Abnormal Event Detection In Videos Using Deep Embedding
This addresses the challenge of detecting diverse abnormal events in surveillance videos, which is incremental as it builds on existing unsupervised methods with a novel joint optimization approach.
The paper tackles unsupervised anomaly detection in surveillance videos by proposing a hybrid architecture that jointly optimizes a deep neural network and the anomaly detection task, achieving improved detection performance without labeled anomalous data.
Abnormal event detection or anomaly detection in surveillance videos is currently a challenge because of the diversity of possible events. Due to the lack of anomalous events at training time, anomaly detection requires the design of learning methods without supervision. In this work we propose an unsupervised approach for video anomaly detection with the aim to jointly optimize the objectives of the deep neural network and the anomaly detection task using a hybrid architecture. Initially, a convolutional autoencoder is pre-trained in an unsupervised manner with a fusion of depth, motion and appearance features. In the second step, we utilize the encoder part of the pre-trained autoencoder and extract the embeddings of the fused input. Now, we jointly train/ fine tune the encoder to map the embeddings to a hypercenter. Thus, embeddings of normal data fall near the hypercenter, whereas embeddings of anomalous data fall far away from the hypercenter.