Real-Time Anomaly Detection and Localization in Crowded Scenes
This addresses the problem of quickly identifying unusual events in crowded environments for surveillance or safety applications, but it is incremental as it builds on existing methods with efficiency improvements.
The paper tackles real-time anomaly detection and localization in crowded scenes by using local and global descriptors with Gaussian classifiers, achieving results comparable to state-of-the-art methods on UCSD ped2 and UMN benchmarks while being more time-efficient.
In this paper, we propose a method for real-time anomaly detection and localization in crowded scenes. Each video is defined as a set of non-overlapping cubic patches, and is described using two local and global descriptors. These descriptors capture the video properties from different aspects. By incorporating simple and cost-effective Gaussian classifiers, we can distinguish normal activities and anomalies in videos. The local and global features are based on structure similarity between adjacent patches and the features learned in an unsupervised way, using a sparse auto- encoder. Experimental results show that our algorithm is comparable to a state-of-the-art procedure on UCSD ped2 and UMN benchmarks, but even more time-efficient. The experiments confirm that our system can reliably detect and localize anomalies as soon as they happen in a video.