Pub Date : 2018-07-09DOI: 10.1109/ISCE.2018.8408908
Shen-Ho Liu, Yin-Tien Wang, C. Hsu, Wei-Yen Wang, Chiang-Heng Chien
A feature-based visual robot localization algorithm is generally responsible for estimating the robot pose based on features from images using cameras. To address the issues of estimation accuracy and required computational time, an improved visual odometry (VO) system is proposed using direct approach of perspective-3-point (P3P) algorithm as well as map management method. Furthermore, a GUI platform is designed using MATLAB so that performances of the proposed VO system can be easily observed by users. In order to validate the reliability of the proposed system, various experiments are conducted using a binocular camera, where experimental results show that the proposed VO system outperforms conventional algorithms in terms of estimation accuracy and runtime efficiency.
{"title":"Using MATLAB as auxiliary tool in visual localization for mobile robots","authors":"Shen-Ho Liu, Yin-Tien Wang, C. Hsu, Wei-Yen Wang, Chiang-Heng Chien","doi":"10.1109/ISCE.2018.8408908","DOIUrl":"https://doi.org/10.1109/ISCE.2018.8408908","url":null,"abstract":"A feature-based visual robot localization algorithm is generally responsible for estimating the robot pose based on features from images using cameras. To address the issues of estimation accuracy and required computational time, an improved visual odometry (VO) system is proposed using direct approach of perspective-3-point (P3P) algorithm as well as map management method. Furthermore, a GUI platform is designed using MATLAB so that performances of the proposed VO system can be easily observed by users. In order to validate the reliability of the proposed system, various experiments are conducted using a binocular camera, where experimental results show that the proposed VO system outperforms conventional algorithms in terms of estimation accuracy and runtime efficiency.","PeriodicalId":114660,"journal":{"name":"2018 International Symposium on Consumer Technologies (ISCT)","volume":"259 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132825161","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 : 2018-07-09DOI: 10.1109/ISCE.2018.8408907
W. Kao, Kuan-Jen Huang, Yi-Chin Chiu, Ming-Yang Hung, Chun-Wei Shen
On the whole, it would not be an enjoyable experience to read documents on cellular phones or electronic readers with their tiny size of the screen. Namely, to view the entire content, the user may need to keep scrolling up and down and resizing the content manually. Thanks to the advances of gaze tracker development, which have made potential to integrate the function of gaze tracking and automatic image magnification function on the reader to improve the user experiences. In this paper, we present a new tool that detects the user gaze point on the screen and resize the local image to improve the visibility. The tool integrates a visible-spectrum gaze tracker, fixation/saccade analyzer, and image magnifier. In order to further upgrade the user experience, a new motion scheme of the viewing window has been proposed and the system meets the real-time requirement for the application.
{"title":"Real-time image magnifier with visible-spectrum gaze tracker","authors":"W. Kao, Kuan-Jen Huang, Yi-Chin Chiu, Ming-Yang Hung, Chun-Wei Shen","doi":"10.1109/ISCE.2018.8408907","DOIUrl":"https://doi.org/10.1109/ISCE.2018.8408907","url":null,"abstract":"On the whole, it would not be an enjoyable experience to read documents on cellular phones or electronic readers with their tiny size of the screen. Namely, to view the entire content, the user may need to keep scrolling up and down and resizing the content manually. Thanks to the advances of gaze tracker development, which have made potential to integrate the function of gaze tracking and automatic image magnification function on the reader to improve the user experiences. In this paper, we present a new tool that detects the user gaze point on the screen and resize the local image to improve the visibility. The tool integrates a visible-spectrum gaze tracker, fixation/saccade analyzer, and image magnifier. In order to further upgrade the user experience, a new motion scheme of the viewing window has been proposed and the system meets the real-time requirement for the application.","PeriodicalId":114660,"journal":{"name":"2018 International Symposium on Consumer Technologies (ISCT)","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134446266","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 : 2018-05-11DOI: 10.1109/ISCE.2018.8408911
Sheharyar Khan, Ahmad Farhan Latif, S. Sohaib
The existing power generation sources are unable to meet the hyper escalating electricity demand. Common solution is to install new generation plants to fulfill the electricity demand which it is not cost-effective. A cheap and effective solution is to monitor all the appliances running inside a building and to use them efficiently. Non-intrusive load monitoring (NILM) is one of the economical techniques to identify the appliances on the basis of their unique load signatures. In this paper, a machine learning based technique is presented to identify the devices for monitoring purposes. A low-cost hardware setup, called Appliance Identification and Management System (AIMS) is developed to identify and control the appliances remotely. The appliance identification algorithm is developed in Python and deployed on Raspberry Pi, coupled with Arduino. The hardware setup furnishes consumers with the real-time status of all home appliances on their smartphone and web server. Controlling module is also integrated with the identification hardware to provide smart access to consumer for the remote control of home appliances.
