A. Chauvet, Tomo Miyazaki, Yoshihiro Sugaya, S. Omachi
{"title":"Adaptive Post Filter for Reducing Block Artifacts in High Efficiency Video Coding","authors":"A. Chauvet, Tomo Miyazaki, Yoshihiro Sugaya, S. Omachi","doi":"10.1109/ICMSSP.2016.014","DOIUrl":"https://doi.org/10.1109/ICMSSP.2016.014","url":null,"abstract":"This paper describes an adaptive deblocking postfilter based on neural networks for use in H.265 High Efficiency Video Coding (HEVC). Blocking noise is a common problem in video coding caused by the division of the frame into blocks. The filter is adaptive because it uses different filter parameters depending on block characteristics. We use a modified HEVC decoder to export the block information to the filter. Blocks are put in different categories according to transform and prediction parameters. We train the filter in each case to optimize the internal parameters. We find that a 2-layer convolutional neural network is able to outperform the in-loop deblocking filter for a moderate processing cost. We propose to apply the filter after the HEVC in-loop deblocking filter. We demonstrate that our filter helps further reduce visual artifacts in video.","PeriodicalId":243235,"journal":{"name":"2016 International Conference on Multimedia Systems and Signal Processing (ICMSSP)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126784249","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}
{"title":"Interactive Object Extraction from a Video Based on Seed-Line Tracking","authors":"Takahiro Hayashi, Yusuke Narita","doi":"10.1109/ICMSSP.2016.015","DOIUrl":"https://doi.org/10.1109/ICMSSP.2016.015","url":null,"abstract":"This paper presents a method for extracting a non-rigid moving object from a video sequence. In order to actualize object extraction with minimal user interaction, we combine alpha matting and seed-line tracking. In the proposed method, the object region is separated from background based on seed lines given by user as a cue, and then the seed lines are automatically tracked to the next frames to actualize automatic object extraction from the frame sequence. With the alpha matting, the boundary of the object region in each frame is refined. The experimental results have shown that by the seed-line tracking user input can be significantly reduced and that the boundary refinement by alpha matting works effectively.","PeriodicalId":243235,"journal":{"name":"2016 International Conference on Multimedia Systems and Signal Processing (ICMSSP)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114895819","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}
{"title":"Impression Estimation of a Video Based on the Valence-Arousal Model","authors":"Takahiro Hayashi, T. Yoshida","doi":"10.1109/ICMSSP.2016.018","DOIUrl":"https://doi.org/10.1109/ICMSSP.2016.018","url":null,"abstract":"BGM (background music) of a video plays an important role for making a video impressive. Although a large number of royalty-free music clips are available on the web, it is still difficult for amateur video creators to select appropriate music clips for their videos. In this paper, we propose a computational method for estimating the impression of a video from auditory and visual features of a video. The impression of a video is modeled as the valence and arousal values. Based on the method, we propose a BGM recommendation system for supporting video creators. Experimental results have shown the effective of the impression estimation of a video based on the valence and arousal model.","PeriodicalId":243235,"journal":{"name":"2016 International Conference on Multimedia Systems and Signal Processing (ICMSSP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130188018","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}
M. Yoneda, T. Akagi, S. Dohta, W. Kobayashi, Yoshinori Moriwake, Feifei Cho
{"title":"Development of Flow Rate Control Type Quasi-Servo Valve Using Small-Sized On/Off Valves","authors":"M. Yoneda, T. Akagi, S. Dohta, W. Kobayashi, Yoshinori Moriwake, Feifei Cho","doi":"10.1109/ICMSSP.2016.026","DOIUrl":"https://doi.org/10.1109/ICMSSP.2016.026","url":null,"abstract":"In a pneumatic driving system, a servo valve is most expensive equipment compared with pneumatic actuators. In a wearable driving system, the mass and size of a valve also becomes serious concern. The purpose of this study is to reduce the burden of the user by using a small and light-weight quasi-servo valve that consists of inexpensive on/off valves and an embedded controller. The relation between input duty ratio and output flow rate of the valve is nonlinear. In the previous study, a pressure control type quasi-servo valve using a pressure transducer was also developed. However, the cost of the valve was increased. In this paper, to develop a lower-cost valve with good controllability, the flow rate control type quasi-servo valve by compensating the input duty-ratio of the valve is proposed and tested. The performance of the tested valve was also investigated. As a result, the valve can generate the proportional output flow rate according to the input voltage.","PeriodicalId":243235,"journal":{"name":"2016 International Conference on Multimedia Systems and Signal Processing (ICMSSP)","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115608913","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}
{"title":"Color Image Reconstructions from Bessel-Fourier Moments","authors":"Bo Pang, S. Liao","doi":"10.1109/ICMSSP.2016.013","DOIUrl":"https://doi.org/10.1109/ICMSSP.2016.013","url":null,"abstract":"In this research, a study on color image reconstruction from Bessel-Fourier moments is conducted. We have calculated the Bessel-Fourier moments of a color image in three different color channels, reconstructed images in different color channels, and integrated the separately reconstructed images to a color image. Our experimental results show that the color image reconstruction performances from different radial and Fourier orders of Bessel-Fourier moments, up to n = m = 100, are highly satisfactory.","PeriodicalId":243235,"journal":{"name":"2016 International Conference on Multimedia Systems and Signal Processing (ICMSSP)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124098542","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}
