System and method for portable active 3D scanning
A method for generating a three-dimensional model of an object, by a scanning system including a client-side device including: an acquisition system configured to capture images; and an interaction system including a display device and a network interface includes: capturing a plurality of images of the object by the acquisition system, the images being captured from a plurality of different poses of the acquisition system; computing depth maps from the images of the objects, each of the depth maps corresponding to one of the poses of the acquisition system; combining the depth maps to generate a combined point cloud; and displaying, on the display device, the combined point cloud or a 3D mesh model generated from the combined point cloud.
1. A three-dimensional (3D) scanning system comprising a plurality of acquisition systems configured to capture images, each acquisition system comprising:
a depth camera;
a processor and memory; and
a network interface,
the memory of each of the acquisition systems storing instructions that, when executed by the processor, cause the corresponding acquisition system to:
control the depth camera of the corresponding acquisition system to capture a plurality of images of one or more objects, the plurality of acquisition systems capturing images concurrently and from different poses with respect to the one or more objects;
compute a partial 3D model of a portion of the one or more objects based on the images captured by the corresponding acquisition system; and
transmit the partial 3D model of the portion of the one or more objects to an offline processing system via the network interface.
2. The 3D scanning system of claim 1 , wherein the depth camera of each acquisition system comprises:
a first infrared camera having a first optical axis and a first field of view,
a second infrared camera spaced apart from the first infrared camera and having a second optical axis substantially parallel to the first optical axis and a second field of view overlapping the first field of view;
a color camera having an optical axis substantially parallel to the first optical axis and the second optical axis and having a field of view overlapping the first field of view and the second field of view; and
an infrared illuminator configured to illuminate a region within the first field of view of the first infrared camera and the second field of view of the second infrared camera,
wherein the acquisition system is configured to control the first infrared camera, the second infrared camera, and the color camera to capture images substantially simultaneously.
3. The 3D scanning system of claim 1 , wherein the offline processing system comprises:
a processor and memory; and
a network interface,
the memory storing instructions that, when executed by the processor, cause the processor to:
receive the partial 3D models from the plurality of acquisition systems via the network interface of the offline processing system;
combine the partial 3D models generated by the acquisition systems having different poses with respect to the one or more objects to generate a combined 3D model of an object of the one or more objects;
detect one or more defects in the object based on the combined 3D model of the object; and
store a report of the detected one or more defects in association with the object.
4. The 3D scanning system of claim 3 , wherein the memory of the offline processing system further stores instructions that, when executed by the processor, cause the processor to detect the one or more defects in the object based on the combined 3D model by:
comparing the combined 3D model to a reference model; and
identifying portions of the combined 3D model that differ from the reference model as the one or more defects in the object.
5. The 3D scanning system of claim 3 , wherein the memory of the offline processing system further stores instructions that, when executed by the processor, cause the processor to detect the one or more defects in the object based on the combined 3D model by:
synthesizing a plurality of two dimensional views of the object; and
classifying the two dimensional views of the object using a convolutional neural network trained to detect defects based on a plurality of training data comprising 3D models of defective and undefective objects.
6. The 3D scanning system of claim 1 , wherein the offline processing system comprises:
a processor and memory; and
a network interface,
the memory storing instructions that, when executed by the processor, cause the processor to:
receive the partial 3D models from the plurality of acquisition systems via the network interface of the offline processing system;
combine the partial 3D models generated by the acquisition systems having different poses with respect to the one or more objects to generate a combined 3D model of an object of the one or more objects;
recognize the object to compute a classification; and
store the classification of the object.
7. The 3D scanning system of claim 1 , wherein the offline processing system comprises:
a processor and memory; and
a network interface,
the memory storing instructions that, when executed by the processor, cause the processor to:
receive the partial 3D models from the plurality of acquisition systems via the network interface of the offline processing system;
combine the partial 3D models generated by the acquisition systems having different poses with respect to the one or more objects to generate a combined 3D model;
estimate a volume of the one or more objects; and
store the estimated volume of the one or more objects.
