A Scene-Agnostic Framework with Adversarial Training for Abnormal Event Detection in Video.

Abnormal event detection in video is a complex computer vision problem that has attracted significant attention in recent years. The complexity of the task arises from the commonly-agreed definition of an abnormal event, that is, a rarely occurring event that typically depends on the surrounding context. Following the standard formulation of abnormal event detection as outlier detection, we propose a scene-agnostic framework that learns from training videos containing only normal events. Our framework is composed of an object detector, a set of appearance and motion auto-encoders, and a discriminator. Since our framework only looks at object detections, it can be applied to different scenes, provided that abnormal events are defined identically across scenes. This makes our method scene agnostic, as we rely strictly on objects that can cause anomalies, and not on the background. To overcome the lack of abnormal data during training, we propose an adversarial learning strategy for the auto-encoders. We create a scene-agnostic set of out-of-domain adversarial examples, which are correctly reconstructed by the auto-encoders before applying gradient ascent on the adversarial examples. We further utilize the adversarial examples to serve as abnormal examples when training a binary classifier to discriminate between normal and abnormal latent features and reconstructions. Furthermore, to ensure that the auto-encoders focus only on the main object inside each bounding box image, we introduce a branch that learns to segment the main object. We compare our framework with the state-of-the-art methods on three benchmark data sets, using various evaluation metrics. Compared to existing methods, the empirical results indicate that our approach achieves favorable performance on all data sets.