Chair of Multimedia Telecommunications and Microelectronics


Robert Ratajczak

Robert Ratajczak


(born 1985) received M.Sc. degree from Poznan University of Technology in 2010. He is a Ph.D. student at the Chair of Multimedia Telecommunications and Microelectronics. The main areas of his professional activities are stereoscopic image processing, object detection and video compression algorithms.

Awards

Research projects

Publications

International journals

  1. Marek Domański, Olgierd Stankiewicz, Krzysztof Wegner, Maciej Kurc, Jacek Konieczny, Jakub Siast, Jakub Stankowski, Robert Ratajczak, Tomasz Grajek,
    High Efficiency 3D Video Coding Using New Tools Based on View Synthesis,
    IEEE Transactions on Image Processing, Special Issue on 3D Video Representation, Compression, & Rendering, Vol. 22, No. 9, September 2013, pp. 3517-3527,
    Full textEndNoteCitationDOI

International conferences

  1. Krzysztof Wegner, Dominika Łosiewicz, Marek Domański, Adrian Dziembowski, Tomasz Grajek, Adam Grzelka, Dawid Mieloch, Robert Ratajczak, Olgierd Stankiewicz, Jakub Stankowski, Krzysztof Wegner,
    Real-time virtual navigation provision by simple means,
    International Conference on Signals and Electronic Systems, ICSES 2018, Kraków, Poland, September 10-12 2018,
    EndNoteCitation
  2. Tomasz Grajek, Robert Ratajczak, Marek Domański, Krzysztof Wegner,
    Limitations of Vehicle Length Estimation Using Stereoscopic Video Analysis,
    20th International Conference on Systems, Signals and Image Processing, IWSSIP 2013, Bucharest, Romania, 7-9 July 2013, pp. 27-30, ISBN: 978-1-4799-0941-4,
    Full textEndNoteCitation
  3. Robert Ratajczak, Tomasz Grajek, Krzysztof Wegner, Krzysztof Klimaszewski, Maciej Kurc, Marek Domański,
    Vehicle Dimensions Estimation Scheme Using AAM on Stereoscopic Video,
    10th IEEE International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2013, Workshop on Vehicle Retrieval in Surveillance (VRS) 2013, Kraków, Poland, 27-30 August 2013, pp. 478-482,
    Full textEndNoteCitation
  4. Robert Ratajczak, Marek Domański, Krzysztof Wegner,
    Vehicle Size Estimation from Stereoscopic Video,
    19th International Conference on Systems, Signals and Image Processing, IWSSIP 2012, Vienna, Austria, 11-13 April 2012, pp. 405-408, ISBN: 978-1-4577-2191-5 ,
    Full textEndNoteCitation
  5. Marek Domański, Jacek Konieczny, Maciej Kurc, Robert Ratajczak, Jakub Siast, Olgierd Stankiewicz, Jakub Stankowski, Krzysztof Wegner,
    3D video compression by coding of disoccluded regions,
    19th IEEE International Conference on Image Processing (ICIP 2012), Orlando, Florida, U.S.A., 30 September - 3 October 2012, pp. 1317-1320,
    Full textEndNoteCitationDOI

International conferences - standardization

  1. Krzysztof Wegner, Tomasz Grajek, Adam Grzelka, Mateusz Lorkiewicz, Robert Ratajczak, Olgierd Stankiewicz, Jakub Stankowski, Hubert Żabiński, Marek Domański,
    Depth Estimation Reference Software extension for lightfield images,
    ISO/IEC JTC1/SC29/WG11 MPEG2019, m46126, Marrakech, Morocco, 13-19 January 2019,
    Full textEndNoteCitation
  2. Marek Domański, Tomasz Grajek, Damian Karwowski, Krzysztof Klimaszewski, Jacek Konieczny, Maciej Kurc, Adam Łuczak, Robert Ratajczak, Jakub Siast, Olgierd Stankiewicz, Jakub Stankowski, Krzysztof Wegner,
    Multiview HEVC – experimental results,
    Joint Collaborative Team on Video Coding (JCT-VC) of ITU-T SG16 WP3 and ISO/IEC JTC1/SC29/WG11, MPEG 2011 / M22147, Geneva, Switzerland, 28 November - 02 December 2011,
    Full textEndNoteCitation

