Pub Date : 2014-10-01DOI: 10.1109/GCCE.2014.7031315
Zhi Jin, T. Tillo, Fei Cheng
This paper proposes an unsupervised technique for detecting planar surfaces on single depth map image. The proposed method can detect planar surfaces by adopting dynamic seed growing technique without using texture information. So aided with this mechanism to control the growing process, each seed patch can grow to its maximum extent and then the next seed patch begins to grow. This process avoids over-segmentation of the whole scene. Moreover, it allows detecting semi-planer surfaces. Compared with one popular planar surface detection algorithms, i.e., RANdom SAmples Consensus(RANSAC), the accuracy of the proposed method is superior on typical indoor scenes. The proposed method can have huge technical potential for image/video segmentation and coding, enhancing the depth information of time-of-flight cameras, and finally it could be used for navigation system for humanoid robotics.
{"title":"Planar surfaces detection on depth map using patch based approach","authors":"Zhi Jin, T. Tillo, Fei Cheng","doi":"10.1109/GCCE.2014.7031315","DOIUrl":"https://doi.org/10.1109/GCCE.2014.7031315","url":null,"abstract":"This paper proposes an unsupervised technique for detecting planar surfaces on single depth map image. The proposed method can detect planar surfaces by adopting dynamic seed growing technique without using texture information. So aided with this mechanism to control the growing process, each seed patch can grow to its maximum extent and then the next seed patch begins to grow. This process avoids over-segmentation of the whole scene. Moreover, it allows detecting semi-planer surfaces. Compared with one popular planar surface detection algorithms, i.e., RANdom SAmples Consensus(RANSAC), the accuracy of the proposed method is superior on typical indoor scenes. The proposed method can have huge technical potential for image/video segmentation and coding, enhancing the depth information of time-of-flight cameras, and finally it could be used for navigation system for humanoid robotics.","PeriodicalId":145771,"journal":{"name":"2014 IEEE 3rd Global Conference on Consumer Electronics (GCCE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124204998","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 : 2014-10-01DOI: 10.1109/GCCE.2014.7031162
Shih-Han Hsu, Hsu-Yung Cheng, Chih-Chang Yu
This work proposes a gesture-based left and right hand recognition algorithm for dynamic interface adjustment by using the information of the accelerometer and the touch screen on a mobile device. We design a warping method that aligns accelerometer signals with their corresponding positions of unlock-screen gestures. By projecting samples onto feature space and using a support vector machine classifier, the proposed method yields high recognition accuracy. The experiments also show that the proposed method is able to make correct decisions for a new user without pre-gathering information from the user.
{"title":"Classification of holding hand for dynamic interface adjustment on mobile devices","authors":"Shih-Han Hsu, Hsu-Yung Cheng, Chih-Chang Yu","doi":"10.1109/GCCE.2014.7031162","DOIUrl":"https://doi.org/10.1109/GCCE.2014.7031162","url":null,"abstract":"This work proposes a gesture-based left and right hand recognition algorithm for dynamic interface adjustment by using the information of the accelerometer and the touch screen on a mobile device. We design a warping method that aligns accelerometer signals with their corresponding positions of unlock-screen gestures. By projecting samples onto feature space and using a support vector machine classifier, the proposed method yields high recognition accuracy. The experiments also show that the proposed method is able to make correct decisions for a new user without pre-gathering information from the user.","PeriodicalId":145771,"journal":{"name":"2014 IEEE 3rd Global Conference on Consumer Electronics (GCCE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123380797","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 : 2014-10-01DOI: 10.1109/GCCE.2014.7031175
K. Mano, Kazuhiro Minami, H. Maruyama
Anonymization is a common technique for publishing a location data set in a privacy-preserving way. However, such an anonymized data set lacks trajectory information of users, which could be beneficial to many location-based analytic services. In this paper, we present a dynamic pseudonym scheme for constructing alternate possible paths of mobile users to protect their location privacy. We introduce a formal definition of location privacy for pseudonym-based location data sets and develop a polynomial-time verification algorithm for determining whether each user in a given location data set has sufficient number of possible paths to disguise the user's true movements. We also provide the correctness proof of the algorithm.
