Systems and methods for compression of three dimensional depth sensing
Aspects of the embodiments are directed to time-of-flight (ToF) imaging systems and method for image processing. The ToF imaging system can include a depth sensor; a light steering device; a photodetector; and an image processor. The ToF imaging system can be configured to acquiring a first image of a scene by the photodetector; identifying one or more regions of interest of the scene from the first image; and capturing a depth map of at least one of the one or more regions of interest.
1. A method for image processing and engendering three-dimensional time-of-flight depth map, the method comprising:
acquiring a first two-dimensional image of a scene;
segmenting the first two-dimensional image, whereby segmentation is the process of partitioning a digital image into multiple segments;
identifying one or more regions of interest of the scene from the segmentation of the first two-dimensional image; and
capturing a three-dimensional time-of-flight depth map of at least one of the one or more regions of interest, in which the three-dimensional time-of-flight depth map is a subset representative of the first image of the scene.
2. The method of claim 1 , wherein regions of interest are data samples within the first two-dimensional image of the scene for a particular purpose of identification.
3. The method of claim 1 , wherein acquiring the first image comprises capturing a two-dimensional image of the scene.
4. The method of claim 1 , wherein acquiring the first image comprises receiving a captured, two-dimensional image of the scene from an imaging device.
5. The method of claim 1 , wherein capturing the time-of-flight depth map comprises:
identifying one or more sets of pixels that form the at least one region of interest; and
scanning at least some of the pixels of the one or more sets of pixels that form the at least one region of interest with a three-dimensional imaging device.
6. The method of claim 1 , wherein acquiring the first image of the scene comprises capturing a low resolution depth map of the scene.
7. The method of claim 6 , further comprising:
identifying, from the low resolution depth map, one or more regions of interest of at least a portion of the scene;
scanning the one or more regions of interest with a higher resolution depth scan.
8. The method of claim 7 , wherein scanning the one or more regions of interest with a higher resolution depth scan comprises scanning the one or more regions of interest with a narrow solid angle light beam emitted from the imaging device.
9. The method of claim 7 , wherein scanning the one or more regions of interest with a higher resolution depth scan comprises scanning the one or more regions of interest with a reduced scanning step size.
10. An imaging system for 3-dimensional depth mapping comprising:
a first camera configured to acquire a first two-dimensional image of a scene;
an image processor configured to:
segment the first two-dimensional image, whereby segmentation is the process of partitioning a digital image into multiple segments;
identify one or more regions of interest of the scene from the segmentation of the first two-dimensional image, wherein regions of interest are data samples within the first two-dimensional image of the scene for a particular purpose of identification; and
capture a three-dimensional time-of-flight depth map of at least one of the one or more regions of interest.
11. The imaging system of claim 10 , wherein regions of interest are data samples within the first two-dimensional image of the scene for a particular purpose of identification.
12. The imaging system of claim 10 , wherein acquiring the first image comprises capturing a two-dimensional image of the scene.
13. The imaging system of claim 10 , wherein acquiring the first image comprises receiving a captured, two-dimensional image of the scene from an imaging device.
14. The imaging system of claim 10 , wherein capturing the depth map comprises:
identifying one or more rows of pixels that form the at least one region of interest; and
scanning at least some of the pixels of the one or more rows of pixels that form the at least one region of interest with a three-dimensional imaging device.
15. The imaging system of claim 10 , further comprising second camera configured to acquire a second image of the scene;
wherein acquiring the first and second images of the scene comprises deriving a low resolution depth map of the scene using stereo imaging of the first and second images.
16. The imaging system of claim 15 , further comprising:
identifying, from the low resolution depth map, one or more regions of interest of at least a portion of the scene;
scanning the one or more regions of interest with a higher resolution depth scan.
17. The imaging system of claim 16 , wherein scanning the one or more regions of interest with a higher resolution depth scan comprises scanning the one or more regions of interest with a narrow solid angle light beam emitted from the imaging device.
18. The imaging system of claim 16 , wherein scanning the one or more regions of interest with a higher resolution depth scan comprises scanning the one or more regions of interest with a reduced scanning step size.
19. The imaging system of claim 10 , wherein the first camera comprises an adjustable lens and the image processor is configured to:
determine a depth of an object within the region of interest; and
configure the adjustable lens into a focused position for capturing an image of the object.
20. The imaging system of claim 10 , wherein the time-of-flight imaging system is configured to:
capture a high-resolution depth map of the scene prior to acquiring the first image of the scene;
perform segmentation of the scene based on the high-resolution depth map; and identify one or more regions of interest based on the segmentation of the scene.
21. An apparatus for image processing and engendering three-dimensional time-of-flight depth map, the apparatus comprising:
means for acquiring a first two-dimensional image of a scene;
means for segmenting the first two-dimensional image, whereby segmentation is the process of partitioning a digital image into multiple segments;
means for identifying one or more regions of interest of the scene from the segmentation of the first two-dimensional image; and
means for capturing a three-dimensional time-of-flight depth map of at least one of the one or more regions of interest, in which the three-dimensional time-of-flight depth map is a subset representative of the first image of the scene.