首页 > 论文 > 激光与光电子学进展 > 57卷 > 12期(pp:121504--1)

复杂光照场景的道路区域提取算法及Benchmark

Road Region Extraction Algorithm and Benchmark for Complex Illumination Road Scene

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

针对复杂光照情况下的道路区域提取问题,提出一种基于颜色不变量和暗原色分割的道路区域提取算法,该算法通过正交分解法提取光照不变图像,并基于暗原色先验的道路图像聚类分割,提取图像的消失点等道路信息,构造软投票函数来判别道路区域,经过形态学处理得到最终精确的道路区域。为了有效评价复杂光照场景的道路区域提取算法的精度和效率,构建了一套复杂光照场景的道路图像数据集,并针对9种道路区域提取的算法构建了Benchmark。实验结果表明,所提方法能有效降低阴影等干扰因素的影响,与另外8种算法相比,本文算法能够实现与最新算法具有相近或更加准确的精度,并且本文算法在消失点位置提取准确时,道路的提取效果比其他算法更加完整和精确。此外,本文构建的数据集和Benchmark能够有效地用于测评复杂光照环境下道路区域提取算法的性能。

Abstract

For extracting the road under complex illumination environment, a road region extraction algorithm is proposed based on color invariant and dark primary color segmentation. The illumination invariant image is obtained with orthogonal decomposition method, and the road information such as vanishing point of image can be extracted based on the clustering segmentation of the dark primary color prior road image. The road region is identified by a constructed soft voting function, and the final accurate road is obtained after morphological processing. In order to effectively evaluate the accuracy and efficiency of the road region extraction algorithm on complex illumination scenes, we construct a complex illumination road scene image dataset for road region extraction and builds benchmark for nine road area extraction algorithms. Experimental results show that the proposed method can effectively reduce the influence of other interference factors such as shadow. Compared with the other eight algorithms, the proposed algorithm can achieve similar accuracy or more accurate than the latest algorithms. Moreover, when the extraction of vanishing point position is accurate, the road extraction performance is more complete and accurate than other algorithms. In addition, the dataset and benchmark built in this paper can effectively evaluate the performance of road region extraction algorithms in complex illumination environment.

广告组6 - 调制器
补充资料

中图分类号:TP391

DOI:10.3788/LOP57.121504

所属栏目:机器视觉

基金项目:河北省自然科学基金;

收稿日期:2019-11-02

修改稿日期:2019-11-13

网络出版日期:2020-06-01

作者单位    点击查看

杨景超:河北交通职业技术学院电气与信息工程系, 河北 石家庄 050091
李勇:东北大学信息科学与工程学院, 辽宁 沈阳 110819
张建君:东北大学信息科学与工程学院, 辽宁 沈阳 110819

联系人作者:李勇(leoqiulin@126.com)

备注:河北省自然科学基金;

【1】Hillel A, Lerner R, Levi D, et al. Recent progress in road and lane detection: a survey [J]. Machine Vision and Applications. 2014, 25(3): 727-745.

【2】Ding W L, Li Y. Efficient vanishing point detection method in complex urban road environments [J]. IET Computer Vision. 2015, 9(4): 549-558.

【3】Ding W L, Li Y, Wang W F, et al. Vanishing point detection algorithm for urban road image based on the envelope of perpendicular and parallel lines [J]. Acta Optica Sinica. 2014, 34(10): 1015002.
丁伟利, 李勇, 王文锋, 等. 基于垂线包络和平行线对的城市道路图像消失点检测算法 [J]. 光学学报. 2014, 34(10): 1015002.

【4】Kong H, Audibert J Y, Ponce J. General road detection from a single image [J]. IEEE Transactions on Image Processing. 2010, 19(8): 2211-2220.

【5】Tian Z, Xu C, Mi C, et al. Road segmentation based on vanishing point and principal orientation estimation [J]. Journal of Computer Research and Development. 2014, 51(4): 762-772.
田峥, 徐成, 米超, 等. 基于消失点和主方向估计的道路分割算法 [J]. 计算机研究与发展. 2014, 51(4): 762-772.

【6】Fang H, Jia R, Lu J P. Segmentation of full vision images based on colour and texture features [J]. Transactions of Beijing Institute of Technology. 2010, 30(8): 935-939.
方浩, 贾睿, 卢嘉鹏. 基于颜色和纹理特征的道路图像分割 [J]. 北京理工大学学报. 2010, 30(8): 935-939.

