Pub Date : 2022-07-06DOI: 10.1109/ICCE-Taiwan55306.2022.9869188
Yaozong Gan, Ren Togo, Takahiro Ogawa, M. Haseyama
This paper presents a scene retrieval method in soccer videos with video vision Transformer (ViViT). In soccer coaching, it is difficult for the training staff to find the required scenes efficiently from the large number of soccer videos. We tackle this problem with a simple yet effective method. We train ViViT and obtain the output token features of the soccer scene by the pre-trained ViViT model. The output tokens of the pre-trained ViViT contain spatio-temporal information of soccer scenes. We then transform a query scene and candidate scenes into output token features using the pre-trained ViViT and calculate the similarity between the tokens with cosine similarity. We conducted experiments on SoccerNet-V2dataset. The experimental results show that the proposed method achieves outstanding retrieval accuracy compared to the previous methods.
{"title":"Scene Retrieval in Soccer Videos by Spatial-temporal Attention with Video Vision Transformer","authors":"Yaozong Gan, Ren Togo, Takahiro Ogawa, M. Haseyama","doi":"10.1109/ICCE-Taiwan55306.2022.9869188","DOIUrl":"https://doi.org/10.1109/ICCE-Taiwan55306.2022.9869188","url":null,"abstract":"This paper presents a scene retrieval method in soccer videos with video vision Transformer (ViViT). In soccer coaching, it is difficult for the training staff to find the required scenes efficiently from the large number of soccer videos. We tackle this problem with a simple yet effective method. We train ViViT and obtain the output token features of the soccer scene by the pre-trained ViViT model. The output tokens of the pre-trained ViViT contain spatio-temporal information of soccer scenes. We then transform a query scene and candidate scenes into output token features using the pre-trained ViViT and calculate the similarity between the tokens with cosine similarity. We conducted experiments on SoccerNet-V2dataset. The experimental results show that the proposed method achieves outstanding retrieval accuracy compared to the previous methods.","PeriodicalId":164671,"journal":{"name":"2022 IEEE International Conference on Consumer Electronics - Taiwan","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116078375","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}
The application of artificial intelligence to the diagnosis of ECG is of great significance. We combine machine learning algorithm with deep learning algorithm to give full play to the advantages of different algorithms by ensemble learning. Finally, we fuse the selected models so that the accuracy of identifying five kinds of arrhythmias can reach 94%. Particularly, the accuracy of class F beat which is difficult to identify has also been improved.
{"title":"An Integration Method for ECG Multi-Classification","authors":"Chao-Xin Xie, Minghui Fan, Liang-Hung Wang, Pao-Cheng Huang","doi":"10.1109/ICCE-Taiwan55306.2022.9869291","DOIUrl":"https://doi.org/10.1109/ICCE-Taiwan55306.2022.9869291","url":null,"abstract":"The application of artificial intelligence to the diagnosis of ECG is of great significance. We combine machine learning algorithm with deep learning algorithm to give full play to the advantages of different algorithms by ensemble learning. Finally, we fuse the selected models so that the accuracy of identifying five kinds of arrhythmias can reach 94%. Particularly, the accuracy of class F beat which is difficult to identify has also been improved.","PeriodicalId":164671,"journal":{"name":"2022 IEEE International Conference on Consumer Electronics - Taiwan","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123681849","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 : 2022-07-06DOI: 10.1109/ICCE-Taiwan55306.2022.9869093
Wanpeng Shao, Ken'ichi Kakizaki, Shunsuke Araki, T. Mukai
When setting up a terrestrial laser scanner near the target building and performing 3D measurement, the return measurements get corrupted because of the reflectivity and transparency of the glass objects. The discrimination of reflections and indoor points from the outdoor environment is a challenging task. As the first step of removing these erroneous measurements, it is important to detect these glass planes framed in the building façade. In this study, we propose an unsupervised segmentation approach in combination with the threshold of Gaussian distribution to extract transparent and reflective glass planes from point clouds with intensity attributes. For practical validation, our approach is evaluated on two scan points of a building with many glass components.
