Pub Date : 2020-10-30DOI: 10.1109/ICNSC48988.2020.9238096
Shichao Chen, Qijie Li, Hua Zhang, F. Zhu, Gang Xiong, Ying Tang
As the number of devices connected to the Internet of things (IoT) surges, the amount of data explodes. Therefore it not only increases the bandwidth load of data transmission but also aggravates the computing and storage load of a cloud platform. At the same time, the traditional computing paradigm centered on cloud computing cannot meet the real-time requirements in many application scenarios. The emergence of edge computing can solve the problems of realtime data processing and network bandwidth occupation in the current IoT scene. In this paper, according to the characteristics of IoT, such as fragmented data, heterogeneous network, and limited energy consumption, the architecture of an IoT edge computing system is constructed to suit better an IoT scene. In addition, the application of edge computing key technologies such as virtualization, edge intelligence, computing offload, collaborative scheduling and micro-services in resource-constrained IoT scenarios is analyzed in detail. Finally, the functions and application of energy consumption monitoring and optimization to a central air-conditioning system are analyzed and summarized, which is a typical application of edge computing in the context of the IoT.
{"title":"An IoT Edge Computing System Architecture and its Application","authors":"Shichao Chen, Qijie Li, Hua Zhang, F. Zhu, Gang Xiong, Ying Tang","doi":"10.1109/ICNSC48988.2020.9238096","DOIUrl":"https://doi.org/10.1109/ICNSC48988.2020.9238096","url":null,"abstract":"As the number of devices connected to the Internet of things (IoT) surges, the amount of data explodes. Therefore it not only increases the bandwidth load of data transmission but also aggravates the computing and storage load of a cloud platform. At the same time, the traditional computing paradigm centered on cloud computing cannot meet the real-time requirements in many application scenarios. The emergence of edge computing can solve the problems of realtime data processing and network bandwidth occupation in the current IoT scene. In this paper, according to the characteristics of IoT, such as fragmented data, heterogeneous network, and limited energy consumption, the architecture of an IoT edge computing system is constructed to suit better an IoT scene. In addition, the application of edge computing key technologies such as virtualization, edge intelligence, computing offload, collaborative scheduling and micro-services in resource-constrained IoT scenarios is analyzed in detail. Finally, the functions and application of energy consumption monitoring and optimization to a central air-conditioning system are analyzed and summarized, which is a typical application of edge computing in the context of the IoT.","PeriodicalId":412290,"journal":{"name":"2020 IEEE International Conference on Networking, Sensing and Control (ICNSC)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123801613","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 : 2020-10-30DOI: 10.1109/ICNSC48988.2020.9238107
Yulian Cao, Mengchu Zhou, Wenfeng Li, G. Lodewijks
Particle swarm optimization (PSO) attracts much attention due to its ability in solving complex practical engineering problems effectively. To further improve its performance, a heterogeneous particle swarm optimizer (HPSO) is proposed in this work. Five widely used benchmark functions are selected to test its efficiency. Furthermore, five state-of-the-art improved PSO variants are selected for a comparisons purpose. The results demonstrate that HPSO is better than the other five algorithms. A logistics problem in aircraft manufacturing is then studied and solved. The results show HPSO's superiority over its tested PSO variants.
{"title":"Heterogeneous Particle Swarm Optimizer and its Application in Aircraft Manufacturing Logistics","authors":"Yulian Cao, Mengchu Zhou, Wenfeng Li, G. Lodewijks","doi":"10.1109/ICNSC48988.2020.9238107","DOIUrl":"https://doi.org/10.1109/ICNSC48988.2020.9238107","url":null,"abstract":"Particle swarm optimization (PSO) attracts much attention due to its ability in solving complex practical engineering problems effectively. To further improve its performance, a heterogeneous particle swarm optimizer (HPSO) is proposed in this work. Five widely used benchmark functions are selected to test its efficiency. Furthermore, five state-of-the-art improved PSO variants are selected for a comparisons purpose. The results demonstrate that HPSO is better than the other five algorithms. A logistics problem in aircraft manufacturing is then studied and solved. The results show HPSO's superiority over its tested PSO variants.","PeriodicalId":412290,"journal":{"name":"2020 IEEE International Conference on Networking, Sensing and Control (ICNSC)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125463676","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 : 2020-10-30DOI: 10.1109/ICNSC48988.2020.9238118
Xingzi Liu, Frank Jiang, Rongbai Zhang
Inspired from the iForest algorithmic scheme, we propose an iForest-based blockchain social media anomaly behavior detection method via the improved tree algorithm, for the purpose of isolating the anomalous behaviors as an outlier. The model is integrated with the smart contract structure of blockchain. In the overall system, the user data is sent to the intelligent contract for a period of time. After the identification of the abnormal behavior of social media users, the abnormal behavior in blockchain is marked and stored in the abnormal chain. To a certain extent, the scheme protects users' privacy, improves the efficiency and accuracy of iForest anomaly detection, and is more suitable for multi-dimensional heterogenous data-centric social media user behavior detection.
