The Experts below are selected from a list of 579 Experts worldwide ranked by ideXlab platform
André Kaup - One of the best experts on this subject based on the ideXlab platform.
-
EUSIPCO - Automatic TV logo removal using statistical based logo detection and frequency selective inpainting
2005Co-Authors: Katrin Meisinger, Tobias Troeger, Marcus Zeller, André KaupAbstract:This paper outlines a method for automatically removing logos characterizing a broadcast station in TV sequences. First, the logo is detected automatically based on change detection of moving videos assuming that the image content is changing over time except for the location of the logo. In order to obtain initial logo masks, difference images between frames are binarized by thresholding. The final logo mask is obtained by subsequently refining the change masks by contour relaxation based on Markov Random Fields. Then, the image signal surrounding the logo is extrapolated using a frequency selective method and placed instead of the logo. The proposed algorithm is developed for TV sequences sampled from Analog Television, dealing thus with real world problems as noise, sampling and real logos.
-
Automatic TV logo removal using statistical based logo detection and frequency selective inpainting
2005 13th European Signal Processing Conference, 2005Co-Authors: Katrin Meisinger, Tobias Troeger, Marcus Zeller, André KaupAbstract:This paper outlines a method for automatically removing logos characterizing a broadcast station in TV sequences. First, the logo is detected automatically based on change detection of moving videos assuming that the image content is changing over time except for the location of the logo. In order to obtain initial logo masks, difference images between frames are binarized by thresholding. The final logo mask is obtained by subsequently refining the change masks by contour relaxation based on Markov Random Fields. Then, the image signal surrounding the logo is extrapolated using a frequency selective method and placed instead of the logo. The proposed algorithm is developed for TV sequences sampled from Analog Television, dealing thus with real world problems as noise, sampling and real logos.
H. Watanabe - One of the best experts on this subject based on the ideXlab platform.
-
A VLSI chip set for ghost cancellation and waveform equalization of Analog Television signals
[Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics Speech and Signal Processing, 1992Co-Authors: C. Erskine, S. Kusevitzky, J. Orihara, H. WatanabeAbstract:A VLSI digital filter chip set suitable for performing ghost cancellation and waveform equalization of Analog TV signals is described. The complete chip set consists of one 72-tap and two 288-tap finite impulse response transversal filters. The devices, capable of operation at up to 15-MHz sampling rates, are appropriate for use with oversampled NTSC Television signals. The three chip set (capable of performing 10 billion multiple-accumulate operations per second) provides full coverage for the Ghost Canceller Reference signal in Japan, and is also suitable for ghost cancellation in other countries as new reference signals are developed and broadcast.
-
ICASSP - A VLSI chip set for ghost cancellation and waveform equalization of Analog Television signals
[Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics Speech and Signal Processing, 1992Co-Authors: C. Erskine, S. Kusevitzky, J. Orihara, H. WatanabeAbstract:A VLSI digital filter chip set suitable for performing ghost cancellation and waveform equalization of Analog TV signals is described. The complete chip set consists of one 72-tap and two 288-tap finite impulse response transversal filters. The devices, capable of operation at up to 15-MHz sampling rates, are appropriate for use with oversampled NTSC Television signals. The three chip set (capable of performing 10 billion multiple-accumulate operations per second) provides full coverage for the Ghost Canceller Reference signal in Japan, and is also suitable for ghost cancellation in other countries as new reference signals are developed and broadcast. >
Katrin Meisinger - One of the best experts on this subject based on the ideXlab platform.
-
EUSIPCO - Automatic TV logo removal using statistical based logo detection and frequency selective inpainting
2005Co-Authors: Katrin Meisinger, Tobias Troeger, Marcus Zeller, André KaupAbstract:This paper outlines a method for automatically removing logos characterizing a broadcast station in TV sequences. First, the logo is detected automatically based on change detection of moving videos assuming that the image content is changing over time except for the location of the logo. In order to obtain initial logo masks, difference images between frames are binarized by thresholding. The final logo mask is obtained by subsequently refining the change masks by contour relaxation based on Markov Random Fields. Then, the image signal surrounding the logo is extrapolated using a frequency selective method and placed instead of the logo. The proposed algorithm is developed for TV sequences sampled from Analog Television, dealing thus with real world problems as noise, sampling and real logos.
