Video summarization has arisen as a method that can help with efficient storage, rapid browsing, indexing, fast retrieval, and quick sharing of the material. The amount of video data created has grown exponentially over time. Huge amounts of video are produced continuously by a large number of cameras. Processing these massive amounts of video requires a lot of time, labor, and hardware storage. In this situation, a video summary is crucial. The architecture of video summarization demonstrates how a lengthy film may be broken down into shorter, story-like segments. Numerous sorts of studies have been conducted in the past and continue now. As a result, several approaches and methods—from traditional computer vision to more modern deep learning approaches—have been offered by academics. However, several issues make video summarization difficult, including computational hardware, complexity, and a lack of datasets. Many researchers have recently concentrated their research efforts on developing efficient methods for extracting relevant information from videos. Given that data is gathered constantly, seven days a week, this study area is crucial for the advancement of video surveillance systems that need a lot of storage capacity and intricate data processing. To make data analysis easier, make it easier to store information, and make it easier to access the video at any time, a summary of video data is necessary for these systems. In this paper, methods for creating static or dynamic summaries from videos are presented. The authors provide many approaches for each literary form. The authors have spoken about some features that are utilized to create video summaries.