Recognition and pose estimation of unoccluded three-dimensional objects from a two-dimensional perspective view by banks of neural networks

In her foundational study of Neolithic clay tokens, the renowned archaeologist Denise Schmandt-Besserat identified that different token shapes represented different goods and were used in accounting and distribution. When these tokens came to be stored in sealed clay envelopes (likely representing a debt), each token was impressed on the outside of the envelope before being placed inside (thus allowing people to see quickly what was within). Three-dimensional objects were thus reduced to two-dimensional representations, the first form of writing (and contributing to cuneiform script). These clay envelopes in turn developed into pictographic tablets; here each token did not have to be impressed into the clay in a 'one, one, one' system, but instead quantity was indicated by a numerical symbol - abstract number was born. Much of Schmandt-Besserat’s work can be found online at https://sites.utexas.edu/dsb/. Her book ‘How Writing Came About’ was listed by American Scientist magazine as one of the 100 books that shaped science in the 20th century, and she remains an active expert on all things ‘token’.

Download Full-text

A system for generating virtual seeds

Scientia Agricola ◽

10.1590/s0103-90161998000500007 ◽

1998 ◽

Vol 55 (spe) ◽

pp. 39-45 ◽

Cited By ~ 2

Author(s):

Y. Sako ◽

K. Fujimura ◽

M.B. McDonald ◽

D. James

Keyword(s):

Three Dimensional ◽

Promising Method ◽

Two Dimensional ◽

Dimensional Representation ◽

Accurate Identification ◽

Computer Screen ◽

Three Dimensional Objects ◽

Three Dimensional Representation ◽

Quicktime Vr

Seed analysts need to identify seeds, and seed catalogs are used as a reference to accomplish this task. Conventional seed catalogs supply two-dimensional photographs and hand-drawn diagrams. In this study, a new, three-dimensional representation of seeds is developed to supplement these traditional photographs and drawings. QuickTime VR is a promising method for viewing three-dimensional objects on a computer screen. It permits manipulation of an object by rotating and viewing it from any pre-specified angle at an interactive speed, allowing the viewer the sense of examining a hand-held object. In this study, QuickTime VR object movies of seeds were created as interactive "movies" of seeds that can be rotated and scaled to give the viewer the sensation of examining actual seeds. This approach allows the examination of virtual seeds from any angle, permitting more accurate identification of seeds by seed analysts.

Download Full-text

Addition of Illuminator Fiber Optic to Produce 3 Dimension Effects in Micrographic Observation Using Upright Microscope

Proceeding International Conference on Science and Engineering ◽

10.14421/icse.v3.551 ◽

2020 ◽

Vol 3 ◽

pp. 493-496

Author(s):

Sutriyono ◽

Widodo ◽

Retno Suryandari

Keyword(s):

Optical Fiber ◽

Experimental Method ◽

Daphnia Magna ◽

High Intensity ◽

Fiber Optic ◽

Three Dimensional ◽

Two Dimensional ◽

Three Dimensional Objects ◽

Stereo Microscope ◽

Total Magnification

Microscope is one of the tools used in practicums with high intensity. The use of a microscope adjusts to the object to be observed in order to obtain optimal micrographic results. Stereo microscopes are used to observe three-dimensional objects. Upright microscopes are used to observe two-dimensional objects. This study aims to combine the two advantages of stereo microscopy that can produce three-dimensional micrography with the advantages of an upright microscope that has a high total magnification. The method used in this study is an experimental method by adding an optical fiber illuminator in the use of an upright microscope and then applying it in various observations. The conclusion of this research is the addition of an optical fiber illuminator in observations using an upright microscope can replace the function of a stereo microscope; can produce three-dimensional effects and increase magnification in Daphnia magna micrographic observations.

Download Full-text

Visual Pursuit of Two-Dimensional/Three-Dimensional Objects on Video Clips: Effects on the Human Body

Universal Access in Human-Computer Interaction. Access to Interaction - Lecture Notes in Computer Science ◽

10.1007/978-3-319-20681-3_25 ◽

2015 ◽

pp. 264-272

Author(s):

Masumi Takada ◽

Masaki Sakai ◽

Masaru Miyao ◽

Hiroki Takada

Keyword(s):

Human Body ◽

Three Dimensional ◽

Two Dimensional ◽

Visual Pursuit ◽

Three Dimensional Objects ◽

Video Clips

Download Full-text

Feasibility Study of Textureless Object Detection and Pose Estimation Based on a Model with 3D Edgels and Surfaces

Paladyn Journal of Behavioral Robotics ◽

10.1515/pjbr-2015-0012 ◽

2015 ◽

Vol 6 (1) ◽

Author(s):

Kimitoshi Yamazaki ◽

Kiyohiro Sogen ◽

Takashi Yamamoto ◽

Masayuki Inaba

Keyword(s):

Object Detection ◽

Feasibility Study ◽

Pose Estimation ◽

Template Matching ◽

Input Data ◽

Three Dimensional ◽

Target Object ◽

Textural Features ◽

Two Dimensional ◽

Home Appliances

Abstract This paper describes a method for the detection of textureless objects. Our target objects include furniture and home appliances, which have no rich textural features or characteristic shapes. Focusing on the ease of application, we define a model that represents objects in terms of three-dimensional edgels and surfaces. Object detection is performed by superimposing input data on the model. A two-stage algorithm is applied to bring out object poses. Surfaces are used to extract candidates fromthe input data, and edgels are then used to identify the pose of a target object using two-dimensional template matching. Experiments using four real furniture and home appliances were performed to show the feasibility of the proposed method.We suggest the possible applicability in occlusion and clutter conditions.

Download Full-text