Pub Date : 2022-02-01DOI: 10.1109/ICTech55460.2022.00010
Wanlin Yang
In the development of network technology innovation, data information and access equipment in the overall optimization of the application, so that the corresponding web technology has become more mature, social residents participate in the online shopping experience has become rich and colorful, thus speeding up the rapid development of e-commerce industry. In electric business platform trading amount under the background of rising, accumulated by the construction of service platform to comment on the value of the data and transaction data accumulated large quantities of information, the system analyzes electric business service platform of data information, not only to clear the user of the product of real feeling, also can solve the problem such as traditional platform run slower. Therefore, in this study, Hadoop platform is used to build e-commerce big data platform, and combined algorithm is designed for the platform recommendation engine, so as to ensure that the platform can have more rapid and accurate recommendation function during service operation.
{"title":"The Construction of a Big Data E-Commerce Service Platform Driven by a Cloud Contact Center","authors":"Wanlin Yang","doi":"10.1109/ICTech55460.2022.00010","DOIUrl":"https://doi.org/10.1109/ICTech55460.2022.00010","url":null,"abstract":"In the development of network technology innovation, data information and access equipment in the overall optimization of the application, so that the corresponding web technology has become more mature, social residents participate in the online shopping experience has become rich and colorful, thus speeding up the rapid development of e-commerce industry. In electric business platform trading amount under the background of rising, accumulated by the construction of service platform to comment on the value of the data and transaction data accumulated large quantities of information, the system analyzes electric business service platform of data information, not only to clear the user of the product of real feeling, also can solve the problem such as traditional platform run slower. Therefore, in this study, Hadoop platform is used to build e-commerce big data platform, and combined algorithm is designed for the platform recommendation engine, so as to ensure that the platform can have more rapid and accurate recommendation function during service operation.","PeriodicalId":290836,"journal":{"name":"2022 11th International Conference of Information and Communication Technology (ICTech))","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125445066","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 : 2022-02-01DOI: 10.1109/ICTech55460.2022.00089
Wenjing Chen, Pin Wang
With the development of data monitoring system for industrial equipment, the convenience of data monitoring is paid more and more attention. Traditional data monitoring mostly uses specialized software or visual interface on the device to achieve the purpose of monitoring data, the workflow will be more complex. Even if there is a unified device to receive the data, it is not realistic to monitor all the time. In addition, for the load problem of the micro device, mounting the OPC UA client by itself is heavy. Therefore, in order to improve the visibility of field device data, reduce the load of micro devices and simplify the complex workflow, this paper studies the cross-platform device monitoring system based on OPC UA. The local OPC UA server is used to collect data from industrial devices, and the collected data is processed and transferred to the cloud storage system. The stateless RESTful HTTP request style simplifies the complexity of implementing data transfer between a generic client (browser or other HTTP client) and a Web server, and truly enables users to monitor data anytime and anywhere without consuming too many resources.
{"title":"Cross-Platform Device Monitoring System Based on OPC UA","authors":"Wenjing Chen, Pin Wang","doi":"10.1109/ICTech55460.2022.00089","DOIUrl":"https://doi.org/10.1109/ICTech55460.2022.00089","url":null,"abstract":"With the development of data monitoring system for industrial equipment, the convenience of data monitoring is paid more and more attention. Traditional data monitoring mostly uses specialized software or visual interface on the device to achieve the purpose of monitoring data, the workflow will be more complex. Even if there is a unified device to receive the data, it is not realistic to monitor all the time. In addition, for the load problem of the micro device, mounting the OPC UA client by itself is heavy. Therefore, in order to improve the visibility of field device data, reduce the load of micro devices and simplify the complex workflow, this paper studies the cross-platform device monitoring system based on OPC UA. The local OPC UA server is used to collect data from industrial devices, and the collected data is processed and transferred to the cloud storage system. The stateless RESTful HTTP request style simplifies the complexity of implementing data transfer between a generic client (browser or other HTTP client) and a Web server, and truly enables users to monitor data anytime and anywhere without consuming too many resources.","PeriodicalId":290836,"journal":{"name":"2022 11th International Conference of Information and Communication Technology (ICTech))","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115772922","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 : 2022-02-01DOI: 10.1109/ICTech55460.2022.00107
Xijun Zhao, Yongjie Yang
With the increasing demand for indoor positioning, indoor positioning technology has attracted much attention and research in recent years. In order to make the warehouse intelligent, this paper designs and implements an AOA indoor positioning system based on Bluetooth 5.1 to realize the asset positioning in warehouse. This system design mainly includes three parts: Bluetooth beacon, Bluetooth positioning base station and PC software design. It mainly realizes the data communication between the Bluetooth beacon and the Bluetooth positioning base station. The Bluetooth positioning base station realizes the positioning of the Bluetooth beacon through the azimuth angle and transmits it to PC software. The PC software processes the data of Bluetooth base station, completes the coordinate calculation of positioning information, and finally realizes the display of positioning information.
