2018 14th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)最新文献

筛选
英文 中文
Object 3D Reconstruction Based on Photometric Stereo and Inverted Rendering 基于光度立体和倒立渲染的物体三维重建
Anish R. Khadka, Paolo Remagnino, V. Argyriou
{"title":"Object 3D Reconstruction Based on Photometric Stereo and Inverted Rendering","authors":"Anish R. Khadka, Paolo Remagnino, V. Argyriou","doi":"10.1109/SITIS.2018.00039","DOIUrl":"https://doi.org/10.1109/SITIS.2018.00039","url":null,"abstract":"Methods for 3D reconstruction such as Photometric stereo recover the shape and reflectance properties using multiple images of an object taken with variable lighting conditions from a fixed viewpoint. Photometric stereo assumes that a scene is illuminated only directly by the illumination source. As result, indirect illumination effects due to inter-reflections introduce strong biases in the recovered shape. Our suggested approach is to recover scene properties in the presence of indirect illumination. To this end, we proposed an iterative PS method combined with a reverted Monte-Carlo ray tracing algorithm to overcome the inter-reflection effects aiming to separate the direct and indirect lighting. This approach iteratively reconstructs a surface considering both the environment around the object and its concavities. We demonstrate and evaluate our approach using three datasets and the overall results illustrate improvement over the classic PS approaches.","PeriodicalId":267494,"journal":{"name":"2018 14th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123076537","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}
引用次数: 4
Predictive Sampling of Facial Expression Dynamics Driven by a Latent Action Space 基于潜在动作空间的面部表情动态预测采样
Giuseppe Boccignone, Matteo Bodini, Vittorio Cuculo, G. Grossi
{"title":"Predictive Sampling of Facial Expression Dynamics Driven by a Latent Action Space","authors":"Giuseppe Boccignone, Matteo Bodini, Vittorio Cuculo, G. Grossi","doi":"10.1109/SITIS.2018.00031","DOIUrl":"https://doi.org/10.1109/SITIS.2018.00031","url":null,"abstract":"We present a probabilistic generative model for tracking by prediction the dynamics of affective spacial expressions in videos. The model relies on Bayesian filter sampling of facial landmarks conditioned on motor action parameter dynamics; namely, trajectories shaped by an autoregressive Gaussian Process Latent Variable state-space. The analysis-by-synthesis approach at the heart of the model allows for both inference and generation of affective expressions. Robustness of the method to occlusions and degradation of video quality has been assessed on a publicly available dataset.","PeriodicalId":267494,"journal":{"name":"2018 14th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121259176","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}
引用次数: 8
DOTK: Descriptive Ontology for Territorial Knowledge for Sustainability 可持续性领域知识的描述性本体
Ezoji Amer, M. Nada
{"title":"DOTK: Descriptive Ontology for Territorial Knowledge for Sustainability","authors":"Ezoji Amer, M. Nada","doi":"10.1109/SITIS.2018.00070","DOIUrl":"https://doi.org/10.1109/SITIS.2018.00070","url":null,"abstract":"Ontology is a useful method that can share a common understanding of the structure of information, make domain assumption explicit and analyze the domain knowledge. Representation of territorial knowledge based on the ontology is an approach which explains the nature and reasoning of this knowledge for sustainability. This paper proposes a descriptive ontology for territorial knowledge (DOTK) based on foundation ontology. DOTK ontology is an ontology of domain and its aim is enhancing the sustainable knowledge of actors within industries according to territorial knowledge. Extracting the concepts of the domain is from scientific study. This ontology is a guide for contracting of operational ontology and semantic graph demonstrate the rules between concepts of territorial knowledge. This work is ongoing research for applying of this ontology in the special domain. This study will be considered which part of DOTK and how can help to actors of hierarchical level within industries.","PeriodicalId":267494,"journal":{"name":"2018 14th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123428581","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}
引用次数: 0
NIR Camera Based Mobile Seat Belt Enforcement System Using Deep Learning Techniques 基于近红外相机的基于深度学习技术的移动安全带执法系统
Burak Balci, Bensu Alkan, Alperen Elihos, Y. Artan
