|
|
Video Shot Boundary Detection
Suja, Dušan ; Řezníček, Ivo (referee) ; Hradiš, Michal (advisor)
This thesis is concerned about video cut detections. Introduction explaining methods for video shot cut detecting, their advantages and disadvantages their speed and accuracy. Next chapters deal with implemented methods for detection of hard cuts using C++ library OpenCV
|
|
|
Shot Boundary Detection
Klicnar, Lukáš ; Herout, Adam (referee) ; Beran, Vítězslav (advisor)
Shot boundary detection is a process of automatically finding the boundaries between shots in a video. This work primarily deals with detection of hard-cuts, but gradual transitions are also considered. At first, fundamental terms of this field are explained, commonly used methods are shortly described. The main part of this work is design and implementation of system for shot boundary detection based on combination of two methods. The first one is comparison of color histograms for adjacent frames. Second approach is based on visual feature tracking. The analysis of behavior of those features is done by estimating their first derivatives. Proposed system was tested on small, manually annotated set of test data, which showed that both features are suitable for this task. Detector proved its ability to find hard-cuts with good precision. It was also able to detect some gradual transitions.
|
|
|
Tool for Collection and Processing of Sports Videos
Bahník, Marek ; Zemčík, Pavel (referee) ; Herout, Adam (advisor)
The aim of this thesis is to create a tool in Python for downloading videos from YouTube and parsing them into usable form for possible neural network training. Videos are split into separate clips using proprietary method of comparing two frames around suspect frame. These clips are furthermore classified on a~scale of relevance using optical flow. To download quality videos from YouTube, user has to input proper search word and custom filters. This tool is not fully automated and optimized, but it is designet to make dataset creation much faster and simpler. In general user has to intervene manually and check output data.
|
|
|
Detekce střihů a vyhledávání známých scén ve videu s pomocí metod hlubokého učení
Souček, Tomáš ; Lokoč, Jakub (advisor) ; Peška, Ladislav (referee)
Video retrieval represents a challenging problem with many caveats and sub-problems. This thesis focuses on two of these sub-problems, namely shot transition detection and text-based search. In the case of shot detection, many solutions have been proposed over the last decades. Recently, deep learning-based approaches improved the accuracy of shot transition detection using 3D convolutional architectures and artificially created training data, but one hundred percent accuracy is still an unreachable ideal. In this thesis we present a deep network for shot transition detection TransNet V2 that reaches state-of- the-art performance on respected benchmarks. In the second case of text-based search, deep learning models projecting textual query and video frames into a joint space proved to be effective for text-based video retrieval. We investigate these query representation learning models in a setting of known-item search and propose improvements for the text encoding part of the model. 1
|
|
|
Video Shot Boundary Detection
Suja, Dušan ; Řezníček, Ivo (referee) ; Hradiš, Michal (advisor)
This thesis is concerned about video cut detections. Introduction explaining methods for video shot cut detecting, their advantages and disadvantages their speed and accuracy. Next chapters deal with implemented methods for detection of hard cuts using C++ library OpenCV
|
|
|
Shot Boundary Detection
Klicnar, Lukáš ; Herout, Adam (referee) ; Beran, Vítězslav (advisor)
Shot boundary detection is a process of automatically finding the boundaries between shots in a video. This work primarily deals with detection of hard-cuts, but gradual transitions are also considered. At first, fundamental terms of this field are explained, commonly used methods are shortly described. The main part of this work is design and implementation of system for shot boundary detection based on combination of two methods. The first one is comparison of color histograms for adjacent frames. Second approach is based on visual feature tracking. The analysis of behavior of those features is done by estimating their first derivatives. Proposed system was tested on small, manually annotated set of test data, which showed that both features are suitable for this task. Detector proved its ability to find hard-cuts with good precision. It was also able to detect some gradual transitions.
|
guest ::
