Monocular Visual Odometry with Cyclic Estimation
| Autor: | Altamiro Amadeu Susin, Marcelo Negreiros, Fabio Pereira, Joel Augusto Luft, Gustavo Ilha |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
050210 logistics & transportation
Monocular Computer science business.industry Orientation (computer vision) 05 social sciences Perspective (graphical) Feature extraction ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION 02 engineering and technology Position (vector) 0502 economics and business 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Computer vision Artificial intelligence Visual odometry business Rotation (mathematics) Pose |
| Zdroj: | SIBGRAPI |
| DOI: | 10.1109/sibgrapi.2017.7 |
| Popis: | Monocular Visual Odometry (MVO) estimates the camera position and orientation, based on images generated by a single camera. In this paper a new sparse MVO system for camera equipped vehicles is proposed. Three view cyclic Perspective-n-Point with adaptive threshold is used for camera pose estimation, perspective image transformations are used to improve tracking, and a multi-attribute cost function selects ground features for scale recovery. Results using the KITTI dataset show that the proposed system achieves 1.29% average translation error and average rotation precision of 0.0029 degrees per meter. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|