Is it Raining Outside? Detection of Rainfall using General-Purpose Surveillance Cameras

TL;DR

This paper presents a new CNN-based rain detection system using surveillance cameras, outperforming previous methods on a large, real-world dataset, with significant implications for weather-aware surveillance applications.

Contribution

The study introduces a CNN-based rain detection approach and evaluates it on a new extensive dataset, demonstrating superior performance over existing methods.

Findings

The CNN method outperforms the previous state-of-the-art in rain detection accuracy.

Region-of-interest selection significantly affects detection performance.

The new dataset enables robust evaluation of rain detection algorithms.

Abstract

In integrated surveillance systems based on visual cameras, the mitigation of adverse weather conditions is an active research topic. Within this field, rain removal algorithms have been developed that artificially remove rain streaks from images or video. In order to deploy such rain removal algorithms in a surveillance setting, one must detect if rain is present in the scene. In this paper, we design a system for the detection of rainfall by the use of surveillance cameras. We reimplement the former state-of-the-art method for rain detection and compare it against a modern CNN-based method by utilizing 3D convolutions. The two methods are evaluated on our new AAU Visual Rain Dataset (VIRADA) that consists of 215 hours of general-purpose surveillance video from two traffic crossings. The results show that the proposed 3D CNN outperforms the previous state-of-the-art method by a large margin on all metrics, for both of the traffic crossings. Finally, it is shown that the choice of region-of-interest has a large influence on performance when trying to generalize the investigated methods. The AAU VIRADA dataset and our implementation of the two rain detection algorithms are publicly available at https://bitbucket.org/aauvap/aau-virada.