Pub Date : 2012-12-13DOI: 10.1109/GCCE.2012.6379642
Pei-Jun Lee, Wen-Jay Yu, Chi-Feng Chuang
In Binocular depth generation algorithm, the depth value can be found by the disparity estimation by taking advantage of the similarity in these two views which be captured at the same time. However, it's not easy to find the accurate depth value if there is high similarity in color space around the area. To reduce the matching error in the regions with high similarity, the pixel information on the edge of the objects in color space can be used to predict the depth value of the object. This paper proposes an object region determination based on watershed segmentation algorithm to generate a matching window for stereo matching. To reduce the depth discontinuity and the computation time for disparity estimation on all pictures, this paper uses the motion vector information to compensate depth value for the successive depth video. Thus, depth map generated by the proposed algorithm can produce more suitable stereo images. Experimental results show that the stereo scopic reliability can be improved by the proposed algorithm in high stereoscopic sequence. The SSIM is increased about 0.34 and the PSNR is increased about 0.55dB when the proposed algorithm is used to compare the other approaches.
{"title":"Watershed-based stereo matching algorithm for depth map generation","authors":"Pei-Jun Lee, Wen-Jay Yu, Chi-Feng Chuang","doi":"10.1109/GCCE.2012.6379642","DOIUrl":"https://doi.org/10.1109/GCCE.2012.6379642","url":null,"abstract":"In Binocular depth generation algorithm, the depth value can be found by the disparity estimation by taking advantage of the similarity in these two views which be captured at the same time. However, it's not easy to find the accurate depth value if there is high similarity in color space around the area. To reduce the matching error in the regions with high similarity, the pixel information on the edge of the objects in color space can be used to predict the depth value of the object. This paper proposes an object region determination based on watershed segmentation algorithm to generate a matching window for stereo matching. To reduce the depth discontinuity and the computation time for disparity estimation on all pictures, this paper uses the motion vector information to compensate depth value for the successive depth video. Thus, depth map generated by the proposed algorithm can produce more suitable stereo images. Experimental results show that the stereo scopic reliability can be improved by the proposed algorithm in high stereoscopic sequence. The SSIM is increased about 0.34 and the PSNR is increased about 0.55dB when the proposed algorithm is used to compare the other approaches.","PeriodicalId":299732,"journal":{"name":"The 1st IEEE Global Conference on Consumer Electronics 2012","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129340935","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 : 2012-12-13DOI: 10.1109/GCCE.2012.6379639
K. Fukui, S. Ishimitsu, T. Yamanaka, H. Nagoshi
Japan has a rapidly aging society. Concurrently, the number of patients suffering speech disorders is increasing every year, and the incidence rate is higher as age increases. Those suffering from speech disorders face communication problems in daily conversation. They are often able to communicate with speech substitutes, but these typically do not provide a sufficient sound frequency range to be understood in conversation. Therefore, we proposed a speech support system using body-conducted speech recognition. This system retrieves speech from body-conducted speech via a transfer function, using recognition to select a sub-word sequence and its duration. In this study, we demonstrate the effectiveness of producing clear body-conducted speech using a linear predictive coefficient instead of a transfer function. Then, instead of dividing body-conducted speech into syllables in a heuristic manner as in past studies, we used continuous sub-word recognition automatically. The improvement of the generated speech was confirmed in a jury test and articulatory feature analysis.
{"title":"Improvement of sound quality using support system for speech disorders","authors":"K. Fukui, S. Ishimitsu, T. Yamanaka, H. Nagoshi","doi":"10.1109/GCCE.2012.6379639","DOIUrl":"https://doi.org/10.1109/GCCE.2012.6379639","url":null,"abstract":"Japan has a rapidly aging society. Concurrently, the number of patients suffering speech disorders is increasing every year, and the incidence rate is higher as age increases. Those suffering from speech disorders face communication problems in daily conversation. They are often able to communicate with speech substitutes, but these typically do not provide a sufficient sound frequency range to be understood in conversation. Therefore, we proposed a speech support system using body-conducted speech recognition. This system retrieves speech from body-conducted speech via a transfer function, using recognition to select a sub-word sequence and its duration. In this study, we demonstrate the effectiveness of producing clear body-conducted speech using a linear predictive coefficient instead of a transfer function. Then, instead of dividing body-conducted speech into syllables in a heuristic manner as in past studies, we used continuous sub-word recognition automatically. The improvement of the generated speech was confirmed in a jury test and articulatory feature analysis.","PeriodicalId":299732,"journal":{"name":"The 1st IEEE Global Conference on Consumer Electronics 2012","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129361930","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 : 2012-12-13DOI: 10.1109/GCCE.2012.6379557
H. Ito
A method to embed overlay information such as captions and annotations in images is proposed. The overlay information is mixed and hidden in one of the color components on a display having redundant color representation capabilities. Normal viewers do not see the hidden information since other color components are adjusted such that a resulting image has the same combination of primary colors as the original one. The hidden information could be extracted by simple filtering and would be overlaid in images on proprietary viewer screens. In this paper we assume that the display has yellow pixels in addition to the normal RGB colors which we exclusively use to transmit the overlay information. We derive a formula for the color components to keep the overlay image invisible taking into account the nonlinearity of the display characteristics. The dynamic range of the overlay channel is limited by the image contents. We compute the channel capacity for some test images. We have conducted fundamental experiments where the monitor has been emulated by a normal three color display and have verified that the hidden information can be made almost invisible if nonlinearity of the display is properly compensated.
