ABSTRACT
The development of Human Action Recognition (HAR) system is getting popular. This project developed a HAR system for the application in the surveillance system to minimize the man-power for providing security to the citizens such as public safety and crime prevention. In this research, deep learning network using Recurrent Neural Network (RNN) with Long Short-Term Memory (LSTM) are used to analyze dynamic video motion of sport actions and classify different types of actions and their performance. It could classify different types of human motion with a small number of video frame for efficiency and memory saving. The current accuracy achieved is up to 92.9% but with high potential of further improvement.
- Timothy Revell. 2017. Computer vision algorithms pick out petty crime in CCTV footage. (January 2017). Retrieved July 9, 2018 from https://www.newscientist.com/article/2116970-computer-vision-algorithms-pick-out-petty-crime-in-cctv-footage/Google Scholar
- Paul Brown, Robin McGloughlin, and Chris Day. 2012. Poolview Plus ™ - Underwater Swimming Pool Camera, Drowing Prevention, Pool Safety. (September 2012). Retrieved June 22, 2018 from http://www.poolview.co.uk/poolview-plusGoogle Scholar
- Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long Short-term Memory. Neural Computation 9, 8 (December 1997), 1735--1780. Google ScholarDigital Library
- Zhe Cao and Tomas Simon. 2017. Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields. (April 2017).Google Scholar
- Rohith Gandhi. 2018. Introduction to Sequence Models - RNN, Bidirectional RNN, LSTM, GRU. (June 2018). Retrieved November 10, 2018 from https://towardsdatascience.com/introduction-to-sequence-models-rnn-bidirectional-rnn-lstm-gru-73927ec9df15Google Scholar
- Andrej Karpathy. 2015. The Unreasonable Effectiveness of Recurrent Neural Networks. (May 2015). Retrieved September 23, 2018 from http://karpathy.github.io/2015/05/21/rnn-effectiveness/Google Scholar
- Ian Goodfellow, Yoshua Bengio, and Aaron Courville. 2017. Deep learning, Cambridge, MA: The MIT Press. Google ScholarDigital Library
- Amar Budhiraja. 2016. Learning Less to Learn Better-Dropout in (Deep) Machine learning. (December 2016). Retrieved September 13, 2018 from https://medium.com/@amarbudhiraja/https-medium-com-amarbudhiraja-learning-less-to-learn-better-dropout-in-deep-machine-learning-74334da4bfc5Google Scholar
- Amar Budhiraja. 2016. Learning Less to Learn Better-Dropout in (Deep) Machine learning. (December 2016). Retrieved September 13, 2018 from https://medium.com/@amarbudhiraja/https-medium-com-amarbudhiraja-learning-less-to-learn-better-dropout-in-deep-machine-learning-74334da4bfc5Google Scholar
- Srini Ananthakrishnan. 2018. Recognition Design. (October 2018). Retrieved September 23, 2018 from https://github.com/srianant/computer_vision/blob/master/openposeGoogle Scholar
- Pierre Baldi and Peter Sadowski. 2014. The dropout learning algorithm. Artificial Intelligence 210 (May 2014), 78--122.Google Scholar
Index Terms
- Artificial Intelligence for Sport Actions and Performance Analysis using Recurrent Neural Network (RNN) with Long Short-Term Memory (LSTM)
Recommendations
Human activity detection from inertial data using RNN and LSTM network
With the advancement of smartphones and the rapid development of artificial intelligence, human activity detection systems help to improve human welfare and health. However, these systems need to be constantly renewed, improved and updated. In this paper, ...
Sales Demand Forecast based on Recurrent Neural Network∗
EITCE '22: Proceedings of the 2022 6th International Conference on Electronic Information Technology and Computer EngineeringIn this paper, we compare the performance of RNN, LSTM and GRU, which are the most popular cyclic neural networks, in predicting the total sales of products in each store next month. A dropout layer is added to the model to reduce over-fitting. The ...
Detecting spamming reviews using long short-term memory recurrent neural network framework
ICEEG '18: Proceedings of the 2nd International Conference on E-commerce, E-Business and E-GovernmentSome unethical companies may hire workers (fake review spammers) to write reviews to influence consumers' purchasing decisions. However, it is not easy for consumers to distinguish real reviews posted by ordinary users or fake reviews post by fake ...
Comments