Pub Date : 2020-12-01DOI: 10.1109/ITCA52113.2020.00150
L. Min, Luo Weifeng
Fourier Transform Profilometry (FTP) and Phase Measurement Profilometry (PMP) are 3D surface measurement techniques that have been widely used, however, FTP has some defects, such as high requirement for space carrier frequency of projection fringe and easy loss of high-frequency components of measured object. High precision measurement based on PMP is difficult to realize dynamic measurement. However, Temporal Fourier Transform Profilometry (TFTP) can realize high-precision 3D reconstruction of dynamic objects. Therefore, this paper deeply explores the implementation process of TFTP method, it is proved that this method can retain the high-frequency components of the measured object to realize 3D surface reconstruction under the condition of low space carrier frequency projection. In addition, this paper discusses the influence of relevant parameters on the results of 3D reconstruction, and compares FTP method and TFTP method. On this basis, a measuring system is proposed, which is simple to construct and operate, and can quickly reconstruct the 3D shape of objects.
{"title":"Research on 3D Reconstruction Method Based on Temporal Fourier Transform Profilometry","authors":"L. Min, Luo Weifeng","doi":"10.1109/ITCA52113.2020.00150","DOIUrl":"https://doi.org/10.1109/ITCA52113.2020.00150","url":null,"abstract":"Fourier Transform Profilometry (FTP) and Phase Measurement Profilometry (PMP) are 3D surface measurement techniques that have been widely used, however, FTP has some defects, such as high requirement for space carrier frequency of projection fringe and easy loss of high-frequency components of measured object. High precision measurement based on PMP is difficult to realize dynamic measurement. However, Temporal Fourier Transform Profilometry (TFTP) can realize high-precision 3D reconstruction of dynamic objects. Therefore, this paper deeply explores the implementation process of TFTP method, it is proved that this method can retain the high-frequency components of the measured object to realize 3D surface reconstruction under the condition of low space carrier frequency projection. In addition, this paper discusses the influence of relevant parameters on the results of 3D reconstruction, and compares FTP method and TFTP method. On this basis, a measuring system is proposed, which is simple to construct and operate, and can quickly reconstruct the 3D shape of objects.","PeriodicalId":103309,"journal":{"name":"2020 2nd International Conference on Information Technology and Computer Application (ITCA)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131910886","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}
Based on the overall consideration of observation environment, observation system, data quality, and forecast application, the evaluation system is preliminarily established by using AHP combined with quantitative and qualitative analysis which realizes the quantitative evaluation of geoelectric field observation efficiency.
{"title":"Preliminary Study on Efficiency Evaluation of Geoelectric Field Observation","authors":"Xiangmin Dong, Hui-fang Zhang, Xia Li, Yiliang Guan","doi":"10.1109/ITCA52113.2020.00116","DOIUrl":"https://doi.org/10.1109/ITCA52113.2020.00116","url":null,"abstract":"Based on the overall consideration of observation environment, observation system, data quality, and forecast application, the evaluation system is preliminarily established by using AHP combined with quantitative and qualitative analysis which realizes the quantitative evaluation of geoelectric field observation efficiency.","PeriodicalId":103309,"journal":{"name":"2020 2nd International Conference on Information Technology and Computer Application (ITCA)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134575536","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 : 2020-12-01DOI: 10.1109/ITCA52113.2020.00128
Yizhuo Rao, Chengyuan Duan, Xiao Wei
With the repaid development of the Internet, multimedia data such as image, text, video, audio is increasing, which brings opportunities and challenges to the development of the economy and science. Cross-modal data entity resolution aims to find different objective descriptions of the semantically similar items from objects in different modalities. However, different modality data have the features with underlying heterogeneity and high-level semantic related. Starting from the problem of modality gap between cross-modal data, this paper introduces how to use the idea of confrontational learning to solve the cross-modal data entity resolution problem between images and text from the aspects of feature extraction and emotional state association.