{"title":"Pseudonym exchange for privacy-preserving publishing of trajectory data set","authors":"K. Mano, Kazuhiro Minami, H. Maruyama","doi":"10.1109/GCCE.2014.7031175","DOIUrl":"https://doi.org/10.1109/GCCE.2014.7031175","url":null,"abstract":"Anonymization is a common technique for publishing a location data set in a privacy-preserving way. However, such an anonymized data set lacks trajectory information of users, which could be beneficial to many location-based analytic services. In this paper, we present a dynamic pseudonym scheme for constructing alternate possible paths of mobile users to protect their location privacy. We introduce a formal definition of location privacy for pseudonym-based location data sets and develop a polynomial-time verification algorithm for determining whether each user in a given location data set has sufficient number of possible paths to disguise the user's true movements. We also provide the correctness proof of the algorithm.","PeriodicalId":145771,"journal":{"name":"2014 IEEE 3rd Global Conference on Consumer Electronics (GCCE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114210043","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 : 2014-10-01DOI: 10.1109/GCCE.2014.7031312
M. Iwaki, Y. Yano, Yoshiki Chigira
We investigated the perceived direction of the arrival of sound using bone-conduction headphones. Sounds were separately presented through air-conduction headphones or bone-conduction headphones in a series of experiments and participants judged the direction of arrival. The perceived direction through the bone-conduction headphones inclined toward the center. We propose a design concept to compensate for this discrepancy of the perceived direction of arrival for hearing aids.
{"title":"Measurement and adjustment methods of sound source direction perceived through bone-conduction headphones","authors":"M. Iwaki, Y. Yano, Yoshiki Chigira","doi":"10.1109/GCCE.2014.7031312","DOIUrl":"https://doi.org/10.1109/GCCE.2014.7031312","url":null,"abstract":"We investigated the perceived direction of the arrival of sound using bone-conduction headphones. Sounds were separately presented through air-conduction headphones or bone-conduction headphones in a series of experiments and participants judged the direction of arrival. The perceived direction through the bone-conduction headphones inclined toward the center. We propose a design concept to compensate for this discrepancy of the perceived direction of arrival for hearing aids.","PeriodicalId":145771,"journal":{"name":"2014 IEEE 3rd Global Conference on Consumer Electronics (GCCE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116177832","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 : 2014-10-01DOI: 10.1109/GCCE.2014.7031143
T. Muraoka, H. Ikeda
Visual strain will be caused by PC operations for a long time a day, which might fail health of human eyes if it continues a week or more. Any action to check it by oneself needs to be done every time PC operations are continued for a multiple of hours. We propose a visual fatigue checker to simply test the fatigue of human eyes and to help us to resume visual health from the fatigue, if any, with some expected recovery time.
{"title":"Visual fatigue checker for keeping eyes healthy -to test visual strain caused by PC operations-","authors":"T. Muraoka, H. Ikeda","doi":"10.1109/GCCE.2014.7031143","DOIUrl":"https://doi.org/10.1109/GCCE.2014.7031143","url":null,"abstract":"Visual strain will be caused by PC operations for a long time a day, which might fail health of human eyes if it continues a week or more. Any action to check it by oneself needs to be done every time PC operations are continued for a multiple of hours. We propose a visual fatigue checker to simply test the fatigue of human eyes and to help us to resume visual health from the fatigue, if any, with some expected recovery time.","PeriodicalId":145771,"journal":{"name":"2014 IEEE 3rd Global Conference on Consumer Electronics (GCCE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124123043","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 : 2014-10-01DOI: 10.1109/GCCE.2014.7031121
T. Mizoguchi, Yoshihiro Ito
This paper assesses influence of QoS degradation caused by 6to4 and IPsec on QoE of Web services by experiment. Since utilization of 6to4 and IPsec requires some overheads, QoS degradation caused by them is inevitable. The degradation can also deteriorate QoE of the Web service, but the affect of the degradation has not been clarified. From the experimental results, the authors confirm QoS degradation but see little QoE deterioration. This implies 6to4 and IPSec are usable from a user's point of view.
