发布求助
文献互助 智能选刊 最新文献

2022 IEEE International Conference on Consumer Electronics (ICCE)最新文献

筛选
英文 中文
People Removal Using Edge and Depth Information 使用边缘和深度信息的人物去除
2022 IEEE International Conference on Consumer Electronics (ICCE) Pub Date : 2022-01-07 DOI: 10.1109/ICCE53296.2022.9730122
Shunsuke Yae, M. Ikehara
{"title":"People Removal Using Edge and Depth Information","authors":"Shunsuke Yae, M. Ikehara","doi":"10.1109/ICCE53296.2022.9730122","DOIUrl":"https://doi.org/10.1109/ICCE53296.2022.9730122","url":null,"abstract":"In this paper, we propose a people removal method from a single image for privacy and other reasons using a three-stage network of depth estimation, semantic segmentation, and inpainting, as shown in Fig. 1. In this three-stage network, we improve semantic segmentation for detecting people. We focus on a special situation of a person and construct a network. It is known that the accuracy of conventional methods can be improved by using edge information. The accuracy of segmentation can be further improved by increasing the accuracy of the edge map. In addition, edge detection does not work well when the person and the background are of the similar color, because edge detects the brightness change of the image. Therefore, in this paper, an adversarial loss function for edge maps is proposed. In addition, since an image with people is expected to have a depth difference from the background image, we use a trained depth estimation network to include the depth image in the input. In this way, it is possible to construct a network for people removal with a high accuracy both quantitatively and qualitatively.","PeriodicalId":350644,"journal":{"name":"2022 IEEE International Conference on Consumer Electronics (ICCE)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121766064","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}
引用次数: 1
Bridging Fuzz Testing and Metamorphic Testing for Classification of Machine Learning 桥接模糊测试和变形测试用于机器学习分类
2022 IEEE International Conference on Consumer Electronics (ICCE) Pub Date : 2022-01-07 DOI: 10.1109/ICCE53296.2022.9730476
Dongsu Kang
{"title":"Bridging Fuzz Testing and Metamorphic Testing for Classification of Machine Learning","authors":"Dongsu Kang","doi":"10.1109/ICCE53296.2022.9730476","DOIUrl":"https://doi.org/10.1109/ICCE53296.2022.9730476","url":null,"abstract":"Artificial Intelligence (AI) built-in Consumer Electronics is popular, but it is hard to test and evaluate AI-based system with the existing performance metrics. Even though AI-based systems are implemented in software with flexibility, bias and non-determinism property etc., they can suffer the same defects as other software. That is why new software testing approaches are needed when testing AI-based systems. Therefore, this paper proposes a bridging approach between fuzz testing and metamorphic testing focus on the classification of machine learning. This approach can be used as a test oracle for classification of training data.","PeriodicalId":350644,"journal":{"name":"2022 IEEE International Conference on Consumer Electronics (ICCE)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122178659","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}
引用次数: 0
3D LiDAR Automatic Driving Environment Detection System Based on MobileNetv3-YOLOv4 基于MobileNetv3-YOLOv4的三维激光雷达自动驾驶环境检测系统
2022 IEEE International Conference on Consumer Electronics (ICCE) Pub Date : 2022-01-07 DOI: 10.1109/ICCE53296.2022.9730329
Ting-Wei Chen, Mingfeng Lu, Wei-Zhe Yan, Yunqi Fan
{"title":"3D LiDAR Automatic Driving Environment Detection System Based on MobileNetv3-YOLOv4","authors":"Ting-Wei Chen, Mingfeng Lu, Wei-Zhe Yan, Yunqi Fan","doi":"10.1109/ICCE53296.2022.9730329","DOIUrl":"https://doi.org/10.1109/ICCE53296.2022.9730329","url":null,"abstract":"In this paper, we proposed 3D LiDAR Automatic Driving Environment Detection System Based on MobileNetv3-YOLOv4. In recent years, artificial intelligence and automatic driving technology have developed very rapidly. Automatic driving has the advantages of law-abiding and fast response, which can significantly reduce driver and passenger casualties. However, due to the large number of parameters and complexity of most object detection neural networks, the computation time required is huge. To solve this problem, this paper applies the lightweight technique of Mobilenetv3 to significantly improve the original object detection neural network, and finds the region of interest by using point cloud de-grounding and clustering algorithms. The data from the region of interest is fed into the Mobilenetv3-YOLOv4 neural network for detection to perform the high accuracy of object detection.","PeriodicalId":350644,"journal":{"name":"2022 IEEE International Conference on Consumer Electronics (ICCE)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129443968","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}
