摘要
非结构化道路通常没有清晰的边界及车道线,环境较为复杂,传统的基于道路纹理、颜色特征的分割方法无法满足实时性和准确性的要求。针对非结构化道路场景,提出了基于改进BiSeNet的轻量化语义分割模型,采用轻量化主干提取网络和引入深度可分离卷积,优化速度控制;在最后的特征融合阶段引入通道注意力,自适应地选择重要特征,抑制冗余信息,提高非结构化道路分割的准确性。改进后模型参数量仅有1.11×106,检测速度提升18.83%,F1-score达到了96.74%。对比其他主流语义分割模型,该算法具有参数量小、速度快、准确率高等优势,可为非结构化道路场景下无人驾驶车辆的安全运行提供参考。
Unstructured roads usually have no clear boundaries and lane lines,and the environment is more complex.The traditional segmentation methods based on road texture and color features cannot meet the requirements of real-time performance and accuracy.For unstructured road scenes,a lightweight semantic segmentation model based on improved BiSeNet was proposed,which adopted the lightweight trunk extraction network and introduced the depthwise separable convolution to optimize the speed control.The channel attention was introduced in the final feature fusion stage to adaptively select important features,suppress redundant information,and improve the accuracy of unstructured road segmentation.The number of parameters of the improved model is only 1.11×106,the detection speed is increased by 18.83%,and the F1-score reaches 96.74%.Compared with other mainstream semantic segmentation models,the proposed algorithm has the advantages of small parameters,high speed and high accuracy,which can provide a reference for the safe operation of unmanned vehicles in unstructured road scenarios.
作者
宋亮
谷玉海
石文天
SONG Liang;GU Yuhai;SHI Wentian(Beijing Key Laboratory of Measurement and Control of Mechanical and Electrical System Technology,Beijing Information Science and Technology University,Beijing 100192,China;School of Materials Science and Mechanical Engineering,Beijing Technology and Business University,Beijing 100148,China)
出处
《应用光学》
CAS
北大核心
2023年第3期556-564,共9页
Journal of Applied Optics
基金
北京市科技委促进高校内涵发展-学科建设专项资助项目(5112011015)
机电系统测控北京市重点实验室开放课题资助(KF20202223204)。
关键词
无人驾驶
非结构化道路
深度可分离卷积
注意力机制
语义分割
unmanned driving
unstructured road
depthwise separable convolution
attention mechanism
semantic segmentation