{"title":"A New Social User Anomaly Behavior Detection System Based on Blockchain and Smart Contract","authors":"Xingzi Liu, Frank Jiang, Rongbai Zhang","doi":"10.1109/ICNSC48988.2020.9238118","DOIUrl":"https://doi.org/10.1109/ICNSC48988.2020.9238118","url":null,"abstract":"Inspired from the iForest algorithmic scheme, we propose an iForest-based blockchain social media anomaly behavior detection method via the improved tree algorithm, for the purpose of isolating the anomalous behaviors as an outlier. The model is integrated with the smart contract structure of blockchain. In the overall system, the user data is sent to the intelligent contract for a period of time. After the identification of the abnormal behavior of social media users, the abnormal behavior in blockchain is marked and stored in the abnormal chain. To a certain extent, the scheme protects users' privacy, improves the efficiency and accuracy of iForest anomaly detection, and is more suitable for multi-dimensional heterogenous data-centric social media user behavior detection.","PeriodicalId":412290,"journal":{"name":"2020 IEEE International Conference on Networking, Sensing and Control (ICNSC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117145136","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}
Autonomous exploration and mapping is an important part of autonomous navigation of mobile robots in an unknown environment. This paper proposes a new 3D exploration strategy based on the wavefront algorithm. RGB-D camera is used to obtain environmental information. The diffusion process of wavefront algorithm is used to find frontier points. Firstly, selection function determines the next frontier point to be explored. Then, the mobile robot moves to the frontier point according to the path planned by the way of wavefront algorithm. When the mobile robot reaches the frontier point and completes the mapping, the mobile robot continues to search for the next frontier point. Finally, the exploration strategy is tested using the Robot Operating System (ROS). Simulational experiment shows that the 3D exploration based on the wavefront algorithm can choose the right frontier point and complete the exploration task quickly.
{"title":"Autonomous 3D Exploration of Indoor Environment Based on Wavefront Algorithm**This research is supported by the National Natural Science Foundation of China (61673288, 61773273).","authors":"Chunhua Tang, Yefeng Liang, Shumei Yu, Rongchuan Sun, Jianying Zheng","doi":"10.1109/ICNSC48988.2020.9238092","DOIUrl":"https://doi.org/10.1109/ICNSC48988.2020.9238092","url":null,"abstract":"Autonomous exploration and mapping is an important part of autonomous navigation of mobile robots in an unknown environment. This paper proposes a new 3D exploration strategy based on the wavefront algorithm. RGB-D camera is used to obtain environmental information. The diffusion process of wavefront algorithm is used to find frontier points. Firstly, selection function determines the next frontier point to be explored. Then, the mobile robot moves to the frontier point according to the path planned by the way of wavefront algorithm. When the mobile robot reaches the frontier point and completes the mapping, the mobile robot continues to search for the next frontier point. Finally, the exploration strategy is tested using the Robot Operating System (ROS). Simulational experiment shows that the 3D exploration based on the wavefront algorithm can choose the right frontier point and complete the exploration task quickly.","PeriodicalId":412290,"journal":{"name":"2020 IEEE International Conference on Networking, Sensing and Control (ICNSC)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129312088","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 : 2020-10-30DOI: 10.1109/ICNSC48988.2020.9238100
Yiping Gao, Liang Gao, Xinyu Li
Intelligent defect recognition (IDR) is one of the important technologies in production. Deep learning (DL) has drawn more and more attentions in IDR. Whereas, DL methods usually need large labelled training datasets, while the unlabeled is idle and not considered yet. In some cases, the requirement is difficult to satisfy. This is because labelling large datasets are costly, and the defect recognition might be delayed until getting enough labelled samples. To overcome this limitation, a semi-supervised DL approach for defect recognition, which uses the unlabeled samples to improve the accuracy, is introduced in this paper. This method uses a convolutional autoencoder to extract the common feature from both labelled and unlabeled samples, and only a few samples are required to finetune the network. The experimental results suggest that the proposed method achieves competitive results under limited labelled samples, and the accuracy outperforms the other approachs. Furthermore, the noise analysis also suggest this method performs robust for noisey samples.