{"title":"Review on Deep Adversarial Learning of Entity Resolution for Cross-Modal Data","authors":"Yizhuo Rao, Chengyuan Duan, Xiao Wei","doi":"10.1109/ITCA52113.2020.00128","DOIUrl":"https://doi.org/10.1109/ITCA52113.2020.00128","url":null,"abstract":"With the repaid development of the Internet, multimedia data such as image, text, video, audio is increasing, which brings opportunities and challenges to the development of the economy and science. Cross-modal data entity resolution aims to find different objective descriptions of the semantically similar items from objects in different modalities. However, different modality data have the features with underlying heterogeneity and high-level semantic related. Starting from the problem of modality gap between cross-modal data, this paper introduces how to use the idea of confrontational learning to solve the cross-modal data entity resolution problem between images and text from the aspects of feature extraction and emotional state association.","PeriodicalId":103309,"journal":{"name":"2020 2nd International Conference on Information Technology and Computer Application (ITCA)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114731766","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 : 2020-12-01DOI: 10.1109/ITCA52113.2020.00088
Yuxuan Gao, Yuan-long Hou
In many cases, drone is needed to detect objects from high altitude. The lack of training samples of this object category will have a bad impact on the task. In this paper, we design a few-shot detector for drone images. It adopts anchor-free one-stage framework, which lead to more reasonable definition of positive and negative samples and faster speed. We introduce attention mechanism to enable our model match the objects of same categories and distinguish the different class objects and propose a matching score map to utilize the similarity information of attention feature map. The similarity probability of each pixel region for support category is integrated into regression bounding boxes to obtain the similarity probability of each regression bounding box. Finally, through soft-NMS, the predicted detection bounding boxes for support category objects are generated. Compared with YOLOv3 on DOTA dataset, our model is proved to be effective for few-shot detection task of drone images.
{"title":"Anchor-Free Few-Shot Object Detection for Densely Arranged Small Targets in Drone Images","authors":"Yuxuan Gao, Yuan-long Hou","doi":"10.1109/ITCA52113.2020.00088","DOIUrl":"https://doi.org/10.1109/ITCA52113.2020.00088","url":null,"abstract":"In many cases, drone is needed to detect objects from high altitude. The lack of training samples of this object category will have a bad impact on the task. In this paper, we design a few-shot detector for drone images. It adopts anchor-free one-stage framework, which lead to more reasonable definition of positive and negative samples and faster speed. We introduce attention mechanism to enable our model match the objects of same categories and distinguish the different class objects and propose a matching score map to utilize the similarity information of attention feature map. The similarity probability of each pixel region for support category is integrated into regression bounding boxes to obtain the similarity probability of each regression bounding box. Finally, through soft-NMS, the predicted detection bounding boxes for support category objects are generated. Compared with YOLOv3 on DOTA dataset, our model is proved to be effective for few-shot detection task of drone images.","PeriodicalId":103309,"journal":{"name":"2020 2nd International Conference on Information Technology and Computer Application (ITCA)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114831901","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 : 2020-12-01DOI: 10.1109/ITCA52113.2020.00165
Lizong Lin, Xiaoming Wang
Nowadays, there are various types of smart bracelets in the market, and their functions are becoming more and more complex. However, there are not many bracelets facing the elderly and many of the physiological behaviors and living conditions of the elderly are different from those of the young. For example, the elderly are facing the risk of losing and falling. For these reasons, based on the Android system, this article has studied a smart bracelet system that not only collects heart rate and blood pressure, but also addresses the problems of falling and losing of the elderly. The bracelet in this article is a functional design for a specific group, which has important meaning and practical value.
{"title":"Design of a smart bracelet system for the elderly based on MTK6580","authors":"Lizong Lin, Xiaoming Wang","doi":"10.1109/ITCA52113.2020.00165","DOIUrl":"https://doi.org/10.1109/ITCA52113.2020.00165","url":null,"abstract":"Nowadays, there are various types of smart bracelets in the market, and their functions are becoming more and more complex. However, there are not many bracelets facing the elderly and many of the physiological behaviors and living conditions of the elderly are different from those of the young. For example, the elderly are facing the risk of losing and falling. For these reasons, based on the Android system, this article has studied a smart bracelet system that not only collects heart rate and blood pressure, but also addresses the problems of falling and losing of the elderly. The bracelet in this article is a functional design for a specific group, which has important meaning and practical value.","PeriodicalId":103309,"journal":{"name":"2020 2nd International Conference on Information Technology and Computer Application (ITCA)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115114497","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 : 2020-12-01DOI: 10.1109/ITCA52113.2020.00018
Jielu Yan, L. Ruan
High performance computer is a typical large-scale system which has a large number of high-density electronic devices system. The self-circulating evaporative cooling system provides a new method to solve the cooling problem. However, the system is a composite parallel system which is different with the previous study and application. Therefore, the operation characteristics of the minimum parallel unit for the system was studied through experiment in this paper.
