Академический Документы
Профессиональный Документы
Культура Документы
Dana Cobzas
Supervisor: Hong Zhang
Range sensors Modelers Real scene Geometric model + texture New view
[Pollefeys & van Gool]
Navigation environment
Localization/ Tracking
Robot
Map
Navigation map: representation of the navigation space Goal: tracking/localizing the robot
This thesis
Investigates the applicability of IBMR techniques in mobile robotics.
Questions addressed:
Is it possible to use an IBM as navigation map for mobile robotics? Do they provide desired accuracy for the specific applications localization and tracking? What advantages do they offer compared to traditional geometric-based models?
Approach
Solution:
Reconstructed geometric model combined with image information 2 models Model1: calibrated: panorama with depth Model2: uncalibrated: geometric model with dynamic texture Applications in localization/tracking and predictive display
Model1: Overview
Standard panorama: - no parallax, reprojection from the same viewpoint Solution adding depth/disparity information:
1. Using two panoramic images for stereo 2. Depth from standard planar image stereo 3. Depth from laser range-finder
+ depth map
Model 1: Applications
Absolute localization:
Input: image+depth Features: planar patches vertical lines
Incremental localization:
Predictive display:
Model 2: Overview
Tracking Geometric model
Dynamic texture
Rendering
Input images
Model
Applications
Geometric structure
Tracked features
poses structure
Dynamic texture
Input Images Re-projected geometry Texture
Variability basis
I1
It
3D SSD Tracking
Goal: determine camera motion (rot+transl) from image differences Assumes: sparse geometric model of the scene Features: planar patches
3D Model
motion
past motion
current motion
Tracking example
Thesis contributions
Contrast calibrated and uncalibrated methods for capturing scene geometry and appearance from images:
panoramic model with depth data (calibrated) geometric model with dynamic texture (uncalibrated)
Demonstrate the use of the models as navigation maps with applications in mobile robotics
absolute localization incremental localization model-based tracking predictive display
Thesis questions
Is it possible to use an image-based model as navigation map for mobile robotics?
A combination of geometric and image-based model can be used as navigation map.
Do they provide desired accuracy for the specific applications localization, tracking?
The geometric model (reconstructed from images) is used for localization/tracking algorithms. The accuracy of the algorithm depends on the accuracy of the reconstructed model. The model accuracy can also be improved during navigation as different levels of accuracy are needed depending on the location (large space/narrow space) future work.
Future work
Mobile Robotics Map
Improve map during navigation Different map resolutions depending on robot pose Incorporate uncertainty in robot pose and features Light, occlusion invariant features Predictive display: control robots motion by pointing o dragging in image space