3D Scanning with Kinect v2

Posts made in March, 2015

Camera Orientation

Camera Orientation

By on Mar 25, 2015 in Uncategorized |

The Camera Orientation settings allow for the 3D Scan to be standing upright when the camera is scanning at an angle. Pictured above is the ground highlighted while the camera is at a -37.3 degrees and a height of 1.3 meters. There is a foam display board lying on the ground to show how well tuned the camera alignment is. How it Works Normally, anything you scan will be considered oriented to the Scanner. This means that if you have the scanner at a 45 degree angle, the 3D scan will come out at a 45 degree angle. By specifying the angles of rotation, the scan area will automatically adjust itself to be upright. The ground can be highlighted, making it easier to make sure that the camera orientation is correct. Easier Alignments The main use of this is to make aligning 3D scans easier, as you will only need to transpose (move) the 3D scan and you won’t need to rotate it. Another use of this is having the scans already standing upright, so when attaching a base, the object is already standing up correctly. This is also used in auto aligning scans (currently only planned for the pro...

Read More
Pre-Integration Smoothing

Pre-Integration Smoothing

By on Mar 25, 2015 in Uncategorized |

On the left, the depth frames were smoothed before averaging out interference. On the right, no settings were changed. Applying the smoothing filter can sometimes look really great and remove unneeded bumps and ruffles. However, it can also remove needed depth detail or make facial features less...

Read More
HD Image Alignment for the Kinect V2

HD Image Alignment for the Kinect V2

By on Mar 24, 2015 in Uncategorized |

Finally! After days of trying different approaches, we’ve finally come up with an automatic image alignment for the scans. This is what would normally come out, but after filtering and altering the shape, most of the color would get lost. However, now we’ve created an approach that saves the original image source and can reapply it at any point during the process. The above 2 images may look the same quality, this is because the number of points available to color is low, you can still tell it’s better quality by checking out details like the eyes and cords in the...

Read More
Finding an HD image alignment for the Kinect V2

Finding an HD image alignment for the Kinect V2

By on Mar 24, 2015 in Uncategorized |

Because the depth camera and color camera are different devices, the images they produce do not automatically overlap. The color camera will have different lensing effects than the depth camera. The further away from the center, the more pronounced the effect will be. Because each Kinect V2 has its own camera parameters (they are tested for and set at the factory), a simple fixed solution is not feasible–what will work perfectly on one specific Kinect may not yield the same results on another Kinect. Microsoft has included a feature to auto-align the images, however, this only provides a standard definition image–the one above has not been resized, it’s the full size output from the HD that has been ‘aligned’ with depth. A little coding magic can grab additional pixel information and double the resolution as seen here (click to open in new window): Now to add some additional code to grab more data, to get rid of those grid lines. And there you have it: an HD quality image that uses Microsoft’s alignment method. (I’ll clean up those left over white specs later.) After a good nights rest, I cleaned up the process and here is the...

Read More
Average Depth Change vs Depth Interference

Average Depth Change vs Depth Interference

By on Mar 18, 2015 in Uncategorized |

Average Depth Change The Average Depth Change averages the change in distance around a pixel. So if the pixel being viewed has 2 pixels on each side of it that are +2mm and -2mm, the total change would be 4 and average out to 2. The average is then used to color the pixel: 1-10 will color it blue, 1-100 will color it green, 1-1000 will color it red. The option to change the sensitivity just multiples the average depth by the sensitivity setting. If the sensitivity level is too high, the blue and green streams cut off so the display is still distinguishable. Depth Interference Display The Depth Interference shows in red how much each pixel has changed from the prior frame; if there is no pixel data then it is colored dark red. How to utilize The Average Depth Change will let you see when angles are too steep, the Interference Display will show you ‘static’ or when there is too much change frame to...

Read More
Note: Scan from Life is in no way affiliated with Microsoft. We are an entirely separate company that has created a product that is dependent on a Microsoft owned product.