[1]胡强,屈蔷,何鑫.改进的多特征融合人行道检测算法[J].应用科技,2020,47(2):35-43.[doi:10.11991/yykj.201906016]
 HU Qiang,QU Qiang,HE Xin.An improved sidewalk detection algorithm based on multi-feature fusion[J].Applied science and technology,2020,47(2):35-43.[doi:10.11991/yykj.201906016]
点击复制

改进的多特征融合人行道检测算法(/HTML)
分享到:

《应用科技》[ISSN:1009-671X/CN:23-1191/U]

卷:
第47卷
期数:
2020年2期
页码:
35-43
栏目:
智能科学与技术
出版日期:
2020-03-05

文章信息/Info

Title:
An improved sidewalk detection algorithm based on multi-feature fusion
作者:
胡强1 屈蔷1 何鑫2
1. 南京航空航天大学 自动化学院,江苏 南京 211106;
2. 南京航空航天大学 计算机科学与技术学院,江苏 南京 211106
Author(s):
HU Qiang1 QU Qiang1 HE Xin2
1. College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China;
2. College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China
关键词:
人行道检测超像素Gabor纹理光照不变空间三维深度多特征融合机器学习马尔可夫随机场
Keywords:
sidewalk detectionsuper-pixelGabor textureillumination invariant spacethree-dimensional depthmulti-feature fusionmachine learningMarkov random field
分类号:
TP391
DOI:
10.11991/yykj.201906016
文献标志码:
A
摘要:
道路检测相关研究多基于KITTI等车道公开数据集展开,由于车道与人行道存在颜色、材质和周围环境等差异,准确地检测出人行道区域成为一个需要解决的问题。本文将应用场景设置为室外人行道,提出了一种改进的基于多特征融合的人行道检测算法。首先使用SLIC超像素算法获取超像素图以减少噪声干扰和后续训练维度;然后计算各超像素块特征,利用新的Gabor滤波器纹理提取方法降低时间复杂度,并加入基于主成分分析(PCA)的光照不变空间特征和三维的深度梯度特征提高检测准确度,选用Adaboost分类器对融合的特征向量进行训练并预测人行道区域;最后采用马尔可夫随机场对分割结果进行优化。本方法是通用的,不依赖于道路外观和结构的先验,在创建的人行道数据集上进行实验,证明了该算法的有效性。
Abstract:
Research on road detection is mostly based on open datasets of lane such as KITTI. Due to the differences in color, material and surrounding environment between lanes and sidewalks, accurate detection of the sidewalk area is also a problem that needs to be solved. Therefore, the application scenario is set as an outdoor sidewalk in this paper, proposing an improved sidewalk detection algorithm based on multi-feature fusion. Firstly, SLIC super-pixel algorithm is used to obtain super-pixel image to reduce the noise interference and follow-up training dimension. Then, calculating each super-pixel block feature, a new texture extraction method based on Gabor filter is proposed to reduce the time complexity, and the principal components analysis (PCA)-based illumination invariant spatial features and three-dimensional depth gradient features are added to improve detection accuracy. The Adaboost classifier is used to train the fused feature vectors and predict the sidewalk area. Finally, the Markov random field is used to optimize the segmentation results. This method is universal and does not depend on a priori road appearance and structure. The validity of the algorithm is verified by the experiment based on the created sidewalk datasets.

参考文献/References:

[1] 李迎春, 付兴建, 薛琴. 基于RGB熵的非结构化道路分割方法[J]. 计算机工程与设计, 2017, 38(6): 1571–1574
[2] 傅重添, 杨健, 路飞飞. 基于纹理的复杂环境下道路消失点检测算法[J]. 计算机应用与软件, 2014, 31(6): 292–294, 314
[3] SHINZATO P Y, GRASSI V, OSORIO F S, et al. Fast visual road recognition and horizon detection using multiple artificial neural networks[C]//Proceedings of 2012 IEEE Intelligent Vehicles Symposium. Alcala de Henares, Spain, 2012: 1090–1095.
[4] WANG Qi, FANG Jianwu, YUAN Yuan. Adaptive road detection via context-aware label transfer[J]. Neurocomputing, 2015, 158: 174–183.
[5] VALENTE M, STANCIULESCU B. Real-time method for general road segmentation[C]//Proceedings of 2017 IEEE Intelligent Vehicles Symposium. Los Angeles, USA, 2017: 443–447.
[6] WU Meiqing, LAM S K, SRIKANTHAN T. Nonparametric technique based high-speed road surface detection[J]. IEEE transactions on intelligent transportation systems, 2015, 16(2): 874–884.
[7] YANG Qingqing, FAN Shengli, WANG Lang, et al. Road detection by RANSAC on randomly sampled patches with slanted plane prior[C]//Proceedings of the IEEE 13th International Conference on Signal Processing (ICSP). Chengdu, China, 2016: 929–933.
[8] GAO Qi, FENG Yan, WANG Li. A real-time lane detection and tracking algorithm[C]//Proceedings of the IEEE 2nd Information Technology, Networking, Electronic and Automation Control Conference (ITNEC). Chengdu, China, 2017: 1230–1234.
[9] 陈飞, 章东平. 基于多尺度特征融合的Faster-RCNN道路目标检测[J]. 中国计量大学学报, 2018, 29(4): 394–397
[10] KANG Yousun, YAMAGUCHI K, NAITO K, et al. Road image segmentation and recognition using hierarchical Bag-of-Textons method[C]//Proceedings of the 5th Pacific Rim Symposium on Advances in Image and Video Technology. Gwangju, South Korea, 2011: 248–256.
[11] YUE Xinyu, WANG Fangrong, GUO Baicang, et al. Disparity map optimization based on edge detection[C]//Proceedings of 2018 Chinese Control and Decision Conference (CCDC). Shenyang, China, 2018: 3311–3315.
[12] CHACRA D A, ZELEK J. Road segmentation in street view images using texture information[C]//Proceedings of the 13th Conference on Computer and Robot Vision (CRV). Victoria, Canada, 2016: 424–431.
[13] NGUYEN T T, SPEHR J, ZUG S, et al. Multisource fusion for robust road detection using online estimated reliabilities[J]. IEEE transactions on industrial informatics, 2018, 14(11): 4927–4939.
[14] ALVAREZ J M A, LOPEZ A M. Road detection based on illuminant invariance[J]. IEEE transactions on intelligent transportation systems, 2011, 12(1): 184–193.

备注/Memo

备注/Memo:
收稿日期:2019-06-25。
基金项目:江苏省科技成果转化项目(BA2015052)
作者简介:胡强,男,硕士研究生;屈蔷,女,副教授,硕士生导师
通讯作者:屈蔷,E-mail:qq@nuaa.edu.cn
更新日期/Last Update: 2020-04-21