Pub Date : 2021-08-17DOI: 10.1109/ICUFN49451.2021.9528612
Jingjing Wang, Xianqing Wang, Jishen Peng, J. Hwang, J. Park
With the development of Wi-Fi technology, the IEEE 802.11n series communication protocol and the subsequent wireless LAN protocols use multiple-input multiple-output (MIMO) and orthogonal frequency division multiplexing (OFDM) technologies. Channel state information (CSI) fingerprint positioning technology based on fine-grained channel state information is widely used in the field of WIFI indoor positioning. However, the propagation of CSI is still affected by indoor multipath, and we cannot obtain signals in some corner areas. Therefore, CSI needs a suitable calibration method to improve the accuracy of the position estimation system. This paper proposes a fine-grained CSI fingerprint location algorithm based on Principal Component Analysis (PCA). This novel algorithm uses a dimensionality reduction method on the basis of the Discrete Wavelet Transform (DWT) to optimize, eliminate the noise and redundancy of the original data and reduce the positioning error. Experimental results show that the proposed approach achieves significant localization accuracy improvement over using the RSSI fingerprint method and original CSI fingerprint method, while it incurs much less computational complexity. Meanwhile, the algorithm improves the influence of multiple paths in a complex indoor environment on location, and the method can obtain more accurate location results.
{"title":"Indoor Fingerprinting Localization Based on Fine-grained CSI using Principal Component Analysis","authors":"Jingjing Wang, Xianqing Wang, Jishen Peng, J. Hwang, J. Park","doi":"10.1109/ICUFN49451.2021.9528612","DOIUrl":"https://doi.org/10.1109/ICUFN49451.2021.9528612","url":null,"abstract":"With the development of Wi-Fi technology, the IEEE 802.11n series communication protocol and the subsequent wireless LAN protocols use multiple-input multiple-output (MIMO) and orthogonal frequency division multiplexing (OFDM) technologies. Channel state information (CSI) fingerprint positioning technology based on fine-grained channel state information is widely used in the field of WIFI indoor positioning. However, the propagation of CSI is still affected by indoor multipath, and we cannot obtain signals in some corner areas. Therefore, CSI needs a suitable calibration method to improve the accuracy of the position estimation system. This paper proposes a fine-grained CSI fingerprint location algorithm based on Principal Component Analysis (PCA). This novel algorithm uses a dimensionality reduction method on the basis of the Discrete Wavelet Transform (DWT) to optimize, eliminate the noise and redundancy of the original data and reduce the positioning error. Experimental results show that the proposed approach achieves significant localization accuracy improvement over using the RSSI fingerprint method and original CSI fingerprint method, while it incurs much less computational complexity. Meanwhile, the algorithm improves the influence of multiple paths in a complex indoor environment on location, and the method can obtain more accurate location results.","PeriodicalId":318542,"journal":{"name":"2021 Twelfth International Conference on Ubiquitous and Future Networks (ICUFN)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121699127","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-08-17DOI: 10.1109/ICUFN49451.2021.9528537
Yu-Hung Chen, Jiann-Liang Chen
This study proposes a novel machine learning architecture that uses deep learning technology to extract features from the structure of a web page and construct a model for phishing detection. Hackers can commit crimes through a variety of Internet technologies. In recent years, phishing incidents have become more frequent, and the rapid development of information technology has enabled hackers to develop more advanced phishing attacks. Furthermore, the release of phishing toolkits, which are collections of software tools, make it easier for people with minimal technical skills to launch their own phishing attacks. Therefore, more attention must be paid to the prevention of such attacks. Protection from phishing websites has various aspects, including user training, public awareness, technical security measures and others. In this research, we further improve the phishing detection on phishing kits. This research proposes to use the combination HTML structural feature with the features proposed by AI@ntiPhish1.0 to train the phishing detection model. Relevant experimental results demonstrate that the combination of AI@ntiPhish1.0 features with extracted HTML structural features is more effective on detecting the phishing kits, increasing the accuracy thereof from 82% to 87.2%.
