复杂场景非结构化道路消失点检测算法

doi:10.3901/JME.2022.12.121

机械工程学报 ›› 2022, Vol. 58 ›› Issue (12): 121-129.doi: 10.3901/JME.2022.12.121

扫码分享

复杂场景非结构化道路消失点检测算法

徐建华¹, 豆毅庚², 丁子豪¹, 宋春雷¹, 陈家斌¹, 杨永亮³

1. 北京理工大学自动化学院北京 100081;
2. 西安爱生技术集团有限公司西安 710065;
3. 北京科技大学自动化学院北京 100083

收稿日期:2021-09-29 修回日期:2022-03-29 出版日期:2022-06-20 发布日期:2022-09-14
通讯作者: 豆毅庚(通信作者),男,1996年出生。主要研究方向为组合导航技术与智能控制。E-mail:douyigeng@163.com
作者简介:徐建华,男,1975年出生,博士,副研究员,硕士研究生导师。主要研究方向为组合导航技术与图像识别算法。E-mail:xujianhua@bit.edu.cn;丁子豪,男,1996年出生,硕士研究生。主要研究方向为组合导航技术与强化学习。E-mail:dingzihao@ieee.org;宋春雷,男,1973年出生,博士,副研究员,硕士研究生导师。主要研究方向为组合导航技术与图像识别算法。E-mail:songchunlei@bit.edu.cn;陈家斌,男,1964年出生,博士,教授,博士研究生导师。主要研究方向为惯性器件与组合导航。E-mail:chenjiabin@bit.edu.cn;杨永亮,男,1988年出生,博士,副教授,硕士研究生导师。主要研究方向为机器视觉与强化学习。E-mail:yangyongliang@ustb.edu.cn
基金资助:
国家自然科学基金资助项目（61903028）

Unstructured Road Vanishing Point Detection Algorithm for Complex Scenes

XU Jianhua¹, DOU Yigeng², DING Zihao¹, SONG Chunlei¹, CHEN Jiabin¹, YANG Yongliang³

1. School of Automation, Beijing Institute of Technology, Beijing 100081;
2. Xi'an ASN Technology Group Co., Ltd., Xi'an 710065;
3. School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing 100083

Received:2021-09-29 Revised:2022-03-29 Online:2022-06-20 Published:2022-09-14

摘要/Abstract

摘要： 道路消失点检测算法广泛应用于智慧交通、自动驾驶等领域。现有的基于图像纹理特征的道路消失点检测算法易受场景中竖直灯杆等建筑物影响，存在着部分场景下鲁棒性差的问题。针对这一问题，提出一种复杂场景非结构化道路消失点检测算法。首先，该方法通过图像纹理角度特征对投票点权重进行更新，使得竖直建筑物中的图像纹理被削弱；其次，使用区域生长算法得到道路区域并对该区域内的投票点权重进行加强，进而增强图像感兴趣区域的纹理提取。试验表明，提出的算法能够在复杂场景下准确地检测到道路消失点，且具有一定的鲁棒性。

关键词: 消失点检测, Gabor滤波器, 局部区域软投票

Abstract: The road vanishing point detection algorithm is widely used in fields such as intelligent transportation and autonomous driving. Existing road vanishing point detection algorithms based on image texture features are easily affected by buildings such as vertical light poles in the scene, and have the problem of poor robustness in some scenes. In response to this problem, the article proposes an unstructured road vanishing point detection algorithm for complex scenes. First, the method updates the weights of voting points through the angle features of the image texture so that the image texture in the area of the vertical building is weakened; Secondly, the area growth algorithm is used to obtain the road area, and the weight of the voting points in the road area is strengthened, and then Enhanced texture extraction of regions of interest in images. Experiments show that the proposed algorithm can accurately detect the vanishing points of roads in complex scenes and has a certain degree of robustness.

Key words: vanishing point detection, Gabor filter, soft voting in local areas

中图分类号:

TP391

徐建华, 豆毅庚, 丁子豪, 宋春雷, 陈家斌, 杨永亮. 复杂场景非结构化道路消失点检测算法[J]. 机械工程学报, 2022, 58(12): 121-129.

XU Jianhua, DOU Yigeng, DING Zihao, SONG Chunlei, CHEN Jiabin, YANG Yongliang. Unstructured Road Vanishing Point Detection Algorithm for Complex Scenes[J]. Journal of Mechanical Engineering, 2022, 58(12): 121-129.

