Skip to main content
. 2021 Aug 14;21(16):5486. doi: 10.3390/s21165486

Figure 7.

Figure 7

Hybrid model (VGG16-LSTM): Column (A) represents the sequence of images extracted from the videos. Group (B) represents the convolutional layers based of a VGG16. Group (C) represents the long short-term memory (LSTM) layer responsible for learning temporal features. Group (D) represents the classification layer.