{"title":"Effect of QoS degradation caused by 6to4 and IPsec on QoE for Web services","authors":"T. Mizoguchi, Yoshihiro Ito","doi":"10.1109/GCCE.2014.7031121","DOIUrl":"https://doi.org/10.1109/GCCE.2014.7031121","url":null,"abstract":"This paper assesses influence of QoS degradation caused by 6to4 and IPsec on QoE of Web services by experiment. Since utilization of 6to4 and IPsec requires some overheads, QoS degradation caused by them is inevitable. The degradation can also deteriorate QoE of the Web service, but the affect of the degradation has not been clarified. From the experimental results, the authors confirm QoS degradation but see little QoE deterioration. This implies 6to4 and IPSec are usable from a user's point of view.","PeriodicalId":145771,"journal":{"name":"2014 IEEE 3rd Global Conference on Consumer Electronics (GCCE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130278402","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 : 2014-10-01DOI: 10.1109/GCCE.2014.7031342
Cláudio H. A. Rodrigues, Eliel de Lima Reis, V. Lucena
This paper describes a proposal for a Second Screen solution designed for the Brazilian Digital Television System - SBTVD. Our solution allows users to access and to interact with additional content related to the broadcasted program through the internet (synchronously with the content displayed on digital TV screen). The proposed architecture makes use of a specific protocol, the Transmission Transport Stream. It will carry the information needed to allow receivers of digital TV to communicate with multiple Second Screen devices relying nearby (such as smartphones, tablets, and PDAs). These devices must be running a dedicated software application in order to connect to the World Wide Web accessing the desired additional information. The motivation for this work is to bring to users with limited resources, the ones watching broadcasted over the air programs, the opportunity to benefit from the Second Screen technology. These users, in possession of our Second Screen mobile application will be able to access additional information synchronized with the programs live broadcasted, opening new opportunities for broadcaster and users.
{"title":"Second Screen prototype for broadcasted digital TV users in ISDB-Tb standard","authors":"Cláudio H. A. Rodrigues, Eliel de Lima Reis, V. Lucena","doi":"10.1109/GCCE.2014.7031342","DOIUrl":"https://doi.org/10.1109/GCCE.2014.7031342","url":null,"abstract":"This paper describes a proposal for a Second Screen solution designed for the Brazilian Digital Television System - SBTVD. Our solution allows users to access and to interact with additional content related to the broadcasted program through the internet (synchronously with the content displayed on digital TV screen). The proposed architecture makes use of a specific protocol, the Transmission Transport Stream. It will carry the information needed to allow receivers of digital TV to communicate with multiple Second Screen devices relying nearby (such as smartphones, tablets, and PDAs). These devices must be running a dedicated software application in order to connect to the World Wide Web accessing the desired additional information. The motivation for this work is to bring to users with limited resources, the ones watching broadcasted over the air programs, the opportunity to benefit from the Second Screen technology. These users, in possession of our Second Screen mobile application will be able to access additional information synchronized with the programs live broadcasted, opening new opportunities for broadcaster and users.","PeriodicalId":145771,"journal":{"name":"2014 IEEE 3rd Global Conference on Consumer Electronics (GCCE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134205224","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}
Depth from Defocus (DFD) is known as the technology which is able to estimate depth in the scene by a monocular camera without any additive devices. Using this advantage of DFD, we improved the speed of Auto Focus (AF). To apply DFD to AF, it is necessary to capture 2 images that have a small amount of “difference in focal positions” (we call DiFP). In this paper, we show the performance of the depth estimation when the DiFP is changed, and verify that Low Pass Filter is a good solution to get robust depth.