National journals

Patents & Applications

  1. Marek Domański, Tomasz Grajek, Krzysztof Klimaszewski, Adam Łuczak, Robert Ratajczak, Krzysztof Wegner,
    A system and method for object dimension estimation using 3D models,
    Patent office: USPTO, Status: granted,
    Application number: US 14/690484, Filling date: 20.04.2015,
    Patent number: US 9430850, Date of Patent: 30.08.2016,
    EndNoteCitation
  2. Marek Domański, Tomasz Grajek, Krzysztof Klimaszewski, Maciej Kurc, Jakub Stankowski, Robert Ratajczak, Krzysztof Wegner,
    A system and method for object dimension estimation,
    Patent office: USPTO, Status: granted,
    Application number: US 14/664983, Filling date: 23.03.2015,
    Patent number: US 9384417, Date of Patent: 5.07.2016,
    EndNoteCitation
  3. Marek Domański, Tomasz Grajek, Krzysztof Klimaszewski, Maciej Kurc, Jakub Stankowski, Robert Ratajczak, Krzysztof Wegner,
    A system and method for object dimension estimation,
    Patent office: EPO, Status: granted,
    Application number: EP 15160202.06, Filling date: 23.03.2015,
    Publication number: EP 3073442, Publication date: 28.09.2016,
    Patent number: EP 3073442, Date of Patent: 01.03.2017,
    Validated in: PL, DE, FR, GB,
    EndNoteCitation
  4. Marek Domański, Krzysztof Klimaszewski, Jacek Konieczny, Maciej Kurc, Robert Ratajczak, Jakub Siast, Olgierd Stankiewicz, Jakub Stankowski, Krzysztof Wegner,
    Image coding method,
    Patent office: USPTO, Status: granted,
    Application number: US 13/680652, Filling date: 19.11.2012,
    Publication number: US 2013/0129235A1, Publication date: 23.05.2013,
    Patent number: US 8761527, Date of Patent: 24.06.2014,
    EndNoteCitation

2019

  1. Krzysztof Wegner, Tomasz Grajek, Adam Grzelka, Mateusz Lorkiewicz, Robert Ratajczak, Olgierd Stankiewicz, Jakub Stankowski, Hubert Żabiński, Marek Domański,
    Depth Estimation Reference Software extension for lightfield images,
    ISO/IEC JTC1/SC29/WG11 MPEG2019, m46126, Marrakech, Morocco, 13-19 January 2019,
    Full textEndNoteCitation

2018

  1. Krzysztof Wegner, Dominika Łosiewicz, Marek Domański, Adrian Dziembowski, Tomasz Grajek, Adam Grzelka, Dawid Mieloch, Robert Ratajczak, Olgierd Stankiewicz, Jakub Stankowski, Krzysztof Wegner,
    Real-time virtual navigation provision by simple means,
    International Conference on Signals and Electronic Systems, ICSES 2018, Kraków, Poland, September 10-12 2018,
    EndNoteCitation

    Abstract

    The paper reports the results on virtual navigation in a sports hall. The video data is gathered and processed off-line thus producing the multiview plus depth representation of a scene. This representation is an input to the rendering server. Even a typical PC computer is able to serve a number of users that freely and independently navigate in real - time and watch virtual video. The users are able to navigate in the scene changing the virtual viewpoint and virtual view direction. The service is provided through a webpage, so a viewer does not need to install any software on smartphone, tablet or notebook. The paper discusses the technical solutions together with the rationale for their choice.

2017

2015

  1. Marek Domański, Tomasz Grajek, Krzysztof Klimaszewski, Adam Łuczak, Robert Ratajczak, Krzysztof Wegner,
    A system and method for object dimension estimation using 3D models,
    Patent office: USPTO, Status: granted,
    Application number: US 14/690484, Filling date: 20.04.2015,
    Patent number: US 9430850, Date of Patent: 30.08.2016,
    EndNoteCitation

  2. Marek Domański, Tomasz Grajek, Krzysztof Klimaszewski, Maciej Kurc, Jakub Stankowski, Robert Ratajczak, Krzysztof Wegner,
    A system and method for object dimension estimation,
    Patent office: USPTO, Status: granted,
    Application number: US 14/664983, Filling date: 23.03.2015,
    Patent number: US 9384417, Date of Patent: 5.07.2016,
    EndNoteCitation

  3. Marek Domański, Tomasz Grajek, Krzysztof Klimaszewski, Maciej Kurc, Jakub Stankowski, Robert Ratajczak, Krzysztof Wegner,
    A system and method for object dimension estimation,
    Patent office: EPO, Status: granted,
    Application number: EP 15160202.06, Filling date: 23.03.2015,
    Publication number: EP 3073442, Publication date: 28.09.2016,
    Patent number: EP 3073442, Date of Patent: 01.03.2017,
    Validated in: PL, DE, FR, GB,
    EndNoteCitation

  4. Marek Domański, Adrian Dziembowski, Tomasz Grajek, Adam Grzelka, Łukasz Kowalski, Maciej Kurc, Adam Łuczak, Dawid Mieloch, Robert Ratajczak, Jarosław Samelak, Olgierd Stankiewicz, Jakub Stankowski, Krzysztof Wegner,
    Methods of High Efficiency Compression for Transmission of Spatial Representation of Motion Scenes,
    IEEE International Conference on Multimedia and Expo ICME 2015, Torino, Italy, June 29-July 3 2015,
    Full textEndNoteCitation

    Abstract

    The paper reports the hitherto obtained results of the research project that deals with scene representations that are suitable for free navigation around the scene. These scene representations are acquired from a limited number of cameras located around the scene. The project is aimed at the development of an efficient compression technology and the experimental environment for testing such technology. The paper reports some new multiview test sequences with the circular camera arrangement, including the hybrid ones that have been acquired using also the depth sensors. Finally, the paper also briefly reports the recent results of the new compression technology being under development. This technology outperforms the state-of-the-art 3D-HEVC.

