Pub Date : 2021-11-22DOI: 10.1109/ICESIT53460.2021.9696490
Liukui Chen, Xiaoxing Wang, H. Jiang, Li Tang, Zuojin Li, Yao Du
In recent years, with the rapid development of biometrics technology, vein recognition is slowly integrating into our lives. At present, there are many related applications of hand veins and finger veins. The palm veins are deep under the skin and interfere with palm prints, which increases the difficulty of obtaining them, resulting in relatively few applications. Based on the research of palm vein image acquisition, this paper designs a set of auxiliary acquisition equipment to complete the acquisition of vein images under a comfortable somatosensory. The device takes the Raspberry Pi as the core of the model, supplemented by accessories such as luminous light source, optical sensor, control chip and small display, which can complete the collection of vein images. And through the algorithm of restricted contrast histogram equalization, Gaussian denoising, gabor filtering and other algorithms optimized for palm veins in the Raspberry Pi, the palm vein lines are enhanced to improve the image quality. The model integrates multiple modules into one mold, greatly reduces the volume of the model, improves the speed of the overall collection process, and has good application value.
{"title":"Design of Palm Vein Platform and Pattern Enhancement Model Based on Raspberry Pi","authors":"Liukui Chen, Xiaoxing Wang, H. Jiang, Li Tang, Zuojin Li, Yao Du","doi":"10.1109/ICESIT53460.2021.9696490","DOIUrl":"https://doi.org/10.1109/ICESIT53460.2021.9696490","url":null,"abstract":"In recent years, with the rapid development of biometrics technology, vein recognition is slowly integrating into our lives. At present, there are many related applications of hand veins and finger veins. The palm veins are deep under the skin and interfere with palm prints, which increases the difficulty of obtaining them, resulting in relatively few applications. Based on the research of palm vein image acquisition, this paper designs a set of auxiliary acquisition equipment to complete the acquisition of vein images under a comfortable somatosensory. The device takes the Raspberry Pi as the core of the model, supplemented by accessories such as luminous light source, optical sensor, control chip and small display, which can complete the collection of vein images. And through the algorithm of restricted contrast histogram equalization, Gaussian denoising, gabor filtering and other algorithms optimized for palm veins in the Raspberry Pi, the palm vein lines are enhanced to improve the image quality. The model integrates multiple modules into one mold, greatly reduces the volume of the model, improves the speed of the overall collection process, and has good application value.","PeriodicalId":164745,"journal":{"name":"2021 IEEE International Conference on Emergency Science and Information Technology (ICESIT)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116377086","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 today's society, high-rise residential buildings are mostly high-rise buildings, and high-rise residential buildings are frequently fired and difficult to rescue, causing huge losses to people's lives and property. It is very important to construct fire detection and pre-treatment programs before fire rescue. At present, the fire analysis and emergency pretreatment system at the fire scene of high-rise residential buildings are lacking, and the fire prevention and control equipment has false alarms, high delay and low efficiency, or even no pre-rescue pre-treatment. In response to these problems, this paper proposes the application of terminal-edge-cloud-based edge computing in the fire detection of residential buildings. This architecture sinks the environmental parameters monitored by the fire prevention and control equipment to the edge gateway for data storage and processing. Achieve efficient fire identification, low-latency feedback and fire prevention and control. This article analyzes the edge gateway design and multi-sensor data fusion in the architecture, and finally combs the process of residential building fire from occurrence to treatment. The research results can provide reference for the construction of high-rise residential building fire detection network, and to a certain extent Realize rapid fire prevention and control.