{"title":"Intelligent Learning Architecture with Hybrid Features for Phishing Detection","authors":"Yu-Hung Chen, Jiann-Liang Chen","doi":"10.1109/ICUFN49451.2021.9528537","DOIUrl":"https://doi.org/10.1109/ICUFN49451.2021.9528537","url":null,"abstract":"This study proposes a novel machine learning architecture that uses deep learning technology to extract features from the structure of a web page and construct a model for phishing detection. Hackers can commit crimes through a variety of Internet technologies. In recent years, phishing incidents have become more frequent, and the rapid development of information technology has enabled hackers to develop more advanced phishing attacks. Furthermore, the release of phishing toolkits, which are collections of software tools, make it easier for people with minimal technical skills to launch their own phishing attacks. Therefore, more attention must be paid to the prevention of such attacks. Protection from phishing websites has various aspects, including user training, public awareness, technical security measures and others. In this research, we further improve the phishing detection on phishing kits. This research proposes to use the combination HTML structural feature with the features proposed by AI@ntiPhish1.0 to train the phishing detection model. Relevant experimental results demonstrate that the combination of AI@ntiPhish1.0 features with extracted HTML structural features is more effective on detecting the phishing kits, increasing the accuracy thereof from 82% to 87.2%.","PeriodicalId":318542,"journal":{"name":"2021 Twelfth International Conference on Ubiquitous and Future Networks (ICUFN)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124958221","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-08-17DOI: 10.1109/ICUFN49451.2021.9528536
Md. Morshed Alam, Md. Osman Ali, M. Shahjalal, Byung-deok Chung, Y. Jang
The integration of artificial intelligence with home energy management systems (HEMS) due to the development of advanced metering infrastructure is a promising scheme to improve the usage of renewable energy in a residential application. In the paper, energy management among multiple co-operative households with PV-Storage integrated generation system in a home micro-grid in the presence of short-term prediction of power generation and consumption is studied. In such a home microgrid system, the central energy storage system (C.ESS) is considered that is connected with multiple household and PV panels. The key parameters that are responsible for optimum scheduling of C.ESS are forecasted PV power generation, forecasted household energy consumption, dynamic state of charge (SOC), and base level of energy consumption. In this paper, firstly, the prediction of short-term generation and consumption based on the long short-term memory (LSTM) algorithm is done. Then, this forecasted data is used as the constraint to the control algorithm for optimum scheduling. Therefore, the amount of power that will be supplied from C.ESS is also determined for properly utilizing the stored energy. The simulation results of the proposed scheme show the robustness and effectiveness in the home microgrid environment.
{"title":"Optimal Energy Management Among Multiple Households with Integrated Shared Energy Storage System (ESS)","authors":"Md. Morshed Alam, Md. Osman Ali, M. Shahjalal, Byung-deok Chung, Y. Jang","doi":"10.1109/ICUFN49451.2021.9528536","DOIUrl":"https://doi.org/10.1109/ICUFN49451.2021.9528536","url":null,"abstract":"The integration of artificial intelligence with home energy management systems (HEMS) due to the development of advanced metering infrastructure is a promising scheme to improve the usage of renewable energy in a residential application. In the paper, energy management among multiple co-operative households with PV-Storage integrated generation system in a home micro-grid in the presence of short-term prediction of power generation and consumption is studied. In such a home microgrid system, the central energy storage system (C.ESS) is considered that is connected with multiple household and PV panels. The key parameters that are responsible for optimum scheduling of C.ESS are forecasted PV power generation, forecasted household energy consumption, dynamic state of charge (SOC), and base level of energy consumption. In this paper, firstly, the prediction of short-term generation and consumption based on the long short-term memory (LSTM) algorithm is done. Then, this forecasted data is used as the constraint to the control algorithm for optimum scheduling. Therefore, the amount of power that will be supplied from C.ESS is also determined for properly utilizing the stored energy. The simulation results of the proposed scheme show the robustness and effectiveness in the home microgrid environment.","PeriodicalId":318542,"journal":{"name":"2021 Twelfth International Conference on Ubiquitous and Future Networks (ICUFN)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116186129","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-08-17DOI: 10.1109/ICUFN49451.2021.9528769
Yong-An Jung, Sang-Bong Byun, H. Shin, D. Han, Soo-Hyun Cho, Sung-Hun Lee
The primary synchronization signal (PSS) and secondary synchronization signal (SSS) transmitted in the 5G are used to perform a synchronization procedure. This paper proposes an effective residual frequency offset (RFO) estimation method in a 5G new radio (NR) system. The proposed RFO estimation method applies two branches correlation using PSS and SSS sequence. This paper shows via the simulation results that the inherent property of the PSS and SSS signals is exploited for a robust RFO estimation at various delay spread of wireless environments. It is demonstrated that the proposed RFO estimation scheme is efficient for the 5G NR system.