{"title":"NIR Camera Based Mobile Seat Belt Enforcement System Using Deep Learning Techniques","authors":"Burak Balci, Bensu Alkan, Alperen Elihos, Y. Artan","doi":"10.1109/SITIS.2018.00045","DOIUrl":"https://doi.org/10.1109/SITIS.2018.00045","url":null,"abstract":"Camera based traffic enforcement solutions have been ubiquitously employed in many countries around the world. Many companies offer camera based solutions towards toll violation, seat belt violation, red light violation, and speed violation enforcement. These systems are typically mounted on a fixed platform to hold the camera and the illuminator. However, installation of these fixed platforms is costly and their operation range is limited to the surrounding area of the installation. In this study, we propose a mobile seat belt enforcement system that can operate on mobile police vehicles. Proposed system utilizes deep learning algorithms towards the detection of the most common traffic violation; not wearing a seat belt while driving. Using a camera system placed on top of a vehicle, real world images are captured during day and night time. We conducted experiments using a test set containing 2600 real world images and achieved an overall accuracy of 83% on seat belt detection task.","PeriodicalId":267494,"journal":{"name":"2018 14th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121916483","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}
引用次数: 1
An Advertisement Effect Simulator for Single Source Data and Its Experimental Evaluation 单源数据广告效果模拟器及其实验评价
Yutaro Hara, Yoshitaka Sakurai, S. Tsuruta, Eriko Sakurai
{"title":"An Advertisement Effect Simulator for Single Source Data and Its Experimental Evaluation","authors":"Yutaro Hara, Yoshitaka Sakurai, S. Tsuruta, Eriko Sakurai","doi":"10.1109/SITIS.2018.00083","DOIUrl":"https://doi.org/10.1109/SITIS.2018.00083","url":null,"abstract":"In the past, advertisements commercial advertisements in TV, Newspapers and Radio broadcasts were very common in Japan and most other countries in the world. Meanwhile, the contact situation to the media has been changing due to recent changes in lifestyles and the spread of smartphones and tablet-type devices worldwide. Therefore, when a company would like to announce their own product, cross media advertisement has become important. However, when announcing products, it is quite costly to advertise on various media. Hence, there are some problems how should company decide, what method of advertisement is the best. In this research, based on the single source data, Nomura Research Institute Ltd. investigates and provides, we create a simulator to estimate advertisement effect in each media. This simulation is based on data. Therefore, the precision of the simulation is affected by the number of data. The objective of this research is to find a relation between the number of data and the precision of the advertising effectiveness. For this purpose, we conducted experiments to observe changes in advertisement effectiveness when changing the number of consumers using a simulator, and the results are summarized.","PeriodicalId":267494,"journal":{"name":"2018 14th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129254344","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}
引用次数: 0
SurfaceVox - Exploring Sound Control for Gesture-Tracking Interactive Surfaces 探索声音控制的手势跟踪交互式表面
Andreas Braun, Martin Majewski, Joachim Loge, Florian Kirchbuchner, Arjan Kuijper
{"title":"SurfaceVox - Exploring Sound Control for Gesture-Tracking Interactive Surfaces","authors":"Andreas Braun, Martin Majewski, Joachim Loge, Florian Kirchbuchner, Arjan Kuijper","doi":"10.1109/SITIS.2018.00113","DOIUrl":"https://doi.org/10.1109/SITIS.2018.00113","url":null,"abstract":"Almost 100 years ago, the thereminvox was the first electronic musical instrument that could be controlled without contact. With precise positioning of two hands, the player controls pitch and volume of a sine sound, by changing the distance from two antennas. We present SurfaceVox, which combines the technology behind the thereminvox with an additional acoustic sensor to create a musical instrument that combines mid-air and touch gesture control. We explore various scenarios of sound synthesis and combine the system with an augmented reality application. SurfaceVox has been evaluated in a study with thirteen users for input precision, perceived workload, as well as pragmatic and hedonistic qualities of the application.","PeriodicalId":267494,"journal":{"name":"2018 14th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124555414","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}
引用次数: 0
Multi-size Pooling for Stereo Matching Cost 立体匹配成本的多尺度池化
Zehua Fu, M. Ardabilian
{"title":"Multi-size Pooling for Stereo Matching Cost","authors":"Zehua Fu, M. Ardabilian","doi":"10.1109/SITIS.2018.00040","DOIUrl":"https://doi.org/10.1109/SITIS.2018.00040","url":null,"abstract":"Dense stereo matching is always a fundamental problem in computer vision due to its wide application related to three dimension scene reconstruction. In this paper, we present a framework to produce better unary features for stereo matching. To aggregate context information and take advantages of different representations, we first extract several features maps from multi-size patches with parameter-shared convolutional layers. Then we proposed two multi-size pooling modules to fuse spatial information. Experimental results prove that our proposed framework with both two pooling models improves the quality of unary features and effectively lower the error rates of disparity maps calculated from unary matching costs on both KITTI 2012 and KITTI 2015 datasets. Moreover, our proposed pooling modules can be easily applied to the feature extraction stage of end-to-end stereo matching frameworks.","PeriodicalId":267494,"journal":{"name":"2018 14th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116255536","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}
