A New Monocular Pose Estimation Method for the Coplanar P4P Problem
Source abstract
Abstract
The Perspective of N Points (PNP) problem in optical measurement and machine vision is to estimate the pose parameters of an object by a monocular image. For traditional coplanar P4P methods, the four points must have known coordinates or be a rectangle’s four vertices. In this paper, a new method of the P4P problem for parallelogram objects without shape parameters is proposed to solve the objects’ pose and shape parameters based on the parallelogram vertices’ relative coordinate constraints. The correctness and effectiveness of the method have been verified through experiments. In addition to being used to estimate a parallelogram object’s pose and shape, the new method extends the conclusions of the coplanar P4P problem when the four points are a parallelogram’s four vertices.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Image and Object Detection Techniques · Advanced Measurement and Metrology Techniques · Robotics and Sensor-Based Localization
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Advanced Interdisciplinary Studies, National University of Defense Technology, Changsha 410073, China
College of Aerospace Science and Engineering, National University of Defense Technology, Changsha 410073, China
Funding
National Natural Science Foundation of China
References (20)
Show source-provided references
1. Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography10.1145/358669.358692 ↗
2. On the number of solutions for the p4p problem
3. A note on the number of solutions of the noncoplanar P4P problem10.1109/34.993561 ↗
4. Complete Singularity Analysis for the Perspective-Four-Point Problem10.1007/s11263-020-01420-0 ↗
5. A short note on P4P problem
6. Bujnak, M., Kukelova, Z., and Pajdla, T. (2008, January 23–28). A general solution to the P4P problem for camera with unknown focal length. Proceedings of the 2008 IEEE Computer Society Conference on Computer Vision and Pattern, Anchorage, AK, USA.10.1109/CVPR.2008.4587793 ↗
7. A note on unique solution conditions of the P3P Problem
8. A general recursive linear method and unique solution pattern design for the perspective-n-point problem10.1016/j.imavis.2007.08.008 ↗
9. Linear N-point camera pose determination10.1109/34.784291 ↗
10. An analytical solution to the perspective-n-point problem for common planar camera and for catadioptric sensor10.1142/S0219467808003015 ↗
11. Monocular vision-based iterative pose estimation algorithm from corresponding feature points10.1007/s11432-010-4017-6 ↗
12. Computationally efficient iterative pose estimation for space robot based on vision
13. Bundle Adjustment methods in engineering photogrammetry10.1111/j.1477-9730.1980.tb00020.x ↗
14. Triggs, W., Zisserman, A., and Szeliski, R. (2000). Bundle adjustment—A modern synthesis. Vision Algorithms: Theory and Practice, Springer. LNCS.10.1007/3-540-44480-7 ↗
15. Hana, K., Karel, J., Radek, F., and Daniel, B. (2020). Indoor Positioning Using PnP Problem on Mobile Phone Images. ISPRS Int. J. Geo-Inf., 9.10.3390/ijgi9060368 ↗
16. Indoor positioning algorithm based on improved convolutional neural network10.1007/s00521-021-06112-5 ↗
17. Two AUVs Guidance Method for Self-Reconfiguration Mission Based on Monocular Vision10.1109/JSEN.2020.3042306 ↗
18. A high-precision online monitoring system for surface settlement imaging of railway subgrade10.1016/j.measurement.2020.107707 ↗
19. Determining camera parameters from the perspective projection of a quadrilateral10.1016/0031-3203(91)90019-2 ↗
20. A new efficient and direct solution for pose estimation using quadrangular targets: Algorithm and evaluation10.1109/34.391388 ↗