Human Action Recognition Using LRCN & LSTM

DOI

10.2991/978-94-6463-529-4_6How to use a DOI?

Keywords

Human Activity; CNN; long short-term memory; frame extraction; Recognition; LRCN

Abstract

Recent developments in artificial intelligence have enabled the world to detect objects, learn their surroundings, and forecast the next sequences. The cost of surveillance systems is reduced as a result of the development of embedded technology. The surroundings are being captured by the surveillance equipment and are being kept in memory. To interpret the environmental data we collected and understand the scenario, deep learning is used. This Paper examines the notion of using film to identify human action and behavior. Additionally, this Paper suggests combining LSTM and CNN for analyzing the video. Convolution processing transforms the input into relevant spatial information. To create temporal features, the collected features are fed into lengthy short-term modules and Long term recurrent convolution network. The hypothesized attention elements were fed by the feature maps of the LSTM and LRCN. It captures in the video’s frame the really valuable instructive aspects. Using video, these models can identify human behaviors. The experimental findings demonstrated that the proposed model performed more accurately and efficiently.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Swapnil Patil
AU  - Devyani Ushir
AU  - Komal Shinde
AU  - Aditya Vhanmane
AU  - Siddharth Bhorge
PY  - 2024
DA  - 2024/10/04
TI  - Human Action Recognition Using LRCN & LSTM
BT  - Proceedings of the International Conference on Signal Processing and Computer Vision (SIPCOV-2023)
PB  - Atlantis Press
SP  - 58
EP  - 65
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-529-4_6
DO  - 10.2991/978-94-6463-529-4_6
ID  - Patil2024
ER  -