面向智能车的地下停车场环视特征地图构建与定位

doi:10.11947/j.AGCS.2021.20210205

测绘学报 ›› 2021, Vol. 50 ›› Issue (11): 1574-1584.doi: 10.11947/j.AGCS.2021.20210205

面向智能车的地下停车场环视特征地图构建与定位

周哲^1,2, 胡钊政^1,2, 李娜³, 肖汉彪¹, 伍锦祥¹

1. 武汉理工大学智能交通系统研究中心, 湖北武汉 430063;
2. 武汉理工大学重庆研究院, 重庆 401120;
3. 武汉理工大学自动化学院, 湖北武汉 430070

收稿日期:2021-04-22 修回日期:2021-09-23 发布日期:2021-12-07
通讯作者: 胡钊政 E-mail:zzhu@whut.edu.cn
作者简介:周哲(1990—),男,博士生,研究方向为高精度视觉地图构建与导航。
基金资助:
国家重点研发计划（2018YFB1600801）；国家自然科学基金（U1764262）；重庆市自然科学基金（cstc2020jcyj-msxmX0978）；武汉市科技局技术创新项目（2020010601012165；2020010602011973；2020010602012003）

Visual map from around view system for intelligent vehicle localization in underground parking lots

ZHOU Zhe^1,2, HU Zhaozheng^1,2, LI Na³, XIAO Hanbiao¹, WU Jinxiang¹

1. Intelligent Transportation Systems Research Center, Wuhan University of Technology, Wuhan 430063, China;
2. Chongqing Research Institute of Wuhan University of Technology, Chongqing 401120, China;
3. School of Automation, Wuhan University of Technology, Wuhan 430070, China

Received:2021-04-22 Revised:2021-09-23 Published:2021-12-07
Supported by:
The National Key Research and Development Program of China (No. 2018YFB1600801);The National Natural Science Foundation of China (No. U1764262);The National Natural Science Foundation of Chongqing of China (No. cstc2020jcyj-msxmX0978);The Funding of Wuhan Science and Technology Bureau (Nos. 2020010601012165;2020010602011973;2020010602012003)

摘要/Abstract

摘要： 针对地下停车场环境GPS信号缺失的问题，本文在环视特征地图构建的基础上，提出基于二阶马尔科夫模型的粒子滤波定位算法（Markov model-particle filter，MM-PF），实现智能车在地下停车场环境中的高精度定位。在该模型中，环视特征地图节点被定义为粒子，查询图像被定义为观测数据。在状态转移过程中，引入二阶马尔可夫模型，对短时间车辆运动进行建模，构建状态转移模型。利用图像的全局特征建立当前车辆获取的图像与各粒子（环视地图节点）之间的匹配关系，从获取的汉明距离建立粒子权重分布模型，可以大幅提高系统的计算效率。当前车辆的位置由局部特征匹配获得。选取两个典型的地下停车场场景对本文算法进行验证，在选取的两个场景中，本文算法平均定位精度小于0.38 m，定位误差均方差小于0.29 m，定位误差在1 m以下的概率不低于95.4%。试验结果表明：本文所提出的二阶MM-PF算法能够将车辆的运动信息与视觉信息相融合，相较于对比算法，定位精度与稳健性得到大幅提高。

关键词: 智能车, 视觉定位, 二阶马尔可夫模型, 粒子滤波算法

Abstract: In view of the lack of GPS signal in the underground parking lots, the second-order Markov model and particle filter (MM-PF) method for intelligent vehicle localization in underground parking lots is proposed based on the construction of a visual feature map from around view. In the method, the nodes of the visual feature map are defined as particles, while the query images are defined as observation data. In the process of state transition, the second-order Markov model is introduced to model the motion of the vehicles in a short time. In addition, holistic features are employed to establish the matching relationship between the query image and each particle (visual feature map node) by assigning particle weights based on Hamming distance. In the experiments, two typical underground parking lots are selected to verify the method. In both scenarios, the mean error of localization is less than 0.38 m, the mean square error is less than 0.29 m. The probability of positioning error below 1 m is not less than 95.4%. Experimental results demonstrate that the proposed method can integrate both the motion and visual features to enhance localization performance. Experimental results also show that the proposed method outperforms state-of-the-art ones in terms of localization accuracy and robustness.

