Results 1  10
of
45
Perceptionbased 3d triangle mesh segmentation using fast marching watersheds
 in Proceedings of the International Conference on Computer Vision and Pattern Recognition, II
, 2003
"... In this paper, we describe an algorithm called Fast Marching Watersheds that segments a triangle mesh into visual parts. This computer vision algorithm leverages a human vision theory known as the minima rule. Our implementation computes the principal curvatures and principal directions at each vert ..."
Abstract

Cited by 46 (3 self)
 Add to MetaCart
In this paper, we describe an algorithm called Fast Marching Watersheds that segments a triangle mesh into visual parts. This computer vision algorithm leverages a human vision theory known as the minima rule. Our implementation computes the principal curvatures and principal directions at each vertex of a mesh, and then our hillclimbing watershed algorithm identifies regions bounded by contours of negative curvature minima. These regions fit the definition of visual parts according to the minima rule. We present evaluation analysis and experimental results for the proposed algorithm. 1.
Approximate convex decomposition of polygons
 In Proc. 20th Annual ACM Symp. Computat. Geom. (SoCG
, 2004
"... We propose a strategy to decompose a polygon, containing zero or more holes, into “approximately convex” pieces. For many applications, the approximately convex components of this decomposition provide similar benefits as convex components, while the resulting decomposition is significantly smaller ..."
Abstract

Cited by 42 (6 self)
 Add to MetaCart
(Show Context)
We propose a strategy to decompose a polygon, containing zero or more holes, into “approximately convex” pieces. For many applications, the approximately convex components of this decomposition provide similar benefits as convex components, while the resulting decomposition is significantly smaller and can be computed more efficiently. Moreover, our approximate convex decomposition (ACD) provides a mechanism to focus on key structural features and ignore less significant artifacts such as wrinkles and surface texture. We propose a simple algorithm that computes an ACD of a polygon by iteratively removing (resolving) the most significant nonconvex feature (notch). As a by product, it produces an elegant hierarchical representation that provides a series of ‘increasingly convex ’ decompositions. A user specified tolerance determines the degree of concavity that will be allowed in the lowest level of the hierarchy. Our algorithm computes an ACD of a simple polygon with n vertices and r notches in O(nr) time. In contrast, exact convex decomposition is NPhard or, if the polygon has no holes, takes O(nr 2) time. Models and movies can be found on our webpages at:
Flux Invariants for Shape
 In CVPR
, 2003
"... We consider the average outward flux through a Jordan curve of the gradient vector field of the Euclidean distance function to the boundary of a 2D shape. Using an alternate form of the divergence theorem, we show that in the limit as the area of the region enclosed by such a curve shrinks to zero, ..."
Abstract

Cited by 33 (4 self)
 Add to MetaCart
(Show Context)
We consider the average outward flux through a Jordan curve of the gradient vector field of the Euclidean distance function to the boundary of a 2D shape. Using an alternate form of the divergence theorem, we show that in the limit as the area of the region enclosed by such a curve shrinks to zero, this measure has very different behaviours at medial points than at nonmedial ones, providing a theoretical justification for its use in the HamiltonJacobi skeletonization algorithm of [7]. We then specialize to the case of shrinking circular neighborhoods and show that the average outward flux measure also reveals the object angle at skeletal points. Hence, formulae for obtaining the boundary curves, their curvatures, and other geometric quantities of interest, can be written in terms of the average outward flux limit values at skeletal points. Thus this measure can be viewed as a Euclidean invariant for shape description: it can be used to both detect the skeleton from the Euclidean distance function, as well as to explicitly reconstruct the boundary from it. We illustrate our results with several numerical simulations. 1.
Dressed Human Modeling, Detection, and Parts Localization
, 2001
"... This dissertation presents an integrated human shape modeling, detection, and body part localization vision system. It demonstrates that the system can (1) detect pedestrians in various shapes, sizes, postures, partial occlusion, and clothing from a moving vehicle using stereo cameras; (2) locate th ..."
Abstract

Cited by 27 (1 self)
 Add to MetaCart
(Show Context)
This dissertation presents an integrated human shape modeling, detection, and body part localization vision system. It demonstrates that the system can (1) detect pedestrians in various shapes, sizes, postures, partial occlusion, and clothing from a moving vehicle using stereo cameras; (2) locate the joints of a person automatically and accurately without employing any markers around the joints.
The shape of holes
 Cognition
, 2003
"... Abstract The shape of holes can be recognized as accurately as the shape of objects ..."
Abstract