引用次数: 2
Detecting Hardcoded Login Information from User Input 从用户输入检测硬编码登录信息
2022 IEEE International Conference on Consumer Electronics (ICCE) Pub Date : 2022-01-07 DOI: 10.1109/ICCE53296.2022.9730410
Minami Yoda, Shuji Sakuraba, Y. Sei, Yasuyuki Tahara, Akihiko Ohsuga
{"title":"Detecting Hardcoded Login Information from User Input","authors":"Minami Yoda, Shuji Sakuraba, Y. Sei, Yasuyuki Tahara, Akihiko Ohsuga","doi":"10.1109/ICCE53296.2022.9730410","DOIUrl":"https://doi.org/10.1109/ICCE53296.2022.9730410","url":null,"abstract":"Internet of Things (IoT) for smart homes provides high levels of convenience, but it introduces the risk of private data leakage. There were reports in 2020 of some firmware containing hardcoded login information that allows anyone to access the firmware via the Internet. According to OWASP 2018, the most common IoT vulnerability is “weak, guessable, or hardcoded passwords. “ In this paper, we proposed a method for detecting hardcoded login information (username and password) in IoT devices using static analysis with a focus on the user input value. An attacker enters values when attempting to log into IoT devices. As a result, we believe that tracing user input value is an effective method for detecting hardcoded login information. To the best of our knowledge, our method is the first method focusing on user input. This method is also effective to protect from the first vulnerability from the OWASP's ranking. We tested the method's capability by searching six real-world firmware files that contained hardcoded login information. The results showed that the method found the target information within a smaller candidate list than the previous study, implying that our method is more accurate than other searches.","PeriodicalId":350644,"journal":{"name":"2022 IEEE International Conference on Consumer Electronics (ICCE)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131195117","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}
引用次数: 0
Efficient Convolutional Neural Network Accelerator Based on Systolic Array 基于收缩阵列的高效卷积神经网络加速器
2022 IEEE International Conference on Consumer Electronics (ICCE) Pub Date : 2022-01-07 DOI: 10.1109/ICCE53296.2022.9730180
Yeong-Kang Lai, Yu-Jen Tsai
{"title":"Efficient Convolutional Neural Network Accelerator Based on Systolic Array","authors":"Yeong-Kang Lai, Yu-Jen Tsai","doi":"10.1109/ICCE53296.2022.9730180","DOIUrl":"https://doi.org/10.1109/ICCE53296.2022.9730180","url":null,"abstract":"This paper uses 72 PE as the basis for convolution operations, which can handle 3 x 3 and 1 x 1 filter sizes. Moreover, using the Systolic Array design architecture, the data reuse of this architecture is better than general PE architecture. Systolic Array architecture only needs to access once. This paper integrates Convolution and Max Pooling. This hardware verifies on Xilinx ZCU102 FPGA board. The hardware uses quantized weight parameters, and the hardware arithmetic precision is UINT8. The operation frequency sets at 100 MHz, throughput can reach 14.4 GOPs. The efficiency is 98.90%, the bandwidth is 150.82 MB, and Convolution integrates Max-Pooling to save 31.75% of DRAM access. In the future, the Operation Frequency can increase to more than 200 MHZ. The increase in the number of PEs can enhance the efficiency of parallel operations, which can effectively improve the throughput of the hardware.","PeriodicalId":350644,"journal":{"name":"2022 IEEE International Conference on Consumer Electronics (ICCE)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121322019","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}
引用次数: 0
Improvement of Object Segmentation Accuracy in Aerial Images 航空图像中目标分割精度的提高
2022 IEEE International Conference on Consumer Electronics (ICCE) Pub Date : 2022-01-07 DOI: 10.1109/ICCE53296.2022.9730543
