... About lab . ... Online Journal "Computer graphics and multimedia" (in russian) . ... Methods of subjective video quality assessment . ... Our research is aimed at methods of subjective video quality assessments and evaluation of objective quality metrics. ... Because of the lack of tools for conducting subjective tests in the public domain, we created MSU Perceptual Video Quality tool. ... MSU CQE . ... MSU PVQ tool was used for the Subjective Comparison of Modern Video Codecs. ...
... About lab . ... Roadway video passport systems are widely-used for detailed road mapping which allows roadway quality monitoring and repair planning. ... Typical roadway images are strongly differed to each other in colors and texture, some examples are shown below. ... When preprocessing is completed our algorithm is trained on a part of rectified road image with the help of user input. ... We take advantage of image segments classification for object detection on road images. ... Source image . ...
... About lab . ... Online Journal "Computer graphics and multimedia" (in russian) . ... GML BOLT v. 1.1 November 17, 2009 Download . ... Balanced On-line Learning Toolkit is an open-source library that contains a set of on-line classifier interfaces and their implementations. ... Some of toolbox classifiers can also efficiently learn from class-unbalanced streams. ... IClassifier -- the interface for a learned classifier that has been introduced in A.Vezhnevets' GML AdaBoost Toolbox . ...
... About lab . ... Online Journal "Computer graphics and multimedia" (in russian) . ... Photorealistic rendering used in many spheres such as cinema, architecture design, light design, computer games (light maps) and others. The speed is a central problem of photorealistic rendering. ... That s why, acceleration of photorealistic rendering is very important. ... We develop a system that support followed algorithms: . Backward ray tracing . ... See http://ray-tracing.ru/en for more information. ...
... Поступление в лабораторию . ... Электронный журнал "Компьютерная графика и мультимедиа" . ... Filter is intended for representation of moving object phases. ... On second pass motion phases of selected object are built. ... Next follow experimental results of MSU Motion Phase. ... Car motion phases . One more example of MSU Motion Phase on fragment from Matrix film. ... MSU Motion Phase example video (WMV, 6.7MB) . MSU Motion Phase filter home page . MSU Motion Phase example video . ...
... About lab . ... MSU Graphics & Media Lab (Video Group) . Filter is intended for representation of moving object phases. ... On second pass motion phases of selected object are built. ... Next follow experimental results of MSU Motion Phase. ... Car motion phases . One more example of MSU Motion Phase on fragment from Matrix film. Neo motion phases . MSU Motion Phase example video (WMV, 6.7MB) . MSU Motion Phase filter home page . MSU Motion Phase example video . ...
... About lab . ... Multiple object detection . ... Online Journal "Computer graphics and multimedia" (in russian) . ... To detect multiple objects of interest, the methods based on Hough transform use non-maxima supression or mode seeking in order to locate and to distinguish peaks in Hough images. ... Iterations of the Hough-like algorithm for multiple object instances detection: . ... Barinova O, Lempitsky V, Kohli P. On detection of multiple object instances using Hough transform . ...
... Поступление в лабораторию . ... Электронный журнал "Компьютерная графика и мультимедиа" . Учебные курсы лаборатории . ... The LidarK library provides an open-source framework for processing multidimensional point data such as 3D LIDAR scans. ... We called the data structure we designed Seg-Tree . Seg-Tree is a modification of the R-Tree data structure by Antonin Guttman [1984] , which is just an hierarchy of enclosed bounding boxes. ... GML LidarK Library v. 2.0 September 10, 2010 Download . ...
... About lab . ... The LidarK library provides an open-source framework for processing multidimensional point data such as 3D LIDAR scans. ... Download LidarK 2.0 , or browse for the previous versions and data samples . ... We called the data structure we designed Seg-Tree . ... GML LidarK Library v. 2.0 September 10, 2010 Download . GML LidarK Library v. 1.2 December 5, 2008 Download . GML LidarK Library v. 1.1 September 9,2008 Download . GML LidarK Library v. 1.0 July 1, 2008 Download . ...
... Поступление в лабораторию . ... Электронный журнал "Компьютерная графика и мультимедиа" . Учебные курсы лаборатории . ... Traditionaly, study marterials like lectures, textbooks, etc. have been presented to blind and visually impaired students as continous sound files, sometimes broken into several parts. Absence of structure and content-based navigation do not help students in better understanding the audial material. ...