{"title":"Residual Frequency offset Estimation Scheme for 5G NR System","authors":"Yong-An Jung, Sang-Bong Byun, H. Shin, D. Han, Soo-Hyun Cho, Sung-Hun Lee","doi":"10.1109/ICUFN49451.2021.9528769","DOIUrl":"https://doi.org/10.1109/ICUFN49451.2021.9528769","url":null,"abstract":"The primary synchronization signal (PSS) and secondary synchronization signal (SSS) transmitted in the 5G are used to perform a synchronization procedure. This paper proposes an effective residual frequency offset (RFO) estimation method in a 5G new radio (NR) system. The proposed RFO estimation method applies two branches correlation using PSS and SSS sequence. This paper shows via the simulation results that the inherent property of the PSS and SSS signals is exploited for a robust RFO estimation at various delay spread of wireless environments. It is demonstrated that the proposed RFO estimation scheme is efficient for the 5G NR system.","PeriodicalId":318542,"journal":{"name":"2021 Twelfth International Conference on Ubiquitous and Future Networks (ICUFN)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121775283","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-08-17DOI: 10.1109/ICUFN49451.2021.9528800
Sang-Hobn Oh, Soon-Yong Park
This paper proposes a 3D spatial upsampling algorithm using a 2D LiDAR and a single camera. These two devices are placed on the same line, and both data are acquired by rotating the stage 360° around a vertical axis using a step motor. The obtained data is used to calibrate between the LiDAR and the camera. And a high-density 3D map is generated through a proposed two-step upsampling method using HSD-based guide image.
{"title":"Lidar Upsampling Using HSD Color Space Guided Image","authors":"Sang-Hobn Oh, Soon-Yong Park","doi":"10.1109/ICUFN49451.2021.9528800","DOIUrl":"https://doi.org/10.1109/ICUFN49451.2021.9528800","url":null,"abstract":"This paper proposes a 3D spatial upsampling algorithm using a 2D LiDAR and a single camera. These two devices are placed on the same line, and both data are acquired by rotating the stage 360° around a vertical axis using a step motor. The obtained data is used to calibrate between the LiDAR and the camera. And a high-density 3D map is generated through a proposed two-step upsampling method using HSD-based guide image.","PeriodicalId":318542,"journal":{"name":"2021 Twelfth International Conference on Ubiquitous and Future Networks (ICUFN)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116543619","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-08-17DOI: 10.1109/ICUFN49451.2021.9528650
Ji-Eun Shin, Hyun-Woo Jeong, Jiwon Jeong
The multi-band UWAS communication techniques are effective in terms of performance and throughput efficiency. However, the multi-band configuration in a particular band affects the output from the entire bands. This problem can be solved through a receiving end that analyzes error rates of each band. In this paper, we proposed an estimation BER algorithm which get the reliability of received data to set the weighting value to each band. Therefore, we analyzed the efficiency of multi-band transmission scheme with estimation BER and 3 [dB] performance gain is obtained.
{"title":"A Weighted Multi-band Algorithm Using Estimation BER in Underwater Acoustic Communication","authors":"Ji-Eun Shin, Hyun-Woo Jeong, Jiwon Jeong","doi":"10.1109/ICUFN49451.2021.9528650","DOIUrl":"https://doi.org/10.1109/ICUFN49451.2021.9528650","url":null,"abstract":"The multi-band UWAS communication techniques are effective in terms of performance and throughput efficiency. However, the multi-band configuration in a particular band affects the output from the entire bands. This problem can be solved through a receiving end that analyzes error rates of each band. In this paper, we proposed an estimation BER algorithm which get the reliability of received data to set the weighting value to each band. Therefore, we analyzed the efficiency of multi-band transmission scheme with estimation BER and 3 [dB] performance gain is obtained.","PeriodicalId":318542,"journal":{"name":"2021 Twelfth International Conference on Ubiquitous and Future Networks (ICUFN)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126509648","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-08-17DOI: 10.1109/ICUFN49451.2021.9528778
Reza E. Rad, Sungjin Kim, B. S. Rikan, Kangyoon Lee
This paper presents a high power and highly efficient 5.8 GHz differential two-stage cascode Class-A Power Amplifier (PA) for a Wireless Power Transfer (WPT) system. The PA is designed in a standard General Purpose (GP) 180 nm CMOS technology. The process does not apply any Radio Frequency (RF) devices such as inductor nor transformer which are essential for an RF design. A full custom-made transformer is proposed and optimized at 5.8 GHz which is modeled using EMX analysis. The proposed transformer shows 1.5 nH and 1.28 nH inductance at the primary and secondary sides of the transformer while their quality factor reaches up to 11.4 and 11 at 5.8 GHz, respectively. Even though reaching higher efficiencies in CMOS processes is more challenging than the GaN processes, the proposed PA has a relatively high Power Added Efficiency (PAE) of 33%. The power gain of the PA is 19.47 dB at 5.8 GHz. The average current consumption of the PA is 144 mA while the power supply is 1.8V.