{"title":"Research on Fire Detection Method of High-rise Residential Buildings Based on Cloud Edge Fusion Computing","authors":"Tingting Wen, Guorong Chen, Yixuan Zhang, Yanbing Xiao, Bocheng Wang, Biaobiao Hu","doi":"10.1109/ICESIT53460.2021.9696541","DOIUrl":"https://doi.org/10.1109/ICESIT53460.2021.9696541","url":null,"abstract":"In today's society, high-rise residential buildings are mostly high-rise buildings, and high-rise residential buildings are frequently fired and difficult to rescue, causing huge losses to people's lives and property. It is very important to construct fire detection and pre-treatment programs before fire rescue. At present, the fire analysis and emergency pretreatment system at the fire scene of high-rise residential buildings are lacking, and the fire prevention and control equipment has false alarms, high delay and low efficiency, or even no pre-rescue pre-treatment. In response to these problems, this paper proposes the application of terminal-edge-cloud-based edge computing in the fire detection of residential buildings. This architecture sinks the environmental parameters monitored by the fire prevention and control equipment to the edge gateway for data storage and processing. Achieve efficient fire identification, low-latency feedback and fire prevention and control. This article analyzes the edge gateway design and multi-sensor data fusion in the architecture, and finally combs the process of residential building fire from occurrence to treatment. The research results can provide reference for the construction of high-rise residential building fire detection network, and to a certain extent Realize rapid fire prevention and control.","PeriodicalId":164745,"journal":{"name":"2021 IEEE International Conference on Emergency Science and Information Technology (ICESIT)","volume":"121 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123690192","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 : 2021-11-22DOI: 10.1109/ICESIT53460.2021.9696521
Zhitang He
This paper introduces the technical scheme and process, key links and technologies, adjustment results and accuracy of data processing of Xinjiang first order gravity network. In the data preprocessing of Xinjiang first order gravity network, various corrections are taken into account, and rigorous mathematical models are adopted; in the adjustment, reliable methods and technologies such as “strong and weak benchmark” combined adjustment method and gross error test are adopted, which ensure the accuracy and reliability of the data processing results. After adjustment, the mean square error of all gravity points is ± 17.9×10−8 ms−2, and the mean square error of the weakest point (XJ12 at Turgat station) is ± 30.6×10−8 ms−2. It has positive reference significance and reference value for data processing of regional gravity reference network.
{"title":"Data processing and analysis of Xinjiang first order gravity network","authors":"Zhitang He","doi":"10.1109/ICESIT53460.2021.9696521","DOIUrl":"https://doi.org/10.1109/ICESIT53460.2021.9696521","url":null,"abstract":"This paper introduces the technical scheme and process, key links and technologies, adjustment results and accuracy of data processing of Xinjiang first order gravity network. In the data preprocessing of Xinjiang first order gravity network, various corrections are taken into account, and rigorous mathematical models are adopted; in the adjustment, reliable methods and technologies such as “strong and weak benchmark” combined adjustment method and gross error test are adopted, which ensure the accuracy and reliability of the data processing results. After adjustment, the mean square error of all gravity points is ± 17.9×10−8 ms−2, and the mean square error of the weakest point (XJ12 at Turgat station) is ± 30.6×10−8 ms−2. It has positive reference significance and reference value for data processing of regional gravity reference network.","PeriodicalId":164745,"journal":{"name":"2021 IEEE International Conference on Emergency Science and Information Technology (ICESIT)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116884585","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 : 2021-11-22DOI: 10.1109/ICESIT53460.2021.9696556
Gang-song Dong, Yumei Lu, C. Li
With the rapid development of Chinese economy, Our country has been in the forefront of automobile producing countries. As the number of cars continues to rise, people pay more and more attention to the interior environment, the interior air quality requirements are also constantly improving, the interior environment problems are widely concerned. This paper designs a car environment monitoring system with wireless sensor network as serial port. The system is composed of single chip microcomputer, wireless sensor network technology and sensor module. The gas sensor is used to detect the concentration of formaldehyde, PM2.5, carbon monoxide and carbon dioxide, which have great influence on human health. The parameters collected by various sensors in the car are transmitted to the main control chip STM32F103RCT6 through the wireless sensor network module. STM32F103RCT6 analyzes and processes the data to achieve the goal of monitoring the air quality in the car. When the concentration of harmful gas in the car exceeds the threshold value, the voice broadcast can timely remind people to deal with the environment in the car, reduce the harmful gas in the car, so as to achieve the purpose of improving the driving environment, to meet people's health needs for the air environment in the car.
