AD-Graph: Weakly Supervised Anomaly Detection Graph Neural Network

Abstract

The main challenge faced by video-based real-world anomaly detection systems is the accurate learning of unusual events that are irregular, complicated, diverse, and heterogeneous in nature. Several techniques utilizing deep learning have been created to detect anomalies, yet their effectiveness on real-world data is often limited due to the insufficient incorporation of motion patterns. To address these problems and enhance the traditional functionality of anomaly detection systems for surveillance video data, we propose a weakly supervised graph neural-network-assisted video anomaly detection framework called AD-Graph. To identify temporal information from a series of frames, we extract 3D visual and motion features and represent these in a language-based knowledge graph format. Next, a robust clustering strategy is applied to group together meaningful neighbourhoods of the graph with similar vertices. Furthermore, spectral filters are applied to these graphs, and spectral graph theory is used to generate graph signals and detect anomalous events. Extensive experimental results over two challenging datasets, UCF-Crime and ShanghaiTech, show improvements of 0.35% and 0.78% against a state-of-the-art model.

Enhancing Short-Term Electrical Load Forecasting for Sustainable Energy Management in Low-Carbon Buildings

“…Scholars in the fields of computer vision [51,52], image recognition [53,54], and video data analysis [55][56][57][58] are presently interested in the results of new deep learning models, particularly the CNN, a branch of AI that takes its primary inspirations from the human vision system [59]. Because of sharing weights and the internal connection approach, the CNN model has demonstrated impressive results in a variety of applications, including energy forecasting, load management prediction, and numerous others.…”

Research on New Greenable Class Gravity Retaining Wall Structure Technology Based on Video Monitoring

“…Users can monitor road deformation in real time. In order to solve the problem of the limited effectiveness of deep learning on real-world data, Waseem Ullah et al [19] proposed a weakly supervised graph neural-network-assisted video anomaly detection framework called AD-Graph and represented 3D visual and motion features based on a language knowledge graph format, which greatly improved the effectiveness of the existing models. Waseem Ullah [20] also proposed a new anomaly recognition model based on a deep convolutional neural network (CNN).…”