# Risky Action Recognition in Lane Change Video Clips using Deep Spatiotemporal Networks with Segmentation Mask Transfer

## TL;DR

This paper presents a deep spatiotemporal network using Mask R-CNN and LSTM to classify risky lane change actions from monocular video clips, achieving high accuracy and offering an accessible alternative to sensor-based systems.

## Contribution

It introduces a novel deep learning framework combining Mask R-CNN and LSTM for risk classification in lane change videos, with comprehensive evaluation of feature extractors.

## Key findings

- Achieved 0.937 AUC score in risk classification.
- Demonstrated effectiveness of Mask R-CNN for spatial feature extraction.
- Provided open-source code and models for further research.

## Abstract

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.