BMAN: Bidirectional Multi-scale Aggregation Networks for Abnormal Event Detection

Abstract

Abnormal event detection is an important task in video surveillance systems. In this paper, we propose a novel bidirectional multi-scale aggregation networks (BMAN) for abnormal event detection. The proposed BMAN learns spatiotemporal patterns of normal events to detect deviations from the learned normal patterns as abnormalities. The BMAN consists of two main parts: an inter-frame predictor and an appearance motion joint detector. The inter-frame predictor is devised to encode normal patterns, which generates an inter-frame using bidirectional multi-scale aggregation based on attention. With the feature aggregation, robustness for object scale variations and complex motions is achieved in normal pattern encoding. Based on the encoded normal patterns, abnormal events are detected by the appearance-motion joint detector in which both appearance and motion characteristics of scenes are considered. Comprehensive experiments are performed, and the results show that the proposed method outperforms the existing state-of-the-art methods.

Existing System

Trajectory-based Methods, Local Low-level Feature-based Methods

Proposed System

The major contributions of this paper are as follows. 1) To the best of our knowledge, the proposed method is a first attempt to deal with multi-scale and attention schemes with fully learnable neural networks in abnormal event detection. Utilizing the bidirectional multi-scale and attention encoding, the proposed model robustly learns normal patterns including object scale variations and complex motions. 2) Based on the learned normal patterns, the appearancemotion joint detector is devised to detect abnormal events by analyzing appearance and motion characteristics of target scenes. Analyses in appearance and motion domains work complementarily for detecting abnormal events. In addition, the resulting detection is interpretable on the visual basis of where the detected events occur at each scene.

Architecture

BLOCK DIAGRAM