{"title":"A New Semi-Supervised Deep Learning Approach for Intelligent Defects Recognition","authors":"Yiping Gao, Liang Gao, Xinyu Li","doi":"10.1109/ICNSC48988.2020.9238100","DOIUrl":"https://doi.org/10.1109/ICNSC48988.2020.9238100","url":null,"abstract":"Intelligent defect recognition (IDR) is one of the important technologies in production. Deep learning (DL) has drawn more and more attentions in IDR. Whereas, DL methods usually need large labelled training datasets, while the unlabeled is idle and not considered yet. In some cases, the requirement is difficult to satisfy. This is because labelling large datasets are costly, and the defect recognition might be delayed until getting enough labelled samples. To overcome this limitation, a semi-supervised DL approach for defect recognition, which uses the unlabeled samples to improve the accuracy, is introduced in this paper. This method uses a convolutional autoencoder to extract the common feature from both labelled and unlabeled samples, and only a few samples are required to finetune the network. The experimental results suggest that the proposed method achieves competitive results under limited labelled samples, and the accuracy outperforms the other approachs. Furthermore, the noise analysis also suggest this method performs robust for noisey samples.","PeriodicalId":412290,"journal":{"name":"2020 IEEE International Conference on Networking, Sensing and Control (ICNSC)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129426402","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 : 2020-10-30DOI: 10.1109/ICNSC48988.2020.9238106
Yaping Fu, Xiwang Guo, Liang Qi
Remanufacturing has attracted increasing interest in recent years since it plays important roles in environmental protection and energy-saving. This work presents a scheduling problem from an uncertain remanufacturing process including three subsystems, i.e., disassembly, reprocessing and reassembly ones. Disassembly and reassembly shops contain multiple workstations in parallel to disassemble end-of-life (EOL) products and reassemble the components, respectively. A reprocessing shop is a hybrid flow shop to process the components disassembled from EOL products. A stochastic programming model is established to minimize the expected makespan. In order to solve it efficiently, a learning-based shuffled frog-leaping algorithm is proposed, where a learning mechanism by using obtained searching information is developed to strengthen its exploration and exploitation abilities. Extensive experiments are performed on a set of test problems. The proposed algorithm is compared with a genetic algorithm and simulated annealing algorithm used in some existing studies. The results demonstrate that it is a more promising optimizer to solve the concerned problem than them.
