Research Progresses of Pose Estimation Based on Virtual Cameras

Fig. 2. Basic schematic diagram of mainstream inertial-unit-based pose estimation system^[32-33]. (a) Pose estimation system based on laser inertial units; (b) pose estimation system based on fiber optic inertial units; (c) pose estimation system based on MEMS inertial units

Download full size

Fig. 3. Virtual camera imaging system based on a bipartite prism. (a) Virtual viewpoint imaging system^[55]; (b) virtual camera imaging system^[56]

Download full size

Fig. 4. Virtual camera imaging system based on a micro-prism array^[64-65]. (a) System schematic; (b) reconstruction principle; (c) beam propagation principle; (d) system composition; (e) traditional endoscopic imaging; (f) virtual camera imaging

Download full size

$Virtual camera imaging system based on a grating diffraction[68]$

Fig. 5. Virtual camera imaging system based on a grating diffraction^[68]

Download full size

Fig. 6. Mirror-based adjustable virtual camera imaging system^[70-72]. (a) Single mirror; (b) double mirrors; (c) triple mirrors; (d) triple mirrors with a beam splitter; (e) four mirrors; (f) dual mirrors with a prismatic mirror

Download full size

Fig. 7. Schematic illustration of 3D imaging using FMCW LiDAR^[81]. (a) System layout; (b) multi-beam scanning mechanism using Risley prisms

Download full size

Fig. 8. Pose estimation system based on dynamic virtual cameras^［86］

Download full size

Fig. 9. Basic principle of target pose estimation based on point feature^[90]

Download full size

Fig. 10. Pose estimation based on CAD template matching^[104]

Download full size

Fig. 11. Basic principle of pose estimation method based on graph neural network^[133]

Download full size

Table 1. Performance comparison of mainstream pose estimation systems

View table

Table 1. Performance comparison of mainstream pose estimation systems

Name	Accuracy	Efficiency	Target	Range	Touching	Adaptability	Dynamic measurement	Cost
Coordinate measuring arm	Angle：1″~2″ Position：5-10 μm+3.3 μm/m	+	N	≤5 m	Y	+++	N	++
Laser tracker	Angle：1″~2″ Position：10-20 μm+6 μm/m	+++	Y	≤80 m	N	++	Y	+++
Total station	Angle：0.5″~1″ Position：0.6 mm±1 mm/m	++	Y	≥100 m	N	+++	N	++
IMU	Angle：0.3° Position：2 cm	++	N		N	++	Y	++
Monocular+rangefinder	Angle：1° Position：3 mm	++	N	≤30 m	N	++	Y	+
Binocular	Angle：0.2° Position：0.1 mm+1.2 mm/m	++	N/Y	≤10 m	N	+	Y	+
Biprism-based system	Position：≤2.36%	+++	N/Y	≤50 mm	N	++	Y	+
Mirror-based system	Angle：≤1° Position：≤12 mm	++	N/Y	≥60 mm	N	++	Y	+
Rotating-prism-based system	Angle：≤0.4° Position：≤0.4 mm	++	N/Y	≥80 mm	N	+++	Y	+

Table 2. Comparison of mainstream pose estimation methods

View table

Table 2. Comparison of mainstream pose estimation methods

Category	Method	Accuracy	Time consuming	Robustness	Online performance	Scope of application
Pose estimation based on 2D information	Target feature	+++	+	+	++	+++
Pose estimation based on 2D information	Template matching	+++	++	+++	+	+
Pose estimation based on 3D information	Feature matching	++	++	+	+	+++
Pose estimation based on 3D information	Absolute orientation	+++	+/++	+	+	++
Pose estimation based on deep learning	Direct regression	+	+++	++	+++	+
Pose estimation based on deep learning	Indirect regression	++	+++	++	+++	+

Tools

Get Citation

Copy Citation Text

Anhu Li, Zhaojun Deng, Xingsheng Liu, Hao Chen. Research Progresses of Pose Estimation Based on Virtual Cameras[J]. Laser & Optoelectronics Progress, 2022, 59(14): 1415002

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites

Paper Information

Category: Machine Vision

Received: Mar. 30, 2022

Accepted: May. 11, 2022

Published Online: Jul. 1, 2022

The Author Email: Anhu Li (lah@tongji.edu.cn)

DOI:10.3788/LOP202259.1415002

Topics

laser devices and laser physics

Lasers and Laser Optics

Laser physics

laser manufacturing

Instrumentation, Measurement and Metrology