Multi-Class Lane Semantic Segmentation using Efficient Convolutional Networks
This work addresses the problem of distinguishing lane types in autonomous driving, offering an incremental improvement over existing methods.
The paper tackled multi-class lane semantic segmentation for self-driving vehicles by proposing Feature Size Selection and Degressive Dilation Block techniques, resulting in improved accuracy with real-time inference on high-resolution images.
Lane detection plays an important role in a self-driving vehicle. Several studies leverage a semantic segmentation network to extract robust lane features, but few of them can distinguish different types of lanes. In this paper, we focus on the problem of multi-class lane semantic segmentation. Based on the observation that the lane is a small-size and narrow-width object in a road scene image, we propose two techniques, Feature Size Selection (FSS) and Degressive Dilation Block (DD Block). The FSS allows a network to extract thin lane features using appropriate feature sizes. To acquire fine-grained spatial information, the DD Block is made of a series of dilated convolutions with degressive dilation rates. Experimental results show that the proposed techniques provide obvious improvement in accuracy, while they achieve the same or faster inference speed compared to the baseline system, and can run at real-time on high-resolution images.