Three-dimensional object model tagging
View Patent ↗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.
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.