Key words: intelligent vehicle, vision localization, second-order Markov model, particle filter algorithm

中图分类号:

P285.3

周哲, 胡钊政, 李娜, 肖汉彪, 伍锦祥. 面向智能车的地下停车场环视特征地图构建与定位[J]. 测绘学报, 2021, 50(11): 1574-1584.

ZHOU Zhe, HU Zhaozheng, LI Na, XIAO Hanbiao, WU Jinxiang. Visual map from around view system for intelligent vehicle localization in underground parking lots[J]. Acta Geodaetica et Cartographica Sinica, 2021, 50(11): 1574-1584.

参考文献

[1] SUHR J K, JANG J, MIN D, et al. Sensor fusion-based low-cost vehicle localization system for complex urban environments[J]. IEEE Transactions on Intelligent Transportation Systems, 2017, 18(5): 1078-1086.
[2] 中国科学技术协会. 中国科协发布2020重大科学问题和工程技术难题[EB/OL]. [2020-08-16]. https://www.cast.org.cn/art/2020/8/16/art_90_130822.html. China Association for Science and Technology. China association for science and technology issues 2020[EB/OL]. [2020-08-16]. https://www.cast.org.cn/art/2020/8/16/art_90_130822.html.
[3] 陈国良, 张言哲, 汪云甲, 等. WiFi-PDR室内组合定位的无迹卡尔曼滤波算法[J]. 测绘学报, 2015, 44(12): 1314-1321. DOI:10.11947/j.AGCS.2015.20140691. CHEN Guoliang, ZHANG Yanzhe, WANG Yunjia, et al. Unscented kalman filter algorithm for WiFi-PDR integrated indoor positioning[J]. Acta Geodaetica et Cartographica Sinica, 2015, 44(12): 1314-1321. DOI:10.11947/j.AGCS.2015.20140691.
[4] SUN Wei, XUE Min, TANG Hongwei, et al. Augmentation of fingerprints for indoor WiFi localization based on gaussian process regression[J].IEEE Transactions on Vehicular Technology, 2018, 67(11): 10896-10905.
[5] LU Weixin, ZHOU Yao, WAN Guowei, et al. L3-Net: towards learning based LiDAR localization for autonomous driving[C]//Proceedings of 2019 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach, CA, USA: IEEE, 2020: 6382-6391.
[6] 李祎承, 胡钊政, 王相龙, 等. 面向智能车定位的道路环境视觉地图构建[J]. 中国公路学报, 2018, 31(11): 138-146,213. LI Yicheng, HU Zhaozheng, WANG Xianglong, et al. Construction of a visual map based on road scenarios for intelligent vehicle localization[J]. China Journal of Highway and Transport, 2018, 31(11): 138-146,213.
[7] PIASCO N, SIDIBÉ D, DEMONCEAUX C, et al. A survey on visual-based localization: on the benefit of heterogeneous data[J]. Pattern Recognition, 2018, 74, 90-109.
[8] MUR-ARTAL R, TARDÓS J D. ORB-SLAM2: An open-source SLAM system for monocular, stereo, and RGB-D cameras[J]. IEEE Transactions on Robotics, 2017, 33(5): 1255-1262.
[9] 邸凯昌, 万文辉, 赵红颖, 等. 视觉SLAM技术的进展与应用[J]. 测绘学报, 2018, 47(6): 770-779. DOI:10.11947/j.AGCS.2018.20170652. DI Kaichang, WAN Wenhui, ZHAO Hongying, et al. Progress and applications of visual SLAM[J]. Acta Geodaetica et Certographica Sinica, 2018, 47(6): 770-779. DOI:10.11947/j.AGCS.2018.20170652.
[10] 刘经南, 詹骄, 郭迟, 等. 智能高精地图数据逻辑结构与关键技术[J]. 测绘学报, 2019, 48(8): 939-953. DOI: 10.11947/j.AGCS.2019.20190125. LIU Jingnan, ZHAN Jiao, GUO Chi, et al. Data logic structure and key technologies on intelligent high-precision map[J]. Acta Geodaetica et Certographica Sinica, 2019, 48(8): 939-953. DOI: 10.11947/j.AGCS.2019.20190125.
[11] LATEGAHN H, STILLER C. Vision-only localization[J]. IEEE Transactions on Intelligent Transportation Systems, 2014. 15(3): 1246-1257.
[12] LOWE D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2): 91-110.
[13] RUBLEE E, RABAUD V, KONOLIGE K, et al. ORB: An efficient alternative to SIFT or SURF[C]//Proceedings of 2011 IEEE International Conference on Computer Vision (ICCV). Barcelona, Spain: IEEE, 2011: 2564-2571.
[14] HANA K, JEDLIKA K, FIALA R, et al. Indoor positioning using PnP problem on mobile phone images[J]. International Journal of Geo-Information, 2020,9(6): 1-18.
[15] LI Yicheng, HU Zhaozheng, CAI Yingfeng, et al. Visual map-based localization for intelligent vehicles from multi-view site matching[J]. IEEE Transactions on Intelligent Transportation Systems, 2020, 22(2): 1068-1079.
[16] BAMPIS L, GASTERATOS A. Revisiting the bag-of-visual-words model: a hierarchical localization architecture for mobile systems[J]. Robotics and Autonomous Systems, 2019, 113: 104-119.
[17] JEONG J, CHO Y, KIM A. Road-SLAM: road marking based SLAM with lane-level accuracy[C]//Proceedings of 2017 IEEE Intelligent Vehicles Symposium (IV). Redondo Beach, CA, USA: IEEE, 2017: 1736-1473.
[18] HUANG Gang. HU Zhaozheng, TAO Qianwen, et al. Improved intelligent vehicle self-localization with integration of sparse visual map and high speed pavement visual odometry[J]. Journal of Automobile Engineering, 2021, 235(1): 177-187.
[19] HUANG Yewei, ZHAO Junqiao, HE Xudong, et al, Vision-based semantic mapping and localization for autonomous indoor parking[C]//Proceedings of 2018 IEEE Intelligent Vehicles Symposium. Changshu, China: IEEE, 2018: 636-641.
[20] YIN Peng, SRIVATSAN R A, CHEN Yin, et al. MRS-VPR: A multi-resolution sampling based global visual place recognition method[C]//Proceedings of 2019 IEEE International Conference on Robotics and Automation (ICRA). Montreal, QC, Canada: IEEE, 2019: 7137-7142.
[21] 刘国忠, 胡钊政. 基于SURF和ORB全局特征的快速闭环检测[J]. 机器人, 2017, 39(1): 36-45. LIU Guozhong, HU Zhaozheng. Fast closed loop detection based on SURF and ORB global features[J]. Robot, 2017, 39(1): 36-45.
[22] SONG Chunhe, ZHAO Hai, JING Wei, et al. Robust video stabilization based on particle filtering with weighted feature points[J].IEEE Transactions on Consumer Electronics, 2021,58(2): 570-577.
[23] CHANG Y L, HSU L Y, CHEN O T, et al. Auto-calibration around-view monitoring system[C]//Proceedings of 2013 IEEE 78th Vehicular Technology Conference (VTC Fall). Las Vegas, NV, USA: IEEE, 2013: 1-5.
[24] CUMMINS M, NEWMAN P. FAB-MAP: Probabilistic localization and mapping in the space of appearance[J]. The International Journal of Robotics Research, 2008, 27(6):647-665.