{"title":"Scheduling a Stochastic Remanufacturing Process with Disassembly, Reprocessing and Reassembly","authors":"Yaping Fu, Xiwang Guo, Liang Qi","doi":"10.1109/ICNSC48988.2020.9238106","DOIUrl":"https://doi.org/10.1109/ICNSC48988.2020.9238106","url":null,"abstract":"Remanufacturing has attracted increasing interest in recent years since it plays important roles in environmental protection and energy-saving. This work presents a scheduling problem from an uncertain remanufacturing process including three subsystems, i.e., disassembly, reprocessing and reassembly ones. Disassembly and reassembly shops contain multiple workstations in parallel to disassemble end-of-life (EOL) products and reassemble the components, respectively. A reprocessing shop is a hybrid flow shop to process the components disassembled from EOL products. A stochastic programming model is established to minimize the expected makespan. In order to solve it efficiently, a learning-based shuffled frog-leaping algorithm is proposed, where a learning mechanism by using obtained searching information is developed to strengthen its exploration and exploitation abilities. Extensive experiments are performed on a set of test problems. The proposed algorithm is compared with a genetic algorithm and simulated annealing algorithm used in some existing studies. The results demonstrate that it is a more promising optimizer to solve the concerned problem than them.","PeriodicalId":412290,"journal":{"name":"2020 IEEE International Conference on Networking, Sensing and Control (ICNSC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125819196","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 : 2020-10-30DOI: 10.1109/ICNSC48988.2020.9238088
Qiong Shi, Pei Yang, Chunlin Chen
Spatial description plays an important role in the design of human-robot interaction systems for intelligent robots. In this paper, we model the preference of the types of spatial description by collecting spatial constructions in two groups of tabletop task experiments, where the participants use spatial constructions to instruct the partner (human/robot) to pick up an indicated object. The preference modeling process is implemented by analyzing the probabilistic distribution of different types of spatial description (including different reference frames) of these participants in five typical scenarios regarding the partners of human and robot, respectively. The results provide a basis for the design of collaborative robots when interacting with people and will help improve the efficiency of human-centered human-robot interaction.
{"title":"Preference Modeling of Spatial Description in Human-Robot Interaction","authors":"Qiong Shi, Pei Yang, Chunlin Chen","doi":"10.1109/ICNSC48988.2020.9238088","DOIUrl":"https://doi.org/10.1109/ICNSC48988.2020.9238088","url":null,"abstract":"Spatial description plays an important role in the design of human-robot interaction systems for intelligent robots. In this paper, we model the preference of the types of spatial description by collecting spatial constructions in two groups of tabletop task experiments, where the participants use spatial constructions to instruct the partner (human/robot) to pick up an indicated object. The preference modeling process is implemented by analyzing the probabilistic distribution of different types of spatial description (including different reference frames) of these participants in five typical scenarios regarding the partners of human and robot, respectively. The results provide a basis for the design of collaborative robots when interacting with people and will help improve the efficiency of human-centered human-robot interaction.","PeriodicalId":412290,"journal":{"name":"2020 IEEE International Conference on Networking, Sensing and Control (ICNSC)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123073632","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 : 2020-10-30DOI: 10.1109/ICNSC48988.2020.9238064
Z. Dong, Guofeng Zhang, Ai-Guo Wu
In this paper, the master equations for a two-level system driven by three photons has been derived. Particularly, the incident photons are distributed in two input channels, namely, the first input channel contains a two-photon state, while another single-photon state is in the second input channel. The excitation probabilities of the two-level system are simulated with different bandwidths of input photons. The influence of the number of input photons and channels on the atomic excitation is concluded.
{"title":"Atomic excitation for a two-level system driven by three input photons","authors":"Z. Dong, Guofeng Zhang, Ai-Guo Wu","doi":"10.1109/ICNSC48988.2020.9238064","DOIUrl":"https://doi.org/10.1109/ICNSC48988.2020.9238064","url":null,"abstract":"In this paper, the master equations for a two-level system driven by three photons has been derived. Particularly, the incident photons are distributed in two input channels, namely, the first input channel contains a two-photon state, while another single-photon state is in the second input channel. The excitation probabilities of the two-level system are simulated with different bandwidths of input photons. The influence of the number of input photons and channels on the atomic excitation is concluded.","PeriodicalId":412290,"journal":{"name":"2020 IEEE International Conference on Networking, Sensing and Control (ICNSC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130002183","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 : 2020-10-30DOI: 10.1109/ICNSC48988.2020.9238063
Xiaoping Xiong, Wenliang Wu, Ning Li, Deran Tu, Shuang Xu, Jie Zhang, Zhi Wei
With the development of big data technologies and algorithms, the in-depth analysis of user data collected by user call center becomes possible. Traditional customer call center has notable shortcomings in the intelligent assessment and analysis of internal and external factors affecting customer behavior. If the impact degree and duration of user complaints cannot be accurately predicted, it will seriously hinder employee performance evaluation and enterprise development. In this paper, we proposed a novel framework to do the user profiling and predicted the user's complain probability. The experiments conducted on the 95598 call center users in Guangxi in the first quarter of 2018 show that the developed model has better distinguishing ability and accuracy than the traditional Logistics model in evaluating user behaviors. It can effectively predict the behavior of power users in advance, which is beneficial for power companies to avoid the risk of complaints, thus continuously and effectively improve user experiences, and has substantial economic and social benefits.
