| Popis: |
This research introduces a novel deep learning-based approach for anomaly identification in surveillance films. The suggested approach is built on a deep network that has been taught to recognise objects and human activity in films. The technique was evaluated on five large-scale datasets from the real world, including UCF-Crime, XD-Violence, UBI-Fights, and CCTV-Fights, UCF-101, as well as on artificial datasets with various object sizes, appearances, and activity types. We extract features from video frames using a 3D-convolutional neural network (3D-CNN), followed by convolutional short-term memory (ConvLSTM), and then conduct classification and recognition based on these characteristics. The results demonstrate that, when compared to state-of-the-art approaches described in the comparison, the suggested method achieves high accuracy and AUC in both indoor and outdoor scenarios.. |