{"title":"An AOA Indoor Positioning System Based on Bluetooth 5.1","authors":"Xijun Zhao, Yongjie Yang","doi":"10.1109/ICTech55460.2022.00107","DOIUrl":"https://doi.org/10.1109/ICTech55460.2022.00107","url":null,"abstract":"With the increasing demand for indoor positioning, indoor positioning technology has attracted much attention and research in recent years. In order to make the warehouse intelligent, this paper designs and implements an AOA indoor positioning system based on Bluetooth 5.1 to realize the asset positioning in warehouse. This system design mainly includes three parts: Bluetooth beacon, Bluetooth positioning base station and PC software design. It mainly realizes the data communication between the Bluetooth beacon and the Bluetooth positioning base station. The Bluetooth positioning base station realizes the positioning of the Bluetooth beacon through the azimuth angle and transmits it to PC software. The PC software processes the data of Bluetooth base station, completes the coordinate calculation of positioning information, and finally realizes the display of positioning information.","PeriodicalId":290836,"journal":{"name":"2022 11th International Conference of Information and Communication Technology (ICTech))","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131831523","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 : 2022-02-01DOI: 10.1109/ICTech55460.2022.00034
Jin Gao, Wen-liang Li, Wei Zhou, Hua Chen, Min Qiao
Advanced emergency braking system (AEBS) can automatically brake when there is a risk of collision with the car in front or pedestrians, and play a role of slowing down and avoiding accidents. AEBS is widely used in China's commercial vehicles. Based on the inexhaustibility of scenarios in intelligent system testing, it is urgent to expand the demand of test scenarios. Based on the accident orientation of commercial vehicles, this paper carried out scene classification by coupling collision target and collision form, constructed AEBS test scenario system, proposed test indicators, and verified its feasibility.
{"title":"Research on Simulation Test Method of Advanced Emergency Braking System of Commercial Vehicles","authors":"Jin Gao, Wen-liang Li, Wei Zhou, Hua Chen, Min Qiao","doi":"10.1109/ICTech55460.2022.00034","DOIUrl":"https://doi.org/10.1109/ICTech55460.2022.00034","url":null,"abstract":"Advanced emergency braking system (AEBS) can automatically brake when there is a risk of collision with the car in front or pedestrians, and play a role of slowing down and avoiding accidents. AEBS is widely used in China's commercial vehicles. Based on the inexhaustibility of scenarios in intelligent system testing, it is urgent to expand the demand of test scenarios. Based on the accident orientation of commercial vehicles, this paper carried out scene classification by coupling collision target and collision form, constructed AEBS test scenario system, proposed test indicators, and verified its feasibility.","PeriodicalId":290836,"journal":{"name":"2022 11th International Conference of Information and Communication Technology (ICTech))","volume":"485 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131881135","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 : 2022-02-01DOI: 10.1109/ICTech55460.2022.00045
Yue-fang Dong, Wei-wei Fu, Zhe Zhou, Hai-Long Zhu
Based on the current high-performance, low-power, high computing density processor, on the basis of analysing the main fatigue characteristics of human body, combined with real-time image processing technology, data processing technology and machine learning related theories and algorithms, this paper studies a fast and accurate method to identify the mental state of other people. Base d on the method, a portable or wearable on-line monitoring device for eye movement and head movement parameters is designed, which can continuously monitor the wearer for a long time and achieve the function expectation of real-time judging the wearer's awakening state.