散焦深度(Depth from Defocus, DFD)是一种无需任何附加设备就能通过单目相机估算场景深度的技术。利用DFD的这个优势,我们提高了自动对焦(AF)的速度。为了将DFD应用于自动对焦,有必要捕获2张有少量“焦位差异”的图像(我们称之为DiFP)。在本文中,我们展示了当DiFP改变时深度估计的性能,并验证了低通滤波器是获得鲁棒深度的良好解决方案。
{"title":"Depth from Defocus applied to Auto Focus","authors":"Shunsuke Yasugi, Khang Nguyen, Kozo Ezawa, Takashi Kawamura","doi":"10.1109/GCCE.2014.7031237","DOIUrl":"https://doi.org/10.1109/GCCE.2014.7031237","url":null,"abstract":"Depth from Defocus (DFD) is known as the technology which is able to estimate depth in the scene by a monocular camera without any additive devices. Using this advantage of DFD, we improved the speed of Auto Focus (AF). To apply DFD to AF, it is necessary to capture 2 images that have a small amount of “difference in focal positions” (we call DiFP). In this paper, we show the performance of the depth estimation when the DiFP is changed, and verify that Low Pass Filter is a good solution to get robust depth.","PeriodicalId":145771,"journal":{"name":"2014 IEEE 3rd Global Conference on Consumer Electronics (GCCE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131473467","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 : 2014-10-01DOI: 10.1109/GCCE.2014.7031316
Akinobu Ando, Shota Itagaki, Hidetoshi Takeno, T. Torii, Darold Davis
In this study, we developed a Multiple Skill Practice Management and results feedback System - sawing and planning. The system can be used for a beginner's vocational learning. Using this system, learners are able to meta-recognize their own skills without a teacher. This system consists of two parts; learners' motion sensing part by using smartphones, and store and visualization part of the data. Smartphones are attached to the learner's body or a tool. In order to investigate the learner's motion, three axis acceleration sensors and three axis gyro sensors equipped in the smartphones are used. Using the system, learners as well as teachers can grasp how they used a tool and how they moved their body as feedback from result of their own practice. In the visualization part, their results display at same time using various charts and table; line graphs, a radar chart, and numerical data in a table. Our system could decrease a teacher's work load to teach and students could improve their skill without a teacher.
{"title":"Development a Multiple Skill Practice Management and result feedback System for “Smart Vocational Learning” by using smartphones","authors":"Akinobu Ando, Shota Itagaki, Hidetoshi Takeno, T. Torii, Darold Davis","doi":"10.1109/GCCE.2014.7031316","DOIUrl":"https://doi.org/10.1109/GCCE.2014.7031316","url":null,"abstract":"In this study, we developed a Multiple Skill Practice Management and results feedback System - sawing and planning. The system can be used for a beginner's vocational learning. Using this system, learners are able to meta-recognize their own skills without a teacher. This system consists of two parts; learners' motion sensing part by using smartphones, and store and visualization part of the data. Smartphones are attached to the learner's body or a tool. In order to investigate the learner's motion, three axis acceleration sensors and three axis gyro sensors equipped in the smartphones are used. Using the system, learners as well as teachers can grasp how they used a tool and how they moved their body as feedback from result of their own practice. In the visualization part, their results display at same time using various charts and table; line graphs, a radar chart, and numerical data in a table. Our system could decrease a teacher's work load to teach and students could improve their skill without a teacher.","PeriodicalId":145771,"journal":{"name":"2014 IEEE 3rd Global Conference on Consumer Electronics (GCCE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131507696","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 : 2014-10-01DOI: 10.1109/GCCE.2014.7031250
Noriko Akazawa, Kai Yawata, Dan Takeda, Yasuichi Nakayama, Hiroyasu Kakuda, Mitsugu Suzuki
The use of information devices in educational settings has been increasing over the years. We propose a learning support system that is an expansion of the original Kinect system. The proposed expansion has been implemented using the Kinect motion capture system to recognize “air characters” written by the body actions of learners and is used in this study for practicing Japanese letters expressed in Romaji by a combination of alphabets. We believe that students can have fun with learning by performing body actions, thus keeping their motivation to learn high. We had some elementary school students operate the system and then evaluated the results.
{"title":"A playing and learning support system using Kinect for Romaji","authors":"Noriko Akazawa, Kai Yawata, Dan Takeda, Yasuichi Nakayama, Hiroyasu Kakuda, Mitsugu Suzuki","doi":"10.1109/GCCE.2014.7031250","DOIUrl":"https://doi.org/10.1109/GCCE.2014.7031250","url":null,"abstract":"The use of information devices in educational settings has been increasing over the years. We propose a learning support system that is an expansion of the original Kinect system. The proposed expansion has been implemented using the Kinect motion capture system to recognize “air characters” written by the body actions of learners and is used in this study for practicing Japanese letters expressed in Romaji by a combination of alphabets. We believe that students can have fun with learning by performing body actions, thus keeping their motivation to learn high. We had some elementary school students operate the system and then evaluated the results.","PeriodicalId":145771,"journal":{"name":"2014 IEEE 3rd Global Conference on Consumer Electronics (GCCE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130834241","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}