Goal-oriented Object Importance Estimation in On-road Driving Videos
This work addresses the problem of improving autonomous driving systems by identifying important objects for safer and more efficient control decisions, though it is incremental as it builds on existing object detection and importance estimation methods.
The paper tackles the problem of estimating object importance in on-road driving videos by considering road users' influence on driver control decisions, using a framework that incorporates visual dynamics and driving goals. Experimental results show that this goal-oriented method outperforms baselines, with significant improvements in left-turn and right-turn scenarios, and it enhances binary brake prediction by incorporating object importance information.
We formulate a new problem as Object Importance Estimation (OIE) in on-road driving videos, where the road users are considered as important objects if they have influence on the control decision of the ego-vehicle's driver. The importance of a road user depends on both its visual dynamics, e.g., appearance, motion and location, in the driving scene and the driving goal, \emph{e.g}., the planned path, of the ego vehicle. We propose a novel framework that incorporates both visual model and goal representation to conduct OIE. To evaluate our framework, we collect an on-road driving dataset at traffic intersections in the real world and conduct human-labeled annotation of the important objects. Experimental results show that our goal-oriented method outperforms baselines and has much more improvement on the left-turn and right-turn scenarios. Furthermore, we explore the possibility of using object importance for driving control prediction and demonstrate that binary brake prediction can be improved with the information of object importance.