3D Object Pose Estimation Research Articles

Generate a 3D CAD models for Pose Estimation

The pose estimation of 3D object of products in production line is needed beforehand. In order to perform shape measurement of objects corresponding to speed of the mass production lines before the contact measurement is done, the information of shape representation and matching of object is required. Objects are compared with its descriptor. The descriptor conceptually subtracted from each other to form a scalar metric. If the value difference is smaller, the object shape is considered closer to each other. The rotation object from its original pose can produce the information to estimate its rotation pose by using the boundary. In this paper, we proposed the method to measure 3D object pose from the designing stage of 3D CAD data.

3D Pose estimation of symmetrical objects of unknown shape

The estimation of the pose of an object is a frequent requirement in computer vision tasks. This paper outlines a method for estimating the pose of an object having a plane of bilateral symmetry but of otherwise unknown shape. The method can operate with a set of 3D range data suffering from self-occlusion, as is obtained from a single viewpoint.

COMBINED MODEL-BASED 3D OBJECT RECOGNITION

This paper presents a combined model-based 3D object recognition method motivated by the robust properties of human vision. The human visual system (HVS) is very efficient and robust in identifying and grabbing objects, in part because of its properties of visual attention, contrast mechanism, feature binding, multiresolution and part-based representation. In addition, the HVS combines bottom-up and top-down information effectively using combined model representation. We propose a method for integrating these aspects under a Monte Carlo method. In this scheme, object recognition is regarded as a parameter optimization problem. The bottom-up process initializes parameters, and the top-down process optimizes them. Experimental results show that the proposed recognition model is feasible for 3D object identification and pose estimation.

A 3D image processing method for manufacturing process automation

Three-dimensional (3D) image processing provides a useful tool for machine vision applications. Typically a 3D vision system is divided into data acquisition, low-level processing, object representation and matching. In this paper, a 3D object pose estimation method is developed for an automated manufacturing assembly process. The experimental results show that the 3D pose estimation method produces accurate geometrical information for an automated material handling application.

An effective 3D target recognition model imitating robust methods of the human visual system

This paper presents a model of 3D object recognition motivated from the robust properties of human vision system (HVS). The HVS shows the best efficiency and robustness for an object identification task. The robust properties of the HVS are visual attention, contrast mechanism, feature binding, multi-resolution, size tuning, and part-based representation. In addition, bottom-up and top-down information are combined cooperatively. Based on these facts, a plausible computational model integrating these facts under the Monte Carlo optimization technique was proposed. In this scheme, object recognition is regarded as a parameter optimization problem. The bottom-up process is used to initialize parameters in a discriminative way; the top-down process is used to optimize them in a generative way. Experimental results show that the proposed recognition model is feasible for 3D object identification and pose estimation in visible and infrared band images.

Automatic generation of RBF networks using wavelets

Learning can be viewed as mapping from an input space to an output space. Examples of these mappings are used to construct a continuous function that approximates the given data and generalizes for intermediate instances. Radial-basis function (RBF) networks are used to formulate this approximating function. A novel method is introduced that automatically constructs a generalized radial-basis function (GRBF) network for a given mapping and error bound. This network is shown to be the smallest network within the error bound for the given mapping. The integral wavelet transform is used to determine the parameters of the network. Simple one-dimensional examples are used to demonstrate how the network constructed using the transform is superior to that constructed using standard ad hoc optimization techniques. The paper concludes with the automatic generation of GRBF networks for a multi-dimensional problem, namely, real-time 3D object recognition and pose estimation. The results of this application are favorable.

Pose Estimation Method Based on Potential Field Matching and its Convergence Characteristics.

We propose a 3D object pose estimation method based on pattern matching of the potential fields generated from objects. In our recognition method, the potential fields of both an input object and a model object are generated at first. Secondly, the potential field of the model object is translated and rotated to match with that of the input object. The transformation parameters, i. e., the unknown parameters, are estimated by a nonlinear least squares method, and the position and orientation of the input object are estimated. Furthermore, we clarify some convergence characteristics quantitatively. We also show some ranges, where the solution converges to an optimum value, for two kinds of methods in order to generate the potential field.

On the Parametrization of the Three-Dimensional Rotation Group

Parameterization of group of rotations of Euclidean three-dimensional space applied to integration of rigid body motion equations