A Review on Key Features and Novel Methods for Video Summarization
Vinsent Paramanantham1, S. Suresh Kumar2
1Vinsent Paramanantham, Faculty of Computing, Sathyabama University, Chennai (Tamil Nadu), India.
2Dr. S. Suresh Kumar, Principal, Swarnandhra College of Engineering and Technology, Narasapur (A.P), India.
Manuscript received on 22 July 2022 | Revised Manuscript received on 16 February 2023 | Manuscript Accepted on 15 February 2023 | Manuscript published on 28 February 2023 | PP: 88-105 | Volume-12 Issue-3, February 2023 | Retrieval Number: 100.1/ijeat.F37370811622 | DOI: 10.35940/ijeat.F3737.0212323
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: This paper discusses techniques, algorithms, and evaluation methods used in online, offline, supervised, unsupervised, multi-video, and clustering methods for video summarisation and multi-view video summarisation, drawing on various references. We have studied multiple techniques in the literature and described the features used for generating video summaries, along with evaluation methods, including supervised and unsupervised algorithms, as well as the datasets employed. We have covered the survey on the new frontier of research in computational intelligence techniques, such as Artificial Neural Networks (ANN) and other evolutionary algorithms for VS, using both supervised and unsupervised methods. We highlight single and multi-video summarisation, considering features such as video, audio, and semantic embeddings for VS in the literature. A careful presentation is attempted to bring the performance comparison with Precision, Recall, F-Score, and manual methods to evaluate the VS.
Keywords: Video Summarization, Multi-View Video Summarization, Online Offline Video Highlighting, Key Frames, Sparse Coding, Feature Extraction, Sparse Land, CNN, RNN, LSTM.
Scope of the Article: Artificial Neural Network