12.2.2 2-D Lines with 3-D Structure

Chapter Contents (Back)
Matching, Models. Matching, Lines. Line Matching.

Rodriguez, J.J., and Aggarwal, J.K.,
Matching Aerial Images to 3-D Terrain Maps,
PAMI(12), No. 12, December 1990, pp. 1138-1149.
IEEE Abstract.
IEEE DOI BibRef 9012
Terrain Matching by Analysis of Aerial Images,
Navigation Using Image Sequence Analysis and 3-D Terrain Matching,
3DWS89(200-207). Matching, Surfaces. First compute the 3-D representation of the terrain using stereo. Then convert both the map and the scene into "Cliff" maps using edge detection. Finally, match the contours in the edge maps to find the location. BibRef

Ben-Arie, J.,
The Probabilistic Peaking Effect of Viewed Angles and Distances with Application to 3-D Object Recognition,
PAMI(12), No. 8, August 1990, pp. 760-774.
IEEE DOI BibRef 9008

Ben-Arie, J.,
The Properties of Viewed Angles and Distances with Application to 3-D Object Recognition,
ICPR88(I: 309-312).
IEEE DOI BibRef 8800

Bergevin, R.[Robert], and Levine, M.D.[Martin D.],
Part Decomposition of Objects from Single View Line Drawings,
CVGIP(55), No. 1, January 1992, pp. 73-83.
WWW Link. Decompose line drawings into separate components. Not using line labeling kinds of techniques. BibRef 9201

Bergevin, R., and Levine, M.D.,
Extraction of Line Drawing Features for Object Recognition,
PR(25), No. 3, March 1992, pp. 319-334.
WWW Link. BibRef 9203
Earlier: ICPR90(I: 496-501).

Bergevin, R., and Levine, M.D.,
Generic Object Recognition: Building and Matching Coarse Descriptions from Line Drawing,
PAMI(15), No. 1, January 1993, pp. 19-36.
IEEE DOI BibRef 9301
Generic Object Recognition: Building Coarse 3D Descriptions from Line Drawings,
3DWS89(68-74). The paper makes strong claims regarding the type of matching techniques and the quality. It matches line drawings to one model. It uses recognition by components as proposed by Biederman. BibRef

Ellis, R.E.,
Geometric Uncertainties in Polyhedral Object Recognition,
RA(7), 1991, pp. 361-371. BibRef 9100

Ellis, R.E.,
Uncertainty Estimates for Polyhedral Object Recognition,
CRA89(348-353). BibRef 8900

Bodington, R.M., Sullivan, G.D., and Baker, K.D.,
Consistent Labelling of Image Features Using an Assumption-Based Truth Maintenance System,
IVC(7), No. 1, February 1989, pp. 43-49.
WWW Link. BibRef 8902

Grosky, W.I., and Mehrotra, R.,
Index-Based Object Recognition in Pictorial Data Management,
CVGIP(52), No. 3, December 1990, pp. 416-436.
WWW Link. Model driven recognition. BibRef 9012

Chou, S.L., Tsai, W.H.,
Line Segment Matching for 3D Computer Vision Using a New Iteration Scheme,
MVA(6), 1993, pp. 191-205. BibRef 9300

Mehrotra, R., Gary, J.E.,
Similar-Shape Retrieval in Shape Data Management,
Computer(28), No. 9, September 1995, pp. 57-62. Database. Matching of contours to find similar shapes. Generate a feature index from the database item and the query and match them. BibRef 9509

Reid, I.D., Brady, J.M.,
Recognition of Object Classes from Range Data,
AI(78), No. 1-2, October 1995, pp. 289-326.
WWW Link. BibRef 9510
Earlier: ICCV93(302-307).
IEEE DOI Match line based models to images. See also Recognition of Parameterized Objects from 3D Data: A Parallel Implementation. BibRef

Reid, I.D., Brady, J.M.,
Model-Based Recognition and Range Imaging for a Guided Vehicle,
IVC(10), No. 3, April 1992, pp. 197-207.
WWW Link. BibRef 9204

Chang, Y.L., Leou, J.J.,
Representation and Matching of Feature Patterns for Robot Operation Monitoring,
RA(10), No. 4, 1995, pp. 143-151. BibRef 9500