【7】Zhang G, Zheng N N, Cui C, et al. An efficient road detection method in noisy urban environment . [C]∥2009 IEEE Intelligent Vehicles Symposium, June 3-5, 2009. Xi''''an, China. IEEE. 2009, 556-561.

【8】Wang K, Huang Z, Zhong Z H. Multi-feature fusion based lane understanding algorithm [J]. China Journal of Highway and Transport. 2013, 26(4): 176-183.
王科, 黄智, 钟志华. 基于多特征融合的道路理解方法 [J]. 中国公路学报. 2013, 26(4): 176-183.

【9】Chen C L, Tai C L. Adaptive fuzzy color segmentation with neural network for road detections [J]. Engineering Applications of Artificial Intelligence. 2010, 23(3): 400-410.

【10】Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation . [C]∥2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 7-12, 2015. Boston, MA, USA. IEEE. 2015, 3431-3440.

【11】Oliveira G L, Burgard W, Brox T. Efficient deep models for monocular road segmentation . [C]∥2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), October 9-14, 2016. Daejeon, South Korea. IEEE. 2016, 4885-4891.

【12】Qu L Q, Tian J D, Han Z, et al. Pixel-wise orthogonal decomposition for color illumination invariant and shadow-free image [J]. Optics Express. 2015, 23(3): 2220-2239.

【13】Duan Z G, Qu L Q, Tian J D, et al. Outdoor illumination shadow detection based on orthogonal decomposition [J]. Acta Optica Sinica. 2016, 36(8): 0815002.
段志刚, 屈靓琼, 田建东, 等. 基于正交分解的室外光照阴影检测 [J]. 光学学报. 2016, 36(8): 0815002.

【14】He K M, Sun J, Tang X O. Single image haze removal using dark channel prior [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2011, 33(12): 2341-2353.

【15】Wang E D, Sun AN, Li Y, et al. Fast vanishing point detection method based on road border region estimation [J]. IET Image Processing. 2018, 12(3): 361-373.

【16】Ding W, Li Y, Wang W. An effective unstructured road navigation and intelligent warning system method based on vanishing point [J]. Opto-Electronic Engineering. 2016, 43(10): 63-69.

【17】Wang W F, Ding W L, Li Y, et al. An efficient road detection algorithm based on parallel edges [J]. Acta Optica Sinica. 2015, 35(7): 0715001.
王文锋, 丁伟利, 李勇, 等. 一种高效的基于平行边缘的道路识别算法 [J]. 光学学报. 2015, 35(7): 0715001.

【18】Duan Z G, Li Y, Wang E D, et al. Road and navigation line detection algorithm from shadow image based on the illumination invariant image [J]. Acta Optica Sinica. 2016, 36(12): 1215004.
段志刚, 李勇, 王恩德, 等. 基于光照不变图像的阴影图像道路及导航线提取算法 [J]. 光学学报. 2016, 36(12): 1215004.

【19】Li Y, Tong G F, Sun A N, et al. Road extraction algorithm based on intrinsic image and vanishing point for unstructured road image [J]. Robotics and Autonomous Systems. 2018, 109: 86-96.

【20】Wang E D, Li Y, Sun AN, et al. Road detection based on illuminant invariance and quadratic estimation [J]. Optik. 2019, 185: 672-684.

【21】Li Y, Ding W L, Zhang X G, et al. Road detection algorithm for autonomous navigation systems based on dark channel prior and vanishing point in complex road scenes [J]. Robotics and Autonomous Systems. 2016, 85: 1-11.

【22】Yu F, Xian W Q, Chen Y Y, et al. BDD100K: a diverse driving video database with scalable annotation tooling [2019-11-01].https: ∥arxiv.[2019-11-01]. 0, org/abs/1805: 04687.

引用该论文

Yang Jingchao,Li Yong,Zhang Jianjun. Road Region Extraction Algorithm and Benchmark for Complex Illumination Road Scene[J]. Laser & Optoelectronics Progress, 2020, 57(12): 121504

杨景超,李勇,张建君. 复杂光照场景的道路区域提取算法及Benchmark[J]. 激光与光电子学进展, 2020, 57(12): 121504

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF