Intelligent pixel-level pavement marking detection using 2D laser pavement images

This paper proposes a robust semantic segmentation algorithm named as Marking-DNet to implement pixel-level recognition of pavement markings. The proposed Marking-DNet presents an improved encoder-decoder architecture based on DeepLabV3+. Different from DeepLabv3+, feature maps of four different scales are imported from the encoder into the decoder of Marking-DNet, resulting in more levels of information exchange. Additionally, the Object-Contextual Representation and the Convolutional Block Attention Module are both employed in Marking-DNet to conduct contextual learning more efficiently and implement spatial and channel attention explicitly. The F-measure and Intersection-Over-Union attained by the Marking-DNet on 1500 testing images are 93.59% and 87.96% respectively. Experimental results demonstrate that Marking-DNet outperforms six state-ofthe-art semantic segmentation models in detecting pavement markings using both private and public image datasets. According to the performances on 5,506 pavement images, it is found that Marking-DNet can detect various complex pavement markings accurately, except for some heavily-worn markings.

Automated summary

This paper proposes a robust semantic segmentation algorithm named Marking-DNet for pixel-level recognition of pavement markings. It improves the encoder-decoder architecture of DeepLabV3+ by importing feature maps from four different scales, resulting in enhanced information exchange. Marking-DNet employs the Object-Contextual Representation and the Convolutional Block Attention Module to conduct contextual learning more efficiently and explicitly implement spatial and channel attention. Experimental results demonstrate that Marking-DNet outperforms six state-of-the-art semantic segmentation models in detecting pavement markings using both private and public image datasets, accurately detecting various complex pavement markings except for heavily-worn ones.