Brake Light Detection Algorithm for Predictive Braking

Abstract

There has recently been a rapid increase in the number of partially automated systems in passenger vehicles. This has necessitated a greater focus on the effect the systems have on the comfort and trust of passengers. One significant issue is the delayed detection of stationary or harshly braking vehicles. This paper proposes a novel brake light detection algorithm in order to improve ride comfort. The system uses a camera and YOLOv3 object detector to detect the bounding boxes of the vehicles ahead of the ego vehicle. The bounding boxes are preprocessed with L*a*b colorspace thresholding. Thereafter, the bounding boxes are resized to a 30 × 30 pixel resolution and fed into a random forest algorithm. The novel detection system was evaluated using a dataset collected in the Helsinki metropolitan area in varying conditions. Carried out experiments revealed that the new algorithm reaches a high accuracy of 81.8%. For comparison, using the random forest algorithm alone produced an accuracy of 73.4%, thus proving the value of the preprocessing stage. Furthermore, a range test was conducted. It was found that with a suitable camera, the algorithm can reliably detect lit brake lights even up to a distance of 150 m.

Keywords

• advanced cruise control
• collision avoidance
• machine vision
• machine learning
• transportation