Look at Adjacent Frames: Video Anomaly Detection without Offline Training
This addresses the problem of detecting anomalies in video streams for surveillance or monitoring applications, offering an incremental improvement over existing offline-free methods.
The paper tackles video anomaly detection without offline training by using an online-optimized multilayer perceptron to reconstruct frames from frequency information, achieving strong performance on benchmark datasets.
We propose a solution to detect anomalous events in videos without the need to train a model offline. Specifically, our solution is based on a randomly-initialized multilayer perceptron that is optimized online to reconstruct video frames, pixel-by-pixel, from their frequency information. Based on the information shifts between adjacent frames, an incremental learner is used to update parameters of the multilayer perceptron after observing each frame, thus allowing to detect anomalous events along the video stream. Traditional solutions that require no offline training are limited to operating on videos with only a few abnormal frames. Our solution breaks this limit and achieves strong performance on benchmark datasets.