{"title":"Embedding overlay information in images on four color displays","authors":"H. Ito","doi":"10.1109/GCCE.2012.6379557","DOIUrl":"https://doi.org/10.1109/GCCE.2012.6379557","url":null,"abstract":"A method to embed overlay information such as captions and annotations in images is proposed. The overlay information is mixed and hidden in one of the color components on a display having redundant color representation capabilities. Normal viewers do not see the hidden information since other color components are adjusted such that a resulting image has the same combination of primary colors as the original one. The hidden information could be extracted by simple filtering and would be overlaid in images on proprietary viewer screens. In this paper we assume that the display has yellow pixels in addition to the normal RGB colors which we exclusively use to transmit the overlay information. We derive a formula for the color components to keep the overlay image invisible taking into account the nonlinearity of the display characteristics. The dynamic range of the overlay channel is limited by the image contents. We compute the channel capacity for some test images. We have conducted fundamental experiments where the monitor has been emulated by a normal three color display and have verified that the hidden information can be made almost invisible if nonlinearity of the display is properly compensated.","PeriodicalId":299732,"journal":{"name":"The 1st IEEE Global Conference on Consumer Electronics 2012","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126809511","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 : 2012-12-13DOI: 10.1109/GCCE.2012.6379543
T. Haraikawa
On behalf of the Technical Program Committee of GCCE 2012, I would like to welcome you to the 1st Global Conference on Consumer Electronics. Just like International CES + ICCE, GCCE 2012 held with CEATEC, one of the biggest Consumer Electronics Show in the world, has many interesting keynotes, symposium, and of course paper/poster presentations!
{"title":"Introduction to the Technical Program of IEEE GCCE 2012","authors":"T. Haraikawa","doi":"10.1109/GCCE.2012.6379543","DOIUrl":"https://doi.org/10.1109/GCCE.2012.6379543","url":null,"abstract":"On behalf of the Technical Program Committee of GCCE 2012, I would like to welcome you to the 1st Global Conference on Consumer Electronics. Just like International CES + ICCE, GCCE 2012 held with CEATEC, one of the biggest Consumer Electronics Show in the world, has many interesting keynotes, symposium, and of course paper/poster presentations!","PeriodicalId":299732,"journal":{"name":"The 1st IEEE Global Conference on Consumer Electronics 2012","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129096221","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 : 2012-12-13DOI: 10.1109/GCCE.2012.6379640
Ying-Wen Bai, Ming-Feng Hsueh
In this paper we propose the design of an autonomous robotic vacuum cleaner by using three-dimensional vector coordinates to guide its path. Our design is fully adapted to planning an effective mode for completing the cleaning task in an unknown environment. In addition we propose a dynamic return path for recharging, including the relative coordinates of the record starting point and the current position. The cleaner calculates the distance from the location of the base and then plans the return path.
