Combining Scale-Space and Similarity-Based Aspect Graphs for Fast 3D Object Recognition
The DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.
Abstract
This paper describes an approach for recognizing instances of a 3D object in a single camera image and for determining their 3D poses. A hierarchical model is generated solely based on the geometry information of a 3D CAD model of the object. The approach does not rely on texture or reflectance information of the object's surface, making it useful for a wide range of industrial and robotic applications, e.g., bin-picking. A hierarchical view-based approach that addresses typical problems of previous methods is applied: It handles true perspective, is robust to noise, occlusions, and clutter to an extent that is sufficient for many practical applications, and is invariant to contrast changes. For the generation of this hierarchical model, a new model image generation technique by which scale-space effects can be taken into account is presented. The necessary object views are derived using a similarity-based aspect graph. The high robustness of an exhaustive search is combined with an efficient hierarchical search. The 3D pose is refined by using a least-squares adjustment that minimizes geometric distances in the image, yielding a position accuracy of up to 0.12 percent with respect to the object distance, and an orientation accuracy of up to 0.35 degree in our tests. The recognition time is largely independent of the complexity of the object, but depends mainly on the range of poses within which the object may appear in front of the camera. For efficiency reasons, the approach allows the restriction of the pose range depending on the application. Typical runtimes are in the range of a few hundred ms.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Distinctive Image Features from Scale-Invariant Keypoints
Lowe, D. G. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000029664.99615.94 · Cited by 55,589
SURF: Speeded Up Robust Features
Bay, H., Tuytelaars, T., & Van Gool, L. (2006) · Lecture Notes in Computer Science · doi:10.1007/11744023_32 · Cited by 14,955
Shape matching and object recognition using shape contexts
Belongie, S., Malik, J., & Puzicha, J. (2002) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.993558 · Cited by 6,306
Comparing images using the Hausdorff distance
Huttenlocher, D. P., Klanderman, G. A., & Rucklidge, W. J. (1993) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.232073 · Cited by 4,545
Monocular model-based 3D tracking of rigid objects: a survey
Lepetit, V., & Fua, P. (2005) · Foundations and Trends® in Computer Graphics and Vision · doi:10.1561/0600000001 · Cited by 484 · cited 1×
“View-based approaches have the drawback that the accuracy of the resulting object pose is limited to the density of the sampled views.”
Background
Research works printed but not linked: 40
- 10.1109/34.106994 · DOI · Paper page
- Lanser, 1995, Robust Video-Based Object Recognition Using CAD Models, Proc. Intelligent Autonomous Systems, 529
- 10.1016/S0262-8856(98)00100-0 · DOI
- 10.1016/S0262-8856(99)00075-X · DOI
- 10.1007/BF00365595 · DOI · Paper page
- 10.1007/BF00337644 · DOI · Paper page
- 10.1109/3468.823482 · DOI
- Schiffenbauer, 2001, A Survey of Aspect Graphs
- 10.1109/34.121788 · DOI · Paper page
- 10.1023/B:VISI.0000013088.59081.4c · DOI
- 10.1109/34.244674 · DOI
- 10.1109/CVPR.1996.517114 · DOI
- 10.1007/978-3-540-45243-0_24 · doi:10.1007/978-3-540-45243-0_24
- 10.1016/0004-3702(87)90070-1 · DOI · Paper page
- 10.1109/34.134043 · DOI · Paper page
- 10.1007/3-540-58240-1_17 · doi:10.1007/3-540-58240-1_17
- 10.1016/S0167-8655(97)00175-X · DOI
- 10.1006/cviu.2000.0865 · DOI
- 10.1109/ICCV.2005.173 · DOI · Paper page
- 10.1016/0004-3702(95)00023-2 · DOI
- 10.1006/cviu.1998.0701 · doi:10.1006/cviu.1998.0701
- 10.1109/34.908963 · DOI
- 10.1109/ICIAP.2003.1234048 · DOI
- 10.1109/CVPR.2005.320 · DOI · Paper page
- Pilet, Real-Time Non-Rigid Surface Detection, 822
- 10.1109/TPAMI.2006.188 · DOI · Paper page
- 10.1109/ICCV.2007.4409004 · DOI
- 10.1023/A:1007927317325 · doi:10.1023/a:1007927317325
- 10.1109/TPAMI.2002.1017620 · DOI · Paper page
- Steger, 2002, Occlusion, Clutter, and Illumination Invariant Object Recognition, Int’l Archives of Photogrammetry and Remote Sensing, 34, 345
- 10.1007/978-3-540-69321-5_14 · DOI
- 10.1109/ROBOT.2009.5152511 · DOI · Paper page
- Steger, 2007, Machine Vision Algorithms and Applications
- 10.1109/ICCV.1999.791202 · DOI · Paper page
- 10.1016/0734-189X(86)90223-9 · doi:10.1016/0734-189x(86)90223-9
- Steger, 2000, Subpixel-Precise Extraction of Lines and Edges, Int’l Archives of Photogrammetry and Remote Sensing, 33, 141
- 10.1016/0031-3203(81)90009-1 · DOI · Paper page
- 10.1016/S0031-3203(03)00169-9 · DOI
- Kender, What Is a ‘Degenerate’ View?, 801
- 10.1109/34.784283 · DOI
Cited by
SSD-6D: Making RGB-Based 3D Detection and 6D Pose Estimation Great Again
Kehl, W., Manhardt, F., Tombari, F., Ilic, S., & Navab, N. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.169 · Cited by 1,047
“Most of the best performing 3D detectors follow a view-based paradigm, in which a discrete set of object views is generated and used for subsequent feature computation [31, 14].”
BackgroundModeling alcohol-associated liver disease in a human Liver-Chip
Nawroth, J. C., Petropolis, D. B., Manatakis, D. V., Maulana, T. I., Burchett, G., Schlünder, K., Witt, A., Shukla, A., Kodella, K., Ronxhi, J., et al. (2021) · Cell Reports · doi:10.1016/j.celrep.2021.109393 · Cited by 88
6D object position estimation from 2D images: a literature review
Marullo, G., Tanzi, L., Piazzolla, P., & Vezzetti, E. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-022-14213-z · Cited by 64
“To the contrary, in [16, 58], the methodology need a further step of refinement to estimate the pose.”
MethodMachine Vision based Sample-Tube Localization for Mars Sample Return
Daftry, S., Ridge, B., Seto, W., Pham, T.-H., Ilhardt, P., Maggiolino, G., van der Merwe, M., Brinkman, A., Mayo, J., Kulczyski, E., et al. (2021) · 2021 IEEE Aerospace Conference (50100) · doi:10.1109/aero50100.2021.9438364 · Cited by 10
“The view-based approaches [35], [36], [37] compare a given image of the object with its pre-computed 2D views.”
BackgroundSteger, C. (2017) · Handbook of Machine and Computer Vision · doi:10.1002/9783527413409.ch9 · Cited by 6
Self-citation
Metadata
- Authors
- Ulrich, M., Wiedemann, C., & Steger, C.
- Venue
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Published
- 2012-10
- Volume
- 34
- Issue
- 10
- Pages
- 1902-1914
- ISSN
- 0162-8828 (ISSN-L)
- 2160-9292
- OpenAlex
- W2085334966
- Cited by
- 136
- References
- 5
- FWCI
- 2.07
- Type
- journal article
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.