Abstract
The increasing rate of creation and use of 3D video content leads to a pressing need for methods capable of lowering the cost of 3D video searching, browsing and indexing operations, with improved content selection performance. Video summarisation methods specifically tailored for 3D video content fulfil these requirements. This paper presents a review of the state-of-the-art of a crucial component of 3D video summarisation algorithms: the key-frame extraction methods. The methods reviewed cover 3D video key-frame extraction as well as shot boundary detection methods specific for use in 3D video. The performance metrics used to evaluate the key-frame extraction methods and the summaries derived from those key-frames are presented and discussed. The applications of these methods are also presented and discussed, followed by an exposition about current research challenges on 3D video summarisation methods.
Highlights
The increasing rate of creation and use of 3D video content leads to a pressing need for methods capable of lowering the cost of 3D video searching, browsing and indexing operations, with improved content selection performance
1.4.2 Evaluation metrics Three well-known performance indicators are used in the evaluation of the shot boundary detection (SBD) methods for 2D video: recall rate (R), precision rate (P) [39] and accuracy measure F1 [40]
Precision rate, computed according to Eq (2), is defined as the ratio between the number of shot boundaries detected by an algorithm and the sum of this value with the number of false positives
Summary
The increasing rate of creation and use of 3D video content leads to a pressing need for methods capable of lowering the cost of 3D video searching, browsing and indexing operations, with improved content selection performance. In the video summarisation process, a subset of key-frames or a set of shorter video sub-sequences (with or without audio) are chosen to represent the most important segments of the original video content according to predefined criteria [4]. In regard to 3D video content, a detailed study of the existing scientific literature reveals that comprehensive comparative studies of 3D video summarisation methods are missing To help filling this gap, this paper presents a review of 3D video summarisation methods based on key-frames. This overview of the current state-of-the-art is mainly focused on the methods and features that are used to generate and evaluate 3D video summaries and not so much on the limitations or performance of specific methods. This paper identifies open issues to be investigated in the area of 3D key-frame extraction for summarisation
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