{"title":"Design and Implementation of Vehicle Environment Monitoring System Based on Wireless Sensor Network","authors":"Gang-song Dong, Yumei Lu, C. Li","doi":"10.1109/ICESIT53460.2021.9696556","DOIUrl":"https://doi.org/10.1109/ICESIT53460.2021.9696556","url":null,"abstract":"With the rapid development of Chinese economy, Our country has been in the forefront of automobile producing countries. As the number of cars continues to rise, people pay more and more attention to the interior environment, the interior air quality requirements are also constantly improving, the interior environment problems are widely concerned. This paper designs a car environment monitoring system with wireless sensor network as serial port. The system is composed of single chip microcomputer, wireless sensor network technology and sensor module. The gas sensor is used to detect the concentration of formaldehyde, PM2.5, carbon monoxide and carbon dioxide, which have great influence on human health. The parameters collected by various sensors in the car are transmitted to the main control chip STM32F103RCT6 through the wireless sensor network module. STM32F103RCT6 analyzes and processes the data to achieve the goal of monitoring the air quality in the car. When the concentration of harmful gas in the car exceeds the threshold value, the voice broadcast can timely remind people to deal with the environment in the car, reduce the harmful gas in the car, so as to achieve the purpose of improving the driving environment, to meet people's health needs for the air environment in the car.","PeriodicalId":164745,"journal":{"name":"2021 IEEE International Conference on Emergency Science and Information Technology (ICESIT)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125086057","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 : 2021-11-22DOI: 10.1109/ICESIT53460.2021.9696952
Xilan Zhao, Weizhou Wang, Meikun Wang, Feng Gao, Changnian Lin
Fast and reliable identification on transformer substation devices is the prerequisite for AR system to perform virtual information display and virtual-real fusion. Hence the author proposes to establish a transformer substation equipment recognition model relying on deep-learning technology, and deploy it on edge devices such as AR, etc. Firstly, collect the images and videos of transformer substation devices, obtain the dataset of transformer substation devices, and use the mark labeling software to build the dataset. Secondly, apply the Faster RCNN object identification algorithm to establish the transformer substation devices identification model on the basis of VGG16 convolutional network. Then, improve the precision of the model through data migration model training, parameter optimization, and dataset enhancement methods such as image transformation. Finally, deploy the algorithm to Intel Neural Compute Stick 2, realizing the online identification of major devices in transformer substation such as the main transformer, breaker, voltage transformer, current transformer and control cabinet, and providing basis for the application of AR system on the training, practical inspection, and operation and maintenance.
{"title":"Online substation equipment recognition technology","authors":"Xilan Zhao, Weizhou Wang, Meikun Wang, Feng Gao, Changnian Lin","doi":"10.1109/ICESIT53460.2021.9696952","DOIUrl":"https://doi.org/10.1109/ICESIT53460.2021.9696952","url":null,"abstract":"Fast and reliable identification on transformer substation devices is the prerequisite for AR system to perform virtual information display and virtual-real fusion. Hence the author proposes to establish a transformer substation equipment recognition model relying on deep-learning technology, and deploy it on edge devices such as AR, etc. Firstly, collect the images and videos of transformer substation devices, obtain the dataset of transformer substation devices, and use the mark labeling software to build the dataset. Secondly, apply the Faster RCNN object identification algorithm to establish the transformer substation devices identification model on the basis of VGG16 convolutional network. Then, improve the precision of the model through data migration model training, parameter optimization, and dataset enhancement methods such as image transformation. Finally, deploy the algorithm to Intel Neural Compute Stick 2, realizing the online identification of major devices in transformer substation such as the main transformer, breaker, voltage transformer, current transformer and control cabinet, and providing basis for the application of AR system on the training, practical inspection, and operation and maintenance.","PeriodicalId":164745,"journal":{"name":"2021 IEEE International Conference on Emergency Science and Information Technology (ICESIT)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127203398","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 : 2021-11-22DOI: 10.1109/ICESIT53460.2021.9697048
He Jun, Liu Peng, Jiang Changhui, Liu Pengzheng, Wu Shenke, Zhong Kejia
Personality classification is the process of analyzing and summarizing the relevant emotional information in the text, so as to infer the personality traits in the text. In view of the fact that traditional machine learning methods need to manually label to extract features when dealing with personality classification problems, which leads to poor per-formance of classification results. In this paper, we propose a deep learning method based on the BERT model. The model adopts the Transformer two-way coding structure, which can extract features more effectively than traditional methods. Finally, the Softmax classifier is used to classify the extracted text feature vectors. Qur experiment compares several classical models such as SVM, CNN and LSTM, and the experimental results show that the multi-classification effect of the BERT model is better than other models. It is proved that the BERT model can effectively improve the effect of personality classification.
