• Ishaan Bipin Dwivedi
• Prof. K.S Suresh Babu
• Gaurav Sanjay Mishra
• Ayush Rajendra Dubey
• Abhishek Satish Potare

Video surveillance systems are becoming increasingly prevalent in various applications such as traffic monitoring, security, and law enforcement. However, the large amounts of video data generated by these systems pose significant challenges for effective management and analysis. Video summarization using Deep learning has emerged as a promising technique for condensing long videos into shorter and more meaningful summaries, thereby reducing the time and effort required for video analysis. In this study, we propose an enhanced video summarization approach that integrates both CNN and LRCN models. Firstly, the CNN model is employed to remove static frames from the input video, thereby reducing redundancy. The processed, shortened video is then sent to our LRCN model, trained on the extensive UCF Crime dataset for event recognition. The model processes the input video and tags frames based on the detected events. This results in an output video that is significantly shortened and tagged as per the detected events, giving insights about what is actually happening in the video. Our approach offers a significant reduction in the time and resources required to review surveillance footage, without overlooking critical events. It holds promise for enhancing the efficiency of security systems and has potential applications in various domains requiring video analysis.

Video summarization, Convolutional Neural Network (CNN), Long-term Recurrent Convolution Network (LRCN), Deep learning, Event recognition, University of Central Florida (UCF)

"Surveillance Video Analysis using Event Recognition", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 4, page no.d491-d499, April-2024, Available :http://www.jetir.org/papers/JETIR2404366.pdf

"Surveillance Video Analysis using Event Recognition", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 4, page no. ppd491-d499, April-2024, Available at : http://www.jetir.org/papers/JETIR2404366.pdf