{"title":"Identification of Transparent and Specular Reflective Glass Planes in TLS Data with Intensity Values","authors":"Wanpeng Shao, Ken'ichi Kakizaki, Shunsuke Araki, T. Mukai","doi":"10.1109/ICCE-Taiwan55306.2022.9869093","DOIUrl":"https://doi.org/10.1109/ICCE-Taiwan55306.2022.9869093","url":null,"abstract":"When setting up a terrestrial laser scanner near the target building and performing 3D measurement, the return measurements get corrupted because of the reflectivity and transparency of the glass objects. The discrimination of reflections and indoor points from the outdoor environment is a challenging task. As the first step of removing these erroneous measurements, it is important to detect these glass planes framed in the building façade. In this study, we propose an unsupervised segmentation approach in combination with the threshold of Gaussian distribution to extract transparent and reflective glass planes from point clouds with intensity attributes. For practical validation, our approach is evaluated on two scan points of a building with many glass components.","PeriodicalId":164671,"journal":{"name":"2022 IEEE International Conference on Consumer Electronics - Taiwan","volume":"131 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121475206","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 : 2022-07-06DOI: 10.1109/ICCE-Taiwan55306.2022.9869129
Chao-Chun Ku, Ming-Tien Wu, Ming-Lin Chuang
This paper presents the design of a Wi-Fi 6E planar antenna, which was covered the Wi-Fi 6E operating frequency bands of 2.45 GHz and 5.15 GHz-7.125 GHz. For the antenna design steps and changing the antenna structure effect, they are presented such as change symmetric bow-tie antenna and asymmetric antenna to different lengths. Finally, the simulated and measured results are compared and to verify the feasibility of this antenna design approach.
{"title":"Multiband Antenna Design for Wi-Fi 6E Applications","authors":"Chao-Chun Ku, Ming-Tien Wu, Ming-Lin Chuang","doi":"10.1109/ICCE-Taiwan55306.2022.9869129","DOIUrl":"https://doi.org/10.1109/ICCE-Taiwan55306.2022.9869129","url":null,"abstract":"This paper presents the design of a Wi-Fi 6E planar antenna, which was covered the Wi-Fi 6E operating frequency bands of 2.45 GHz and 5.15 GHz-7.125 GHz. For the antenna design steps and changing the antenna structure effect, they are presented such as change symmetric bow-tie antenna and asymmetric antenna to different lengths. Finally, the simulated and measured results are compared and to verify the feasibility of this antenna design approach.","PeriodicalId":164671,"journal":{"name":"2022 IEEE International Conference on Consumer Electronics - Taiwan","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114970948","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 : 2022-07-06DOI: 10.1109/ICCE-Taiwan55306.2022.9869210
Kohei Hayashi, Rrota Horiuchi, N. Komuro
In recent years, WSNs have been expected to be applied to various fields such as home security, healthcare, and environmental monitoring. A number of studies have been done on IEEE 802.15.4, the standard for WSNs, but they have left some problems and there is still room for improvement. In this paper, we propose a new access control protocol in tree-type heterogeneous sensor networks that achieves low EC, high PDR, and low latency by adjusting the active period so that the buffer occupancy ratio of the relay node is less than 1 to prevent the buffer from overflowing, and then performing channel partitioning and scheduling to avoid packet collisions.
{"title":"Scheduling Method for Improving Transmission and Reception Efficiency in IEEE802.15.4 used Heterogeneous Wireless Sensor Networks","authors":"Kohei Hayashi, Rrota Horiuchi, N. Komuro","doi":"10.1109/ICCE-Taiwan55306.2022.9869210","DOIUrl":"https://doi.org/10.1109/ICCE-Taiwan55306.2022.9869210","url":null,"abstract":"In recent years, WSNs have been expected to be applied to various fields such as home security, healthcare, and environmental monitoring. A number of studies have been done on IEEE 802.15.4, the standard for WSNs, but they have left some problems and there is still room for improvement. In this paper, we propose a new access control protocol in tree-type heterogeneous sensor networks that achieves low EC, high PDR, and low latency by adjusting the active period so that the buffer occupancy ratio of the relay node is less than 1 to prevent the buffer from overflowing, and then performing channel partitioning and scheduling to avoid packet collisions.","PeriodicalId":164671,"journal":{"name":"2022 IEEE International Conference on Consumer Electronics - Taiwan","volume":"85 11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122666284","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 : 2022-07-06DOI: 10.1109/ICCE-Taiwan55306.2022.9869000
Kam-Hong Chan, C. Chao
The identification of drivers is essential for many applications, such as attribution of liability for car accidents and driving risk assessment. Most existing driver identification systems adopt identity keys (such as car keys and smart cards) or biometrics technology (such as face recognition, iris recognition, fingerprint recognition, voiceprint recognition, and vein recognition, etc.) to identify drivers. However, these schemes are unable to detect driver changes during a trip. In this paper, combining voiceprint and acoustic driving characteristics, the driver identity system DriverID is proposed to identify the person who is actually driving. DriverID uses the Deep Residual Network (ResNet) to construct an acoustic recognition model based on the voice key recorded by the driver. In addition, the Convolutional Neural Network (CNN) is used to construct an acoustic driving action recognition model based on the reflection of acoustic signals generated by the user. Combining the two recognition methods, DriverID can correctly identify the driver with high probability. It is believed that DriverID is a practical driver identity system.