{"title":"Personality Classification Based on Bert Model","authors":"He Jun, Liu Peng, Jiang Changhui, Liu Pengzheng, Wu Shenke, Zhong Kejia","doi":"10.1109/ICESIT53460.2021.9697048","DOIUrl":"https://doi.org/10.1109/ICESIT53460.2021.9697048","url":null,"abstract":"Personality classification is the process of analyzing and summarizing the relevant emotional information in the text, so as to infer the personality traits in the text. In view of the fact that traditional machine learning methods need to manually label to extract features when dealing with personality classification problems, which leads to poor per-formance of classification results. In this paper, we propose a deep learning method based on the BERT model. The model adopts the Transformer two-way coding structure, which can extract features more effectively than traditional methods. Finally, the Softmax classifier is used to classify the extracted text feature vectors. Qur experiment compares several classical models such as SVM, CNN and LSTM, and the experimental results show that the multi-classification effect of the BERT model is better than other models. It is proved that the BERT model can effectively improve the effect of personality classification.","PeriodicalId":164745,"journal":{"name":"2021 IEEE International Conference on Emergency Science and Information Technology (ICESIT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130715915","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 : 2021-11-22DOI: 10.1109/icesit53460.2021.9696460
Tianyu Yao
The value of personal information in the era of digital economy is getting higher and higher, and it has become the focus of all groups of the whole society. Commercial banks maintain high-quality personal information resources, and such information is directly related to personal privacy, so they need to perform special information security protection duties compared with ordinary personal information processors. The promulgation of Chinese Civil Code provides basic legal protection for the protection of personal information. Commercial banks should pay attention to the relevant provisions of the Civil Code, use and deal with personal information in a scientific, reasonable and lawful way, and ensure the privacy of natural persons.
{"title":"Mathematical Statistics and Analysis on the Path Mechanism of Protecting Personal Information Relying on Information Digitization and Big Data","authors":"Tianyu Yao","doi":"10.1109/icesit53460.2021.9696460","DOIUrl":"https://doi.org/10.1109/icesit53460.2021.9696460","url":null,"abstract":"The value of personal information in the era of digital economy is getting higher and higher, and it has become the focus of all groups of the whole society. Commercial banks maintain high-quality personal information resources, and such information is directly related to personal privacy, so they need to perform special information security protection duties compared with ordinary personal information processors. The promulgation of Chinese Civil Code provides basic legal protection for the protection of personal information. Commercial banks should pay attention to the relevant provisions of the Civil Code, use and deal with personal information in a scientific, reasonable and lawful way, and ensure the privacy of natural persons.","PeriodicalId":164745,"journal":{"name":"2021 IEEE International Conference on Emergency Science and Information Technology (ICESIT)","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130781313","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 : 2021-11-22DOI: 10.1109/ICESIT53460.2021.9696729
Xiaolong Zhang, Bin Qian, Wei Zhou, Yang Yu, Kai Yang, Xiuming He
Attitude analysis is widely used in various fields, but there is a lack of power operation behavior analysis. In order to realize the violation detection in the process of power operation, ROS and lidar information is used for auxiliary positioning, and OpenPose is used for skeleton extraction and detection. This paper proposes to detect the posture of power operators based on OpenPose, laying a foundation for the violation analysis of power operators. Finally, the algorithm is deployed on the edge processor Jetson Xavier NX. Experimental results show that the algorithm can perform pose detection analysis in the operation process of power operators and meet the requirements of subsequent violation analysis.
{"title":"An intelligent method of violation identification for power operation","authors":"Xiaolong Zhang, Bin Qian, Wei Zhou, Yang Yu, Kai Yang, Xiuming He","doi":"10.1109/ICESIT53460.2021.9696729","DOIUrl":"https://doi.org/10.1109/ICESIT53460.2021.9696729","url":null,"abstract":"Attitude analysis is widely used in various fields, but there is a lack of power operation behavior analysis. In order to realize the violation detection in the process of power operation, ROS and lidar information is used for auxiliary positioning, and OpenPose is used for skeleton extraction and detection. This paper proposes to detect the posture of power operators based on OpenPose, laying a foundation for the violation analysis of power operators. Finally, the algorithm is deployed on the edge processor Jetson Xavier NX. Experimental results show that the algorithm can perform pose detection analysis in the operation process of power operators and meet the requirements of subsequent violation analysis.","PeriodicalId":164745,"journal":{"name":"2021 IEEE International Conference on Emergency Science and Information Technology (ICESIT)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132976903","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 : 2021-11-22DOI: 10.1109/ICESIT53460.2021.9696907
Yihui Fu, Fanliang Bu
Aiming at the problem that the corpus of drug-related fields is not rich and the relevant information of drug-related personnel is insufficient, this paper constructs a 600,000-word-scale drug-related text data set, and proposes a named entity recognition method for drug-related personnel based on ELECTRA-BiLSTM-CRF. First input the labeled text into the ELECTRA pre-training language model to obtain a word vector with better semantic representation; then input the trained word vector into the bidirectional long short-term memory (BiLSTM) network to extract the context feature; finally, the best predicted label sequence is obtained through the conditional random field(CRF). The performance of this model was evaluated on the drug-related text data set. The experimental results showed that the F1 value of the ELECTRA-BiLSTM-CRF model reached 94%, which was better than the BERT-BiLSTM-CRF, BERT-CRF, and BiLSTM-CRF models, which proved this model has a good effect on the named entity recognition of drug-related personnel.
