华中科技大学学报（自然科学版）2016，Vol.44Issue(9)：20-25,6.DOI:10.13245/j.hust.160905
结合场景结构和条件随机场的道路检测
Road detection based on scene structural knowledge and CRF
摘要
Abstract
Existing approaches classify the road area by using appearance-based features,which is vul-nerable to the complicated imaging conditions such as extreme shadows,illumination and occlusion.A new road detection method was proposed to overcome this problem brought about by these factors, which combined the advantages of the structural knowledge and fully connected conditional random fields (CRFs).Firstly,a confidence map of road was generated based on the detection of the vanis-hing point and road boundaries.Secondly,a scene layout map was estimated by training a regression model using superpixel features.Two maps and appearance features were used to calculate the energy function of the CRF.Finally,road pixels could be labeled using an efficient inference method.Experi-mental results prove the effectiveness of the usage of structure information and a fully connected CRF, and the proposed method is robust to the shadows and occlusion in real road scenes.关键词
道路检测/消失点/超像素/全连接条件随机场/场景结构布局/多类别回归器Key words
road detection/vanishing point/super pixels/fully connected condition random field/scene structural layout/multi-class regression分类
信息技术与安全科学引用本文复制引用
邓燕子,卢朝阳,李静..结合场景结构和条件随机场的道路检测[J].华中科技大学学报（自然科学版）,2016,44(9):20-25,6.基金项目
国家自然科学基金资助项目(61502364) （61502364）
中央高校基本科研业务费专项资金资助项目(K50510010007) （K50510010007）