{"title":"A High Power High Efficient 5.8 GHz CMOS Class-A Power Amplifier for a WPT Application","authors":"Reza E. Rad, Sungjin Kim, B. S. Rikan, Kangyoon Lee","doi":"10.1109/ICUFN49451.2021.9528778","DOIUrl":"https://doi.org/10.1109/ICUFN49451.2021.9528778","url":null,"abstract":"This paper presents a high power and highly efficient 5.8 GHz differential two-stage cascode Class-A Power Amplifier (PA) for a Wireless Power Transfer (WPT) system. The PA is designed in a standard General Purpose (GP) 180 nm CMOS technology. The process does not apply any Radio Frequency (RF) devices such as inductor nor transformer which are essential for an RF design. A full custom-made transformer is proposed and optimized at 5.8 GHz which is modeled using EMX analysis. The proposed transformer shows 1.5 nH and 1.28 nH inductance at the primary and secondary sides of the transformer while their quality factor reaches up to 11.4 and 11 at 5.8 GHz, respectively. Even though reaching higher efficiencies in CMOS processes is more challenging than the GaN processes, the proposed PA has a relatively high Power Added Efficiency (PAE) of 33%. The power gain of the PA is 19.47 dB at 5.8 GHz. The average current consumption of the PA is 144 mA while the power supply is 1.8V.","PeriodicalId":318542,"journal":{"name":"2021 Twelfth International Conference on Ubiquitous and Future Networks (ICUFN)","volume":"121 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132554468","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-08-17DOI: 10.1109/ICUFN49451.2021.9528539
Hirofumi Nakajo, T. Fujii
The concept of the smart spectrum has been proposed to deal with the problem of shortage of spectrum, which is a limited resource. In smart spectrum, a database is constructed based on the measured data of the radio environment to manage the spectrum, thus realizing highly efficient spectrum utilization, and its usefulness has been confirmed in several systems. On the other hand, for 5G NR signals, the database based on the smart spectrum has not been studied and its usefulness has not been confirmed. In particular, since 5G millimeter wave (mmWave) signals adopt beamforming technology, it is necessary to estimate the directivity and propagation characteristics of multiple beams. Therefore, in the database construction, we need to measure and manage not only the conventional management for each base station and frequency but also each beam. In this paper, we conduct a measurement campaign of mmWave signals from a local 5G base station in Imabari City, Ehime Prefecture, Japan, and construct a spectrum database. We also discuss the analysis results of mmWave signals based on the constructed database, including the radio propagation of each beam and the comparison with anchor band signals. and confirm the usefulness.
{"title":"Local 5G mmWave Signal Measurement and Analysis for Spectrum Database","authors":"Hirofumi Nakajo, T. Fujii","doi":"10.1109/ICUFN49451.2021.9528539","DOIUrl":"https://doi.org/10.1109/ICUFN49451.2021.9528539","url":null,"abstract":"The concept of the smart spectrum has been proposed to deal with the problem of shortage of spectrum, which is a limited resource. In smart spectrum, a database is constructed based on the measured data of the radio environment to manage the spectrum, thus realizing highly efficient spectrum utilization, and its usefulness has been confirmed in several systems. On the other hand, for 5G NR signals, the database based on the smart spectrum has not been studied and its usefulness has not been confirmed. In particular, since 5G millimeter wave (mmWave) signals adopt beamforming technology, it is necessary to estimate the directivity and propagation characteristics of multiple beams. Therefore, in the database construction, we need to measure and manage not only the conventional management for each base station and frequency but also each beam. In this paper, we conduct a measurement campaign of mmWave signals from a local 5G base station in Imabari City, Ehime Prefecture, Japan, and construct a spectrum database. We also discuss the analysis results of mmWave signals based on the constructed database, including the radio propagation of each beam and the comparison with anchor band signals. and confirm the usefulness.","PeriodicalId":318542,"journal":{"name":"2021 Twelfth International Conference on Ubiquitous and Future Networks (ICUFN)","volume":"130 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124488956","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-08-17DOI: 10.1109/ICUFN49451.2021.9528692
Mark Verana, C. I. Nwakanma, Jae-Min Lee, Dong Seong Kim
The development of intelligent manufacturing and 3D printers is rapidly engaging in the industry. However, 3D printers are challenged by occasional anomalies due to leading to failure in 3D performance. In this work, a fault diagnosis based on a convolutional neural network (CNN) for 3D printers is proposed. We have leveraged an online repository of a set of data streams collected from working 3D printers. The CNN was used to process, detect and classify anomalies in 3D printing with appreciable accuracy. The proposed CNN outperformed the support vector machine (SVM), and artificial neural network (ANN) by 5.1% and 25.7%, respectively.