{"title":"Experiment Study of the Self-circulating Evaporative Cooling System for High Performance Computer","authors":"Jielu Yan, L. Ruan","doi":"10.1109/ITCA52113.2020.00018","DOIUrl":"https://doi.org/10.1109/ITCA52113.2020.00018","url":null,"abstract":"High performance computer is a typical large-scale system which has a large number of high-density electronic devices system. The self-circulating evaporative cooling system provides a new method to solve the cooling problem. However, the system is a composite parallel system which is different with the previous study and application. Therefore, the operation characteristics of the minimum parallel unit for the system was studied through experiment in this paper.","PeriodicalId":103309,"journal":{"name":"2020 2nd International Conference on Information Technology and Computer Application (ITCA)","volume":"174 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123554377","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 : 2020-12-01DOI: 10.1109/itca52113.2020.00106
Ke Dong, Chengjie Zhou, Yihan Ruan, Yuzhi Li
Machine learning has been increasingly prevailing all over the world, especially in the computer vision field. This paper mainly focused on the performance of MobileNetV2 model for image classification. To verify the advanced performance of MobileNetV2 model better, this paper adopted MobileNetVl model as the control group and introduced an experiment of identifying images in a variety of datasets extracted from TensorFlow. With the T-SNE visualization tool, the conclusion can be generated by comparing the accuracy and effectiveness of these two models. The experimental results demonstrated that the proficiency of MobileNetV2 model achieved higher accuracy rates compared to MobileNetVl model. In order to enhance the performance of MobileNetV2, extensive experiments are performed.
{"title":"MobileNetV2 Model for Image Classification","authors":"Ke Dong, Chengjie Zhou, Yihan Ruan, Yuzhi Li","doi":"10.1109/itca52113.2020.00106","DOIUrl":"https://doi.org/10.1109/itca52113.2020.00106","url":null,"abstract":"Machine learning has been increasingly prevailing all over the world, especially in the computer vision field. This paper mainly focused on the performance of MobileNetV2 model for image classification. To verify the advanced performance of MobileNetV2 model better, this paper adopted MobileNetVl model as the control group and introduced an experiment of identifying images in a variety of datasets extracted from TensorFlow. With the T-SNE visualization tool, the conclusion can be generated by comparing the accuracy and effectiveness of these two models. The experimental results demonstrated that the proficiency of MobileNetV2 model achieved higher accuracy rates compared to MobileNetVl model. In order to enhance the performance of MobileNetV2, extensive experiments are performed.","PeriodicalId":103309,"journal":{"name":"2020 2nd International Conference on Information Technology and Computer Application (ITCA)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124901265","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 power applications, it is often difficult for equipment to keep time independently due to channel congestion, equipment disconnection, isolated network operation and other reasons. The long-term failure to obtain accurate time information will lead to the event SOE not having rigorous reference significance when the power terminal fails, and it often takes the data acquisition time of the dispatching master station as the main reference basis, and fails to get a good collaborative judgment effect. In order to meet the urgent needs of time, space and security in power production and management business, eliminate the major hidden dangers of GPS for China's power safety, develop the application of GPS and Beidou dual system timing and positioning, and transition to the application of Beidou III navigation satellite which can cover the world and has higher reliability.