{"title":"Low-cost real-time non-intrusive appliance identification and controlling through machine learning algorithm","authors":"Sheharyar Khan, Ahmad Farhan Latif, S. Sohaib","doi":"10.1109/ISCE.2018.8408911","DOIUrl":"https://doi.org/10.1109/ISCE.2018.8408911","url":null,"abstract":"The existing power generation sources are unable to meet the hyper escalating electricity demand. Common solution is to install new generation plants to fulfill the electricity demand which it is not cost-effective. A cheap and effective solution is to monitor all the appliances running inside a building and to use them efficiently. Non-intrusive load monitoring (NILM) is one of the economical techniques to identify the appliances on the basis of their unique load signatures. In this paper, a machine learning based technique is presented to identify the devices for monitoring purposes. A low-cost hardware setup, called Appliance Identification and Management System (AIMS) is developed to identify and control the appliances remotely. The appliance identification algorithm is developed in Python and deployed on Raspberry Pi, coupled with Arduino. The hardware setup furnishes consumers with the real-time status of all home appliances on their smartphone and web server. Controlling module is also integrated with the identification hardware to provide smart access to consumer for the remote control of home appliances.","PeriodicalId":114660,"journal":{"name":"2018 International Symposium on Consumer Technologies (ISCT)","volume":"10 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116735758","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 : 2018-05-11DOI: 10.1109/ISCE.2018.8408905
M. Yenuchenko
Digital-to-analog converters are widely used in consumer electronics for a message or control signal generation. Two structures of a segmented current-steering DAC are proposed. Both structures improve monotonicity in comparison with the typical segmented DAC structure. The first one is based on a current divider that is connected to an output. The second one is based on a variable bias voltage. Both structures allow to guarantee monotonicity and simplify matching process.
{"title":"Alternative structures of a segmented current-steering DAC","authors":"M. Yenuchenko","doi":"10.1109/ISCE.2018.8408905","DOIUrl":"https://doi.org/10.1109/ISCE.2018.8408905","url":null,"abstract":"Digital-to-analog converters are widely used in consumer electronics for a message or control signal generation. Two structures of a segmented current-steering DAC are proposed. Both structures improve monotonicity in comparison with the typical segmented DAC structure. The first one is based on a current divider that is connected to an output. The second one is based on a variable bias voltage. Both structures allow to guarantee monotonicity and simplify matching process.","PeriodicalId":114660,"journal":{"name":"2018 International Symposium on Consumer Technologies (ISCT)","volume":"107 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131537998","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 : 2018-05-11DOI: 10.1109/ISCE.2018.8408913
A. Muthanna, Abdelhamied A. Ateya, M. Balushi, R. Kirichek
In the device-device communication paradigm (D2D) in 5G networks, an efficient infrastructure is created, allowing the use of various smart urban applications, such as public safety. In future smart cities, the tight deployment of wireless sensor networks can be integrated into 5G networks using D2D communications. D2D communication provides direct communication between neighbouring user devices using cellular or special communication channels, thereby improving spectrum utilization, system capacity and network energy efficiency. This paper discusses the hierarchical communication architecture of D2D, in which the centralized Software-Defined Network controller (SDN) interacts with the Cloud Head (CH) to reduce the number of requested LTE communication channels, thereby improving power consumption. This paper considers the reliability and potential of the architecture, presenting a public safety scenario when occurs any disaster, disconnecting a part of the network.
