International Conference on Vision, Video and Graphics最新文献

{"title":"Rigorous Computing in Computer Vision","authors":"M. Farenzena, Andrea Fusiello","doi":"10.2312/VVG.20051013","DOIUrl":"https://doi.org/10.2312/VVG.20051013","url":null,"abstract":"In this paper we discuss how Interval Analysis can be used to s olve some problems in Computer Vision, namely autocalibration and triangulation. The crucial property o f Interval Analysis is its ability to rigorously bound the range of a function over a given domain. This allows to propag ate input errors with guaranteed results (used in multi-views triangulation) and to search for solution in no n-linear minimisation problems with provably correct branch-and-bound algorithms (used in autocalibration). E xperiments with real calibrated images illustrate the interval approach.","PeriodicalId":137668,"journal":{"name":"International Conference on Vision, Video and Graphics","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127985313","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 Vision-Based Location System using Fiducials","authors":"D. J. Johnston, A. Clark","doi":"10.2312/vvg.20031022","DOIUrl":"https://doi.org/10.2312/vvg.20031022","url":null,"abstract":"A system for vision-based ego location using ‘targets’ or ‘fiducials’ is described. The system is robust and operates on commodity hardware in real time. The accuracy of the system is assessed and found to be good enough to support some augmented reality applications. Two example applications are described: the control of an avatar in a shared virtual environment and a video ‘joystick’ for manipulating 3D models. Categories and Subject Descriptors (according to ACM CCS) : I.4.8 [Image Processing and Computer Vision]: Scene Analysis","PeriodicalId":137668,"journal":{"name":"International Conference on Vision, Video and Graphics","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133851869","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":"On the Editing of Images: Selecting, Cutting and Filling-in","authors":"F. Labrosse","doi":"10.2312/vvg.20031010","DOIUrl":"https://doi.org/10.2312/vvg.20031010","url":null,"abstract":"This paper is two-fold. On the one hand, we present a system using qualitative spatial reasoning to help a user choose parts of an image that form interesting objects. The system then allows the user to cut these parts as if unwanted in the original image. On the other hand, we propose a modification of existing texture synthesis methods to create texture in the holes left by the cutting of previously selected areas of the image. This texture synthesis is constrained so that it creates boundaries between regions that are similar to existing ones and fills-in the created regions, yet producing random enough textures so that the new image looks realistic. The context of this work is post-production special effects in cinema or image manipulation where one often wants to remove parts of an image, e.g. when they correspond to props needed for the filming or objects inadvertently included in the shot. A note to the reader: Most images are better viewed in colour and are available on the electronic version of this paper or at http://users.aber.ac.uk/ffl/ .","PeriodicalId":137668,"journal":{"name":"International Conference on Vision, Video and Graphics","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123486841","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 Model-Based Approach to Image Relighting with a Potential for Real-Time Implementation","authors":"C. Madsen, Rune E. Laursen","doi":"10.2312/VVG.20051032","DOIUrl":"https://doi.org/10.2312/VVG.20051032","url":null,"abstract":"AbstractImage relighting is a very unique special visual effect which promises to have many important practical applica-tions. Image relighting is essentially the process of, given one or more images of some scene, computing what thatscene would look like under some other (arbitrary) lighting conditions, e.g., changing positions and colors of lightsources. Image relighting can for example be used for interior light design. This paper describes an approach toimage relighting which can be implemented to run in real-time by utilizing graphicshardware, as opposed to otherstate-of-the-art approaches which at best run at a few frames per second.Categories and Subject Descriptors (according to ACM CCS) : I.3.4 [Computer Graphics]: Three-DimensionalGraphics and Realism1. IntroductionThis paper addresses the subject of developing relightingtechniques, i.e. techniques allowing a user to completely al-ter the lighting conditions in an image of a real scene. Specif-ically, the paper focuses on techniques providing real-timerelighting functionalities, thus enabling the user to interac-tively change lighting conditions and get \"instant\" visualfeedback. Figure 1 provides an example of the kind of re-lighting this paper addresses. It should be noted that the workpresented here presumes the availability of three things: 1)an original image of the scene, 2) a 3D model of the scene,and 3) a model of the lighting conditions in the scene at thetime the original image is acquired. We will return to waysin which the two last pieces of knowledge can be obtained.Conceptually image relighting in this manner is a two stepprocess. In the first step all effects of the original lightingconditions are removed, e.g., highlights, shadows, and dif-ferences in shading across surfaces due to varying light in-cidence angles. In the second step the scene is subjected tosome arbitrary new lighting conditions and the appearanceof the scene in these conditions is computed. The secondstep thus \"adds\" new highlights, shadows and shading etc.Of these two steps the former is the tricky one, while thelatter can be performed using any preferred rendering tech-nique, e.g., ray tracing, radiosity or standard hardware accel-erated approaches. Which rendering technique is employeddepends on the preferred balance between rendering speedand accuracy in handling various lighting phenomena. In or-der to achieve true real-time performance we have chosen touse a hardware accelerated approach for step 2, thus sacri-ficing certain global illumination