首页 > 论文 > 光学学报 > 38卷 > 10期(pp:1015003--1)

基于自适应分块编码SVM的车道导向箭头多分类方法

Multi Classification Method of Lane Arrow Markings Based on Support Vector Machines with Adaptive Partitioning Coding

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

摘要

针对在道路导向箭头的检测和识别中支持向量机(SVM)多分类器的识别效率下降的问题,提出一种利用简单二分类SVM通过对结果的自定义二进制编码实现导向箭头多分类的方法。对导向箭头感兴趣区域(ROI)图像进行Harris角点粗检测,利用改进FAST-9(Features from accelerated segment test-9)算法对伪角点进行筛选,根据最终获取的角点集合中纵坐标最大的两个角点位置分割图像获得待识别区域;再利用几何不变矩特征训练SVM分类器;对分类结果进行二进制编码,从而实现单一种类SVM下多种导向箭头的分类。算法在实拍获取的500帧图像中进行测试,识别率优于96.8%。结果表明:所提算法不需逆透视变换,利用一种SVM二分类器即可实现导向箭头的识别,有效提高了导向箭头识别的准确率和运行效率。

Abstract

Aiming at the problem of decreasing the recognition efficiency of multi-class Support Vector Machines (SVM) in the detection and classification of lane arrow markings, an improved method for a simple SVM classifier which is applied to realize the multi classification of arrow markings by custom binary encoding for results is proposed. The Harris corner coarseness is detected for the arrow markings region of interest (ROI), and the pseudo corners are screened by improved FAST-9 (features from accelerated segment test-9) algorithm. According to the location of the largest two corners of the ordinate in the final corner set, the recognition area is obtained. The SVM classifier is trained by invariant moments. And the multi classification with one SVM classifier is realized via the binary encoding for results. The algorithm is tested on 500 real images obtained from the real shot, and the recognition rate is superior to 96.8%. The results show that the proposed method does not need inverse perspective transformation. A simple SVM classifier can realize the multi classification of arrow markings, and the accuracy and operation efficiency of arrow marking recognition can be improved effectively.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP391

DOI:10.3788/aos201838.1015003

所属栏目:机器视觉

基金项目:吉林省科技发展计划项目(20170204048GX)

收稿日期:2018-05-07

修改稿日期:2018-06-11

网络出版日期:2018-06-13

作者单位    点击查看

杜恩宇:长春理工大学 光电工程学院光电测控与光信息传输技术教育部重点实验室, 吉林 长春 130022
张宁:长春理工大学 光电工程学院光电测控与光信息传输技术教育部重点实验室, 吉林 长春 130022
李艳荻:长春理工大学 光电工程学院光电测控与光信息传输技术教育部重点实验室, 吉林 长春 130022

联系人作者:张宁(custzn@126.com)

【1】He Y H, Chen S, Pan Y F, et al. Using edit distance and junction feature to detect and recognize arrow road marking[C]∥Proceedings of IEEE International Conference on Intelligent Transportation Systems, 2014: 2317-2323.

【2】Maier G, Pangerl S, Schindler A. Real-time detection and classification of arrow markings using curve-based prototype fitting[C]∥Proceedings of IEEE International Conference on Intelligent Vehicles Symposium, 2011: 442-447.

【3】Suchitra S, Satzoda R K, Srikanthan T. Detection & classification of arrow markings on roads using signed edge signatures[C]∥Proceedings of IEEE International Conference on Intelligent Vehicles Symposium, 2012: 796-801.

【4】Wang N, Liu W, Zhang C, et al. The detection and recognition of arrow markings recognition based on monocular vision[C]∥Chinese Control and Decision Conference, 2009: 4380-4386.

【5】Li Y, He K, Jia P. Road markers recognition based on shape information[C]∥Proceedings of IEEE International Conference on Intelligent Vehicles Symposium, 2007: 117-122.

【6】Hsu C W, Lin C J. A comparison of methods for multiclass support vector machines[J]. IEEE Transactions on Neural Networks, 2002, 13(2): 415-425.

【7】Zhou Z H, Tian X Y, Sun L X, et al. Identification of aluminum alloy grades by fiber-laser induced breakdown spectroscopy combined with support vector machine[J]. Laser & Optoelectronics Progress, 2018, 55(6): 063002.
周中寒, 田雪咏, 孙兰香, 等. Fiber-LIBS技术结合SVM鉴定铝合金牌号[J]. 激光与光电子学进展, 2018, 55(6): 063002.

【8】Platt J C, Cristianini N, Shawe-Taylor J. Large margin DAGs for multiclass classification[J]. Advances in Neural Information Processing Systems, 2000, 12(3): 547-553.

【9】Takahashi F, Abe S. Decision-tree-based multiclass support vector machines[C]∥Proceedings of IEEE International Conference on Neural Information Processing, 2002, 5: 1418-1422.

【10】Li H J, Qiu T S, Song H Y, et al. Separation algorithm of traffic signs based on curvature scale space corner detection[J]. Acta Optica Sinica, 2015, 35(1): 0115002.
李厚杰, 邱天爽, 宋海玉, 等. 基于曲率尺度空间角点检测的交通标志分离算法[J]. 光学学报, 2015, 35(1): 0115002.

引用该论文

Du Enyu,Zhang Ning,Li Yandi. Multi Classification Method of Lane Arrow Markings Based on Support Vector Machines with Adaptive Partitioning Coding[J]. Acta Optica Sinica, 2018, 38(10): 1015003

杜恩宇,张宁,李艳荻. 基于自适应分块编码SVM的车道导向箭头多分类方法[J]. 光学学报, 2018, 38(10): 1015003

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