Pub Date : 2014-10-02DOI: 10.1109/ELINFOCOM.2014.6914420
Kyung-Wook Park, Hyun-Ki Hong, Moohun Lee, Dong-Ho Lee
Multimedia contents with spam tags degrade the quality of the result of multimedia search. Therefore, the metadata related to the content are needed to improve the search results. This paper proposes an efficient multimedia annotation system that not only describes visual information by MPEG-7 visual descriptors but also semi-automatically generates the semantic information by using LSCOM ontology. Especially, we make use of the event-templates which predefine the relations among the events, characters and objects in scenes so that the users can easily create the scene metadata.
{"title":"Unified multimedia annotation system using MPEG-7 visual descriptors and semantic event-templates","authors":"Kyung-Wook Park, Hyun-Ki Hong, Moohun Lee, Dong-Ho Lee","doi":"10.1109/ELINFOCOM.2014.6914420","DOIUrl":"https://doi.org/10.1109/ELINFOCOM.2014.6914420","url":null,"abstract":"Multimedia contents with spam tags degrade the quality of the result of multimedia search. Therefore, the metadata related to the content are needed to improve the search results. This paper proposes an efficient multimedia annotation system that not only describes visual information by MPEG-7 visual descriptors but also semi-automatically generates the semantic information by using LSCOM ontology. Especially, we make use of the event-templates which predefine the relations among the events, characters and objects in scenes so that the users can easily create the scene metadata.","PeriodicalId":360207,"journal":{"name":"2014 International Conference on Electronics, Information and Communications (ICEIC)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132113585","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 : 2014-10-02DOI: 10.1109/ELINFOCOM.2014.6914401
A. Dersingh
Development of low cost, easy to install and unobtrusive sensing systems at home in monitoring human activities especially elderly people is an important trend in smart home technologies. This paper proposes the use of home network's information and information of events of a smartphone in determining human movement. The system architecture is illustrated for a scenario in monitoring movement of aging parents via smartphones.
{"title":"Human movement detection using home network information and events on smartphones","authors":"A. Dersingh","doi":"10.1109/ELINFOCOM.2014.6914401","DOIUrl":"https://doi.org/10.1109/ELINFOCOM.2014.6914401","url":null,"abstract":"Development of low cost, easy to install and unobtrusive sensing systems at home in monitoring human activities especially elderly people is an important trend in smart home technologies. This paper proposes the use of home network's information and information of events of a smartphone in determining human movement. The system architecture is illustrated for a scenario in monitoring movement of aging parents via smartphones.","PeriodicalId":360207,"journal":{"name":"2014 International Conference on Electronics, Information and Communications (ICEIC)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114055589","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 : 2014-10-02DOI: 10.1109/ELINFOCOM.2014.6914360
Hyunjun Kim, J. Kim, Jaihie Kim
This paper proposes an eye detection algorithm robust to head pose variation. First, face region is detected by Viola-Jones algorithm. Second, in order to detect eye robust to pose variation, a window template is generated from the 3D mean face model. Finally, eye is detected and localized by using this window template. In the experiments, the proposed method is tested on CAS-PEAL database.
{"title":"A pose adaptive eye detection method using 3D face information","authors":"Hyunjun Kim, J. Kim, Jaihie Kim","doi":"10.1109/ELINFOCOM.2014.6914360","DOIUrl":"https://doi.org/10.1109/ELINFOCOM.2014.6914360","url":null,"abstract":"This paper proposes an eye detection algorithm robust to head pose variation. First, face region is detected by Viola-Jones algorithm. Second, in order to detect eye robust to pose variation, a window template is generated from the 3D mean face model. Finally, eye is detected and localized by using this window template. In the experiments, the proposed method is tested on CAS-PEAL database.","PeriodicalId":360207,"journal":{"name":"2014 International Conference on Electronics, Information and Communications (ICEIC)","volume":"185 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114095465","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 : 2014-10-02DOI: 10.1109/ELINFOCOM.2014.6914380
Min Gu Kim, Sang Hyoung Lee, I. Suh
In Human-Robot Interaction, an intelligent robot should be able to learn social skills and reproduce such skills according to dynamic human's behaviors. To this end, both motion trajectories of a human and a robot are autonomously segmented, after which social skills are represented by combining hierarchical hidden Markov models and interaction dynamics (i.e., mass-spring-damper) to include three abilities of recognition, reproduction, and adaptation. To validate this, we present the experimental results when using a humanoid robot that performs several social skills.