2013

  1. Tomasz Grajek, Robert Ratajczak, Marek Domański, Krzysztof Wegner,
    Limitations of Vehicle Length Estimation Using Stereoscopic Video Analysis,
    20th International Conference on Systems, Signals and Image Processing, IWSSIP 2013, Bucharest, Romania, 7-9 July 2013, pp. 27-30, ISBN: 978-1-4799-0941-4,
    Full textEndNoteCitation

  2. Marek Domański, Olgierd Stankiewicz, Krzysztof Wegner, Maciej Kurc, Jacek Konieczny, Jakub Siast, Jakub Stankowski, Robert Ratajczak, Tomasz Grajek,
    High Efficiency 3D Video Coding Using New Tools Based on View Synthesis,
    IEEE Transactions on Image Processing, Special Issue on 3D Video Representation, Compression, & Rendering, Vol. 22, No. 9, September 2013, pp. 3517-3527,
    Full textEndNoteCitationDOI

    Abstract

    We propose a new coding technology for 3D video represented by multiple views and the respective depth maps. The proposed technology is demonstrated as an extension of the recently developed high efficiency video coding (HEVC). One base views are compressed into a standard bitstream (like in HEVC). The remaining views and the depth maps are compressed using new coding tools that mostly rely on view synthesis. In the decoder, those views and the depth maps are derived via synthesis in the 3D space from the decoded baseview and from data corresponding to small disoccluded regions. The shapes and locations of those disoccluded regions can be derived by the decoder without any side information transmitted. To achieve high compression efficiency, we propose several new tools such as depth-based motion prediction, joint high frequency layer coding, consistent depth representation, and nonlinear depth representation. The experiments show high compression efficiency of the proposed technology. The bitrate needed for transmission of two side views with depth maps is mostly less than 50% than that of the bitrate for a single-view video.

  3. Robert Ratajczak, Tomasz Grajek, Krzysztof Wegner, Krzysztof Klimaszewski, Maciej Kurc, Marek Domański,
    Vehicle Dimensions Estimation Scheme Using AAM on Stereoscopic Video,
    10th IEEE International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2013, Workshop on Vehicle Retrieval in Surveillance (VRS) 2013, Kraków, Poland, 27-30 August 2013, pp. 478-482,
    Full textEndNoteCitation

2012

  1. Marek Domański, Krzysztof Klimaszewski, Jacek Konieczny, Maciej Kurc, Robert Ratajczak, Jakub Siast, Olgierd Stankiewicz, Jakub Stankowski, Krzysztof Wegner,
    Image coding method,
    Patent office: USPTO, Status: granted,
    Application number: US 13/680652, Filling date: 19.11.2012,
    Publication number: US 2013/0129235A1, Publication date: 23.05.2013,
    Patent number: US 8761527, Date of Patent: 24.06.2014,
    EndNoteCitation

    Abstract

    An image coding method. The method includes encoding a first image, the first image having a reduced spatial resolution relative to an input image, wherein values of the first image depend on energy of corresponding areas of the input image, and encoding a first shape information of the shape of a spatial spectrum of the input image. The method further includes reconstructing a second image from the encoded first image, reconstructing a second shape information from the encoded first shape information, and generating a noise image having an intensity described by the second image and having a spectrum shape described by the second shape information.

  2. Robert Ratajczak, Marek Domański, Krzysztof Wegner,
    Vehicle Size Estimation from Stereoscopic Video,
    19th International Conference on Systems, Signals and Image Processing, IWSSIP 2012, Vienna, Austria, 11-13 April 2012, pp. 405-408, ISBN: 978-1-4577-2191-5 ,
    Full textEndNoteCitation

  3. Marek Domański, Jacek Konieczny, Maciej Kurc, Robert Ratajczak, Jakub Siast, Olgierd Stankiewicz, Jakub Stankowski, Krzysztof Wegner,
    3D video compression by coding of disoccluded regions,
    19th IEEE International Conference on Image Processing (ICIP 2012), Orlando, Florida, U.S.A., 30 September - 3 October 2012, pp. 1317-1320,
    Full textEndNoteCitationDOI

2011

  1. Marek Domański, Tomasz Grajek, Damian Karwowski, Krzysztof Klimaszewski, Jacek Konieczny, Maciej Kurc, Adam Łuczak, Robert Ratajczak, Jakub Siast, Olgierd Stankiewicz, Jakub Stankowski, Krzysztof Wegner,
    Multiview HEVC – experimental results,
    Joint Collaborative Team on Video Coding (JCT-VC) of ITU-T SG16 WP3 and ISO/IEC JTC1/SC29/WG11, MPEG 2011 / M22147, Geneva, Switzerland, 28 November - 02 December 2011,
    Full textEndNoteCitation