Abstract
The recent increase in the number of videos available in cyberspace is due to the availability of multimedia devices, highly developed communication technologies, and low-cost storage devices. These videos are simply stored in databases through text annotation. Content-based video browsing and retrieval are inefficient due to the method used to store videos in databases. Video databases are large in size and contain voluminous information, and these characteristics emphasize the need for automated video structure analyses. Shot boundary detection (SBD) is considered a substantial process of video browsing and retrieval. SBD aims to detect transition and their boundaries between consecutive shots; hence, shots with rich information are used in the content-based video indexing and retrieval. This paper presents a review of an extensive set for SBD approaches and their development. The advantages and disadvantages of each approach are comprehensively explored. The developed algorithms are discussed, and challenges and recommendations are presented.
Highlights
The rapid increase in the amount of multimedia data in cyberspace in the past two decades has prompted a swift increase in data transmission volume and repository size [1]
The drawback of this algorithm is the implantation of a histogram that is sensitive to flashlights, similar backgrounds, and dark frames
In [133], Chung et al proposed a technique for hard transition (HT) and soft transition (ST) known as video rhythm by transforming 3D video data (V) into a 2D image (VR ) such that the pixels along the horizontal or vertical planes are uniformly sampled along a reference line in the corresponding direction of the video frames
Summary
The rapid increase in the amount of multimedia data in cyberspace in the past two decades has prompted a swift increase in data transmission volume and repository size [1]. Video structure analysis is fairly difficult owing to the following video attributes: (1) videos contain more information than images; (2) videos contain a large volume of raw data; and (3) videos lack or possess a very small prior structure Multimedia databases, especially those for videos, created decades ago are comparatively smaller than current databases owing to the aforementioned characteristics, and annotation was performed manually based on keywords. There are some effects that appear in a video shot such as: flash lights or light variations, object/camera motion, camera operation (such as zooming, panning, and tilting), and similar background These effects are highly provoking the accuracy of transitions detection and greatly impact on SBD algorithm performance. A favorable and efficient method for detecting transitions between shots remains unavailable despite the increasing attention devoted to SBD in the last two decades This unavailability is due to the randomness and size of raw video data.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
