/IMCEC51613.2021.9482222","DOIUrl":"https://doi.org/10.1109/IMCEC51613.2021.9482222","url":null,"abstract":"Real-time and accurate evaluation of jamming effect is the key to implement intelligent jamming decision. The existing evaluation method of jamming effect based on radar side is too rough to serve the problem of radar jamming intelligent decision. Based on the syntactic model, a four-layers multi-functional radar signal mode (FMRSM) is proposed in this paper. By analyzing the behavior rules of multi-functional radar(MFR) in the process of radar countermeasure, an online evaluation model of multifunctional radar jamming effect is proposed in combination with FMRSM. The effectiveness of the jamming effect evaluation method is proved by experimental simulation under the background of aircraft penetration.","PeriodicalId":240400,"journal":{"name":"2021 IEEE 4th Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124705259","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 : 2021-06-18DOI: 10.1109/IMCEC51613.2021.9482382
J. Kan, Zongyun Gu, Chun-Yue Ma, Qing Wang
In order to segment leaf image under complex background and improve the accuracy of leaf image segmentation, an image segmentation method based on improved U-shaped network is proposed. Based on the Pytorch deep learning framework, the U-shaped network model FPN is improved, the model adopts the encoder-decoder structure, ResNet50 is used as the trunk network, the encoder receives the image input, the feature extraction is accomplished by convolution, and the decoder uses the bilinear interpolation to complete the image reconstruction and outputs the segmentation results. In order to integrate the underlying position features and high-level semantic features better, the feature fusion module is introduced in the decoder. The experimental results show that the model has a significant effect in plant leaf segmentation, and the technical index is better than most traditional image segmentation algorithms.
{"title":"Leaf Segmentation Algorithm Based on Improved U-shaped Network under Complex Background","authors":"J. Kan, Zongyun Gu, Chun-Yue Ma, Qing Wang","doi":"10.1109/IMCEC51613.2021.9482382","DOIUrl":"https://doi.org/10.1109/IMCEC51613.2021.9482382","url":null,"abstract":"In order to segment leaf image under complex background and improve the accuracy of leaf image segmentation, an image segmentation method based on improved U-shaped network is proposed. Based on the Pytorch deep learning framework, the U-shaped network model FPN is improved, the model adopts the encoder-decoder structure, ResNet50 is used as the trunk network, the encoder receives the image input, the feature extraction is accomplished by convolution, and the decoder uses the bilinear interpolation to complete the image reconstruction and outputs the segmentation results. In order to integrate the underlying position features and high-level semantic features better, the feature fusion module is introduced in the decoder. The experimental results show that the model has a significant effect in plant leaf segmentation, and the technical index is better than most traditional image segmentation algorithms.","PeriodicalId":240400,"journal":{"name":"2021 IEEE 4th Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC)","volume":"176 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114073194","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：