{"title":"User Profiling and Behavior Evaluation Based on Improved Logistics Algorithm","authors":"Xiaoping Xiong, Wenliang Wu, Ning Li, Deran Tu, Shuang Xu, Jie Zhang, Zhi Wei","doi":"10.1109/ICNSC48988.2020.9238063","DOIUrl":"https://doi.org/10.1109/ICNSC48988.2020.9238063","url":null,"abstract":"With the development of big data technologies and algorithms, the in-depth analysis of user data collected by user call center becomes possible. Traditional customer call center has notable shortcomings in the intelligent assessment and analysis of internal and external factors affecting customer behavior. If the impact degree and duration of user complaints cannot be accurately predicted, it will seriously hinder employee performance evaluation and enterprise development. In this paper, we proposed a novel framework to do the user profiling and predicted the user's complain probability. The experiments conducted on the 95598 call center users in Guangxi in the first quarter of 2018 show that the developed model has better distinguishing ability and accuracy than the traditional Logistics model in evaluating user behaviors. It can effectively predict the behavior of power users in advance, which is beneficial for power companies to avoid the risk of complaints, thus continuously and effectively improve user experiences, and has substantial economic and social benefits.","PeriodicalId":412290,"journal":{"name":"2020 IEEE International Conference on Networking, Sensing and Control (ICNSC)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126474078","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 : 2020-10-30DOI: 10.1109/ICNSC48988.2020.9238103
Ying Tang, Shengtao Sun, Ben Wu
The reconstruction of surface mesh from point cloud is compute-intensive but also very important step in the remanufacturing and personalization industries. With more 3D scanners providing lower cost and higher resolution, further detailed point clouds can be gathered without so much effort as before. In manufacturing, there are databases which contain the origin 3D design models of the products. How to utilize the design model data for swift production of related products remains a problem for remanufacturing and customization. In order to develop a knowledge-based way of handling this problem, editing or deforming an existing mesh to match the target is an effective way of easing the workload. In this paper, we introduce a divide-and -conquer process which segments the depth scan data and then find the best match in the database as its source of deformation. The segmentation is performed on 3D point level using global features extracted by 3D CNN. After that we find best match to our knowledge with the same features to acquire a fast meshing of the target object by deforming the existing parts from the match. The deformation of parts are being done sequentially. For further performance improvement, we present a deformation training method employing transfer learning on segment editing process.
{"title":"MatchMesh: Knowledge-based 3D Point Cloud Meshing Using Divide-and-conquer Deformation","authors":"Ying Tang, Shengtao Sun, Ben Wu","doi":"10.1109/ICNSC48988.2020.9238103","DOIUrl":"https://doi.org/10.1109/ICNSC48988.2020.9238103","url":null,"abstract":"The reconstruction of surface mesh from point cloud is compute-intensive but also very important step in the remanufacturing and personalization industries. With more 3D scanners providing lower cost and higher resolution, further detailed point clouds can be gathered without so much effort as before. In manufacturing, there are databases which contain the origin 3D design models of the products. How to utilize the design model data for swift production of related products remains a problem for remanufacturing and customization. In order to develop a knowledge-based way of handling this problem, editing or deforming an existing mesh to match the target is an effective way of easing the workload. In this paper, we introduce a divide-and -conquer process which segments the depth scan data and then find the best match in the database as its source of deformation. The segmentation is performed on 3D point level using global features extracted by 3D CNN. After that we find best match to our knowledge with the same features to acquire a fast meshing of the target object by deforming the existing parts from the match. The deformation of parts are being done sequentially. For further performance improvement, we present a deformation training method employing transfer learning on segment editing process.","PeriodicalId":412290,"journal":{"name":"2020 IEEE International Conference on Networking, Sensing and Control (ICNSC)","volume":"5 10","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133268345","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：