Risky Action Recognition in Lane Change Video Clips using Deep Spatiotemporal Networks with Segmentation Mask Transfer
This work addresses the need for affordable and robust risk estimation in driver assistance systems, though it is incremental as it combines existing methods like Mask R-CNN and LSTM for a specific domain.
The paper tackles the problem of recognizing risky lane change actions in video clips using a deep spatiotemporal network with Mask R-CNN for feature extraction, achieving a 0.937 AUC score on a semi-naturalistic dataset.
Advanced driver assistance and automated driving systems rely on risk estimation modules to predict and avoid dangerous situations. Current methods use expensive sensor setups and complex processing pipeline, limiting their availability and robustness. To address these issues, we introduce a novel deep learning based action recognition framework for classifying dangerous lane change behavior in short video clips captured by a monocular camera. We designed a deep spatiotemporal classification network that uses pre-trained state-of-the-art instance segmentation network Mask R-CNN as its spatial feature extractor for this task. The Long-Short Term Memory (LSTM) and shallower final classification layers of the proposed method were trained on a semi-naturalistic lane change dataset with annotated risk labels. A comprehensive comparison of state-of-the-art feature extractors was carried out to find the best network layout and training strategy. The best result, with a 0.937 AUC score, was obtained with the proposed network. Our code and trained models are available open-source.