{"title":"D2D enabled communication system structure based on software defined networking for 5G network","authors":"A. Muthanna, Abdelhamied A. Ateya, M. Balushi, R. Kirichek","doi":"10.1109/ISCE.2018.8408913","DOIUrl":"https://doi.org/10.1109/ISCE.2018.8408913","url":null,"abstract":"In the device-device communication paradigm (D2D) in 5G networks, an efficient infrastructure is created, allowing the use of various smart urban applications, such as public safety. In future smart cities, the tight deployment of wireless sensor networks can be integrated into 5G networks using D2D communications. D2D communication provides direct communication between neighbouring user devices using cellular or special communication channels, thereby improving spectrum utilization, system capacity and network energy efficiency. This paper discusses the hierarchical communication architecture of D2D, in which the centralized Software-Defined Network controller (SDN) interacts with the Cloud Head (CH) to reduce the number of requested LTE communication channels, thereby improving power consumption. This paper considers the reliability and potential of the architecture, presenting a public safety scenario when occurs any disaster, disconnecting a part of the network.","PeriodicalId":114660,"journal":{"name":"2018 International Symposium on Consumer Technologies (ISCT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128770198","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 : 2018-05-11DOI: 10.1109/ISCE.2018.8408910
A. Belozertsev, Kirill Gusev, Evgenia Grineko, K. Glasman
The paper describes experimental study of Quality of Experience of compressed audiovisual materials when the bandwidth available is changing. We propose a model of QoE multimodal assessment for audiovisual programs of various contents and in a wide range of compressed video and audio data bitrates. On the basis of the model an optimization problem of audio and video bit rate allocation in bandwidth-limited systems can be solved. The approach proposed is based on a cross-modal audiovisual interaction and takes into account that optimal audio and video codec parameters in bandwidth-limited multimedia systems can be content-adaptive.
{"title":"A multimodal quality assessment of compressed materials for adaptive bitrate video streaming","authors":"A. Belozertsev, Kirill Gusev, Evgenia Grineko, K. Glasman","doi":"10.1109/ISCE.2018.8408910","DOIUrl":"https://doi.org/10.1109/ISCE.2018.8408910","url":null,"abstract":"The paper describes experimental study of Quality of Experience of compressed audiovisual materials when the bandwidth available is changing. We propose a model of QoE multimodal assessment for audiovisual programs of various contents and in a wide range of compressed video and audio data bitrates. On the basis of the model an optimization problem of audio and video bit rate allocation in bandwidth-limited systems can be solved. The approach proposed is based on a cross-modal audiovisual interaction and takes into account that optimal audio and video codec parameters in bandwidth-limited multimedia systems can be content-adaptive.","PeriodicalId":114660,"journal":{"name":"2018 International Symposium on Consumer Technologies (ISCT)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124860542","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 : 2018-05-11DOI: 10.1109/ISCE.2018.8408914
M. Butakova, A. Chernov, Petr S. Shevchuk, V. Vereskun
In this paper, we propose the neural fuzzy adaptive control system suited for mobile smart objects. The classification of hybrid neural networks based on fuzzy neuron models is presented. The hybrid adaptive system architecture consisting of triple neural networks is proposed. Fuzzifying process with rules database creation and fuzzy membership functions definitions are considered. Also learning experiments with proposed architecture have been implemented.
