Skip to content
baidut edited this page Apr 29, 2015 · 6 revisions

外文文献翻译

基于新型特征提取和车道分类的健壮的车道检测和跟踪方法 Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference on 4-9 May 2014【C类会议】

摘要——这篇论文引入了一个健壮的车道检测和追踪算法以应付复杂的场景并减少阈值的影响。在车道特征提取中,为了改善特征图和获得转向信息,我们在对称局部阈值上进行了扩展。接着,在创建Hough累加器时,利用前面得到的转向信息减少了计算复杂度(大约60倍),取得了一个更加清晰的累加器。左右车道分类是通过应用一个掩码在Hough累加器上,从而降低了计算复杂度和对阈值的敏感度。 为了量化新的特征图,我们使用了RoMa数据集的地面实况车道标线,而且对比SLT,最优真实positive (TP)和positive(P)的比率的平均水平由69%上升至86%。从超过10K帧中计算出的成功车道检出率为96.2%,显示了系统的鲁棒性。 关键字——车道特征提取,车道检测,Hough变换,卡尔曼滤波

全文翻译 https://github.com/baidut/ITS/wiki/Robust-lane-detection-&-tracking-based-on-novel-feature-extraction-and-lane-categorization


地面自动驾驶车感知技术综述 Electronics, Computers and Artificial Intelligence (ECAI), 2013 International Conference on 27-29 June 2013 【B类会议】

This paper reviews current approaches, challenges, objectives, architecture and trends in the perception, one of the most important systems in autonomous ground vehicles AGV. Several implementations reported in the literature in the past five years are reviewed to see the evolution and to determine the main areas for future research.

Mobileye

Clone this wiki locally