Back to Search
Start Over
3D-Aware Ellipse Prediction for Object-Based Camera Pose Estimation
- Source :
- ORASIS 2021-18èmes journées francophones des jeunes chercheurs en vision par ordinateur, ORASIS 2021-18èmes journées francophones des jeunes chercheurs en vision par ordinateur, Centre National de la Recherche Scientifique [CNRS], Sep 2021, Saint Ferréol, France, ORASIS 2021, ORASIS 2021, Centre National de la Recherche Scientifique [CNRS], Sep 2021, Saint Ferréol, France, 3DV 2020-International Virtual Conference on 3D Vision, 3DV 2020-International Virtual Conference on 3D Vision, Nov 2020, Fukuoka / Virtual, Japan
- Publication Year :
- 2021
- Publisher :
- HAL CCSD, 2021.
-
Abstract
- In this paper, we propose a method for coarse camera pose computation which is robust to viewing conditions and does not require a detailed model of the scene. This method meets the growing need of easy deployment of robotics or augmented reality applications in any environments, especially those for which no accurate 3D model nor huge amount of ground truth data are available. It exploits the ability of deep learning techniques to reliably detect objects regardless of viewing conditions. Previous works have also shown that abstracting the geometry of a scene of objects by an ellipsoid cloud allows to compute the camera pose accurately enough for various application needs. Though promising, these approaches use the ellipses fitted to the detection bounding boxes as an approximation of the imaged objects. In this paper, we go one step further and propose a learning-based method which detects improved elliptic approximations of objects which are coherent with the 3D ellipsoid in terms of perspective projection. Experiments prove that the accuracy of the computed pose significantly increases thanks to our method and is more robust to the variability of the boundaries of the detection boxes. This is achieved with very little effort in terms of training data acquisition -- a few hundred calibrated images of which only three need manual object annotation. Code and models are released at https://github.com/zinsmatt/3D-Aware-Ellipses-for-Visual-Localization.<br />Comment: Presented at 3DV 2020. Code and models released at https://github.com/zinsmatt/3D-Aware-Ellipses-for-Visual-Localization
- Subjects :
- FOS: Computer and information sciences
Camera pose
I.4
Computer science
Computation
Computer Vision and Pattern Recognition (cs.CV)
Computer Science - Computer Vision and Pattern Recognition
02 engineering and technology
[INFO] Computer Science [cs]
010501 environmental sciences
Ellipse
01 natural sciences
[INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]
détection d'objets
0202 electrical engineering, electronic engineering, information engineering
localisation visuelle
Computer vision
[INFO]Computer Science [cs]
Pose
0105 earth and related environmental sciences
Ground truth
ellipse
business.industry
65D19
Deep learning
[INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]
object detection
Object (computer science)
Ellipsoid
020201 artificial intelligence & image processing
Augmented reality
Artificial intelligence
ellipsoid
ellipsoïde
business
Pose de caméra
Subjects
Details
- Language :
- French
- Database :
- OpenAIRE
- Journal :
- ORASIS 2021-18èmes journées francophones des jeunes chercheurs en vision par ordinateur, ORASIS 2021-18èmes journées francophones des jeunes chercheurs en vision par ordinateur, Centre National de la Recherche Scientifique [CNRS], Sep 2021, Saint Ferréol, France, ORASIS 2021, ORASIS 2021, Centre National de la Recherche Scientifique [CNRS], Sep 2021, Saint Ferréol, France, 3DV 2020-International Virtual Conference on 3D Vision, 3DV 2020-International Virtual Conference on 3D Vision, Nov 2020, Fukuoka / Virtual, Japan
- Accession number :
- edsair.doi.dedup.....661232933d6c00f3d67c2fcdcbf5c3c7