Reconstruction and Verification of 3D Object Models for Grasping

In this paper, we describe a recognition method of lung nodule shadows in X-ray CT images using 3-dimensional nodule and blood vessel models. From these 3D object models, artificial CT images are generated as templates. The templates are then applied to input images which comprise of suspicious shadows. If any parameters of the suspicious shadow matches a nodule template rather than any blood vessel template, then it is determined to be abnormal. Otherwise, it is determined to be normal. By applying our new method to the actual lung CT images of 38 patients, the false positive ratio is reduced to 4.31 [shadow/patient] with the sensitivity exceeding 95%.

Download Full-text

Unsupervised learning of 3D object models from partial views

2009 IEEE International Conference on Robotics and Automation ◽

10.1109/robot.2009.5152524 ◽

2009 ◽

Cited By ~ 18

Author(s):

M. Ruhnke ◽

B. Steder ◽

G. Grisetti ◽

W. Burgard

Keyword(s):

Unsupervised Learning ◽

3D Object ◽

Object Models

Download Full-text

Autonomous Visualization of Real Environments for Telepresence Applications

Presence Teleoperators & Virtual Environments ◽

10.1162/pres.1997.6.6.645 ◽

1997 ◽

Vol 6 (6) ◽

pp. 645-657 ◽

Cited By ~ 1

Author(s):

Robert Geist ◽

Todd Stinson ◽

Robert Schalkoff ◽

Sabri Gurbuz

Keyword(s):

Virtual Environments ◽

Structured Light ◽

Surface Patch ◽

Future Research ◽

3D Object ◽

Unstructured Environments ◽

Direct Estimation ◽

Active Laser ◽

3D Surface ◽

Object Models

The autonomous, noncontact creation of virtual environments from existing, real environments is described. The technique uses structured light to provide direct estimation of 3D surface patch parameters. Active (laser) cameras are used to determine 3D object models, and passive camera images are used to generate color and texture. This process, termed virtualization, has immediate application to providing telepresence in previously unmodeled or unstructured environments. An example of the process is shown and directions for future research are indicated.

Download Full-text

Extra FAT: A Photorealistic Dataset for 6D Object Pose Estimation

Electronic Imaging ◽

10.2352/issn.2470-1173.2020.8.imawm-221 ◽

2020 ◽

Vol 2020 (8) ◽

pp. 221-1-221-7

Author(s):

Jianhang Chen ◽

Daniel Mas Montserrat ◽

Qian Lin ◽

Edward J. Delp ◽

Jan P. Allebach

Keyword(s):

Object Detection ◽

Pose Estimation ◽

Object Segmentation ◽

3D Object ◽

Virtual Camera ◽

Image Dataset ◽

Rgb Images ◽

Object Pose Estimation ◽

Object Models

We introduce a new image dataset for object detection and 6D pose estimation, named Extra FAT. The dataset consists of 825K photorealistic RGB images with annotations of groundtruth location and rotation for both the virtual camera and the objects. A registered pixel-level object segmentation mask is also provided for object detection and segmentation tasks. The dataset includes 110 different 3D object models. The object models were rendered in five scenes with diverse illumination, reflection, and occlusion conditions.

Download Full-text

Effortless Scanning of 3D Object Models by Boundary Aligning and Stitching

Proceedings of the 9th International Conference on Computer Vision Theory and Applications ◽

10.5220/0004746406670674 ◽

2014 ◽

Keyword(s):

3D Object ◽

Object Models

Download Full-text

Active 3D object models

[1990] Proceedings Third International Conference on Computer Vision ◽

10.1109/iccv.1990.139543 ◽

2002 ◽

Cited By ~ 4

Author(s):

R.M. Bolle ◽

A. Califano ◽

R. Kjeldsen ◽

R. Mohan

Keyword(s):

3D Object ◽

Object Models

Download Full-text

Understanding Bayesian Rooms Using Composite 3D Object Models

2013 IEEE Conference on Computer Vision and Pattern Recognition ◽

10.1109/cvpr.2013.27 ◽

2013 ◽

Cited By ~ 25

Author(s):

Luca Del Pero ◽

Joshua Bowdish ◽

Bonnie Kermgard ◽

Emily Hartley ◽

Kobus Barnard

Keyword(s):

3D Object ◽

Object Models

Download Full-text

FREE-FORM 3D OBJECT RECOGNITION IN RANGE DATA USING WEAK CORRESPONDENCE BETWEEN LOCAL FEATURES

International Journal of Pattern Recognition and Artificial Intelligence ◽

10.1142/s021800140300285x ◽

2003 ◽

Vol 17 (07) ◽

pp. 1245-1277

Author(s):

RICHARD J. CAMPBELL ◽

PATRICK J. FLYNN

Keyword(s):

Object Recognition ◽

Free Form ◽

3D Object Recognition ◽

Range Data ◽

Dense Range ◽

3D Object ◽

Number Of Factors ◽

Potential Applications ◽

Recognition Systems ◽

Object Models

Model-Based 3D object recognition systems have a variety of potential applications, but widespread use of such systems has not occurred, due to a number of factors including the representational limitations of models. One historical limitation is the discriminatory representation of free-form objects. The system described in this paper recognizes free-form objects in dense range data acquired by a structured light rangefinder. Images and object models are represented as a network of salient segments which are then brought into correspondence until a reliable pose estimate is available. Experiments with a database of images and object models highlight the contributions of this system.

Download Full-text