Video Summarization Using Deep Learning for Cricket Highlights Generation

Authors

  • D. Gaikwad Department of Computer Engineering, AISSMS College of Engineering, Pune, India
  • S. Sarap Department of Computer Engineering, AISSMS College of Engineering, Pune, India
  • D. Y. Dhande Department of Mechanical Engineering, AISSMS College of Engineering, Pune, India

DOI:

https://doi.org/10.3329/jsr.v14i2.56856

Abstract

Recently, video surveillance technology has grown pervasive in many aspects of our lives. Automatic video monitoring produces massive amounts of data that need human examination at some point. The primary emphasis is on reducing storage usage by compressing or eliminating superfluous frames without sacrificing real information. The current effort seeks to close the growing gap between the amounts of real data and the volume. Searching through key events in large video collections is time-consuming and tedious. In this paper, smart surveillance for various applications by using video summarization has been presented. A method for generating highlights has presented which pre-processes extracted Video Frames. Convolutional Neural Networks are then used to evaluate these highlighted frames. The proposed technique extracts and calculates characteristics utilized to generate summary movies. For training deep neural networks, cricket datasets have been used. Experimental results show that the proposed solution attains improved results than other advanced summarization methodologies. Experimental results show that the proposed video summarization method consistently generates high-quality reviews for all types of videos. The proposed video summarization method is easy to use, and it can also help extract highlights of cricket games with high accuracy.

Downloads

Download data is not yet available.
Abstract
85
pdf
60

Downloads

Published

2022-05-01

How to Cite

Gaikwad, D., Sarap, S., & Dhande, D. Y. . (2022). Video Summarization Using Deep Learning for Cricket Highlights Generation. Journal of Scientific Research, 14(2), 533–544. https://doi.org/10.3329/jsr.v14i2.56856

Issue

Section

Section A: Physical and Mathematical Sciences