{"title":"Deep Learning-Based 3D Printer Fault Detection","authors":"Mark Verana, C. I. Nwakanma, Jae-Min Lee, Dong Seong Kim","doi":"10.1109/ICUFN49451.2021.9528692","DOIUrl":"https://doi.org/10.1109/ICUFN49451.2021.9528692","url":null,"abstract":"The development of intelligent manufacturing and 3D printers is rapidly engaging in the industry. However, 3D printers are challenged by occasional anomalies due to leading to failure in 3D performance. In this work, a fault diagnosis based on a convolutional neural network (CNN) for 3D printers is proposed. We have leveraged an online repository of a set of data streams collected from working 3D printers. The CNN was used to process, detect and classify anomalies in 3D printing with appreciable accuracy. The proposed CNN outperformed the support vector machine (SVM), and artificial neural network (ANN) by 5.1% and 25.7%, respectively.","PeriodicalId":318542,"journal":{"name":"2021 Twelfth International Conference on Ubiquitous and Future Networks (ICUFN)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122645222","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-08-17DOI: 10.1109/ICUFN49451.2021.9528609
J. Choi, Min Young Kim
Vision, Radar, and LiDAR sensors are widely used for autonomous vehicle perception technology. Especially object detection and classification are primarily dependent on vision sensors. However, under poor lighting conditions, dazzling sunlight, or bad weathers an object might be difficult to be identified with general vision sensors. In this paper, we propose a sensor fusion system with a thermal infrared camera and LiDAR sensor that can reliably detect and identify objects even in environments where visibility is poor, such as in severe glare and fog or smoke. The proposed method obtains intrinsic parameters by calibrating the thermal infrared camera and LiDAR sensor. Extrinsic calibration algorithm between two sensors is made to obtain the extrinsic parameters (rotation and translation matrix) using 3D calibration targets. This system and proposed algorithm show that it can reliably detect and identify objects even in hard visibility environments, such as in severe glare due to direct sunlight or headlights or in low visibility environments, such as in severe fog or smoke.
{"title":"A Sensor Fusion System with Thermal Infrared Camera and LiDAR for Autonomous Vehicles: Its Calibration and Application","authors":"J. Choi, Min Young Kim","doi":"10.1109/ICUFN49451.2021.9528609","DOIUrl":"https://doi.org/10.1109/ICUFN49451.2021.9528609","url":null,"abstract":"Vision, Radar, and LiDAR sensors are widely used for autonomous vehicle perception technology. Especially object detection and classification are primarily dependent on vision sensors. However, under poor lighting conditions, dazzling sunlight, or bad weathers an object might be difficult to be identified with general vision sensors. In this paper, we propose a sensor fusion system with a thermal infrared camera and LiDAR sensor that can reliably detect and identify objects even in environments where visibility is poor, such as in severe glare and fog or smoke. The proposed method obtains intrinsic parameters by calibrating the thermal infrared camera and LiDAR sensor. Extrinsic calibration algorithm between two sensors is made to obtain the extrinsic parameters (rotation and translation matrix) using 3D calibration targets. This system and proposed algorithm show that it can reliably detect and identify objects even in hard visibility environments, such as in severe glare due to direct sunlight or headlights or in low visibility environments, such as in severe fog or smoke.","PeriodicalId":318542,"journal":{"name":"2021 Twelfth International Conference on Ubiquitous and Future Networks (ICUFN)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125460703","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：