{"title":"Using an adaptive iterative learning algorithm for planning of the path of an autonomous robotic vacuum cleaner","authors":"Ying-Wen Bai, Ming-Feng Hsueh","doi":"10.1109/GCCE.2012.6379640","DOIUrl":"https://doi.org/10.1109/GCCE.2012.6379640","url":null,"abstract":"In this paper we propose the design of an autonomous robotic vacuum cleaner by using three-dimensional vector coordinates to guide its path. Our design is fully adapted to planning an effective mode for completing the cleaning task in an unknown environment. In addition we propose a dynamic return path for recharging, including the relative coordinates of the record starting point and the current position. The cleaner calculates the distance from the location of the base and then plans the return path.","PeriodicalId":299732,"journal":{"name":"The 1st IEEE Global Conference on Consumer Electronics 2012","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116301602","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 : 2012-12-13DOI: 10.1109/GCCE.2012.6379584
M. Takai
This study makes a body model for education of dance how lively a dance trainer moves his/her body so that the dance student can learn dance from the dance trainer who is in the distant place through communication line in virtual dance studio. In late years, network game gives the virtual space enjoying sports, music, and dance to plural people who are in the remote place at the same time. However, the general network game has to attach sensors or devices to the body of the players to input livingness by the movement of them. Therefore, not only they feel botheration in the player attaching sensors or devices, but also it is necessary to spend labor and time to attach sensors or devices to the body. This study proposes Active Quantity to measure with quantity from 0.0 to 1.0 from a dynamic image which photographed the movement of the dance trainer in digital video camera. Furthermore, the proposal method makes the body model that put the silhouette of the dance trainer and Active Quantity together so that the dance students are easy to understand the movement of the dance trainer from sight.
{"title":"Production of body model for education of dance by measurement active quantity","authors":"M. Takai","doi":"10.1109/GCCE.2012.6379584","DOIUrl":"https://doi.org/10.1109/GCCE.2012.6379584","url":null,"abstract":"This study makes a body model for education of dance how lively a dance trainer moves his/her body so that the dance student can learn dance from the dance trainer who is in the distant place through communication line in virtual dance studio. In late years, network game gives the virtual space enjoying sports, music, and dance to plural people who are in the remote place at the same time. However, the general network game has to attach sensors or devices to the body of the players to input livingness by the movement of them. Therefore, not only they feel botheration in the player attaching sensors or devices, but also it is necessary to spend labor and time to attach sensors or devices to the body. This study proposes Active Quantity to measure with quantity from 0.0 to 1.0 from a dynamic image which photographed the movement of the dance trainer in digital video camera. Furthermore, the proposal method makes the body model that put the silhouette of the dance trainer and Active Quantity together so that the dance students are easy to understand the movement of the dance trainer from sight.","PeriodicalId":299732,"journal":{"name":"The 1st IEEE Global Conference on Consumer Electronics 2012","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132380089","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 : 2012-12-13DOI: 10.1109/GCCE.2012.6379959
M. Fukuda, K. Imano
This study examines the use of ultrasonic second harmonic components in the quality control of bolt-fastened structures. An improved method for detecting the second harmonic components, from a bolt fastened with a nut, using the transmission method is constructed. A hexagon head iron bolt was used in the experiments. The bolt was fastened using a digital torque wrench. The second harmonic component increased by approximately 10 dB before and after the bolt was fastened. The sources of second harmonic components were contact acoustic nonlinearity in the screw thread interfaces of the bolt-nut and were the plastic deformation in the bolt with fastening bolt. This result was almost same compared with previous our method. Consequently, usefulness of the novel method for detecting second harmonic ultrasonic components generated from fastened bolt was confirmed.
{"title":"A study of bolt fastening evaluation using second harmonic ultrasonic pulse waves","authors":"M. Fukuda, K. Imano","doi":"10.1109/GCCE.2012.6379959","DOIUrl":"https://doi.org/10.1109/GCCE.2012.6379959","url":null,"abstract":"This study examines the use of ultrasonic second harmonic components in the quality control of bolt-fastened structures. An improved method for detecting the second harmonic components, from a bolt fastened with a nut, using the transmission method is constructed. A hexagon head iron bolt was used in the experiments. The bolt was fastened using a digital torque wrench. The second harmonic component increased by approximately 10 dB before and after the bolt was fastened. The sources of second harmonic components were contact acoustic nonlinearity in the screw thread interfaces of the bolt-nut and were the plastic deformation in the bolt with fastening bolt. This result was almost same compared with previous our method. Consequently, usefulness of the novel method for detecting second harmonic ultrasonic components generated from fastened bolt was confirmed.","PeriodicalId":299732,"journal":{"name":"The 1st IEEE Global Conference on Consumer Electronics 2012","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130217099","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 : 2012-12-13DOI: 10.1109/GCCE.2012.6379947
C. Hsu, Yuan-Jun Chen, Ming-Chih Lu, Shih-An Li
This paper proposes an optimal path planning algorithm incorporating a global and local search mechanism for mobile robots. The global path planning is based on Voronoi graph to establish a backbone path for the map with significantly reduced nodes for the original grid map. With the use of the backbone path, the D* algorithm is adopted to determine a shortest path between the starting and end points. Taking advantages of the D* algorithm and Voronoi graph, the proposed optimal path planning algorithm is capable of obtaining a desired path for the mobile robot, overcoming the efficiency problem while maintaining maximum safety distance from the obstacles when the mobile robot navigates in the environment. Simulation results have confirmed the feasibility of the proposed algorithm for practical use in the real-world environment.
