Local Structure to Solve the Correspondence Search Problem in a Monocular Pose Estimation Scenario

In this paper, a 3-D pose estimation system by using stereo vision with low-cost devices is presented. It is developed as a base system for application development. Two webcams and a planar target with circular markers are used to reduce development cost and computational complexity. To avoid correspondence search problem, user has to select regions of interest (ROI’s) of each marker on the two images in the same sequence before starting the 3-D reconstruction process. Linear triangulation method is applied for 3-D position calculation of each marker. These positions and the positions of the markers referenced in the planar target coordinate frame are used for pose estimation by using least-squares fitting algorithm to obtain the position and orientation of the planar target. The system can be applied for robot tracking as shown in the experiments. The experimental results validate the system’s ability to estimate object pose in real-time with minimum system frequency of 25 Hz.

Download Full-text

Pose estimation using local structure-specific shape and appearance context

2013 IEEE International Conference on Robotics and Automation ◽

10.1109/icra.2013.6630856 ◽

2013 ◽

Cited By ~ 33

Author(s):

Anders Glent Buch ◽

Dirk Kraft ◽

Joni-Kristian Kamarainen ◽

Henrik Gordon Petersen ◽

Norbert Kruger

Keyword(s):

Pose Estimation ◽

Local Structure ◽

Specific Shape

Download Full-text

X-ray microprobe for materials science

Proceedings, annual meeting, Electron Microscopy Society of America ◽

10.1017/s0424820100168013 ◽

1994 ◽

Vol 52 ◽

pp. 56-57

Author(s):

G.E. Ice

Keyword(s):

Crystallographic Orientation ◽

Local Structure ◽

Materials Science ◽

Chemical Information ◽

X Ray Diffraction ◽

Ray Optics ◽

X Ray ◽

Novel Materials ◽

New Information ◽

Elemental Sensitivity

The increasing availability of synchrotron x-ray sources has stimulated the development of advanced hard x-ray (E≥5 keV) microprobes. With new x-ray optics these microprobes can achieve micron and submicron spatial resolutions. The inherent elemental and crystallographic sensitivity of an x-ray microprobe and its inherently nondestructive and penetrating nature will have important applications to materials science. For example, x-ray fluorescent microanalysis of materials can reveal elemental distributions with greater sensitivity than alternative nondestructive probes. In materials, segregation and nonuniform distributions are the rule rather than the exception. Common interfaces to whichsegregation occurs are surfaces, grain and precipitate boundaries, dislocations, and surfaces formed by defects such as vacancy and interstitial configurations. In addition to chemical information, an x-ray diffraction microprobe can reveal the local structure of a material by detecting its phase, crystallographic orientation and strain.Demonstration experiments have already exploited the penetrating nature of an x-ray microprobe and its inherent elemental sensitivity to provide new information about elemental distributions in novel materials.

Download Full-text