参考文献

[1] KHAC C N, CHOI Y, JU H P, et al. A robust road vanishing point detection adapted to the real-world driving scenes[J]. Sensors, 2021, 21(6):2133.
[2] NGUYEN L, PHUNG S L, BOUZERDOUM A. Efficient vanishing point estimation for uion digital Image Computing:Techniques & Applications. IEEE, 2016.
[3] 邢志伟, 朱晓蕊, 何超. 基于行人行为学习的机器人同时定位与可通行区域制图[J]. 机械工程学报, 2019, 55(11):36-45. XING Zhiwei, ZHU Xiaorui, HE Chao. Simultaneous localization and traversable region mapping based on pedestrian behavior learning[J]. Journal of Mechanical Engineering, 2019, 55(11):36-45.
[4] RASMUSSEN C. Grouping dominant orientations for ill-structured road following[C/CD]//Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR) 2004., Washington DC:IEEE, 2004.
[5] 潘奎刚, 石朝侠. 基于主方向加权投票的非结构化道路消失点检测[J]. 计算机工程, 2017, 43(12):237-241. PAN Kuigang, SHI Chaoxia. Vanishing point detection of unstructured road based on dominant orientation weighted voting[J]. Computer Engineering, 2017, 43(12):237-241.
[6] BUI T H, SAITOH T, NOBUYAMA E. Road area detection based on texture orientations estimation and vanishing point detection[C]//Proceedings of the SICE Annual Conference. Nagoya:IEEE, 2013:1138-1143.
[7] ZHANG Y, SU Y, JIAN Y, et al. When Dijkstra meets vanishing point:A stereo vision approach for road detection[J]. IEEE Transactions on Image Processing, 2018(99):1.s
[8] SU Y, ZHANG Y, ALVAREZ J M, et al. An illumination-invariant nonparametric model for urban road detection using monocular camera and single-line lidar[C/CD]//2017 IEEE International Conference on Robotics and Biomimetics (ROBIO). IEEE, 2017.
[9] YING Z, GE L, ZANG X, et al. A novel shadow-free feature extractor for real-time road detection[C/CD]//Acm on Multimedia Conference. ACM, 2016.
[10] GIOI R G, JAKUBOWICZ J, MOREL J, et al. LSD:A fast Line segment detector with a false detection control[C/OL]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, doi:10.1109/TPAMI.2008.300.
[11] CHANG C K, ZHAO J, ITTI L. DeepVP:Deep learning for vanishing point detection on 1 million street view images[C/CD]//2018 IEEE International Conference on Robotics and Automation, 21-25, May 2018, Brisbane, QLD, Australia, 2018.
[12] TECHNICOLOR T, RELATED S, TECHNICOLOR T, et al. Imagenet classification with deep convolutional neural networks[C/CD]//NIPS. Curran A ssociate Inc., 2012.
[13] LI X, ZHU L, YU Z, et al. Adaptive auxiliary input extraction based on vanishing point detection for distant object detection in high-resolution railway scene[C/CD]//201914th IEEE International Conference on Electronic Measurement & Instruments (ICEMI). IEEE, 2019.

[1]	喻惟刚, 文思捷, 李建军, 李心雨. 基于可供性推理的人机协作拆卸序列规划方法[J]. 机械工程学报, 2024, 60(17): 297-309.
[2]	刘宏哲, 陶相如, 徐成, 曹东璞. 一种优化多尺度特征融合的人体姿态估计方法[J]. 机械工程学报, 2024, 60(16): 306-313.
[3]	翟广庆, 肖洪, 郭宏伟, 陶建国, 刘荣强, 邓宗全. 多翼瞬态差速展开机构设计与动力学参数优化[J]. 机械工程学报, 2024, 60(15): 113-122.
[4]	林文广, 刘晓东, 肖人彬. 文本挖掘与专利数据协同驱动的产品功能扩展研究[J]. 机械工程学报, 2024, 60(13): 56-70.
[5]	程锦, 吕昊, 刘振宇, 谭建荣. 考虑多源不确定性的三维CAD软件质量综合评价[J]. 机械工程学报, 2024, 60(13): 235-246.
[6]	刘振宇, 陈轲文, 裘辿, 李明, 张雨豪, 谭建荣, 彭群生. 微观几何设计制造的关键技术与工程应用[J]. 机械工程学报, 2024, 60(13): 268-280.
[7]	李文礼, 张祎楠, 石晓辉, 王梦昕. 基于博弈论的右转无信号交叉口行人行为模拟[J]. 机械工程学报, 2024, 60(10): 86-101.
[8]	申世全, 任锟, 李永国, 韩蕴生, 项琬婷, 耿赫阳. 金属表面异形区域上色轨迹自动规划[J]. 机械工程学报, 2024, 60(7): 258-265.
[9]	杨炜烽, 刘检华, 吕乃静, 马江涛. 基于位置动力学的线缆运动过程仿真方法[J]. 机械工程学报, 2024, 60(6): 21-31,57.
[10]	王小丫, 王鉴, 秦鹏, 韩星程, 聂鹏飞, 韩焱. 基于导波基函数投影变换的单模态超声导波提取方法[J]. 机械工程学报, 2024, 60(4): 250-258.
[11]	宁方立, 邓宗玲, 姚克强, 韦敏. 基于加权核范数最小化的非同步测量声源定位[J]. 机械工程学报, 2024, 60(3): 120-130.
[12]	邓聪颖, 邓子豪, 林丽君, 陈翔, 马莹, 禄盛. 基于迁移学习的变刀具-刀柄夹持状态下数控铣削稳定性预测研究[J]. 机械工程学报, 2024, 60(3): 296-304.
[13]	孙梦楠, 董祉序, 徐威, 孙兴伟, 刘伟军. 基于改进低秩稀疏分解的光斑图像降噪方法研究[J]. 机械工程学报, 2024, 60(2): 17-26.
[14]	王富顺, 池宝涛, 贾志超, 郭前建, 袁伟, 李灿. 一种适用于邻近特征的非结构体网格生成方法[J]. 机械工程学报, 2023, 59(24): 118-130.
[15]	张瑾贤, 吴晓峰, 叶才铭, 杨吉祥, 丁汉. 一种基于点云场景分割与改进配准算法的物体位姿估计方法[J]. 机械工程学报, 2023, 59(22): 176-185.

复杂场景非结构化道路消失点检测算法

Unstructured Road Vanishing Point Detection Algorithm for Complex Scenes

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价