{"title":"Research on Named Entity Recognition Based on ELECTRA and Intelligent Face Image Processing","authors":"Yihui Fu, Fanliang Bu","doi":"10.1109/ICESIT53460.2021.9696907","DOIUrl":"https://doi.org/10.1109/ICESIT53460.2021.9696907","url":null,"abstract":"Aiming at the problem that the corpus of drug-related fields is not rich and the relevant information of drug-related personnel is insufficient, this paper constructs a 600,000-word-scale drug-related text data set, and proposes a named entity recognition method for drug-related personnel based on ELECTRA-BiLSTM-CRF. First input the labeled text into the ELECTRA pre-training language model to obtain a word vector with better semantic representation; then input the trained word vector into the bidirectional long short-term memory (BiLSTM) network to extract the context feature; finally, the best predicted label sequence is obtained through the conditional random field(CRF). The performance of this model was evaluated on the drug-related text data set. The experimental results showed that the F1 value of the ELECTRA-BiLSTM-CRF model reached 94%, which was better than the BERT-BiLSTM-CRF, BERT-CRF, and BiLSTM-CRF models, which proved this model has a good effect on the named entity recognition of drug-related personnel.","PeriodicalId":164745,"journal":{"name":"2021 IEEE International Conference on Emergency Science and Information Technology (ICESIT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130435420","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 : 2021-11-22DOI: 10.1109/ICESIT53460.2021.9697039
Ke Xu, Jun Peng, Xiangren Wang, Shangzhu Jin, Xi Zheng, Qingxia Li
Existing image encryption algorithms for object detection have shortcomings such as small key space, poor anti-attack ability. Therefore, this paper proposes an encryption algorithm based on Logistic map, Chen system, and DNA sequence for object detection image encryption. The main idea is to dynamically generate a prediction frame based on the object detection network, encrypt the image block in the prediction frame for the first time, then encrypt the whole image. The key is employed to drive the Logistic map and Chen system to generate the chaotic sequences, which is used in DNA computing, scrambling, and diffusion operations. This paper describes the design of the encryption algorithm in detail and conducts security analysis, including histogram statistics, adjacent element correlation analysis, and information entropy analysis. The results show that the algorithm has good cryptographic characteristics and strong anti-attack, and can be used for object detection image encryption.
{"title":"An Image Encryption Method for Object Detection Based on Chaotic System and DNA Sequence","authors":"Ke Xu, Jun Peng, Xiangren Wang, Shangzhu Jin, Xi Zheng, Qingxia Li","doi":"10.1109/ICESIT53460.2021.9697039","DOIUrl":"https://doi.org/10.1109/ICESIT53460.2021.9697039","url":null,"abstract":"Existing image encryption algorithms for object detection have shortcomings such as small key space, poor anti-attack ability. Therefore, this paper proposes an encryption algorithm based on Logistic map, Chen system, and DNA sequence for object detection image encryption. The main idea is to dynamically generate a prediction frame based on the object detection network, encrypt the image block in the prediction frame for the first time, then encrypt the whole image. The key is employed to drive the Logistic map and Chen system to generate the chaotic sequences, which is used in DNA computing, scrambling, and diffusion operations. This paper describes the design of the encryption algorithm in detail and conducts security analysis, including histogram statistics, adjacent element correlation analysis, and information entropy analysis. The results show that the algorithm has good cryptographic characteristics and strong anti-attack, and can be used for object detection image encryption.","PeriodicalId":164745,"journal":{"name":"2021 IEEE International Conference on Emergency Science and Information Technology (ICESIT)","volume":"160 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121082226","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：