{"title":"Optimal path planning incorporating global and local search for mobile robots","authors":"C. Hsu, Yuan-Jun Chen, Ming-Chih Lu, Shih-An Li","doi":"10.1109/GCCE.2012.6379947","DOIUrl":"https://doi.org/10.1109/GCCE.2012.6379947","url":null,"abstract":"This paper proposes an optimal path planning algorithm incorporating a global and local search mechanism for mobile robots. The global path planning is based on Voronoi graph to establish a backbone path for the map with significantly reduced nodes for the original grid map. With the use of the backbone path, the D* algorithm is adopted to determine a shortest path between the starting and end points. Taking advantages of the D* algorithm and Voronoi graph, the proposed optimal path planning algorithm is capable of obtaining a desired path for the mobile robot, overcoming the efficiency problem while maintaining maximum safety distance from the obstacles when the mobile robot navigates in the environment. Simulation results have confirmed the feasibility of the proposed algorithm for practical use in the real-world environment.","PeriodicalId":299732,"journal":{"name":"The 1st IEEE Global Conference on Consumer Electronics 2012","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133991272","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 : 2012-12-13DOI: 10.1109/GCCE.2012.6379953
Kuo-Lun Huang, Tai-Ming Chang, P. Chang
In this paper, we propose an object-based audio rendering system, in which the audio signal of each object is distributed to multi-channel systems by spatial parameters. The operation of the rendering system is based on the sound localization theories with the Parametric Stereo (PS) coding structure. The performance of the audio surround effect of a sound moving object is evaluated by subjective listening tests. The experimental result clearly shows that the proposed system is capable of delivering sound moving effect to listeners.
{"title":"An object-based audio rendering system using spatial parameters","authors":"Kuo-Lun Huang, Tai-Ming Chang, P. Chang","doi":"10.1109/GCCE.2012.6379953","DOIUrl":"https://doi.org/10.1109/GCCE.2012.6379953","url":null,"abstract":"In this paper, we propose an object-based audio rendering system, in which the audio signal of each object is distributed to multi-channel systems by spatial parameters. The operation of the rendering system is based on the sound localization theories with the Parametric Stereo (PS) coding structure. The performance of the audio surround effect of a sound moving object is evaluated by subjective listening tests. The experimental result clearly shows that the proposed system is capable of delivering sound moving effect to listeners.","PeriodicalId":299732,"journal":{"name":"The 1st IEEE Global Conference on Consumer Electronics 2012","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131885400","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 : 2012-12-13DOI: 10.1109/GCCE.2012.6379570
Y. Murakami, S. K. T. Utomo, K. Hosono, K. Shigeta
Recently, many of agricultural-work pursuers are recording agricultural-work record on the paper basis. These situation based on paper recording has difficulty to check the past agricultural-work data and the cost control of agricultural products, compared to electrically stored data. Many farmhouses want to manage agricultural-work information, in order to grasp the cost price. Furthermore, the needs for the systematization of cultivated land management from many farming people in Japan So, in this study, we propose cultivated land management system in order to solve these problems. This system stores the agricultural-work data into electrical database through the Web browser.
{"title":"Proposed of cultivation management system with informatics and communication technology","authors":"Y. Murakami, S. K. T. Utomo, K. Hosono, K. Shigeta","doi":"10.1109/GCCE.2012.6379570","DOIUrl":"https://doi.org/10.1109/GCCE.2012.6379570","url":null,"abstract":"Recently, many of agricultural-work pursuers are recording agricultural-work record on the paper basis. These situation based on paper recording has difficulty to check the past agricultural-work data and the cost control of agricultural products, compared to electrically stored data. Many farmhouses want to manage agricultural-work information, in order to grasp the cost price. Furthermore, the needs for the systematization of cultivated land management from many farming people in Japan So, in this study, we propose cultivated land management system in order to solve these problems. This system stores the agricultural-work data into electrical database through the Web browser.","PeriodicalId":299732,"journal":{"name":"The 1st IEEE Global Conference on Consumer Electronics 2012","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130896603","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：