Sujong Kim, YunSung Han, Soobin Jeon, D. Seo
{"title":"Improvement of Object Segmentation Accuracy in Aerial Images","authors":"Sujong Kim, YunSung Han, Soobin Jeon, D. Seo","doi":"10.1109/ICCE53296.2022.9730543","DOIUrl":"https://doi.org/10.1109/ICCE53296.2022.9730543","url":null,"abstract":"With recent advances in UAV technology, research-based on UAV images is underway. UAVs can easily access places that are difficult for people to access and take a wide range of target areas. However, UAV images taken at high altitudes using a drone have object images with a tiny size in the entire background image, resulting in a more significant area error in the area of the detected objects. This paper proposes an accurate area measurement algorithm within an object based on image processing. Also, we evaluated the proposed algorithm by implementing it. The experimental results show that the average duplicate error rate decreased by 14% compared to mask instance segmentation. Finally, the proposed algorithm can more accurately extract small potholes in the images taken at high altitudes.","PeriodicalId":350644,"journal":{"name":"2022 IEEE International Conference on Consumer Electronics (ICCE)","volume":"122 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116472538","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}
引用次数: 0
Design and Implementation of a Smart Air Quality Monitoring and Purifying System for the School Environment 为学校环境设计及实施智能空气质素监测及净化系统
2022 IEEE International Conference on Consumer Electronics (ICCE) Pub Date : 2022-01-07 DOI: 10.1109/ICCE53296.2022.9730505
Hyuntae Cho, Yunju Baek
{"title":"Design and Implementation of a Smart Air Quality Monitoring and Purifying System for the School Environment","authors":"Hyuntae Cho, Yunju Baek","doi":"10.1109/ICCE53296.2022.9730505","DOIUrl":"https://doi.org/10.1109/ICCE53296.2022.9730505","url":null,"abstract":"Students and teachers are exposed to harmful materials in the school where the students generate dusts when playing during the break time. Despite most schools adopting air purifiers in the classroom, the capability of the air purifier is not enough compared to natural ventilation. Therefore, this study proposed a smart air quality monitoring and purifying system for the school environment. The system consists of an outdoor air quality monitoring system, indoor air purifiers, and a server program running on PC. The proposed system allows teachers and students to choose when to use the air purifier or natural ventilation by comparing outdoor air quality and indoor air quality. In addition, the proposed air purifier system includes an intelligent operation that controls the speed of the fan and blower to make sure it does not generate noise that interfere with students in class. This paper also includes the performance evaluation of the air quality monitoring system. As a result, the system has less error than approximately 15% from the reference instrument.","PeriodicalId":350644,"journal":{"name":"2022 IEEE International Conference on Consumer Electronics (ICCE)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126789998","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}
引用次数: 2
Physical Security Using Machine Learning to Detect Lock Picking at Traffic Cabinets 使用机器学习检测交通柜开锁的物理安全
2022 IEEE International Conference on Consumer Electronics (ICCE) Pub Date : 2022-01-07 DOI: 10.1109/ICCE53296.2022.9730555
Hannon Shepard, Michael Young, Billy Kihei
{"title":"Physical Security Using Machine Learning to Detect Lock Picking at Traffic Cabinets","authors":"Hannon Shepard, Michael Young, Billy Kihei","doi":"10.1109/ICCE53296.2022.9730555","DOIUrl":"https://doi.org/10.1109/ICCE53296.2022.9730555","url":null,"abstract":"Traffic systems are filled with essential traffic control equipment and can cause massive infrastructural damage and driver safety if hacked. We explore a machine learning method to detect real-time lock picking to thwart unauthorized access to the electronics. We gather accelerometer and gyroscopic data to train a decision tree model for detecting lock picking. Analysis reveals that a standard deviation feature for only two accelerometer axes is adequate for achieving robust performance. We deployed an real-time decision tree model to an offsite test cabinet that achieves an accuracy of over 95 %.","PeriodicalId":350644,"journal":{"name":"2022 IEEE International Conference on Consumer Electronics (ICCE)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126402515","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}