{"title":"DriverID: Driver Identity System Based on Voiceprint and Acoustic Sensing","authors":"Kam-Hong Chan, C. Chao","doi":"10.1109/ICCE-Taiwan55306.2022.9869000","DOIUrl":"https://doi.org/10.1109/ICCE-Taiwan55306.2022.9869000","url":null,"abstract":"The identification of drivers is essential for many applications, such as attribution of liability for car accidents and driving risk assessment. Most existing driver identification systems adopt identity keys (such as car keys and smart cards) or biometrics technology (such as face recognition, iris recognition, fingerprint recognition, voiceprint recognition, and vein recognition, etc.) to identify drivers. However, these schemes are unable to detect driver changes during a trip. In this paper, combining voiceprint and acoustic driving characteristics, the driver identity system DriverID is proposed to identify the person who is actually driving. DriverID uses the Deep Residual Network (ResNet) to construct an acoustic recognition model based on the voice key recorded by the driver. In addition, the Convolutional Neural Network (CNN) is used to construct an acoustic driving action recognition model based on the reflection of acoustic signals generated by the user. Combining the two recognition methods, DriverID can correctly identify the driver with high probability. It is believed that DriverID is a practical driver identity system.","PeriodicalId":164671,"journal":{"name":"2022 IEEE International Conference on Consumer Electronics - Taiwan","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123907479","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 : 2022-07-06DOI: 10.1109/ICCE-Taiwan55306.2022.9869009
Nan-Ching Tai, Jia-Ling Wu, Chih-Yi Yeh
Augmented reality (AR) that can overlay the interactive digital contents on real scenes has advanced the breadth and depth of the guided tour for architectural heritages. However, it increases the demand for precision in identifying real scenes without physical AR target installation for flexible and natural exploration. In this study, a customized physical convertible stand for a tablet computer that captures an extendable physical target object was developed to calibrate captured scenes and on-site viewing. The developed stand ensures an improved AR touring experience in receiving complex knowledge regarding visited cultural heritage sites.
{"title":"Supplementary Physical Device for In-Depth Augmented Reality Touring of Architectural Heritage Sites","authors":"Nan-Ching Tai, Jia-Ling Wu, Chih-Yi Yeh","doi":"10.1109/ICCE-Taiwan55306.2022.9869009","DOIUrl":"https://doi.org/10.1109/ICCE-Taiwan55306.2022.9869009","url":null,"abstract":"Augmented reality (AR) that can overlay the interactive digital contents on real scenes has advanced the breadth and depth of the guided tour for architectural heritages. However, it increases the demand for precision in identifying real scenes without physical AR target installation for flexible and natural exploration. In this study, a customized physical convertible stand for a tablet computer that captures an extendable physical target object was developed to calibrate captured scenes and on-site viewing. The developed stand ensures an improved AR touring experience in receiving complex knowledge regarding visited cultural heritage sites.","PeriodicalId":164671,"journal":{"name":"2022 IEEE International Conference on Consumer Electronics - Taiwan","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125237878","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 : 2022-07-06DOI: 10.1109/ICCE-Taiwan55306.2022.9869038
C. Hsieh, Quanbin Zhang, Zece Chen
Currently, most indoor surveillance systems employ conventional cameras in a monitored place to have full coverage. However, there are still uncovered areas under surveillance because of the limitation of conventional cameras, for example, the shooting angle restriction. To alleviate the problem, this paper presents a surveillance system based on a fisheye or 360-degree panoramic camera and YOLOv4 object detection. The proposed approach consists of four stages: (i) capture panoramic images, (ii) convert the captured image into a conventional image, (iii) detect objects, that is, human objects, and (iv) record them if necessary. The proposed approach will reduce costs, save installation time, and eliminate areas uncovered in a surveillance system.