Olson, C.F., Huttenlocher, D.P.,
Automatic Target Recognition by Matching Oriented Edge Pixels,
IP(6), No. 1, January 1997, pp. 103-113.
HTML Version.
PDF File. Or:
PDF File. 9703
Determining the Probability of a False Positive When Matching Chains of Oriented Pixels,
ARPA96(1175-1180). BibRef
Recognition by Matching Dense, Oriented Pixels,
IEEE Top Reference. Cornell University. Used for tracking an object in the sequence. BibRef

Olson, C.F., Huttenlocher, D.P., Doria, D.M.,
Recognition by Matching with Edge Location and Orientation,
ARPA96(1167-1174). BibRef 9600

Cass, T.A.[Todd A.],
Polynomial-Time Geometric Matching for Object Recognition,
IJCV(21), No. 1-2, January 1997, pp. 37-61.
DOI Link 9704
Earlier: MIT AI-TR-1470, September 1992. BibRef
Polynomial-Time Object Recognition in the Presence of Clutter, Occlusions, and Uncertainty,
Springer DOI BibRef
And: DARPA92(693-704). BibRef
And: MIT AI Memo-1302, October 1991. BibRef
Feature Matching for Object Localization in the Presence of Uncertainty,
And: MIT AI Memo-1133, May 1990. Pose space search type of recognition, search the parameter space. By using convex regions reduce it to a polynomial time algorithm that matches the maximum number of consistent features. BibRef

Cass, T.A.[Todd A.],
Robust Geometric Matching for 3D Object Recognition,
IEEE DOI BibRef 9400
Robust 2-D Model-Based Object Recognition,
MIT AI-TR-1132, May 1988.
WWW Link. BibRef
A Robust Parallel Implementation of 2D Model-Based Recognition,

Cass, T.A.,
Robust Affine Structure Matching for 3d Object Recognition,
PAMI(20), No. 11, November 1998, pp. 1265-1274.
IEEE DOI BibRef 9811
And: ECCV96(I:492-503).
Springer DOI Indexing. Line descriptions of objects matched to the image. BibRef

Gros, P.[Patrick], Bournez, O.[Olivier], Boyer, E.[Edmond],
Using Local Planar Geometric Invariants to Match and Model Images of Line Segments,
CVIU(69), No. 2, February 1998, pp. 135-155.
DOI Link BibRef 9802

Yi, X.L.[Xi-Lin], Camps, O.I.[Octavia I.],
Line-Based Recognition Using a Multidimensional Hausdorff Distance,
PAMI(21), No. 9, September 1999, pp. 901-916.
IEEE DOI BibRef 9909
Robust Occluding Contour Detection Using the Hausdorff Distance,
Recognition by 4-D Hausdorff distance. Minimize the distance betweeen two sets of points. BibRef

Yi, X., Camps, O.I.,
Line Feature-Based Recognition Using Hausdorff Distance,
IEEE Top Reference. The Pennsylvania State University. Matching line features so that rotation, scale and translation can be separated. BibRef 9500

Chang, C.C.[Chin-Chun], Tsai, W.H.[Wen-Hsiang],
Reliable Determination of Object Pose from Line Features by Hypothesis Testing,
PAMI(21), No. 11, November 1999, pp. 1235-1241.
Find the pose, then test whether the match is sufficient. BibRef

Kang, D.J.[Dong-Joong], Ha, J.E.[Jong-Eun], Kweon, I.S.[In-So],
Fast object recognition using dynamic programming from combination of salient line groups,
PR(36), No. 1, January 2003, pp. 79-90.
WWW Link. 0210

Chung, R.[Ronald], Wong, H.S.[Hau-San],
Polyhedral Object Localization in an Image by Referencing to a Single Model View,
IJCV(51), No. 2, February 2003, pp. 139-163.
DOI Link 0301

Chung, R.,
Object Locating Using a Single Model View,
IEEE Top Reference. The Chinese University of Hong Kong. Matches nodes (junctions) then arcs (using active contours to fit). BibRef 9500

Gleeson, R., Grosshans, F., Hirsch, M., Williams, R.M.,
Algorithms for the Recognition of 2D Images of M Points and N Lines in 3D,
IVC(21), No. 6, June 2003, pp. 497-504.
WWW Link. 0306

