A Novel Human Action Recognition and Behaviour Analysis Technique using SWFHOG

Abstract

In this paper, a new local feature, called, Salient Wavelet Feature with Histogram of Oriented Gradients (SWFHOG) is introduced for human action recognition and behaviour analysis. In the proposed approach, regions having maximum information are selected based on their entropies. The SWF feature descriptor is formed by using the wavelet sub-bands obtained by applying wavelet decomposition to selected regions. To improve the accuracy further, the SWF feature vector is combined with the Histogram of Oriented Gradient global feature descriptor to form the SWFHOG feature descriptor. The proposed algorithm is evaluated using publicly available KTH, Weizmann, UT Interaction, and UCF Sports datasets for action recognition. The highest accuracy of 98.33% is achieved for the UT interaction dataset. The proposed SWFHOG feature descriptor is tested for behaviour analysis to identify the actions as normal or abnormal. The actions from SBU Kinect and UT Interaction dataset are divided into two sets as Normal Behaviour and Abnormal Behaviour. For the application of behaviour analysis, 95% recognition accuracy is achieved for the SBU Kinect dataset and 97% accuracy is obtained for the UT Interaction dataset. Robustness of the proposed SWFHOG algorithm is tested against Camera view angle change and imperfect actions using Weizmann robustness testing datasets. The proposed SWFHOG method shows promising results as compared to earlier methods.

Impulsive Aggression Break, Based on Early Recognition Using Spatiotemporal Features

“…Lejmi et al [37] DBN 65.5% Lejmi et al [28] LSTM 84.62% Verma et al [42] TNN/PIF 93.9% She et al [30] GCA-ST_SRU 94% Jahagirdar and Nagmode [14] SWFHOG_FNN 95.74% Pujol et al [24] LE + HOA + HSGA_SVM 97.85% Learned features GoogleNet 97.5% Feature engineering STPCA + LDA-SVM 97.87% Table 8. Accuracy comparison of the proposed model with others over HF dataset.…”

“…The HOG features achieved the highest sensitivity. Jahagirdar and Nagmode [14] proposed a new descriptor vector of salient wavelet features and a histogram of oriented gradients (SWFHOG). It detected abnormal behaviors using a feed-forward neural network (FNN), with an accuracy of 95% and 97% on the SBU and UT Interaction datasets, respectively.…”

Comparison of feed forward and cascade forward neural networks for human action recognition

“…HOG is successfully used for face recognition in intelligent surveillance system in [16]. A combination of HOG and local feature swine confinement worker (SWF) [17] is seen to give high classification accuracy for UT interaction and UCF sports datasets.…”