Lane Change Classification and Prediction with Action Recognition Networks
This work addresses the problem of safe and efficient driving decision-making for autonomous vehicles, representing an incremental improvement by applying existing action recognition methods to lane change classification.
The paper tackles lane change intention prediction for autonomous driving by proposing an end-to-end framework using action recognition networks on RGB video data, achieving the best classification results on the PREVENTION dataset without requiring additional pre-processing information.
Anticipating lane change intentions of surrounding vehicles is crucial for efficient and safe driving decision making in an autonomous driving system. Previous works often adopt physical variables such as driving speed, acceleration and so forth for lane change classification. However, physical variables do not contain semantic information. Although 3D CNNs have been developing rapidly, the number of methods utilising action recognition models and appearance feature for lane change recognition is low, and they all require additional information to pre-process data. In this work, we propose an end-to-end framework including two action recognition methods for lane change recognition, using video data collected by cameras. Our method achieves the best lane change classification results using only the RGB video data of the PREVENTION dataset. Class activation maps demonstrate that action recognition models can efficiently extract lane change motions. A method to better extract motion clues is also proposed in this paper.