Object recognition by computer - the role of geometric constraints

By W. Grimson. 1991

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Lifting Object Detection Datasets into 3D (2015, background): “Formerly a dominant paradigm, model-based recognition, which reasoned jointly about object identity and 3D geometry [12], [13], [14], was permanently upstaged in the 1990’s by a ﬂurry of view-based approaches [15], [16].”
Single image 3D object detection and pose estimation for grasping (2014, methodology): “Early approaches based on using explicit 3D models are summarized in Grimson's book [3] and focus on efficient techniques for voting in pose space.”
A new algorithm for non-rigid point matching (2000, background): “While the correspondence problem has a long history in rigid, a ne and projective point matching [11], there is relatively a dearth of literature on non-rigid point matching.”
Coarse-to-Fine Face Detection (2004, background): “, 1988), Hough transforms (Rojer and Schwartz, 1992; Amit and Geman, 1999; Amit, 1999), and treestructured search (Grimson, 1990), all of which have influenced our thinking.”
Object Recognition in the Geometric Era: A Retrospective (2006, unknown): “These recognition error statistics were studied extensively by Grimson [28].”
A new point matching algorithm for non-rigid registration (2003, background): “We suspect that this is the main reason why there is relatively a dearth of literature on non-rigid point matching despite a long and rich history on rigid, affine and projective point matching [19].”
Object class recognition by unsupervised scale-invariant learning (2003, background): “[6, 9, 11]), has recently gained some attention in the machine vision literature [1, 2, 3, 4, 13, 14, 19] with an emphasis on the detection of faces [12, 15, 16].”
Active Matching (2008, methodology): “When probabilistic priors are available, the unsatisfying random sampling and preset thresholds of RANSAC have been improved on by probabilistic methods such as the Joint Compatibility Branch and Bound (JCBB) algorithm [11] which matches features via a deterministic interpretation tree [7] and has b”
Markov Random Field Modeling in Image Analysis (2001, methodology): “Pose computation aims to estimate the transformation needed to map an object model from the model coordinate system into the sensory data (Ayache and Faugeras 1986; Faugeras and Hebert 1986; Bolles and Horaud 1986; Stockman 1987; Haralick et al. 1989; Grimson 1990; Umeyama 1991).”
A search engine for 3D models (2003, background): “2D boundary contours rendered from 13 views of each object. characteristic views [Palmer et al. 1981], and how computers recognize photographic images [Grimson 1990] is not directly applicable in our case.”
Comparing Images Using the Hausdorff Distance (1993, unknown): “[4, 8, 11]) can all be viewed as techniques for determining the di erence between shapes.”
Distinctive Image Features from Scale-Invariant Keypoints (2004, unknown): “Fortunately, much better performance can be obtained by clustering features in pose space using the Hough transform (Hough, 1962; Ballard, 1981; Grimson, 1990).”
The MOPED framework: Object recognition and pose estimation for manipulation (2011, background): “Solutions such as grouping (Lowe 1987), interpretation trees (Grimson 1991) or image space clustering (Collet et al. 2009) are often used, but false positives often arise from algorithms not being able to handle unexpected scene complexity.”
A statistical approach to 3d object detection applied to faces and cars (2000, background): “At the other extreme, others use a minimalist feature representation and emphasize geometric relationships [32][41][45][46][47].”
Multidimensional Morphable Models: A Framework for Representing and Matching Object Classes (2004, methodology): “These techniques generally find certain features in an input image (such as lines and corners) and use these features to index into a database of feature vectors for known objects in order to determine if the input image contains features which are very similar to features of objects in the database”
Shape Classification Using the Inner-Distance (2007, background): “The first category (e.g., [3], [19], [14], [37], [15], [46], etc.) builds part models from a set of sample images and usually with some prior knowledge such as the number of parts.”
Distinctive Image Features from Scale-Invariant Keypoints (2004, background): “Fortunately, much better performance can be obtained by clustering features in pose space using the Hough transform (Hough, 1962; Ballard, 1981; Grimson 1990).”