{"title":"Design and Development of Human Fatigue Evaluation Method and Equipment Based on Bayesian Network Classifier","authors":"Yue-fang Dong, Wei-wei Fu, Zhe Zhou, Hai-Long Zhu","doi":"10.1109/ICTech55460.2022.00045","DOIUrl":"https://doi.org/10.1109/ICTech55460.2022.00045","url":null,"abstract":"Based on the current high-performance, low-power, high computing density processor, on the basis of analysing the main fatigue characteristics of human body, combined with real-time image processing technology, data processing technology and machine learning related theories and algorithms, this paper studies a fast and accurate method to identify the mental state of other people. Base d on the method, a portable or wearable on-line monitoring device for eye movement and head movement parameters is designed, which can continuously monitor the wearer for a long time and achieve the function expectation of real-time judging the wearer's awakening state.","PeriodicalId":290836,"journal":{"name":"2022 11th International Conference of Information and Communication Technology (ICTech))","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133231374","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 recent years, real-time 3D reconstruction has gained popularity among many researchers due to its increasing applications. 3D reconstruction methods based on depth estimation have a large number of invalid areas for reconstruction in autonomous driving. To further improve the real-time performance of 3D reconstruction, we propose a novel approach to reduce the consumption of computational resources by extracting significant regions of depth maps. First, binary masks that extract significant regions are generated by a 2D object detection model. Then, we design the TRDE module to extract target regions in generated depth maps. Finally, qualitative and quantitative results on KITTI dataset demonstrate that our approach can perform depth maps optimization and reduce computational resources consumed during the 3D reconstruction. As a result, our method achieves faster 3D reconstruction by fusing 2D object detection and self-supervised monocular depth estimation.
{"title":"Faster 3D Reconstruction by Fusing 2D Object Detection and Self-Supervised Monocular Depth Estimation","authors":"Chao Fan, Zhenyu Yin, Xinxin Huang, Mingshi Li, Xiaohui Wang, Hui Li","doi":"10.1109/ICTech55460.2022.00104","DOIUrl":"https://doi.org/10.1109/ICTech55460.2022.00104","url":null,"abstract":"In recent years, real-time 3D reconstruction has gained popularity among many researchers due to its increasing applications. 3D reconstruction methods based on depth estimation have a large number of invalid areas for reconstruction in autonomous driving. To further improve the real-time performance of 3D reconstruction, we propose a novel approach to reduce the consumption of computational resources by extracting significant regions of depth maps. First, binary masks that extract significant regions are generated by a 2D object detection model. Then, we design the TRDE module to extract target regions in generated depth maps. Finally, qualitative and quantitative results on KITTI dataset demonstrate that our approach can perform depth maps optimization and reduce computational resources consumed during the 3D reconstruction. As a result, our method achieves faster 3D reconstruction by fusing 2D object detection and self-supervised monocular depth estimation.","PeriodicalId":290836,"journal":{"name":"2022 11th International Conference of Information and Communication Technology (ICTech))","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130753207","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 : 2022-02-01DOI: 10.1109/ICTech55460.2022.00101
Zhenduo Liu, Dongsheng Yang
As the basic equipment of the industry, the tool wear will affect the quality of the processed products and production efficiency, so how to use the tool condition monitoring information to accurately predict the residual life of the tool has a high application value. In the application background of industrial big data and industrial equipment fault prediction and health management, the predictive evaluation of milling cutter wear degree of CNC machine tool is carried out by using machine learning method, and then the tool life is accurately predicted. In the process of research and analysis, the milling cutter original data were preprocessed and feature extraction was carried out. A feature set screening method was adopted to screen out feature sets related to the degree of tool wear degradation. Finally, the remaining life of milling cutter was accurately predicted by machine learning model.