phenomena.In our approach step 1 is achieved by a computational ap-proach which requires, as stated above, a 3D model of thescene and a model of the original lighting conditions. Alter-natively, one could in principle acquire fronto-parallel digitalimages of the surfaces in the scene under perfectly diffuse,white-balanced lighting conditions and use these images astextures on the 3D model, which is subsequently renderedunder novel lighting conditions (step 2).","PeriodicalId":137668,"journal":{"name":"International Conference on Vision, Video and Graphics","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126344568","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":"Interpretation of Fuzzy Logic For Texture Queries in CBIR","authors":"S. Kulkarni","doi":"10.2312/vvg.20031024","DOIUrl":"https://doi.org/10.2312/vvg.20031024","url":null,"abstract":"This paper presents a novel fuzzy logic based approach for the interpretation of texture queries. Tamura feature extraction technique is used to extract each texture feature of an image in the database. A term set on each Tamura feature is generated by a fuzzy clustering algorithm to pose a query in terms of natural language. The query can be expressed as a logic combination of natural language terms and tamura feature values. The performance of the technique was evaluated on Brodatz texture benchmark database. Experimental results show that the proposed technique is effective and the retrieved images indicate that those images are suitable for the specific queries.","PeriodicalId":137668,"journal":{"name":"International Conference on Vision, Video and Graphics","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124089094","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":"Visual Recognition of Man-made Materials and Structures in an Office Environment","authors":"Yi-Zhe Song, C. Town","doi":"10.2312/VVG.20051021","DOIUrl":"https://doi.org/10.2312/VVG.20051021","url":null,"abstract":"This paper demonstrates a new approach towards object recognition founded on the development of Neural Network classifiers and Bayesian Networks. The mapping from segmented image region descriptors to semantically meaningful class membership terms is achieved using Neural Networks. Bayesian Networks are then employed to probabilistically detect objects within an image by means of relating region class labels and their surrounding environments. Furthermore, it makes use of an intermediate level of image representation and demonstrates how object recognition can be achieved in this way.","PeriodicalId":137668,"journal":{"name":"International Conference on Vision, Video and Graphics","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127880960","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":"Applications of Clifford Algebra in Mixed Reality Environment","authors":"Edward Ho","doi":"10.2312/vvg.20031027","DOIUrl":"https://doi.org/10.2312/vvg.20031027","url":null,"abstract":"","PeriodicalId":137668,"journal":{"name":"International Conference on Vision, Video and Graphics","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130334080","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":"Multi-View Image Coding with Wavelet Lifting Scheme","authors":"N. Anantrasirichai, C. N. Canagarajah, D. Bull","doi":"10.2312/vvg.20051005","DOIUrl":"https://doi.org/10.2312/vvg.20051005","url":null,"abstract":"In this paper, we present a novel multi-view image codec based on a wavelet lifting scheme. The proposed algorithm applies the disparity estimation and compensation with the lifting scheme. It is very efficient in terms of compressions performance, memory requirements and fast computation. To get the highest multiview image coding efficiencies, two hybrid predictions are proposed; one for effective compression performance and one for compromising when more exact disparity values are required. Moreover, an adaptive weighing in update step and overlapped block disparity compensation are included to yield significant improvements in rate distortion performance. Experimental results show image quality gains of up to 2 dB and 1 dB against using well established methods such as the block-matching Haar and 5/3 wavelet lifting respectively.","PeriodicalId":137668,"journal":{"name":"International Conference on Vision, Video and Graphics","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130744654","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":"Parameter Acquisition of Geometric Primitives within Virtual Environments for Internet-Based Telerobotics","authors":"Jiacheng Tan, G. Clapworthy","doi":"10.2312/vvg.20031012","DOIUrl":"https://doi.org/10.2312/vvg.20031012","url":null,"abstract":"With the aim of improving the efficiency of on-line modelling of virtual environments (VEs) in Internet-based telerobotics (IBT), this paper addresses the modelling of geometric primitives using only a single view of them. By studying the properties and constraints of the primitives under perspective projection, we propose a searching method that uses virtual features as matching templates for the parameter acquisition of 3D objects, the analytical descriptions of which are hard to find.","PeriodicalId":137668,"journal":{"name":"International Conference on Vision, Video and Graphics","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125596322","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":"Quasi-3D cell-based Animation","authors":"M. Qi, P. Willis","doi":"10.2312/vvg.20031015","DOIUrl":"https://doi.org/10.2312/vvg.20031015","url":null,"abstract":"We present a method for image compositing and rendering using 2D geometric shapes or raster images as input primitives, disposed in a 3D environment around which the camera can move. An animation system has been implemented which calculates camera and scene information to render the frames. The key features of this quasi3D system are described. Two animations generated by the system are given as examples.","PeriodicalId":137668,"journal":{"name":"International Conference on Vision, Video and Graphics","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121659176","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}