{"title":"An Indoor Surveillances System Using Fisheye Camera and YOLOV4 Object Detection","authors":"C. Hsieh, Quanbin Zhang, Zece Chen","doi":"10.1109/ICCE-Taiwan55306.2022.9869038","DOIUrl":"https://doi.org/10.1109/ICCE-Taiwan55306.2022.9869038","url":null,"abstract":"Currently, most indoor surveillance systems employ conventional cameras in a monitored place to have full coverage. However, there are still uncovered areas under surveillance because of the limitation of conventional cameras, for example, the shooting angle restriction. To alleviate the problem, this paper presents a surveillance system based on a fisheye or 360-degree panoramic camera and YOLOv4 object detection. The proposed approach consists of four stages: (i) capture panoramic images, (ii) convert the captured image into a conventional image, (iii) detect objects, that is, human objects, and (iv) record them if necessary. The proposed approach will reduce costs, save installation time, and eliminate areas uncovered in a surveillance system.","PeriodicalId":164671,"journal":{"name":"2022 IEEE International Conference on Consumer Electronics - Taiwan","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125242392","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 : 2022-07-06DOI: 10.1109/ICCE-Taiwan55306.2022.9869235
Chieh-Hsun Hsieh, Jyun-Jhih Lin, Po-Hsuan Tseng
Since non-human targets in cluttered environments may often block static humans, we propose a method to simultaneously extract vital signs information from human targets to enhance the location estimation. We mainly enhance the range-angle image (RAI) signal based on the heartbeat estimation.
{"title":"mmWave Radar-based Static Human Localization in Cluttered Environment","authors":"Chieh-Hsun Hsieh, Jyun-Jhih Lin, Po-Hsuan Tseng","doi":"10.1109/ICCE-Taiwan55306.2022.9869235","DOIUrl":"https://doi.org/10.1109/ICCE-Taiwan55306.2022.9869235","url":null,"abstract":"Since non-human targets in cluttered environments may often block static humans, we propose a method to simultaneously extract vital signs information from human targets to enhance the location estimation. We mainly enhance the range-angle image (RAI) signal based on the heartbeat estimation.","PeriodicalId":164671,"journal":{"name":"2022 IEEE International Conference on Consumer Electronics - Taiwan","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129496434","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 : 2022-07-06DOI: 10.1109/ICCE-Taiwan55306.2022.9869083
T. Oyama, Y. Taniguchi
In this paper, to solve eavesdropping by a third party node, we propose a self-organizing method to reduce the eavesdropping area by intentionally causing interference by transmitting noise radio signals at the same timing as the transmitting node by surrounding nodes. We utilize a pulse-coupled oscillator model-based method to adjust the noise signal transmission timing. In addition, to improve the performance of our proposed method, we introduce a method to readjust the synchronization state. We evaluate fundamental performance of our proposed method through simulation evaluations.
{"title":"A self-organizing noise signal transmission method to make eavesdropping difficult in wireless networks","authors":"T. Oyama, Y. Taniguchi","doi":"10.1109/ICCE-Taiwan55306.2022.9869083","DOIUrl":"https://doi.org/10.1109/ICCE-Taiwan55306.2022.9869083","url":null,"abstract":"In this paper, to solve eavesdropping by a third party node, we propose a self-organizing method to reduce the eavesdropping area by intentionally causing interference by transmitting noise radio signals at the same timing as the transmitting node by surrounding nodes. We utilize a pulse-coupled oscillator model-based method to adjust the noise signal transmission timing. In addition, to improve the performance of our proposed method, we introduce a method to readjust the synchronization state. We evaluate fundamental performance of our proposed method through simulation evaluations.","PeriodicalId":164671,"journal":{"name":"2022 IEEE International Conference on Consumer Electronics - Taiwan","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129629289","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：