{"title":"Research and Application of Wear Prediction Method of NC Milling Cutter Based on Data-Driven","authors":"Zhenduo Liu, Dongsheng Yang","doi":"10.1109/ICTech55460.2022.00101","DOIUrl":"https://doi.org/10.1109/ICTech55460.2022.00101","url":null,"abstract":"As the basic equipment of the industry, the tool wear will affect the quality of the processed products and production efficiency, so how to use the tool condition monitoring information to accurately predict the residual life of the tool has a high application value. In the application background of industrial big data and industrial equipment fault prediction and health management, the predictive evaluation of milling cutter wear degree of CNC machine tool is carried out by using machine learning method, and then the tool life is accurately predicted. In the process of research and analysis, the milling cutter original data were preprocessed and feature extraction was carried out. A feature set screening method was adopted to screen out feature sets related to the degree of tool wear degradation. Finally, the remaining life of milling cutter was accurately predicted by machine learning model.","PeriodicalId":290836,"journal":{"name":"2022 11th International Conference of Information and Communication Technology (ICTech))","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128034103","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 : 2022-02-01DOI: 10.1109/ICTech55460.2022.00038
Qing Chen, Qian Xiao, Jun Yan
Railway internal shielded digital signal cable is mainly used in railway ZPW-2000A system., the cable has good shielding performance., can realize the transmission of electrical signal and recovery signal in the same cable at the same time., which can greatly save the project cost. At present., China's high-speed railway mainly uses railway internal shielded digital signal cable., so the quality control requirements of railway internal shielded digital signal cable are becoming stricter. This paper introduces the unqualified classification., insulation process., copper shielding process and single disk test of railway internal shielded digital signal cable., which provides a guarantee for the safe operation of high-speed railway.
{"title":"Test and Research of Digital Signal Cable for High-speed Railway","authors":"Qing Chen, Qian Xiao, Jun Yan","doi":"10.1109/ICTech55460.2022.00038","DOIUrl":"https://doi.org/10.1109/ICTech55460.2022.00038","url":null,"abstract":"Railway internal shielded digital signal cable is mainly used in railway ZPW-2000A system., the cable has good shielding performance., can realize the transmission of electrical signal and recovery signal in the same cable at the same time., which can greatly save the project cost. At present., China's high-speed railway mainly uses railway internal shielded digital signal cable., so the quality control requirements of railway internal shielded digital signal cable are becoming stricter. This paper introduces the unqualified classification., insulation process., copper shielding process and single disk test of railway internal shielded digital signal cable., which provides a guarantee for the safe operation of high-speed railway.","PeriodicalId":290836,"journal":{"name":"2022 11th International Conference of Information and Communication Technology (ICTech))","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124359645","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 : 2022-02-01DOI: 10.1109/ICTech55460.2022.00062
Hiroyuki Mitsuhara, Naoki Miyoshi, M. Shishibori
When a disaster strikes, we evacuate to a shelter. We abandon evacuation or wander aimlessly toward an unknown shelter if we do not remember shelter locations; in the worst-case scenario, we may lose lives before or during evacuation. Residents should remember not only shelter locations in their local community but also shelter capacities and features. In many cases, every resident evacuates to the nearest shelter. If many residents rush into the nearest but small-capacity shelter, some will be unable to enter and will have to go to another shelter. This time-consuming situation must be resolved to help residents evacuate successfully. Furthermore, residents with special needs may end up in an inappropriate shelter if they are unfamiliar with the features of the shelter. We believe that by visiting and observing shelters in advance, residents will be able to recall not only shelter locations and capacities but also shelter features. However, it is difficult to maintain motivation to visit shelters, especially when the shelters are located in remote areas. As a result, we created a prototyped location-based game (a mobile application) that used a geofencing framework similar to Pokémon GO and encouraged players (residents) to visit shelters through a game element. In this game, players visit a shelter to earn a point equal to the shelter's capacity and visit an informative spot about disaster management to collect a digital character by paying a required point from their earned points. The character collection can encourage players to visit numerous shelters, which can lead to remembering numerous shelter locations, capacities and features. We conducted a preliminary comparative experiment, in which the participants were given the task to remember shelter locations and capacities by playing a game or staring at a hazard map. The results of the experiment indicated that our game prototype was effective in helping the participants remember shelter locations and capacities.