... About lab . ... Traditionaly, study marterials like lectures, textbooks, etc. have been presented to blind and visually impaired students as continous sound files, sometimes broken into several parts. Absence of structure and content-based navigation do not help students in better understanding the audial material. ... The document is broken down into continous audio fragments, organized into hierarchical structure (document tree) with navigation between and inside document tree levels; . ...
... About lab . ... Medical image analysis . ... Geometric image parsing . ... Online Journal "Computer graphics and multimedia" (in russian) . ... We present a new optimization parsing framework for the geometric analysis of a single image coming from a man-made environment. ... Download: . ... Tretiak E, Barinova O, Kohli P, Lempitsky V. Geometric image parsing in man-made environments . ... Barinova O, Lempitsky V, Tretiak E, Kohli P. Geometric Image Parsing in Man?Made Environments . ...
... Поступление в лабораторию . ... Электронный журнал "Компьютерная графика и мультимедиа" . Учебные курсы лаборатории . ... We introduce a novel hands free HCI system that enables to navigate mouse cursor through head movements. ... Two modes of mouse control are provided in the system: position based (Direct mode) and speed based (Joystick mode). ... System enables to combine these two modes according to user's preferences. Head Orientation Vector . ... Mouse Control via User's Head Movements". ...
... About lab . ... While camera can be found in PC systems in increasing frequency, possibility of interaction between human and computer via visual face tracking seems to be very enticing. We introduce a novel hands free HCI system that enables to navigate mouse cursor through head movements. ... Face detection and tracking; . ... Two modes of mouse control are provided in the system: position based (Direct mode) and speed based (Joystick mode). ... Mouse Control via User's Head Movements". ...
... About lab . ... Projects . Video processing . Face recognition . ... Selected completed projects . Text recognition . ... Multiple object detection . Alpha-flow for video matting . ... Online Journal "Computer graphics and multimedia" (in russian) . ... Video matting is a problem of separating foreground object from background in a video sequence. ... Sindeyev M, Konushin A, Rother C. Alpha-flow for video matting . ACCV 2012 (Springer LNCS, Vol. 7726), 2012 ( download ) . ...
... Text recognition . ... Contact person: Olga Barinova (obarinova@graphics.cs.msu.ru) . Automatic detection and understanding the text in natural images, such as photographs of city outdoors or building indoors, is a challenging problem. ... Novikova T, Barinova O, Kohli P, Lempitsky V. Large-lexicon attribute-consistent text recognition in natural images . ... Milyaev S, Barinova O, Novikova T, Lempitsky V, Kohli P. Image binarization for end-to-end text understanding in natural images . ...
... Поступление в лабораторию . ... Электронный журнал "Компьютерная графика и мультимедиа" . Учебные курсы лаборатории . ... Video Frame Rate N-Times Up-Conversion . Removal of comb effect from video . ... Smart removal of blocking effects from video . Video Frame Rate Double Up-Conversion . High-quality increase of video color depth . High-quality video resolution enhancement . ... Automatic fixing of shifted fields in video . ... Removal of noise from video . ...
... About lab . ... Online Journal "Computer graphics and multimedia" (in russian) . ... Video Frame Rate N-Times Up-Conversion . Removal of comb effect from video . ... Smart removal of blocking effects from video . Video Frame Rate Double Up-Conversion . High-quality increase of video color depth . High-quality video resolution enhancement . ... Smart enhance of frame sharpness . ... Removal of noise from video . ... Removing of blocking effect from video . ...
... About lab . ... Video processing . ... Video-based tracking . ... Online Journal "Computer graphics and multimedia" (in russian) . ... Compression project . ... VQMT3D (Video Quality Measurement Tool 3D) project was created to improve stereoscopic films. ... Each frame of video sequence is subdivided into regions of two types: foreground and background objects. ... High-quality increase of video color depth . ... Keyframe-based Depth Compression with Depth Propagation for Multiview Video Coding . ...
... About lab . ... Courses . ... Online Journal "Computer graphics and multimedia" (in russian) . Educational courses (in russian) . Compression project . ... x264 codec improvement . Objective comparison of H.264 video codecs . Subjective Assessment of Video Quality (MSU PVQ tool) . Lossless Video Compression (MSU Lossless Video Codec) . Subjective Comparison of Video Codecs . Objective Metrics of Video Quality (MSU VQM tool) . ...