引用次数: 0
Contact Accident Prevention System around Snowplows utilizing LiDAR and Machine Learning Technologies 利用激光雷达和机器学习技术联系扫雪机周围的事故预防系统
2022 IEEE International Conference on Consumer Electronics (ICCE) Pub Date : 2022-01-07 DOI: 10.1109/ICCE53296.2022.9730133
Kohei Omachi, Hiroshi Yamamoto, Y. Kitatsuji
{"title":"Contact Accident Prevention System around Snowplows utilizing LiDAR and Machine Learning Technologies","authors":"Kohei Omachi, Hiroshi Yamamoto, Y. Kitatsuji","doi":"10.1109/ICCE53296.2022.9730133","DOIUrl":"https://doi.org/10.1109/ICCE53296.2022.9730133","url":null,"abstract":"In heavy snowfall areas, the snow removal work by snowplows plays a significant role in securing transportation for local residents. However, there are many pedestrians and cars approaching the snowplows unintentionally, and the snowplow operators should pay attention to avoid the contact accidents with them, which reduces the efficiency of the snow removal work. As a result, it takes a long time to clean the road to keep the safe and secure life of local residents. Therefore, in this study, we develop a new contact accident prevention system around snowplows that detects pedestrians and cars approaching snowplows and notifies the snowplow operator in real-time. In this system, the sensor node installed on the snowplow analyzes the 3D point cloud data obtained by the LiDAR (Light Detection and Ranging) to detect the existence of the pedestrians/cars around the snowplow and notifies the snowplow operator of the results in real-time. In addition, the proposed system adopts the system structure of edge computing so that the system can be used in environments where high-speed mobile communications are not available (e.g., mountainous areas) and the system cannot leverage computing resources on the Internet. Furthermore, a machine learning method is utilized for quickly detecting pedestrians and cars with high accuracy from the 3D point cloud data obtained by the LiDAR.","PeriodicalId":350644,"journal":{"name":"2022 IEEE International Conference on Consumer Electronics (ICCE)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127899521","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}
引用次数: 0
Partial Offloading MEC Optimization Scheme using Deep Reinforcement Learning for XR Real-Time M&S Devices 基于深度强化学习的XR实时M&S设备部分卸载MEC优化方案
2022 IEEE International Conference on Consumer Electronics (ICCE) Pub Date : 2022-01-07 DOI: 10.1109/ICCE53296.2022.9730284
Yunyeong Goh, Minsu Choi, Jaewook Jung, Jong‐Moon Chung
{"title":"Partial Offloading MEC Optimization Scheme using Deep Reinforcement Learning for XR Real-Time M&S Devices","authors":"Yunyeong Goh, Minsu Choi, Jaewook Jung, Jong‐Moon Chung","doi":"10.1109/ICCE53296.2022.9730284","DOIUrl":"https://doi.org/10.1109/ICCE53296.2022.9730284","url":null,"abstract":"With the advent of 5G, the development of extended reality (XR) technology, which combines augmented reality (AR), virtual reality (VR), and advanced human-computer interaction (HCI) technology, is considered one of the key technologies of future metaverse engineering. Especially, XR real-time modeling and simulation (M&S) devices that can be applied to various fields (e.g., emergency training simulations, etc.) have tasks with large amounts of data to be processed. However, if the XR task is processed only by wireless user equipment (UE), the UE's energy may be quickly depleted, and the quality of service (QoS) may not be satisfied. To solve these problems, this paper proposes a partial offloading optimization scheme through multiple access edge computing (MEC). In addition, deep reinforcement learning (DRL) is used to reflect the dynamic state of the MEC system and to minimize the delay. The simulation results show that the proposed scheme optimizes the delay performance by efficiently offloading the XR tasks.","PeriodicalId":350644,"journal":{"name":"2022 IEEE International Conference on Consumer Electronics (ICCE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127706679","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}
引用次数: 2
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：481959085
Book学术官方微信