1 / 10

Multi-view Manhole Detection, Recognition and 3D Localisation

Multi-view Manhole Detection, Recognition and 3D Localisation. Radu Timofte and Luc Van Gool. Problem definition. Input: Large set of views and corresponding camera locations Output: List of manholes. Manholes. High variance in manhole patterns around the world .

chacha
Télécharger la présentation

Multi-view Manhole Detection, Recognition and 3D Localisation

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Multi-view Manhole Detection, Recognition and 3D Localisation Radu Timofte and Luc Van Gool

  2. Problem definition • Input: Large set of views and corresponding camera locations • Output: List of manholes

  3. Manholes • High variance in manhole patterns around the world . • We DO use texture models for manhole validation. For each new region, new texture models are to be trained.

  4. Outline Single view • Segmentation – fast segment selection process with very few missed manholes. • Manholes are usually distinguishable from the surrounding environment => have distinctive textures, shapes, symmetry. • Mean shift method is employed for color segmentation. • Detection – Classifiers based on histograms of Local Binary Patterns as texture descriptors. Multi-view • Global optimization – over single-view detections constrained by 3D geometry

  5. Original image Ground plane projection Segmented image → → Edge Detection and Image Segmentation • The image is projected on the estimated ground plane. • Edge detection and mean shift1 in L*u*v* color space are combined for segmentation 1 D.Comaniciu, P.Meer, “Mean shift: A robust approach toward feature space analysis”, PAMI, 2002

  6. Segmented image Texture image Radial symmetry Projected image + + = Detection • Local Binary Patterns2 is used as a texture descriptor model and radial symmetry3 has pruning purposes. • Each segment is classified according its LBP histogram as manhole or background. 2T.Ojala et al, “Multiresolution gray-scale and rotation invariant texture classication with Local Binary Patterns”, PAMI, 2002 3G.Loy and A. Zelinsky, “Fast Radial Symmetry for Detecting Points of Interest”, PAMI, 2003

  7. 3D Localisation • Single-view manhole detections are grouped under 3D geometric constraints. Projected image Localised manhole ∑ ( ) =

  8. Evaluation • 317 manholes and 270 non-manholes images in testing set. • Detection rate increases with the number of views available for each manhole. • While the single-view detection rate is about 41%, the multi-view evaluation shows 97% manhole detection rate for very low false alarm rate.

  9. Demo

  10. Conclusions • Manhole Detection, Recognition and 3D Localisation is a challenging problem. • We propose a multi-view scheme, which combines 2D and 3D analysis. • Work in progress…

More Related