{"title":"Location-Based Game for Remembering Shelter Locations, Capacities and Features","authors":"Hiroyuki Mitsuhara, Naoki Miyoshi, M. Shishibori","doi":"10.1109/ICTech55460.2022.00062","DOIUrl":"https://doi.org/10.1109/ICTech55460.2022.00062","url":null,"abstract":"When a disaster strikes, we evacuate to a shelter. We abandon evacuation or wander aimlessly toward an unknown shelter if we do not remember shelter locations; in the worst-case scenario, we may lose lives before or during evacuation. Residents should remember not only shelter locations in their local community but also shelter capacities and features. In many cases, every resident evacuates to the nearest shelter. If many residents rush into the nearest but small-capacity shelter, some will be unable to enter and will have to go to another shelter. This time-consuming situation must be resolved to help residents evacuate successfully. Furthermore, residents with special needs may end up in an inappropriate shelter if they are unfamiliar with the features of the shelter. We believe that by visiting and observing shelters in advance, residents will be able to recall not only shelter locations and capacities but also shelter features. However, it is difficult to maintain motivation to visit shelters, especially when the shelters are located in remote areas. As a result, we created a prototyped location-based game (a mobile application) that used a geofencing framework similar to Pokémon GO and encouraged players (residents) to visit shelters through a game element. In this game, players visit a shelter to earn a point equal to the shelter's capacity and visit an informative spot about disaster management to collect a digital character by paying a required point from their earned points. The character collection can encourage players to visit numerous shelters, which can lead to remembering numerous shelter locations, capacities and features. We conducted a preliminary comparative experiment, in which the participants were given the task to remember shelter locations and capacities by playing a game or staring at a hazard map. The results of the experiment indicated that our game prototype was effective in helping the participants remember shelter locations and capacities.","PeriodicalId":290836,"journal":{"name":"2022 11th International Conference of Information and Communication Technology (ICTech))","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122909443","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 : 2022-02-01DOI: 10.1109/ICTech55460.2022.00092
Yu Bo, Wang Qiuru
We propose an improved YOLOv4 small target detection method for small target foreign object (FOD) recognition that requires as few detection accuracy, speed, and model volume parameters as possible so that it can be easily ported to other mobile devices such as video surveillance or UAVs in the future. Firstly, the backbone feature extraction network of YOLOv4 is replaced by the MobileNetV2 model, which aims to reduce the number of model parameters. Secondly, the three enhanced feature extraction layers of the original YOLOv4 are increased to four, and a new shallow-scale enhanced feature extraction layer is added, which enhances the characterization capability of the model without increasing the model complexity, making the improved YOLOv3 network structure better for small target detection.
{"title":"Small Target Foreign Object Detection Based on Improved YOLO Network","authors":"Yu Bo, Wang Qiuru","doi":"10.1109/ICTech55460.2022.00092","DOIUrl":"https://doi.org/10.1109/ICTech55460.2022.00092","url":null,"abstract":"We propose an improved YOLOv4 small target detection method for small target foreign object (FOD) recognition that requires as few detection accuracy, speed, and model volume parameters as possible so that it can be easily ported to other mobile devices such as video surveillance or UAVs in the future. Firstly, the backbone feature extraction network of YOLOv4 is replaced by the MobileNetV2 model, which aims to reduce the number of model parameters. Secondly, the three enhanced feature extraction layers of the original YOLOv4 are increased to four, and a new shallow-scale enhanced feature extraction layer is added, which enhances the characterization capability of the model without increasing the model complexity, making the improved YOLOv3 network structure better for small target detection.","PeriodicalId":290836,"journal":{"name":"2022 11th International Conference of Information and Communication Technology (ICTech))","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124716412","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：