Egocentric Vision-based Future Vehicle Localization for Intelligent Driving Assistance Systems
This work addresses safety-critical prediction for ADAS and autonomous driving, with incremental improvements in accuracy through novel model components.
The paper tackles predicting future vehicle location and scale from an egocentric view for driving assistance systems, introducing a multi-stream RNN model that incorporates optical flow and ego-motion modeling, and presents a new dataset from road intersections.
Predicting the future location of vehicles is essential for safety-critical applications such as advanced driver assistance systems (ADAS) and autonomous driving. This paper introduces a novel approach to simultaneously predict both the location and scale of target vehicles in the first-person (egocentric) view of an ego-vehicle. We present a multi-stream recurrent neural network (RNN) encoder-decoder model that separately captures both object location and scale and pixel-level observations for future vehicle localization. We show that incorporating dense optical flow improves prediction results significantly since it captures information about motion as well as appearance change. We also find that explicitly modeling future motion of the ego-vehicle improves the prediction accuracy, which could be especially beneficial in intelligent and automated vehicles that have motion planning capability. To evaluate the performance of our approach, we present a new dataset of first-person videos collected from a variety of scenarios at road intersections, which are particularly challenging moments for prediction because vehicle trajectories are diverse and dynamic.