STAD-ConvBi-LSTM: Spatio-temporal attention-based deep convolutional Bi-LSTM framework for abnormal activity recognition

Human Activity Recognition has become significant research in computer vision. Real-time systems analyze the actions to endlessly monitor and recognize abnormal activities, thereby enlightening public security and surveillance measures in real-world. However, implementing these frameworks is a challenging task due to miscellaneous actions, complex patterns, fluctuating viewpoints or background cluttering. Recognizing abnormality in videos still needs exclusive focus for accurate prediction and computational efficiency. To address these challenges, this work introduced an efficient novel spatial–temporal attention-based deep convolutional bidirectional long short-term memory framework. Also, proposes a dual attentional convolutional neural network that combines CNN model, bidirectional-LSTM and spatial–temporal attention mechanism to extract human-centric prominent features in video-clips. The result of extensive experimental analysis exhibits that STAD-ConvBi-LSTM outperforms the state-of-the-art methods using five challenging datasets, namely UCF50, UCF101, YouTube-Action, HMDB51, Kinetics-600 and on our Synthesized Action dataset achieving notable accuracies of 98.8%, 98.1%, 81.2%, 97.4%, 88.2% and 96.7%, respectively.