This paper proposes robust algorithms for linebased pose enumeration from a single view, and it reports on their evaluations by simulations. The proposed algorithms incorporate two major refinements into the algorithms originally proposed by Shakunaga [1]. The first refinement, introduction of zone-crossing detection to the 1-d search remarkably decreases the rate of overlooking a correct pose. The second refinement, adaptive selection of a PAT pair considerably reduces the average estimation error. Simulation results show that pose estimation precision depends primarily on the precision of line detection. Although the refinements are widely effective, they are more effective for more precise line detection. For 99% of rigid body samples, the algorithm can estimate rotation with an error of less than 2 degrees, and for 99.9% of the samples, the error is less than 10 degrees. Simulation experiments for articulated objects show similar results by using the second algorithm. The effectiveness of the algorithms is verified in an alignment approach by simulations.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Takeshi SHAKUNAGA, "Refinements and Evaluations of Line-Based Pose Enumeration from a Single Image" in IEICE TRANSACTIONS on Information,
vol. E79-D, no. 9, pp. 1266-1273, September 1996, doi: .
Abstract: This paper proposes robust algorithms for linebased pose enumeration from a single view, and it reports on their evaluations by simulations. The proposed algorithms incorporate two major refinements into the algorithms originally proposed by Shakunaga [1]. The first refinement, introduction of zone-crossing detection to the 1-d search remarkably decreases the rate of overlooking a correct pose. The second refinement, adaptive selection of a PAT pair considerably reduces the average estimation error. Simulation results show that pose estimation precision depends primarily on the precision of line detection. Although the refinements are widely effective, they are more effective for more precise line detection. For 99% of rigid body samples, the algorithm can estimate rotation with an error of less than 2 degrees, and for 99.9% of the samples, the error is less than 10 degrees. Simulation experiments for articulated objects show similar results by using the second algorithm. The effectiveness of the algorithms is verified in an alignment approach by simulations.
URL: https://global.ieice.org/en_transactions/information/10.1587/e79-d_9_1266/_p
Copy
@ARTICLE{e79-d_9_1266,
author={Takeshi SHAKUNAGA, },
journal={IEICE TRANSACTIONS on Information},
title={Refinements and Evaluations of Line-Based Pose Enumeration from a Single Image},
year={1996},
volume={E79-D},
number={9},
pages={1266-1273},
abstract={This paper proposes robust algorithms for linebased pose enumeration from a single view, and it reports on their evaluations by simulations. The proposed algorithms incorporate two major refinements into the algorithms originally proposed by Shakunaga [1]. The first refinement, introduction of zone-crossing detection to the 1-d search remarkably decreases the rate of overlooking a correct pose. The second refinement, adaptive selection of a PAT pair considerably reduces the average estimation error. Simulation results show that pose estimation precision depends primarily on the precision of line detection. Although the refinements are widely effective, they are more effective for more precise line detection. For 99% of rigid body samples, the algorithm can estimate rotation with an error of less than 2 degrees, and for 99.9% of the samples, the error is less than 10 degrees. Simulation experiments for articulated objects show similar results by using the second algorithm. The effectiveness of the algorithms is verified in an alignment approach by simulations.},
keywords={},
doi={},
ISSN={},
month={September},}
Copy
TY - JOUR
TI - Refinements and Evaluations of Line-Based Pose Enumeration from a Single Image
T2 - IEICE TRANSACTIONS on Information
SP - 1266
EP - 1273
AU - Takeshi SHAKUNAGA
PY - 1996
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E79-D
IS - 9
JA - IEICE TRANSACTIONS on Information
Y1 - September 1996
AB - This paper proposes robust algorithms for linebased pose enumeration from a single view, and it reports on their evaluations by simulations. The proposed algorithms incorporate two major refinements into the algorithms originally proposed by Shakunaga [1]. The first refinement, introduction of zone-crossing detection to the 1-d search remarkably decreases the rate of overlooking a correct pose. The second refinement, adaptive selection of a PAT pair considerably reduces the average estimation error. Simulation results show that pose estimation precision depends primarily on the precision of line detection. Although the refinements are widely effective, they are more effective for more precise line detection. For 99% of rigid body samples, the algorithm can estimate rotation with an error of less than 2 degrees, and for 99.9% of the samples, the error is less than 10 degrees. Simulation experiments for articulated objects show similar results by using the second algorithm. The effectiveness of the algorithms is verified in an alignment approach by simulations.
ER -