Three-dimensional object model tagging

• US 9,773,302 B2
• Filed: 10/08/2015
• Issued: 09/26/2017
• Est. Priority Date: 10/08/2015
• Status: Active Grant

• Current Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Original Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Inventors: Wang, Su, Tai, Hung-Shuo, Sharma, Divya
• Primary Examiner(s): Chawan, Sheela C
• Application Number:
  US14/878,889
• Publication Number:
  US 20170103510A1
• Time in Patent Office: 719 Days
• Field of Search: 382154, 382162, 382168, 382166, 382169, 382173, 382181, 382190, 382199, 382203, 382232, 382237, 382250, 382254, 382276, 345419, 345420-428, 345589, 345597
• CPC Class Codes: G06T 17/00 Three dimensional [3D] modelling, e.g. data description of 3D objects
• CPC Class Codes: G06T 2200/24 involving graphical user interfaces [GUIs]
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 2207/10028 Range image; Depth image; 3D point clouds
• CPC Class Codes: G06T 7/0002 Inspection of images, e.g. flaw detection
• CPC Class Codes: G06T 7/33 using feature-based methods
• CPC Class Codes: G06T 7/344 involving models
• CPC Class Codes: G06T 7/38 Registration of image sequences
• CPC Class Codes: G06T 7/50 Depth or shape recovery
• CPC Class Codes: H04N 13/25 using two or more image sensors with different characteristics other than in their location or field of view, e.g. having different resolutions or colour pickup characteristics; using image signals from one sensor to control the characteristics of another sensor

Abstract

In one implementation, a system for three-dimensional object model tagging includes a model engine to generate a model of a three-dimensional (3D) object from a pre-scan of a 3D object; an analysis engine to analyze the model to identify a property of the 3D object predictive of a reconstruction of the 3D object; a tag engine to generate a tag that describes the identified property based on the analysis; and a display engine to display the tag.

Claims

1. A system, comprising:

a processing resource; and

a memory resource storing machine readable instructions to cause the processing resource to;

generate a model of a three-dimensional (3D) object from a pre-scan of the 3D object;

analyze the model to identify a property of the 3D object predictive of a reconstruction of the 3D object;

generate a categorical tag that describes the identified property based on the analysis, wherein the categorical tag is based on similarity between the 3D object and the model;

automatically adjust, without user input, a scan parameter utilized in a subsequent full scan, including a rotation angle, to improve similarity between the 3D object and the model based on the identified property; and

display the categorical tag.

2. The system of claim 1, wherein the pre-scan includes capturing a series of images of the 3D object with an image capturing device having a lower capture resolution than an image capturing device utilized in the subsequent full scan.

3. The system of claim 2, wherein the tag includes information related to adjusting the scan parameter for the subsequent full scan.

4. The system of claim 1, wherein the pre-scan is a series of image captures of the 3D object at different object orientations corresponding to unique rotation angles of the 3D object relative to a scanning device.

5. The system of claim 4, wherein the scanning device includes:

a depth-sensor camera; and

a red, green, blue (RGB) camera.

6. A non-transitory computer readable medium storing instructions executable by a processing resource to cause a computing device to:

generate, at a computing device, a model of a three-dimensional (3D) object from a pre-scan of the 3D object;

analyze, at the computing device, the model to determine a predicted reconstruction of the 3D object;

tag, at the computing device, the model with a tag indicating a property of the object based on the predicted reconstruction, wherein the tag is based on a similarity of the indicated property between the 3D object and the model, and wherein the computing device automatically adjusts, without user input, scan parameters utilized in a subsequent full scan, including a rotation angle, to improve similarity of the indicated property between the 3D object and the model;

display, at the computing device, the tag.

7. The medium of claim 6, comprising instructions to analyze the model by extracting a boundary of the 3D object from a number of two-dimensional (2D) red green blue (RGB) image captures by applying a 2D foreground mask corresponding to the 3D object to the number of 2D RGB image captures.

8. The medium of claim 7, comprising instructions to analyze the model by performing a boundary analysis of a regularity of the extracted boundary.

9. The medium of claim 6, comprising instructions to analyze the model by performing a color analysis of a number of two-dimensional (2D) red green blue (RGB) image captures of the 3D object.

10. The medium of claim 6, comprising instructions to analyze the model by performing a color saturation analysis of a number of two-dimensional (2D) red green blue (RGB) image captures of the 3D object.

11. The medium of claim 6, comprising instructions to analyze the model to determine the predicted reconstruction of the 3D object based on a value determined by the analysis of the model as compared to a predetermined threshold value.