A Shot boundary Detection Technique based on Visual Colour Information
- PDF / 902,439 Bytes
- 16 Pages / 439.642 x 666.49 pts Page_size
- 87 Downloads / 197 Views
A Shot boundary Detection Technique based on Visual Colour Information Saptarshi Chakraborty1
· Dalton Meitei Thounaojam1 · Nidul Sinha1
Received: 22 August 2019 / Revised: 26 August 2020 / Accepted: 9 September 2020 / © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract The paper proposes a novel video segmentation system with maiden application of CIEDE2000 colour-difference and mean luminace pattern. CIEDE2000 colour-difference uses Lab colour space which is a stable and efficient colour space. The main advantage of Lab colour space model is that it can approximate all the available colours perceived by our human eye. CIEDE2000 colour difference is used for detecting abrupt transitions in the video. The novel contribution of the paper is the maiden use of the mean luminance pattern, increasing and decreasing patterns of the mean value of frame luminance, for detecting the gradual transition. The approach is validated on standard databases TRECVid 2001 and 2007 test video database. The performance of the proposed technique is compared with recently reported techniques and found to be superior as compared to other techniques. The accuracy achieved with the proposed method on the standard databases is 95.9% for cut transition, 78.6% for gradual transition and 92.1% overall. Keywords Shot boundary · cut · dissolve · Luminance · Video Segmentation
1 Introduction The Internet has provided a way to access information at any time and from any place. With this feature, the usage of the Internet has expanded and the demand of more information, quick access and availability also has increased tremendously. Due to increase in social networking, on-line shopping, on-line tutorials,etc., the generation of data on the internet is unbounded making it difficult to access the information effectively. Moreover, the data like video contains much raw informations and because of this, it is very tedious to store or retrieve the data with query from user or title of the video [12, 29]. Because of this property, the contents of the video must be analysed throughly before passing it for video analysis, video indexing and video retrieval process. For analyzing the video, it is necessary to divide the video into meaningful segments, called shots. In short, a shot consist of similar contents, Saptarshi Chakraborty
[email protected] 1
Computer Vision Laboratory Department of Computer Science, Engineering, National Institute of Technology Silchar, Assam, India
Multimedia Tools and Applications
either object or features, for a particular consecutive length of frames in a video. The process of finding the boundary between two consecutive shots is known as shot boundary detection. Normally, shot boundary consists of two particular types of transitions - abrupt transition or gradual transition. Abrupt transition is also known as cut transition, since the transition occurs suddenly between two consecutive frames. Gradual transition is an outcome of edit effect where it is broadly classified into fade, d
Data Loading...
