Particle swarm optimization with deep learning for human action recognition S. Jeba Berlin 1 & Mala John 1 Received: 14 February 2019 /Revised: 4 December 2019 /Accepted: 28 January 2020 # Springer Science+Business Media, LLC, part of Springer Nature 2020 Abstract A novel method for human action recognition using a deep learning network with features optimized using particle swarm optimization is proposed. The binary histogram, Harris corner points and wavelet coefficients are the features extracted from the spatiotemporal volume of the video sequence. In order to reduce the computational complexity of the system, the feature space is reduced by particle swarm optimization technique with the multi-objective fitness function. Finally, the performance of the system is evaluated using deep learning neural network (DLNN). Two autoencoders are trained independently and the knowledge embedded in the autoencoders are transferred to the proposed DLNN for human action recognition. The proposed framework achieves an average recognition rate of 91% on UT interaction set 1, 88% on UT interaction set 2, 91% on SBU interaction dataset and 94% on Weizmann dataset. Keywords Video surveillance . Humanactionrecognition . Autoencoder . Deeplearningnetwork . Particle swarm optimization 1 Introduction Video classification is exhaustively explored in computer vision due to its wide range of applications including crowd scene analysis [9], video retrieval [59], health care, human- machine interaction [36] and human action recognition. Among this, human action recognition is an interesting topic that aims in recognizing a particular event of interest in the video sequences. On the other hand, the solution to this problem suffers several bottlenecks [21, 22], which include intra-pattern variation, execution time, camera motion, occlusion, variation in scales, cluttered background and variation in viewpoints. The major tasks in human action recognition involve feature extraction, representation and classification. However, the main Multimedia Tools and Applications https://doi.org/10.1007/s11042-020-08704-0 * S. Jeba Berlin jebaberlin@gmail.com 1 Department of Electronics Engineering, Madras Institute of Technology, Anna University, Chennai, India