Self-explaining analysis of facility environments on 2-lane rural roads with an improved lightweight CNN considering drivers’ visual perception

Journal article, 2024

Speeding is one of the primary contributors to rural road crashes. Self-explaining theory offers a solution to reduce speeding, which suggests that well-designed facility environments (i.e., road facilities and surrounding landscapes) can automatically guide drivers to choose appropriate speeds on different road categories. This study proposes an improved lightweight convolutional neural network (LW-CNN) that includes drivers’ visual perception characteristics (i.e., depth perception and dynamic vision) to conduct the self-explaining analysis of the facility environment on 2-lane rural roads. Data for this study are gathered through naturalistic driving experiments on 2-lane rural roads across five Chinese provinces. A total of 3,502 visual facility environment images, alongside their corresponding operation speeds and speed limits, are collected. The improved LW-CNN exhibits high accuracy and efficiency in predicting operation speeds with these visual facility environment images, achieving a train loss of 0.05% and a validation loss of 0.15%. The semantics of facility environments affecting operation speeds are further identified by combining this LW-CNN with the Gradient-weighted class activation mapping algorithm and the semantic segmentation network. Then, six typical 2-lane rural road categories perceived by drivers with different operation speeds and speeding probability are summarized using k-means clustering. An objective and comprehensive analysis of each category's semantic composition and depth features is conducted to evaluate their influence on drivers’ speeding probability and road category perception. The findings of this study can be directly applied to optimize facility environments from drivers’ visual perception to decrease speeding-related crashes.