Guerra, C.[Concettina], Pascucci, V.[Valerio],
Line-based object recognition using Hausdorff distance: From Range Images to Molecular Secondary Structures,
IVC(23), No. 4, 1 April 2005, pp. 405-415.
WWW Link. 0501

Merckel, L.[Loic], Nishida, T.[Toyoaki],
Accurate Object Recognition Using Orientation Sensor with Refinement on the Lie Group of Spatial Rigid Motions,
IEICE(E91-D), No. 8, August 2008, pp. 2179-2188.
DOI Link 0804
3D Model using line segments. Hypothesize and test pose. BibRef

Tajima, J.[Johji], Kono, H.[Hironori],
Natural Object/Artifact Image Classification Based on Line Features,
IEICE(E91-D), No. 8, August 2008, pp. 2207-2211.
DOI Link 0804
Line length ratio, line direction distribution, edge coverage. Line length ratio performs best. BibRef

Bhat, K.K.S.[K.K. Srikrishna], Heikkila, J.[Janne],
Line Matching and Pose Estimation for Unconstrained Model-to-Image Alignment,
Cameras BibRef

Kamgar-Parsi, B.[Behzad], Kamgar-Parsi, B.[Behrooz],
Matching 2D image lines to 3D models: Two improvements and a new algorithm,

Tateno, K.[Keisuke], Kotake, D.[Daisuke], Uchiyama, S.J.[Shin-Ji],
Model-Based 3D Object Tracking with Online Texture Update,
PDF File. 0905
Matching edge points, then extended edges. BibRef

Carmichael, O.T., Hebert, M.,
Object Recognition by a Cascade of Edge Probes,
BMVC02(Matching/Recognition). 0208

Carmichael, O.T.,
Discriminative Techniques for the Recognition of Complex-Shaped Objects,
CMU-RI-TR-03-34, September, 2003. BibRef 0309 Ph.D.Thesis.
HTML Version. 0501

Carmichael, O.T.,
Discriminant Filters for Object Recognition,
CMU-RI-TR-02-09, March, 2002.
WWW Link. 0205

Escobar, A., Laurendeau, D.[Denis],
Registration of Complex Free-form Objects from 3D Image Edge Using the Hausdorff Distance,
MVA98(xx-yy). BibRef 9800

Müller, W., and Olson, J.,
Automatic Matching of 3-D Models to Imagery,
Ascona95(43-52). Match the wireframe model of the building to the image for registration. BibRef 9500

Hebert, M., and Kanade, T.,
The 3D-Profile Method for Object Recognition,
CVPR85(458-463). (CMU) Recognize Three-Dimensional Objects. From 3-D data get 3-D edges, match to 3-D models (polyhedral models). BibRef 8500

Hoogs, A.[Anthony],
Pose Refinement Using a Parameter Hierarchy,
ARPA96(857-864). Refine the extracted buildings (2D). BibRef 9600

Hoogs, A.[Anthony],
Analysis of learning using segmentation models,
Springer DOI 9709

Hoogs, A.[Anthony], Bajcsy, R.[Ruzena],
Model-Based Learning of Segmentations,
ICPR96(IV: 494-499).
Segmentation modeling,
Springer DOI 9509
Using Scene Context to Model Segmentations,
Context95(xx). (Univ. of Pennsylvania, USA) BibRef

Bajcsy, R.[Ruzena], Hoogs, A.[Anthony],
Segmentation Characterization for Change Detection,
ARPA94(II:1555-1562). Change Detection. BibRef 9400

Bodington, R.M., Sullivan, G.D., and Baker, K.D.,
Experiments on the Use of the ATMS to Lagel Features for Object Recognition,
Springer DOI High Level Vision. Using a truth maintenance system for matching line structures. BibRef 9000

Feng, P.,
A Face Based Algorithm for Matching Two Line Drawings of a Polyhedron,
ICPR88(II: 782-784).
IEEE DOI BibRef 8800

Chapter on Registration, Matching and Recognition Using Points, Lines, Regions, Areas, Surfaces continues in
2-D/3-D Lines Accumuation Techniques .

Last update:Mar 13, 2017 at 16:25:24