{"title":"Power spatiotemporal data sensing application based on Beidou","authors":"You Li, Baoquan Liao, Xiaoou Wu, Chuanfu Xia, Yonghui Zhang, Shuai Huang, Zhixi Yu","doi":"10.1109/ITCA52113.2020.00065","DOIUrl":"https://doi.org/10.1109/ITCA52113.2020.00065","url":null,"abstract":"In power applications, it is often difficult for equipment to keep time independently due to channel congestion, equipment disconnection, isolated network operation and other reasons. The long-term failure to obtain accurate time information will lead to the event SOE not having rigorous reference significance when the power terminal fails, and it often takes the data acquisition time of the dispatching master station as the main reference basis, and fails to get a good collaborative judgment effect. In order to meet the urgent needs of time, space and security in power production and management business, eliminate the major hidden dangers of GPS for China's power safety, develop the application of GPS and Beidou dual system timing and positioning, and transition to the application of Beidou III navigation satellite which can cover the world and has higher reliability.","PeriodicalId":103309,"journal":{"name":"2020 2nd International Conference on Information Technology and Computer Application (ITCA)","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122972909","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 : 2020-12-01DOI: 10.1109/ITCA52113.2020.00063
Xizhi Wu, Rongzhe Liu, Han-Ni Yang, Zizhao Chen
Over the past decade, image classification, which can provide assistance to address complex tasks such as planetary exploration and unmanned driving, has become a hot topic. As a subproblem of image classification, scene image classification has received increasing attention. Based on previous studies, the Xception model achieved superior performance on image classification tasks in comparison with the original Inception model. The Xception model is advantageous at processing image classification, yet it has not been used for scene image classification. To tackle this issue, this paper proposed an Xception based transfer learning, and analyzed the model performance by comparing it with the Inception-V3 model. We found that the Xception based transfer learning significantly outperforms other methods such as Inception-V3, which is nicely demonstrated by the experimental results on the Intel Image Classification Challenge dataset. Furthermore, the Xception has shown greater robustness and ability in generalization with less overfitting problems.
{"title":"An Xception Based Convolutional Neural Network for Scene Image Classification with Transfer Learning","authors":"Xizhi Wu, Rongzhe Liu, Han-Ni Yang, Zizhao Chen","doi":"10.1109/ITCA52113.2020.00063","DOIUrl":"https://doi.org/10.1109/ITCA52113.2020.00063","url":null,"abstract":"Over the past decade, image classification, which can provide assistance to address complex tasks such as planetary exploration and unmanned driving, has become a hot topic. As a subproblem of image classification, scene image classification has received increasing attention. Based on previous studies, the Xception model achieved superior performance on image classification tasks in comparison with the original Inception model. The Xception model is advantageous at processing image classification, yet it has not been used for scene image classification. To tackle this issue, this paper proposed an Xception based transfer learning, and analyzed the model performance by comparing it with the Inception-V3 model. We found that the Xception based transfer learning significantly outperforms other methods such as Inception-V3, which is nicely demonstrated by the experimental results on the Intel Image Classification Challenge dataset. Furthermore, the Xception has shown greater robustness and ability in generalization with less overfitting problems.","PeriodicalId":103309,"journal":{"name":"2020 2nd International Conference on Information Technology and Computer Application (ITCA)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121724733","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 : 2020-12-01DOI: 10.1109/ITCA52113.2020.00028
Jingwen Zhi, Ruibiao Xie, Han Liu, Xiaowei Wang, Guotian Yang, P. Peng, Xiao Luo, Yijun Chen
Interaction technology is one of the core technologies of augmented reality. With the maturity of augmented reality hardware technology and the expansion of application field, interaction technology has been paid more attention and development. This paper sorts out the classification methods of interaction technology, focuses on the research status of interaction technology based on computer vision, external devices and multi-modal, as well as the selection of 3D objects, introduces the latest typical application of interaction technology. Finally, the interaction technology is summarized and prospected.
{"title":"A survey of Interactive Technology in Augmented Reality","authors":"Jingwen Zhi, Ruibiao Xie, Han Liu, Xiaowei Wang, Guotian Yang, P. Peng, Xiao Luo, Yijun Chen","doi":"10.1109/ITCA52113.2020.00028","DOIUrl":"https://doi.org/10.1109/ITCA52113.2020.00028","url":null,"abstract":"Interaction technology is one of the core technologies of augmented reality. With the maturity of augmented reality hardware technology and the expansion of application field, interaction technology has been paid more attention and development. This paper sorts out the classification methods of interaction technology, focuses on the research status of interaction technology based on computer vision, external devices and multi-modal, as well as the selection of 3D objects, introduces the latest typical application of interaction technology. Finally, the interaction technology is summarized and prospected.","PeriodicalId":103309,"journal":{"name":"2020 2nd International Conference on Information Technology and Computer Application (ITCA)","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124124452","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：