Deep Learning Based Anomaly Detection
Summary For video anomaly detection, we apply pretrained models to obtain the foreground and the optical flow as ground truth. Then our model estimates the information by taking only a single frame as input. For human behaviors, we take the human poses as input and use a GCN-based model to predict the future poses. Both the anomaly scores of these two works are given by the error of the estimation.
For defect detection, our model takes patches of the image as input and learns to extract features. The anomaly score of each patch is given by the distance between the patch and all the training patches.

For video anomaly detection, we develop our deep neural network model by utilizing foreground and optical flow information so that the model is focused on analyzing foreground moving objects.
For detecting abnormal human actions, we take confidence scores as weights of the keypoints to alleviate the influence of the occluded keypoints.
For defect detection, the different sizes of patches make our model learn information from large and small region at the same time. Furthermore, we use several grouping and self-supervised learning methods, so the model can extract features well from all types of normal images patches.

The quality of the product is critical to the competitiveness of the company. However, the defect samples that the factory can provide are usually limited, which will greatly reduce the robustness and accuracy of the deep learning models. Therefore, the image anomaly detection technique is a promising solution to these problems.
On the other hand, the abnormal activities of factory personnel may lead to decreased production efficiency and even cause danger in the factory. Therefore, an automated monitoring system is extremely important, which can provide warnings in real time when some abnormal actions or events occur.
Technical Film
Keyword Digital Video Technology Monitor Automatic optical inspection technology and application Labor saving automation Photoelectric signal detection
Provide the latest information of AI research centers and applied industries