Driving maneuver early detection via sequence learning from vehicle signals and video images

作者：

Highlights：

• A novel deep sequential model UMD-DMED is proposed for early detection of five driving maneuver classes: left turn, right turn, left lane change, right lane change, and driving straight.

• The proposed UMD-DMED model contains three major innovative computational components, distance-based representation of driving context, combined vehicle trajectory features and scene-centric features, and a focal loss based LSTM model.

• The extensive experiments are conducted using a data set containing 1078 maneuver events extracted from 37 hours of real-world driving trips from 7 different drivers.

• The proposed UMD-DMED achieved better detection performances and earlier detection time for detecting four classes of driving maneuvers, left and right turns, and left and right lane changes, than other advanced driving maneuver detection algorithms.

摘要

•A novel deep sequential model UMD-DMED is proposed for early detection of five driving maneuver classes: left turn, right turn, left lane change, right lane change, and driving straight.•The proposed UMD-DMED model contains three major innovative computational components, distance-based representation of driving context, combined vehicle trajectory features and scene-centric features, and a focal loss based LSTM model.•The extensive experiments are conducted using a data set containing 1078 maneuver events extracted from 37 hours of real-world driving trips from 7 different drivers.•The proposed UMD-DMED achieved better detection performances and earlier detection time for detecting four classes of driving maneuvers, left and right turns, and left and right lane changes, than other advanced driving maneuver detection algorithms.

论文关键词：Driving maneuver early detection,Deep neural networks,Sequence learning,Advanced driver assistance systems,Computer vision

论文评审过程：Received 20 June 2019, Revised 24 November 2019, Accepted 11 February 2020, Available online 14 February 2020, Version of Record 21 February 2020.

论文官网地址：https://doi.org/10.1016/j.patcog.2020.107276