8. The 3D scanning system of claim 1 , wherein the offline processing system comprises:
a processor and memory; and
a network interface,
the memory storing instructions that, when executed by the processor, cause the processor to:
receive the partial 3D models from the plurality of acquisition systems via the network interface of the offline processing system;
combine the partial 3D models generated by the acquisition systems having different poses with respect to the one or more objects to generate a combined 3D model;
count the number of the one or more objects; and
store the number of the one or more objects.
9. A three-dimensional (3D) scanning system comprising:
a handheld 3D scanning device comprising:
a depth camera; and
a processor and memory,
the memory storing instructions that, when executed by the processor, cause the processor to:
control the depth camera to capture a plurality of images of one or more objects;
compute a 3D model of the one or more objects; and
compute an estimated volume of the one or more objects based on the 3D model.
10. The 3D scanning system of claim 9 , wherein the handheld 3D scanning device further comprises a network interface,
wherein the memory further stores instructions that, when executed by the processor, cause the processor to transmit the estimated volume to an offline processing system of the 3D scanning system via the network interface, and
wherein the offline processing system is configured to store the estimated volume of the one or more objects.
11. The 3D scanning system of claim 10 , wherein the handheld 3D scanning device further comprises a display device, and
wherein the memory further stores instructions that, when executed by the processor, cause the processor to display the estimated volume on the display device.
12. The 3D scanning system of claim 9 , wherein the memory further stores instructions that, when executed by the processor, cause the processor to:
count the number of the one or more objects in the 3D model; and
store the number of the one or more objects.
13. The 3D scanning system of claim 12 , wherein the handheld 3D scanning device further comprises a network interface,
wherein the memory further stores instructions that, when executed by the processor, cause the processor to transmit the number of the one or more objects to an offline processing system of the 3D scanning system via the network interface, and
wherein the offline processing system is configured to store the number of the one or more objects.
14. The 3D scanning system of claim 9 , wherein the depth camera comprises:
a first infrared camera having a first optical axis and a first field of view,
a second infrared camera spaced apart from the first infrared camera and having a second optical axis substantially parallel to the first optical axis and a second field of view overlapping the first field of view;
a color camera having an optical axis substantially parallel to the first optical axis and the second optical axis and having a field of view overlapping the first field of view and the second field of view; and
an infrared illuminator configured to illuminate a region within the first field of view of the first infrared camera and the second field of view of the second infrared camera,
wherein depth camera is configured to control the first infrared camera, the second infrared camera, and the color camera to capture images substantially simultaneously.
15. A method for three-dimensional (3D) scanning by a handheld 3D scanning device comprising: a depth camera; and a processor and memory, the method comprising
controlling, by the processor in accordance with instructions stored in the memory, the depth camera to capture a plurality of images of one or more objects;
computing, by the processor, a 3D model of the one or more objects; and
computing, by the processor, an estimated volume of the one or more objects based on the 3D model.
16. The method of claim 15 , wherein the handheld 3D scanning device further comprises a network interface,
wherein the method further comprises transmitting the estimated volume to an offline processing system via the network interface, and
wherein the offline processing system is configured to store the estimated volume of the one or more objects.
17. The method of claim 16 , wherein the handheld 3D scanning device further comprises a display device, and
wherein the method further comprises displaying the estimated volume on the display device.
18. The method of claim 15 , wherein the method further comprises:
counting, by the processor, the number of the one or more objects based on the 3D model; and
storing, by the processor, in the memory, the number of the one or more objects.
19. The method of claim 18 , wherein the handheld 3D scanning device further comprises a network interface,
wherein the method further comprises transmitting the number of the one or more objects to an offline processing system via the network interface, and
wherein the offline processing system is configured to store the number of the one or more objects.
20. The method of claim 15 , wherein the depth camera comprises:
a first infrared camera having a first optical axis and a first field of view,
a second infrared camera spaced apart from the first infrared camera and having a second optical axis substantially parallel to the first optical axis and a second field of view overlapping the first field of view;
a color camera having an optical axis substantially parallel to the first optical axis and the second optical axis and having a field of view overlapping the first field of view and the second field of view; and
an infrared illuminator configured to illuminate a region within the first field of view of the first infrared camera and the second field of view of the second infrared camera,
wherein depth camera is configured to control the first infrared camera, the second infrared camera, and the color camera to capture images substantially simultaneously.