Cited by 19 (1 self)
 Add to MetaCart
Abstract The shape of holes can be recognized as accurately as the shape of objects
Minimum nearconvex decomposition for robust shape representation
 in Proc. IEEE Int. Conf. Computer Vision
"... Shape decomposition is a fundamental problem for partbased shape representation. We propose a novel shape decomposition method called Minimum NearConvex Decomposition (MNCD), which decomposes 2D and 3D arbitrary shapes into minimum number of “nearconvex ” parts. With the degree of nearconvexit ..."
Abstract

Cited by 18 (4 self)
 Add to MetaCart
(Show Context)
Shape decomposition is a fundamental problem for partbased shape representation. We propose a novel shape decomposition method called Minimum NearConvex Decomposition (MNCD), which decomposes 2D and 3D arbitrary shapes into minimum number of “nearconvex ” parts. With the degree of nearconvexity a user specified parameter, our decomposition is robust to large local distortions and shape deformation. The shape decomposition is formulated as a combinatorial optimization problem by minimizing the number of nonintersection cuts. Two major perception rules are also imposed into our scheme to improve the visual naturalness of the decomposition. The global optimal solution of this challenging discrete optimization problem is obtained by a dynamic subgradientbased branchandbound search. Both theoretical analysis and experiment results show that our approach outperforms the stateoftheart results without introducing redundant parts. Finally we also show the superiority of our method in the application of hand gesture recognition. 1.
Convex Shape Decomposition
"... In this paper, we propose a new shape decomposition method, called convex shape decomposition. We formalize the convex decomposition problem as an integer linear programming problem, and obtain approximate optimal solution by minimizing the total cost of decomposition under some concavity constraint ..."
Abstract

Cited by 17 (2 self)
 Add to MetaCart
(Show Context)
In this paper, we propose a new shape decomposition method, called convex shape decomposition. We formalize the convex decomposition problem as an integer linear programming problem, and obtain approximate optimal solution by minimizing the total cost of decomposition under some concavity constraints. Our method is based on Morse theory and combines information from multiple Morse functions. The obtained decomposition provides a compact representation, both geometrical and topological, of original object. Our experiments show that such representation is very useful in many applications. 1.
Region Segmentation via Deformable ModelGuided Split and Merge
 In Proceedings of the International Conference on Computer Vision (ICCV’01
, 2000
"... An improved method for deformable shapebased image segmentation is described. Image regions are merged together and/or split apart, based on their agreement with an a priori distribution on the global deformation parameters for a shape template. The quality of a candidate region merging is evaluate ..."
Abstract

Cited by 14 (0 self)
 Add to MetaCart
(Show Context)
An improved method for deformable shapebased image segmentation is described. Image regions are merged together and/or split apart, based on their agreement with an a priori distribution on the global deformation parameters for a shape template. The quality of a candidate region merging is evaluated by a cost measure that includes: homogeneity of image properties within the combined region, degree of overlap with a deformed shape model, and a deformation likelihood term. Perceptuallymotivated criteria are used to determine where/how to split regions, based on the local shape properties of the region group's bounding contour. A globally consistent interpretation is determined in part by the minimum description length principle. Experiments show that the modelbased splitting strategy yields a significant improvement in segmention over a method that uses merging alone. 1 Introduction Retrieval by shape is a key topic in contentbased image retrieval research. Unfortunately, retrieval...
Real world realtime automatic recognition of facial expressions
 In Proceedings of IEEE workshop on
, 2003
"... Most facial expression analysis systems attempt to recognize facial expressions from data collected in a highly controlled laboratory with very high resolution frontal faces (face regions greater than 200 x 200 pixels) and cannot handle large head motions. In real environments such as smart meetings ..."
Abstract

Cited by 14 (2 self)
 Add to MetaCart
(Show Context)
Most facial expression analysis systems attempt to recognize facial expressions from data collected in a highly controlled laboratory with very high resolution frontal faces (face regions greater than 200 x 200 pixels) and cannot handle large head motions. In real environments such as smart meetings, a facial expression analysis system must be able to automatically recognize expressions at lower resolution and handle the full range of head motion. This paper describes a realtime system to automatically recognize facial expressions in relatively low resolution face images (around 50x70 to 75x100 pixels). To handle the full range of head motion, we detect the head instead of the face. Then the head pose is estimated based on the detected head. For frontal and near frontal views of the face, the location and shape features are computed for expression recognition. Our system successfully deals with complex real world interactions, as demonstrated on the PETS2003 dataset. 1