计算机科学
人工智能
深度学习
棱锥(几何)
点云
分割
特征(语言学)
特征提取
计算机视觉
图像分割
模式识别(心理学)
语言学
光学
物理
哲学
作者
Siyun Chen,Zhenxin Zhang,Rugang Zhong,Liqiang Zhang,Hao Ma,Lirong Liu
出处
期刊:IEEE Transactions on Geoscience and Remote Sensing
[Institute of Electrical and Electronics Engineers]
日期:2021-01-01
卷期号:59 (1): 784-800
被引量:22
标识
DOI:10.1109/tgrs.2020.2996617
摘要
Accurate and efficient extraction of road marking plays an important role in road transportation engineering, automotive vision, and automatic driving. In this article, we proposed a dense feature pyramid network (DFPN)-based deep learning model, by considering the particularity and complexity of road marking. The DFPN concatenated its shallow feature channels with deep feature channels so that the shallow feature maps with high resolution and abundant image details can utilize the deep features. Thus, the DFPN can learn hierarchical deep detailed features. The designed deep learning model was trained end to end for road marking instance extraction with mobile laser scanning (MLS) point clouds. Then, we introduced the focal loss function into the optimization of deep learning model in road marking segmentation part, to pay more attention to the hard-classified samples with a large extent of background. In the experiments, our method can achieve better results than state-of-the-art methods on instance segmentation of road markings, which illustrated the advantage of the proposed method.
科研通智能强力驱动
Strongly Powered by AbleSci AI