Efficient road specular reflection removal based on gradient properties

Efficient road specular reflection removal based on gradient properties
复制标题

基于梯度特性的高效道路镜面反射去除

DOI:
10.1007/s11042-018-6156-5
复制
发表时间:
2018-05
影响因子:
3.6
通讯作者:
Jinxiang Wang
Jinxiang Wang
中科院分区:
计算机科学4区
文献类型:
--
作者:
Yao Wang;Fangfa Fu;Fengchang Lai;Weizhe Xu;Jinjin Shi;Jinxiang Wang

文献摘要

参考文献

相似文献

在任何给定的一天中,由阳光变化引起的高光会导致立体匹配、物体识别和道路分割失败。这在高级驾驶员辅助系统(ADAS)中是一个严峻的挑战,因为局部高亮度和颜色不连续通常会导致路面或物体的明显模糊。本文提出了一种新的消除高光图像中镜面反射的策略,通过梯度分布来优化漫反射图像。引入暗通道作为初始估计和定位高光的先验。然后采用阈值滤波器将高亮度高光和弱亮度高光区分开来,弱亮度高光既不影响立体匹配,也不影响道路分割。最后,梯度属性(镜面反射和漫反射的变化平滑度),以优化层分离。实验结果表明,该方法在分割速度和准确性上都优于其他方法。
Highlights caused by changes in sunlight throughout any given day cause failure in stereo matching, object recognition, and road segmentation. This is a serious challenge in advanced driver assistance systems (ADAS), because local high brightness and color discontinuities generally result in noticeable blurring of the road surface or object. This paper presents a novel strategy for removing specular reflection from highlight images by gradients distribution to optimize the diffuse image. The dark channel is introduced as a prior to initially estimate and locate the highlight. The threshold filter is then adopted to divide the high-intensity highlight and the weak highlight - the weak highlight affect neither the stereo matching nor road segmentation process. Finally, gradient properties (varying smoothness of specular and diffuse reflections) are presented to optimize the layer separation. Experimental results in speed and accuracy of road segmentation show that proposed method outperforms other techniques for separating highlights from road surfaces.
DOI: 10.1109/cvpr.2005.298
发表时间: 2005-06
期刊: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)
影响因子: --
作者:
R. Tan;K. Ikeuchi
通讯作者: R. Tan;K. Ikeuchi
复杂背景图像中有效维吾尔语文本检测,实现交通提示识别
DOI: 10.1109/tits.2017.2749977
发表时间: 2018-01-01
影响因子: 8.5
作者:
Yan, Chenggang;Xie, Hongtao;Dai, Qionghai
通讯作者: Dai, Qionghai
DOI: 10.1109/cvpr.2006.273
发表时间: 2006-06
期刊: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)
影响因子: --
作者:
P. Tan;Long Quan;Stephen Lin
通讯作者: P. Tan;Long Quan;Stephen Lin
DOI: 10.1109/cvpr.2009.5206542
发表时间: 2009-06
期刊: 2009 IEEE Conference on Computer Vision and Pattern Recognition
影响因子: --
作者:
Qingxiong Yang;K. Tan;N. Ahuja
通讯作者: Qingxiong Yang;K. Tan;N. Ahuja
DOI: 10.1109/34.85655
发表时间: 1991-07-01
影响因子: 23.6
作者:
WOLFF, LB;BOULT, TE
通讯作者: BOULT, TE