Human action recognition using fusion‐based discriminative features and long short term memory classification

Abstract

Summary Proposed is a discriminative feature modeling technique in three orthogonal planes (TOP) for human action recognition (HAR). Pyramidal histogram of orientation gradient‐TOP (PHOG‐TOP) and dense optical flow‐TOP (DOF‐TOP) techniques are utilized for salient motion estimation and description to represent the human action in a compact but distinct manner. The contribution of the work is to explicitly learn the gradual change of visual patterns using fusion of PHOG‐TOP and DOF‐TOP technique to discover the nature of the action. With this feature representation, dimensionality reduction is achieved by deep stacked autoencoders. The encoded feature representation is used in long short term memory (LSTM) classification for HAR. Experiments with better recognition rate demonstrate the discriminative power of the proposed descriptor. Moreover, the proposed modeling and LSTM classification outperforms the state of art methods for HAR.

Human Action Representation Learning Using an Attention-Driven Residual 3DCNN Network

“…Table 3 showcases the results that indicate that our proposed DA-R3DCNN achieved the highest accuracy of 98.6%, surpassing all other methods. The Fusion-based discriminative features method [31]came in second place, with an accuracy of 97.8%. Among the comparative methods, the lowest accuracy on the UCF11 dataset was obtained by the Local-global features + QSVM method [32], which achieved an accuracy of 82.6%.…”

“…Multi-task hierarchical clustering [33] 2017 89.7 BT-LSTM [34] 2018 85.3 Deep autoencoder [35] 2019 96.2 Two-stream attention LSTM [36] 2020 96.9 Weighted entropy-variances based feature selection [37] 2021 94.5 Dilated CNN+BiLSTM+RB [38] 2021 89.0 DS-GRU [39] 2021 97.1 Local-global features + QSVM [32] 2021 82.6 Squeezed CNN [40] 2022 87.4 Fusion-based discriminative features [31] 2022 97.8 BS-2SCN [41] 2022 90.1 3DCNN [42] 2022 85.1 DA-R3DCNN (Proposed) 2023 98.6…”