面向智能车的地下停车场环视特征地图构建与定位

Visual map from around view system for intelligent vehicle localization in underground parking lots

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 5

编辑推荐

Metrics

本文评价

[1]	张星, 林静, 李清泉, 刘涛, 方志祥. 结合感知哈希与空间约束的室内连续视觉定位方法[J]. 测绘学报, 2021, 50(12): 1639-1649.
[2]	邸凯昌, 王镓, 邢琰, 刘召芹, 万文辉, 彭嫚, 王晔昕, 刘斌, 于天一, 李立春, 刘传凯. 深空探测车环境感知与导航定位技术进展与展望[J]. 测绘学报, 2021, 50(11): 1457-1468.
[3]	邵晓航, 吴杭彬, 刘春, 陈晨, 蔡天池, 程帆瑾. 语素关联约束的动态环境视觉定位优化[J]. 测绘学报, 2021, 50(11): 1478-1486.
[4]	庄瀚洋, 王晓亮, 王春香, 杨明. 顾及数字地图中车道走向的车辆跟踪增强算法[J]. 测绘学报, 2021, 50(11): 1522-1533.
[5]	程传奇, 郝向阳, 李建胜, 胡鹏, 张旭. 移动机器人视觉动态定位的稳健高斯混合模型[J]. 测绘学报, 2018, 47(11): 1446-1456.