Predicting road scenes from brief views of driving video

Abstract

If a vehicle is driving itself and asks the driver to take over, how much time does the driver need to comprehend the scene and respond appropriately? Previous work on natural-scene perception suggests that observers quickly acquire the gist, but gist-level understanding may not be sufficient to enable action. The moving road environment cannot be studied with static images alone, and safe driving requires anticipating future events. We performed two experiments to examine how quickly subjects could perceive the road scenes they viewed and make predictions based on their mental representations of the scenes. In both experiments, subjects performed a temporal-order prediction task, in which they viewed brief segments of road video and indicated which of two still frames would come next after the end of the video. By varying the duration of the previewed video clip, we determined the viewing duration required for accurate prediction of recorded road scenes. We performed an initial experiment on Mechanical Turk to explore the space, and a follow-up experiment in the lab to address questions of road type and stimulus discriminability. Our results suggest that representations which enable prediction can be developed from brief views of a road scene, and that different road environments (e.g., city versus highway driving) have a significant impact on the viewing durations drivers require to make accurate predictions of upcoming scenes.