引用次数: 0
Halftone Modulation for Embedding UV Watermarks in Color Printed Images 在彩色印刷图像中嵌入UV水印的半色调调制
V. Kitanovski, Marius Pedersen
{"title":"Halftone Modulation for Embedding UV Watermarks in Color Printed Images","authors":"V. Kitanovski, Marius Pedersen","doi":"10.1109/SITIS.2018.00103","DOIUrl":"https://doi.org/10.1109/SITIS.2018.00103","url":null,"abstract":"A method for embedding ultraviolet (UV) responsive watermarks in CMY printed halftone images, named white modulation (WM), was proposed recently, which is based on the iterative color direct binary search (CDBS) halftoning framework. The CDBS-WM method embeds a visual watermark by modulating the local white paper coverage in order to create a differential response under UV illumination through the substrate fluorescence. In this paper, we present two main extensions of CDBS-WM. First, we propose a printer model suitable for UV watermark embedding in multi-channel printer scenarios - using four or more inks. Second, we propose an improved cost function that is minimized during the CDBS-based iterative embedding that takes into account the UV response of all primaries, as opposed to only the white primary in CDBS-WM. The proposed extensions increase the perceptual uniformity of the embedded UV watermark, as well as the UV watermark strength especially in certain image areas where the CDBS-WM failed to embed watermark.","PeriodicalId":267494,"journal":{"name":"2018 14th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130684240","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}
引用次数: 1
Trajectories and Camera Motion Compensation in Aerial Videos 航拍视频中的轨迹和相机运动补偿
C. Beumier, X. Neyt
{"title":"Trajectories and Camera Motion Compensation in Aerial Videos","authors":"C. Beumier, X. Neyt","doi":"10.1109/SITIS.2018.00037","DOIUrl":"https://doi.org/10.1109/SITIS.2018.00037","url":null,"abstract":"This paper presents a method for trajectory extraction in videos acquired with a slightly moving camera. Trajectories are initialized at Shi-Tomasi [1] feature points and tracked thanks to the Lucas-Kanade [2] algorithm from the openCV library [3]. New feature points are regularly introduced to compensate for track losses and to handle newly appeared objects. A simple and fast method for camera motion compensation has been implemented, using the fact that near static scene points undergo an equal translation between any two images. Local histograms of displacement normally exhibit a clear peak since our application considers scenes with relatively few moving targets. These peaks designate which tracks and thus which points are best to estimate the homographies representing motion between frames of the sequence. Tracking results for pedestrian and vehicles with camera motion compensation are shown and discussed for two test cases with different environment, scenario and different video quality. The usefulness of camera motion compensated trajectories is demonstrated by an example of target classification based on track maximal speed and possible hotspot detection from long track pauses.","PeriodicalId":267494,"journal":{"name":"2018 14th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133163629","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}
引用次数: 0
A Reinforcement Learning-Based Approach for the Risk Management of e-Health Environments: A Case Study 基于强化学习的电子卫生环境风险管理方法:案例研究
Giovanni Paragliola, A. Coronato, Muddasar Naeem, G. Pietro
{"title":"A Reinforcement Learning-Based Approach for the Risk Management of e-Health Environments: A Case Study","authors":"Giovanni Paragliola, A. Coronato, Muddasar Naeem, G. Pietro","doi":"10.1109/SITIS.2018.00114","DOIUrl":"https://doi.org/10.1109/SITIS.2018.00114","url":null,"abstract":"Modern medical software systems are often classified as medical devices and governed by regulations which require stringent risk safety activities to be implemented to minimize the occurrence of risky events. This paper proposes a Reinforcement Learning (RL based approach for training a software agent for risk management of medical software systems. The goal of the RL agent is to avoid that a patient enters in dangerous and undesirable states. At the same time, the agent must be able to reach on a safe state or an exit in a minimum interval of time.","PeriodicalId":267494,"journal":{"name":"2018 14th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124156829","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}
引用次数: 9
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信
小红书