-
Automatic TV logo removal using statistical based logo detection and frequency selective inpainting
2005 13th European Signal Processing Conference, 2005Co-Authors: Katrin Meisinger, Tobias Troeger, Marcus Zeller, André KaupAbstract:This paper outlines a method for automatically removing logos characterizing a broadcast station in TV sequences. First, the logo is detected automatically based on change detection of moving videos assuming that the image content is changing over time except for the location of the logo. In order to obtain initial logo masks, difference images between frames are binarized by thresholding. The final logo mask is obtained by subsequently refining the change masks by contour relaxation based on Markov Random Fields. Then, the image signal surrounding the logo is extrapolated using a frequency selective method and placed instead of the logo. The proposed algorithm is developed for TV sequences sampled from Analog Television, dealing thus with real world problems as noise, sampling and real logos.
C. Erskine - One of the best experts on this subject based on the ideXlab platform.
-
A VLSI chip set for ghost cancellation and waveform equalization of Analog Television signals
[Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics Speech and Signal Processing, 1992Co-Authors: C. Erskine, S. Kusevitzky, J. Orihara, H. WatanabeAbstract:A VLSI digital filter chip set suitable for performing ghost cancellation and waveform equalization of Analog TV signals is described. The complete chip set consists of one 72-tap and two 288-tap finite impulse response transversal filters. The devices, capable of operation at up to 15-MHz sampling rates, are appropriate for use with oversampled NTSC Television signals. The three chip set (capable of performing 10 billion multiple-accumulate operations per second) provides full coverage for the Ghost Canceller Reference signal in Japan, and is also suitable for ghost cancellation in other countries as new reference signals are developed and broadcast.
-
ICASSP - A VLSI chip set for ghost cancellation and waveform equalization of Analog Television signals
[Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics Speech and Signal Processing, 1992Co-Authors: C. Erskine, S. Kusevitzky, J. Orihara, H. WatanabeAbstract:A VLSI digital filter chip set suitable for performing ghost cancellation and waveform equalization of Analog TV signals is described. The complete chip set consists of one 72-tap and two 288-tap finite impulse response transversal filters. The devices, capable of operation at up to 15-MHz sampling rates, are appropriate for use with oversampled NTSC Television signals. The three chip set (capable of performing 10 billion multiple-accumulate operations per second) provides full coverage for the Ghost Canceller Reference signal in Japan, and is also suitable for ghost cancellation in other countries as new reference signals are developed and broadcast. >
Marcus Zeller - One of the best experts on this subject based on the ideXlab platform.
-
EUSIPCO - Automatic TV logo removal using statistical based logo detection and frequency selective inpainting
2005Co-Authors: Katrin Meisinger, Tobias Troeger, Marcus Zeller, André KaupAbstract:This paper outlines a method for automatically removing logos characterizing a broadcast station in TV sequences. First, the logo is detected automatically based on change detection of moving videos assuming that the image content is changing over time except for the location of the logo. In order to obtain initial logo masks, difference images between frames are binarized by thresholding. The final logo mask is obtained by subsequently refining the change masks by contour relaxation based on Markov Random Fields. Then, the image signal surrounding the logo is extrapolated using a frequency selective method and placed instead of the logo. The proposed algorithm is developed for TV sequences sampled from Analog Television, dealing thus with real world problems as noise, sampling and real logos.
-
Automatic TV logo removal using statistical based logo detection and frequency selective inpainting
2005 13th European Signal Processing Conference, 2005Co-Authors: Katrin Meisinger, Tobias Troeger, Marcus Zeller, André KaupAbstract:This paper outlines a method for automatically removing logos characterizing a broadcast station in TV sequences. First, the logo is detected automatically based on change detection of moving videos assuming that the image content is changing over time except for the location of the logo. In order to obtain initial logo masks, difference images between frames are binarized by thresholding. The final logo mask is obtained by subsequently refining the change masks by contour relaxation based on Markov Random Fields. Then, the image signal surrounding the logo is extrapolated using a frequency selective method and placed instead of the logo. The proposed algorithm is developed for TV sequences sampled from Analog Television, dealing thus with real world problems as noise, sampling and real logos.