PR Newswire: TYZX announced it has received a substantial investment from Takata, a global manufacturer of automotive safety systems with more than 33,000 employees worldwide. The Takata investment follows an earlier investment by Microsoft co-founder Paul Allen. TYZX is rumored to be profitable since the first investment.
Industry experts believe that vehicles with 3D vision safety features can help better protect drivers and passengers in collisions, help cars avoid accidents, keep vehicles in appropriate road lanes, and prevent many accidental backup injuries and fatalities, among other benefits.
Meanwhile, Softkinetic-Optrima demoed their system in TI booth at Embedded Show in Yokohama, Japan, Dec. 1-3, 2010. A Youtube video shows the demo:
Update: Primesense has released the drivers to its platform as open source and founded OpenNI.org to promote the further defelopment. In the meantime the open community efforts to reverse engineer Primesense algorithms go on. ROS.org published its take on how the Primesense engine works. Here is the explanation from the site:
"Depth is calculated by triangulation against a known pattern from the projector. The pattern is memorized at a known depth. For a new image, we want to calculate the depth at each pixel. For each pixel in the IR image, a small correlation window (9x9 or 9x7, see below) is used to compare the local pattern at that pixel with the memorized pattern at that pixel and 64 neighboring pixels in a horizontal window (see below for how we estimate the 64-pixel search). The best match gives an offset from the known depth, in terms of pixels: this is called disparity. The Kinect device performs a further interpolation of the best match to get sub-pixel accuracy of 1/8 pixel... Given the known depth of the memorized plane, and the disparity, an estimated depth for each pixel can be calculated by triangulation."
Industry experts believe that vehicles with 3D vision safety features can help better protect drivers and passengers in collisions, help cars avoid accidents, keep vehicles in appropriate road lanes, and prevent many accidental backup injuries and fatalities, among other benefits.
Meanwhile, Softkinetic-Optrima demoed their system in TI booth at Embedded Show in Yokohama, Japan, Dec. 1-3, 2010. A Youtube video shows the demo:
Update: Primesense has released the drivers to its platform as open source and founded OpenNI.org to promote the further defelopment. In the meantime the open community efforts to reverse engineer Primesense algorithms go on. ROS.org published its take on how the Primesense engine works. Here is the explanation from the site:
"Depth is calculated by triangulation against a known pattern from the projector. The pattern is memorized at a known depth. For a new image, we want to calculate the depth at each pixel. For each pixel in the IR image, a small correlation window (9x9 or 9x7, see below) is used to compare the local pattern at that pixel with the memorized pattern at that pixel and 64 neighboring pixels in a horizontal window (see below for how we estimate the 64-pixel search). The best match gives an offset from the known depth, in terms of pixels: this is called disparity. The Kinect device performs a further interpolation of the best match to get sub-pixel accuracy of 1/8 pixel... Given the known depth of the memorized plane, and the disparity, an estimated depth for each pixel can be calculated by triangulation."
3D Sensing News: TYZX, Optrima, Primesense
![3D Sensing News: TYZX, Optrima, Primesense]()
Reviewed by MCH
on
December 08, 2010
Rating:
No comments: