Maximal matching of 3-D points for multiple-object motion estimation

doi:10.1016/0031-3203(88)90016-7

Pattern Recognition

Volume 21, Issue 2, 1988, Pages 75-90

https://doi.org/10.1016/0031-3203(88)90016-7 Get rights and content

Abstract

Determining the relative motion/position between an observer and its environment is an important problem in computer vision. A major task is to find corresponding object features. In this paper, an efficient algorithm for matching 3-D points of multiple rigid objects is presented. The point-matching algorithm determines the correspondence by initiating a pairing of a triplet of noncollinear sensed points with a triplet of reference points and searching for new pairs of corresponding points, one at a time, using local distance and angular constraints. The pairing of each subsequent sensed point with a reference point is determined if the tetrahedron formed by the sensed point and the initial triplet is congruent to that formed by the corresponding reference points. Only simple computations are required in the algorithm. Global consistency of the pairings found by the algorithm is ensured without using model tests. The algorithm can be easily extended to incorporate other geometrical or non-geometrical object attributes to further prune the matching. Results of running the algorithm on synthetic and real data are given.

References (19)

Z. Pinjo et al.
Determining of 3-D object orientation from projections
Pattern Recognition Lett.
(1985)
A. Mitiche et al.
Tracking modeled objects using binocular images
Comput. Vision Graphics Image Process.
(1985)
S. Ullman
The Interpretation of Visual Motion
(1979)
T.S. Huang
Motion analysis
T.S. Huang et al.
Robust algorithm for motion estimation based on two sequential stereo image pairs
H.H. Chen and T.S. Huang, Multiple-object motion estimation by matching 3-D line segments,...
O.D. Faugeras et al.
The representation, recognition and locating of 3-D objects
Int. J. Robotics Res.
(1986)
M.D. Shuster
Approximate algorithms for fast optimal attitude computation
W.E.L. Grimson et al.
Model-based recognition and localization from sparse range or tactile data
Int. J. Robotics Res.
(1984)

There are more references available in the full text version of this article.

Cited by (26)

A relaxation algorithm for real-time multiple view 3D-tracking
2002, Image and Vision Computing
Citation Excerpt :
Consistent labelling according to a set of a priori known constraints has combinatorial complexity [6,7]. The optimal labelling problem can be resolved by techniques such as relational graph matching, graph isomorphism, tree search and relaxation labelling [8–10,49]. Approaches to reducing the combinatorial complexity include knowledge-based clipping, heuristic search, divide-and-conquer and dynamic programming.
In this paper we address the problem of reliable real-time 3D-tracking of multiple objects which are observed in multiple wide-baseline camera views. Establishing the spatio-temporal correspondence is a problem with combinatorial complexity in the number of objects and views. In addition vision-based tracking suffers from the ambiguities introduced by occlusion, clutter and irregular 3D motion. In this paper we present a discrete relaxation algorithm for reducing the intrinsic combinatorial complexity by pruning the decision tree based on unreliable prior information from independent 2D-tracking for each view. The algorithm improves the reliability of spatio-temporal correspondence by simultaneous optimisation over multiple views in the case where 2D-tracking in one or more views are ambiguous. Application to the 3D reconstruction of human movement, based on tracking of skin-coloured regions in three views, demonstrates considerable improvement in reliability and performance. Results demonstrate that the optimisation over multiple views gives correct 3D reconstruction and object labelling in the presence of incorrect 2D-tracking whilst maintaining real-time performance.
Task planning for humanoid robots using look-up table
2002, Robotics and Autonomous Systems
The humanoid robot CENTAUR that has been developed at the Korea Institute of Science and Technology consists of a head, two arms, a trunk, two hands and four legs. In addition to its human-like kinematical structure, it has some sensing units like the stereo vision system, which resembles human sensory organs. By using the stereo vision a three-dimensional pose determination algorithm was developed and integrated to the robot controller. With the imported information on objects from the vision system the task planner autonomously determines reliable motions and grasp sequences of the robot. This planner considers the collision and regrasping cases in order to guarantee a complete planning of the pick and place movement in the total robot workspace. An off-line constructed look-up table makes possible a fast grasp planning for any kind of robot configuration. A comprehensive experiment was accomplished to evaluate the proposed algorithm.
Matching point features under small nonrigid motion
2001, Pattern Recognition
This paper describes a method for matching point features between images of objects that have undergone small nonrigid motion. Feature points are assumed to be available and, given a properly extracted set of feature points, a robust matching is established under the condition that the local nonrigid motion of each point is restricted to a circle of radius δ, where δ is not too large. This is in contrast to other techniques for point matching which assume either rigid motion or nonrigid motion of a known kind. The point matching problem is viewed in terms of weighted bipartite graph matching. In order to account for the possibility that the feature selector can be imprecise, we incorporate a greedy matching strategy with the weighted graph matching algorithm. Our algorithm is robust and insensitive to noise and missing features. The resulting matching can be used with image warping or other techniques for nonrigid motion analysis, image subtraction, etc. We present our experimental results on sequences of mammograms, images of a deformable clay object and satellite cloud images. In the first two cases we provide quantitative comparison with known ground truth.
An algorithmic overview of surface registration techniques for medical imaging
2000, Medical Image Analysis
This paper presents a literature survey of automatic 3D surface registration techniques emphasizing the mathematical and algorithmic underpinnings of the subject. The relevance of surface registration to medical imaging is that there is much useful anatomical information in the form of collected surface points which originate from complimentary modalities and which must be reconciled. Surface registration can be roughly partitioned into three issues: choice of transformation, elaboration of surface representation and similarity criterion, and matching and global optimization. The first issue concerns the assumptions made about the nature of relationships between the two modalities, e.g. whether a rigid-body assumption applies, and if not, what type and how general a relation optimally maps one modality onto the other. The second issue determines what type of information we extract from the 3D surfaces, which typically characterizes their local or global shape, and how we organize this information into a representation of the surface which will lead to improved efficiency and robustness in the last stage. The last issue pertains to how we exploit this information to estimate the transformation which best aligns local primitives in a globally consistent manner or which maximizes a measure of the similarity in global shape of two surfaces. Within this framework, this paper discusses in detail each surface registration issue and reviews the state-of-the-art among existing techniques.
Nonrigid Motion Analysis: Articulated and Elastic Motion
1998, Computer Vision and Image Understanding
Motion of physical objects in the world is, in general, nonrigid. In robotics and computer vision, the motion of nonrigid objects is of growing interest to researchers from a wide spectrum of disciplines. The nonrigid objects being studied may be generally categorized into three groups according to the degree of deformation of body parts: articulated, elastic, and fluid. In articulated motion, individual rigid parts of an object move independently of one another and the motion of the whole object is nonrigid in nature. Elastic motion is nonrigid motion that conforms to a certain degree of continuity or smoothness. Fluid motion violates even the continuity assumption and may involve topological variations and turbulent deformations. This paper presents an overview of existing work on articulated and elastic motion, motivated by problems relating to the motion of the human body and of an animal heart, respectively. We study various approaches for recovering the 3D structure and motion of objects through a sequence of images in a bottom-up fashion, a strategy widely employed by various investigators. These approaches are classified as (1) motion recovery without shape models, and (2) model-based analysis. In the discussion of each algorithm, we also include a description of the complexity of feature and motion constraints, which are highly related to each other.
Vehicle-type motion estimation by the fusion of image point and line features
1998, Pattern Recognition
Three-dimensional (3D) motion estimation is a very important topic in machine vision. However, reliability of the estimated 3D motion seems to be the most challenging problem, especially to the linear algorithms developed for solving a general 3D motion problem (six degrees of freedom). In real applications such as the traffic surveillance and auto-vehicle systems, the observed 3D motion has only three degrees of freedom because of the ground plane constraint (GPC). In this paper, a new iterative method is proposed for solving the above problem. Our method has several advantages: (1) It can handle both the point and line features as its input image data. (2) It is very suitable for parallel processing. (3) Its cost function is so well-conditioned that the final 3D motion estimation is robust and insensitive to noise, which is proved by experiments. (4) It can handle the case of missing data to a certain degree. The above benefits make our method suitable for a real application. Experiments including simulated and real-world images show satisfactory results.

View all citing articles on Scopus

^∗: Now at AT&T Bell Laboratories, 4E-630, Crawfords Corner Road, Holmdel, NJ 07733, U.S.A.

View full text

Maximal matching of 3-D points for multiple-object motion estimation

Abstract

Pattern Recognition Lett.

Comput. Vision Graphics Image Process.

The Interpretation of Visual Motion

Motion analysis

Robust algorithm for motion estimation based on two sequential stereo image pairs

The representation, recognition and locating of 3-D objects

Int. J. Robotics Res.

Approximate algorithms for fast optimal attitude computation

Model-based recognition and localization from sparse range or tactile data

Int. J. Robotics Res.