Two-Stream (2+ 1) D CNN Based on Frame Difference Attention for Driver Behavior Recognition

Yang Zou, Shaoyi Du, HAN Hongcheng, Yuying Liu, Zhiqiang Tian

November, 2023

Abstract

Driving behavior recognition is a key technology in human-machine cooperative driving, which plays an important role in the construction of an intelligent transportation environment. Due to the similarity of drivers ’ actions and backgrounds in driving environments, it’s challenging for existing behavior recognition methods to recognize behaviors in driving environments precisely. To solve these problems, we propose the two-stream (2+1)D CNN with Frame Difference Attention Module. First, we use two streams to process the information captured from the face camera and road camera and use the Squeeze and Excitation attention module to fuse the stream information. Second, we propose the Frame Difference Attention Module to enhance the changes between adjacent frames so that the subtle actions in driving environments can be captured easier. We test our network on the Brain4Cars dataset and have a good performance on it.

Type

Conference paper

Publication

In 2023 10th International Conference on Dependable Systems and Their Applications (DSA)

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

Driver Intention Recognition

Two-Stream (2+ 1) D CNN Based on Frame Difference Attention for Driver Behavior Recognition

Abstract

HAN Hongcheng

PhD Student in Control Science and Engineering