Visual Map Matching Method for Intelligent Vehicles Based on Second-order HMM

被引：0
|
作者：
Zhou Z. [1 ]
Hu Z. [1 ,2 ]
Wang Z. [1 ]
Xiao H. [1 ]
机构：
[1] Intelligent Transport System Center, Wuhan University of Technology, Wuhan
[2] Chongqing Research Institute of Wuhan University of Technology, Chongqing
来源：
Qiche Gongcheng/Automotive Engineering | 2022年 / 44卷 / 02期
关键词：
Intelligent vehicle; Second-order Hidden Markov Model; Vision-based positioning; Visual map;
D O I：
10.19562/j.chinasae.qcgc.2022.02.005
中图分类号：
学科分类号：
摘要：
In this paper, the visual map matching problem is transformed into the optimal visual map node matching problem based on image sequence and a method for visual map matching method based on second-order HMM (Hidden Markov Model) is proposed. In this model, state variables are defined as high precision visual map nodes, and query images are defined as observation variables. In the state transition model, the second-order model is introduced to model the uniform motion of vehicles within a short period of time. Compared with the traditional first-order HMM, the second-order HMM method is more applicable and precise. The paper proposes to use the global image features to establish the matching relationship between the query image and the map nodes, and establish the transmission probability model from the matching Hamming distance, which can effectively improve the efficiency of map matching. Finally, the optimal matching map nodes are obtained by forward algorithm. The performance of the algorithm is verified in closed industrial park, open roads, and the public KITTI datasets, respectively. The experimental results show that the proposed second-order HMM model can effectively integrate vehicle motion information and image information, improve the stability and accuracy of matching, and the performance of the proposed algorithm outperforms traditional single frame matching and sequence matching algorithms. © 2022, Society of Automotive Engineers of China. All right reserved.
引用
收藏
页码：190 / 198
页数：8
相关论文
共 23 条
  • [11] FAN H Q, ZHANG S., Camera localization and map reconstruction algorithm based on temporal-spatial consistency, Robot, 41, 1, pp. 40-49, (2019)
  • [12] FENG G, MA L, TAN X, Et al., Visual map construction using RGB-D sensors for image-based localization in indoor environments, Journal of Sensors, pp. 1-18, (2017)
  • [13] GALVEZ-LOPEZ D, TARDOS J D., Bag of binary words for fast place recognition in image sequences, IEEE Transactions on Robotics, 28, 5, pp. 1188-1197, (2012)
  • [14] CHEN H T, ZHANG B, SUN F C, Et al., Incremental scene detection in outdoor environment based on hierarchical bag-of-words model, Control Theory & Applications, 37, 7, pp. 1471-1480, (2020)
  • [15] GARCIA-FIDALGO E, ORTIZ A., Hierarchical place recognition for topological mapping, IEEE Transactions on Robotics, 33, 5, pp. 1061-1074, (2017)
  • [16] MA L, XUE H, JIA T, Et al., A fast C-GIST based image retrieval method for vision-based indoor localization, Vehicular Technology Conference, pp. 1-5, (2017)
  • [17] LIU G Z, HU Z Z., Fast closed loop detection based on SURF and ORB global features, Robot, 39, 1, pp. 36-45, (2017)
  • [18] WANG X, HU Z, TAO Q W, Et al., Bayesian place recognition based on bag of objects for intelligent vehicle localisation, IET Intelligent Transport Systems, 13, 11, pp. 1736-1744, (2019)
  • [19] KHALIQ A, EHSAN S, MILFORD M, Et al., A holistic visual place recognition approach using lightweight CNNs for severe viewpoint and appearance changes, IEEE Transactions on Robotics, 36, 2, pp. 561-569, (2020)
  • [20] MILFORD M J, WYETH G F., SeqSLAM: Visual route-based navigation for sunny summer days and stormy winter nights, IEEE. 2012 IEEE International Conference on Robotics and Automation, pp. 1643-1649, (2012)
123