{"title":"Learning of social skills for Human-Robot Interaction by hierarchical HMM and interaction dynamics","authors":"Min Gu Kim, Sang Hyoung Lee, I. Suh","doi":"10.1109/ELINFOCOM.2014.6914380","DOIUrl":"https://doi.org/10.1109/ELINFOCOM.2014.6914380","url":null,"abstract":"In Human-Robot Interaction, an intelligent robot should be able to learn social skills and reproduce such skills according to dynamic human's behaviors. To this end, both motion trajectories of a human and a robot are autonomously segmented, after which social skills are represented by combining hierarchical hidden Markov models and interaction dynamics (i.e., mass-spring-damper) to include three abilities of recognition, reproduction, and adaptation. To validate this, we present the experimental results when using a humanoid robot that performs several social skills.","PeriodicalId":360207,"journal":{"name":"2014 International Conference on Electronics, Information and Communications (ICEIC)","volume":"228 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114227399","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 : 2014-10-02DOI: 10.1109/ELINFOCOM.2014.6914446
Jae-Hyun Cho, Erdenetuya Tsogtbaatar, Seong-Hoon Kim, Young-Min Jang, Pham Minh Luan Nguyen, Sang-Bock Cho
Nowadays, due to the increasing need for using black boxes in vehicles, an evolving market is being created; that for example in South Korea, more than 1 million vehicles have been equipped with this device. In this paper, in order to improve the lane detection recognition via Hough transform, we improved the algorithm by set multi-ROI to reduce error rates and unrecognized part of the outside something as a lane. And we applied super-resolution reconstruction to correct the image. Through the proposed algorithm, proposed algorithm increase 0.6% of lane recognition rate and by setting multi-ROI irregular part of the road does not recognize so lane detection error rate was reduced significantly.
{"title":"Improved lane detection system using Hough transform with super-resolution reconstruction algorithm and multi-ROI","authors":"Jae-Hyun Cho, Erdenetuya Tsogtbaatar, Seong-Hoon Kim, Young-Min Jang, Pham Minh Luan Nguyen, Sang-Bock Cho","doi":"10.1109/ELINFOCOM.2014.6914446","DOIUrl":"https://doi.org/10.1109/ELINFOCOM.2014.6914446","url":null,"abstract":"Nowadays, due to the increasing need for using black boxes in vehicles, an evolving market is being created; that for example in South Korea, more than 1 million vehicles have been equipped with this device. In this paper, in order to improve the lane detection recognition via Hough transform, we improved the algorithm by set multi-ROI to reduce error rates and unrecognized part of the outside something as a lane. And we applied super-resolution reconstruction to correct the image. Through the proposed algorithm, proposed algorithm increase 0.6% of lane recognition rate and by setting multi-ROI irregular part of the road does not recognize so lane detection error rate was reduced significantly.","PeriodicalId":360207,"journal":{"name":"2014 International Conference on Electronics, Information and Communications (ICEIC)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124645777","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 : 2014-10-02DOI: 10.1109/ELINFOCOM.2014.6914382
N. S. Suriani, A. Hussain, M. A. Zulkifley
This paper affords a method for the automatic multi-agent event recognition (M-AER) of snatch theft event. M-AER is known to be difficult since parameters such as motion, background, appearance, illumination etc. are constantly changing. In this work, motion vector flow (MVF) and directional motion histogram (DMH) that capture the interaction between two persons in a video sequence are being proposed as input of the M-AER. Assuring result of 90% accuracy has been achieved for the snatch theft detection.
{"title":"Multi-agent event detection system using k-nearest neighbor classifier","authors":"N. S. Suriani, A. Hussain, M. A. Zulkifley","doi":"10.1109/ELINFOCOM.2014.6914382","DOIUrl":"https://doi.org/10.1109/ELINFOCOM.2014.6914382","url":null,"abstract":"This paper affords a method for the automatic multi-agent event recognition (M-AER) of snatch theft event. M-AER is known to be difficult since parameters such as motion, background, appearance, illumination etc. are constantly changing. In this work, motion vector flow (MVF) and directional motion histogram (DMH) that capture the interaction between two persons in a video sequence are being proposed as input of the M-AER. Assuring result of 90% accuracy has been achieved for the snatch theft detection.","PeriodicalId":360207,"journal":{"name":"2014 International Conference on Electronics, Information and Communications (ICEIC)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127827888","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 : 2014-10-02DOI: 10.1109/ELINFOCOM.2014.6914379
M. A. Zulkifley, A. Hussain, M. Mustafa, Aouache Mustapha
Optic disc segmentation is a crucial step in automated glaucoma detection system through Cup-to-Disc ratio measurement. Recent approaches focus on deterministic algorithm of RGB or grey model only. In this paper, we proposed a statistically integrated approach by combining various colour models. The driving motivation is the ability of each colour model to work accurately in certain environments or cases. Histogram of ach colour model of HSV, RGB and grey will be tabulated to approximate the colour distribution. The ratio between the highest and the second highest will be the contribution weightage of the fused output. The performance is simulated by using RIM-One database. The average sensitivity and specificity of the detection are 0.912 and 0.832 respectively.