{"title":"An Improved Artificial Bee Colony for Solving Multi-Objective Optimization Problems","authors":"Sheng-Ta Hsieh, Chun-Ling Lin","doi":"10.1109/ICMSSP.2016.021","DOIUrl":"https://doi.org/10.1109/ICMSSP.2016.021","url":null,"abstract":"Artificial bee colony (ABC) algorithm is a novel optimizer which simulates bees' foraging behavior in solution space for finding global optimal solution with reasonable criteria. In this paper, an improved artificial bee colony is proposed to solve multi-objective (MO) problems. In order to guide bees toward to Pareto optimal solutions, bees' moving behavior is modified to make ABC capable for solving multi-objective problems. In order to test the proposed method, five IEEE CEC 2009 test functions and performance metric are adopted. Besides, three MO optimizers are taken into comparison.","PeriodicalId":243235,"journal":{"name":"2016 International Conference on Multimedia Systems and Signal Processing (ICMSSP)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127096367","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}
{"title":"A Bayesian Network Approach to Study Undergraduates' Brand Consciousness","authors":"H. Ong, Sze Ern Yau, Josephine Ying Ying Looi","doi":"10.1109/ICMSSP.2016.020","DOIUrl":"https://doi.org/10.1109/ICMSSP.2016.020","url":null,"abstract":"This study seeks to explore the causal relationship between the factors affecting the level of brand consciousness among local universities students in Malaysia by using Bayesian network. Bnlearn package in R is used for learning the graphical structure of Bayesian networks from a survey data and to perform some useful inferences. The random variables and their conditional dependencies are represented via a directed acyclic graph. The three types of structural learning algorithms used are constraint-based algorithms, score-based algorithms and hybrid structural learning algorithms. The scores from their respective estimated networks will determine the best-fitted network. From our result, score-based algorithm using Hill-Climbing and Tabu Search algorithm provided the best-fitted network for the data. The most significant effect on the level of apparel's brand consciousness among the undergraduates is their state of origin and the year of study.","PeriodicalId":243235,"journal":{"name":"2016 International Conference on Multimedia Systems and Signal Processing (ICMSSP)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117152578","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}
Kazuhiko Takahashi, Yuka Wakaume, T. Hirayama, M. Hashimoto
{"title":"Remarks on Hypercomplex-Valued Neural Network-Based Direct Adaptive Controller","authors":"Kazuhiko Takahashi, Yuka Wakaume, T. Hirayama, M. Hashimoto","doi":"10.1109/ICMSSP.2016.027","DOIUrl":"https://doi.org/10.1109/ICMSSP.2016.027","url":null,"abstract":"In this study, we investigate the control performance of an adaptive controller using multilayer hypercomplex-valued neural networks, such as complex, hyperbolic, bicomplex and quaternion neural networks. The control system is a direct controller whereby the control input of a plant is synthesized online using the multilayer hypercomplex-valued neural network to track the plant output to the desired output generated by a reference model. Computational experiments to control a multiple-input and multiple-output discrete-time nonlinear plant are conducted to evaluate the capability and characteristics of the hypercomplex–valued neural network–based direct adaptive controller. Experimental results show the feasibility and effectiveness of the proposed controller.","PeriodicalId":243235,"journal":{"name":"2016 International Conference on Multimedia Systems and Signal Processing (ICMSSP)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121496264","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}
{"title":"Enhanced Hemisphere Concept for Color Pixel Classification","authors":"V. Ng, T. Aoki","doi":"10.1109/ICMSSP.2016.016","DOIUrl":"https://doi.org/10.1109/ICMSSP.2016.016","url":null,"abstract":"Most of current clustering methods are designed for general purpose other than a specific color pixel classification use. Color Line model representation emerged as the ultimate method for clustering pixels using RGB color components. However, this method is strongly sensitive to the adjustment of input parameters, which cannot conform to the frequent change of image structures and compositions. In this paper, we address this problem by introducing a hemisphere-grid based method for RGB pixel classification. Our method minimizes the reliance on user provided parameters as well as it can dynamically estimate the proper number of clusters. The properly clustering results prove the robustness and advantages of our method in classifying color pixels for unfamiliar input images.","PeriodicalId":243235,"journal":{"name":"2016 International Conference on Multimedia Systems and Signal Processing (ICMSSP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133678255","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}
S. Murai, S. Fujimoto, Akihiro Yamamoto, T. Kinugasa
{"title":"3D Quasi-Passive Walker of Bipedal Robot with Flat Feet Gait Analysis of 3D Quasi-Passive Walking","authors":"S. Murai, S. Fujimoto, Akihiro Yamamoto, T. Kinugasa","doi":"10.1109/ICMSSP.2016.025","DOIUrl":"https://doi.org/10.1109/ICMSSP.2016.025","url":null,"abstract":"In this paper, we analysis gaits of 3D quasi-passive walker with flat feet driven by an antagonistic pneumatic artificial muscle. Many bipedal robots have been proposed to realize the high energy efficiency walking. The passive dynamic walking does not require control input. Generally, a foot shape of passive dynamic walking robot is an arc foot. It is intended to establish a control method and walking mechanism to achieve energy efficient and stable gait. Therefore, we developed 3D quasi-passive walker with flat feet. An antagonistic mechanism is constituted by a pair of McKibben muscle. And an antagonistic pneumatic system is used as joint actuators of linkage mechanisms which control the torque, joint stiffness and position simultaneously. This paper shows that the 3D quasi-passive walking in the level ground can realize by the simple swinging (sine) input of the frontal direction, and the stride of the robot is proportional to lateral-plane input. Finally, we examine the structure of an ankle, the control method of an antagonistic pneumatic system and these gaits analysis using COP (Center Of Pressure) and ROS (Roll-Over Shapes).","PeriodicalId":243235,"journal":{"name":"2016 International Conference on Multimedia Systems and Signal Processing (ICMSSP)","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132978571","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}