{"title":"Neural fuzzy adaptive control for mobile smart objects","authors":"M. Butakova, A. Chernov, Petr S. Shevchuk, V. Vereskun","doi":"10.1109/ISCE.2018.8408914","DOIUrl":"https://doi.org/10.1109/ISCE.2018.8408914","url":null,"abstract":"In this paper, we propose the neural fuzzy adaptive control system suited for mobile smart objects. The classification of hybrid neural networks based on fuzzy neuron models is presented. The hybrid adaptive system architecture consisting of triple neural networks is proposed. Fuzzifying process with rules database creation and fuzzy membership functions definitions are considered. Also learning experiments with proposed architecture have been implemented.","PeriodicalId":114660,"journal":{"name":"2018 International Symposium on Consumer Technologies (ISCT)","volume":"268 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125095195","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 : 2018-05-11DOI: 10.1109/ISCE.2018.8408927
Ivan Liapin
With the AV1 codec soon coming to the global video streaming market it is important to find a way to efficiently transcode existing streams encoded with previous generation codecs, such as H.264/AVC and H.265/HEVC to AV1. Because of the massively increased computational complexity of AV1 direct re-encoding is not a viable option as of today. This paper proposes a method of fast H.264/H.265 to AV1 stream transcoding based on reusing motion data from H.264/H.265 to track objects in input compressed domain and remove the need to do most of the complex inter-prediction in AV1 encoder. It is shown that the reduction in encoder run time can be significant enough to provide transcoding speeds on par with reference encoders of the previous codec generation.
{"title":"Fast H.264/H.265 to AV1 stream transcoding using a moving object tracker","authors":"Ivan Liapin","doi":"10.1109/ISCE.2018.8408927","DOIUrl":"https://doi.org/10.1109/ISCE.2018.8408927","url":null,"abstract":"With the AV1 codec soon coming to the global video streaming market it is important to find a way to efficiently transcode existing streams encoded with previous generation codecs, such as H.264/AVC and H.265/HEVC to AV1. Because of the massively increased computational complexity of AV1 direct re-encoding is not a viable option as of today. This paper proposes a method of fast H.264/H.265 to AV1 stream transcoding based on reusing motion data from H.264/H.265 to track objects in input compressed domain and remove the need to do most of the complex inter-prediction in AV1 encoder. It is shown that the reduction in encoder run time can be significant enough to provide transcoding speeds on par with reference encoders of the previous codec generation.","PeriodicalId":114660,"journal":{"name":"2018 International Symposium on Consumer Technologies (ISCT)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123840949","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 : 2018-05-11DOI: 10.1109/ISCE.2018.8408915
A. Bukhalov, Viktoriia Chafonova
Iris localization is an active area and complicated task in computer vision systems. This article presents a description of an eye tracking algorithm based on Hough transform.
虹膜定位是计算机视觉系统中的一个活跃领域和复杂任务。提出了一种基于霍夫变换的眼动追踪算法。
{"title":"An eye tracking algorithm based on hough transform","authors":"A. Bukhalov, Viktoriia Chafonova","doi":"10.1109/ISCE.2018.8408915","DOIUrl":"https://doi.org/10.1109/ISCE.2018.8408915","url":null,"abstract":"Iris localization is an active area and complicated task in computer vision systems. This article presents a description of an eye tracking algorithm based on Hough transform.","PeriodicalId":114660,"journal":{"name":"2018 International Symposium on Consumer Technologies (ISCT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130276265","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 : 2018-05-11DOI: 10.1109/ISCE.2018.8408916
V. Vasiliev, F. Inochkin, S. Kruglov, I. Bronshtein
We present raw image processing pipeline for miniature television camera. This pipeline includes image acquisition over serial interface, dark image subtraction with dynamic temperature variation compensation, image flat-fielding, automatic exposure and gain control. Also this includes a progressive-to-interlaced format conversion, specific to analog signal standards. All of these operations are performed inside small-package 4×4mm Lattice iCELP8K FPGA, placed inside miniature camera.
{"title":"Real-time image processing inside a miniature camera using small-package FPGA","authors":"V. Vasiliev, F. Inochkin, S. Kruglov, I. Bronshtein","doi":"10.1109/ISCE.2018.8408916","DOIUrl":"https://doi.org/10.1109/ISCE.2018.8408916","url":null,"abstract":"We present raw image processing pipeline for miniature television camera. This pipeline includes image acquisition over serial interface, dark image subtraction with dynamic temperature variation compensation, image flat-fielding, automatic exposure and gain control. Also this includes a progressive-to-interlaced format conversion, specific to analog signal standards. All of these operations are performed inside small-package 4×4mm Lattice iCELP8K FPGA, placed inside miniature camera.","PeriodicalId":114660,"journal":{"name":"2018 International Symposium on Consumer Technologies (ISCT)","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133571972","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：