{"title":"On analyzing optic disc extraction through weighted colour models","authors":"M. A. Zulkifley, A. Hussain, M. Mustafa, Aouache Mustapha","doi":"10.1109/ELINFOCOM.2014.6914379","DOIUrl":"https://doi.org/10.1109/ELINFOCOM.2014.6914379","url":null,"abstract":"Optic disc segmentation is a crucial step in automated glaucoma detection system through Cup-to-Disc ratio measurement. Recent approaches focus on deterministic algorithm of RGB or grey model only. In this paper, we proposed a statistically integrated approach by combining various colour models. The driving motivation is the ability of each colour model to work accurately in certain environments or cases. Histogram of ach colour model of HSV, RGB and grey will be tabulated to approximate the colour distribution. The ratio between the highest and the second highest will be the contribution weightage of the fused output. The performance is simulated by using RIM-One database. The average sensitivity and specificity of the detection are 0.912 and 0.832 respectively.","PeriodicalId":360207,"journal":{"name":"2014 International Conference on Electronics, Information and Communications (ICEIC)","volume":"203 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116176827","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 : 2014-10-02DOI: 10.1109/ELINFOCOM.2014.6914449
Kyeol Kwon, J. Tak, Jaehoon Choi
A textile circular patch antenna for wireless body area network is proposed. The proposed textile antenna has the radiation directed toward the surface of the human body in the 5.8 GHz industrial, scientific, medical band. In order to consider the practical situations, the numerical experiments were carried out on different body locations such as arm and chest of human.
{"title":"A practical study of textile TM01 mode circular patch antenna for wireless body area network applications","authors":"Kyeol Kwon, J. Tak, Jaehoon Choi","doi":"10.1109/ELINFOCOM.2014.6914449","DOIUrl":"https://doi.org/10.1109/ELINFOCOM.2014.6914449","url":null,"abstract":"A textile circular patch antenna for wireless body area network is proposed. The proposed textile antenna has the radiation directed toward the surface of the human body in the 5.8 GHz industrial, scientific, medical band. In order to consider the practical situations, the numerical experiments were carried out on different body locations such as arm and chest of human.","PeriodicalId":360207,"journal":{"name":"2014 International Conference on Electronics, Information and Communications (ICEIC)","volume":"81 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116342664","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 : 2014-10-02DOI: 10.1109/ELINFOCOM.2014.6914430
W. Bae, D. Jeong
A technique making the loop bandwidth consistent against PVT variations in the ring-VCO based bang-bang PLL/CDR is proposed. Pulse generators are used to implement this technique by cancelling out PVT sensitivity of the ring-VCO. Simulation results show that the loop bandwidth variation is reduced by half with the proposed technique. Also, by using the pulse generators, the loop filter capacitor area is reduced.
{"title":"A study on using pulse generators to design a ring-VCO based bang-bang PLL/CDR with a consistent loop bandwidth","authors":"W. Bae, D. Jeong","doi":"10.1109/ELINFOCOM.2014.6914430","DOIUrl":"https://doi.org/10.1109/ELINFOCOM.2014.6914430","url":null,"abstract":"A technique making the loop bandwidth consistent against PVT variations in the ring-VCO based bang-bang PLL/CDR is proposed. Pulse generators are used to implement this technique by cancelling out PVT sensitivity of the ring-VCO. Simulation results show that the loop bandwidth variation is reduced by half with the proposed technique. Also, by using the pulse generators, the loop filter capacitor area is reduced.","PeriodicalId":360207,"journal":{"name":"2014 International Conference on Electronics, Information and Communications (ICEIC)","volume":"340 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121606774","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 : 2014-10-02DOI: 10.1109/ELINFOCOM.2014.6914369
Huijeong Kim, Farhan Hussain, Sanghyuk Jung, Y. Song
Recently demand-based address mapping scheme for FTL is being widely used, but the existing schemes don't take spatial locality and miss penalty impact into consideration. In this paper, we propose a mapping table management scheme that solves the problems by simply changing the management unit.
{"title":"Management scheme of address mapping information for NAND storage system","authors":"Huijeong Kim, Farhan Hussain, Sanghyuk Jung, Y. Song","doi":"10.1109/ELINFOCOM.2014.6914369","DOIUrl":"https://doi.org/10.1109/ELINFOCOM.2014.6914369","url":null,"abstract":"Recently demand-based address mapping scheme for FTL is being widely used, but the existing schemes don't take spatial locality and miss penalty impact into consideration. In this paper, we propose a mapping table management scheme that solves the problems by simply changing the management unit.","PeriodicalId":360207,"journal":{"name":"2014 International Conference on Electronics, Information and Communications (ICEIC)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115232102","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：