• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Chinese Control Conference >Lane detection of multi-visual-features fusion based on D-S theory
【24h】

Lane detection of multi-visual-features fusion based on D-S theory

机译：基于D-S理论的多视觉特征融合车道检测

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

A novel lane detection algorithm based on multi-visual-features fusion by using D-S evidence theory is introduced to improve the robustness against illumination variations, shadows and road surface cracks, etc. First, the gradient magnitude, gradient direction, hue and value detection operators are chosen to construct the evidence bodies, for which the basic probability assignment functions are designed respectively. Then, after the pretreatment of conflict focal elements, the evidences are combined to obtain the weights of each pixel as lane candidate points according to the maximum reliability criterion. Finally, the parameters of piecewise linear lane model are calculated by weighted Hough transform with constraint and KF is used for lane tracking. The experimental results show that this method can achieve higher reliability and adaptability for lane detection than the algorithm simply using the edge or color feature, and satisfies the real-time requirement for navigation.
机译：引入了一种基于多视觉特征融合的新型车道检测算法通过DS证据理论，提高了对照明变化，阴影和道路表面裂缝等的鲁棒性等。首先，梯度幅度，梯度方向，色调和值检测运算符选择构建证据机构，分别设计了基本概率分配函数。然后，在冲突焦点元件的预处理之后，将证据组合以根据最大可靠性标准获得作为车道候选点的每个像素的权重。最后，通过使用约束和KF用于车道跟踪的加权Hough变换来计算分段线性通道模型的参数。实验结果表明，只需使用边缘或彩色特征，该方法可以实现比算法更高的车道检测的可靠性和适应性，并满足导航的实时要求。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号