Robust Rear Light Status Recognition Using Symmetrical SURFs

Abstract

This paper proposes a new framework to detect vehicle indicator lights and recognize their statuses using symmetrical SRUFs. To detect indicator lights from a vehicle, a symmetrical descriptor is first applied to determine its position from roads. Two advantages can be gained from this scheme, there is no need of background subtraction and it is extremely efficient for real-time analysis applications. After vehicle detection, a new lamp response function is defined for isolating red components from the detected vehicle for rear lamp detection without using any thresholds. This is very different and superior to other state-of-art frameworks in the literature. The positions of rear lamp can be then accurately located by searching the peaks of lamp response function even under daytime or nighttime conditions. To recognize the statuses of a rear lamp, no training stage is needed to train a classifier for lamp status analysis. To achieve this goal, a new mask is designed to make status judgments on a lamp according to only its response sign. Because no any threshold is adopted, various rear lamps and their statuses can be accurately analyzed even under various lighting conditions.