Intel RealSense has been a foundation of Windows Hello, mobile face authentication, depth sensing and 3D VR photography.
It is a foundation enabling technology allowing developers to add 3D, depth and augmented reality (AR) to applications and devices.
Intel now has a new stand-alone, RealSense Tracking Camera
T265 that it sees as a building block for autonomous
devices like drones, robots, AR and even vehicles requiring low latency.
Sagi Ben Moshe, vice president and general manager, Intel
RealSense Group, said,
“Understanding your environment is a critical component for many devices. The T265 was designed to complement our existing Intel RealSense Depth Cameras and provide a quick path to product development with our next-generation integrated V-SLAM (visual inertial odometry simultaneous localisation and mapping ) technology.”
It uses the Intel Movidius Myriad 2 vision processing unit
(VPU), which does on-machine data processing tracking.
It is a small footprint, low-power consumption solution that
is simple to add to existing designs or to build
intellectual property that requires rich visual intelligence.
It is easy to add to small-footprint mobile devices like
lightweight robots and drones, as well as for connectivity with mobile phones
or AR headsets.
For example, integrating the T265 into an agricultural robot
allow it to navigate fields in a precise lawn-mower-style pattern and
intelligently adapt to avoid obstacles in its environment
It is important because
It is ideal for applications where device location tracking is
important, especially in locations
without GPS service. These include warehouses or remote outdoor areas where the
camera uses a combination of known and unknown data to accurately navigate to its destination.
How It’s Different
The Intel RealSense Tracking Camera T265 uses inside-out
tracking, which means the device does not rely on any external sensors to
understand the environment.
It uses 6-degrees-of-freedom (6DoF) inside-out tracking by
gathering inputs from two onboard fish-eye cameras, each with a nominal 170-degree
range of view.
The V-SLAM systems construct and continually update maps of
unknown environments and the location of a device within that environment.
Since all position calculations are on the device, tracking is platform
independent and allows the T265 to run on very low-compute devices.
The T265 complements Intel’s RealSense D400 series cameras,
and the data from both devices can combine
for advanced applications like occupancy mapping, improved 3D scanning and
advanced navigation and collision avoidance in GPS-restricted environments. The
only hardware requirements are sufficient non-volatile memory to boot the
device and a USB 2.0 or 3.0 connection that provides 1.5 watts of power.
The Intel RealSense Tracking Camera T265 is available for pre-order now. It will begin shipping in early March at US$199.
High precision Visual Inertial Odometry Simultaneous
Localization and Mapping algorithms
Intel MovidiusTM Myriad 2.0 VPU
Visual Processing Unit optimised
to run V-SLAM at low 1.5W power
Two Fisheye lenses with combined 163 ±5° FOV
The camera includes two OV9282 imagers with fisheye lenses
for a combined, close to hemispherical 163° field of view for robust tracking even with fast motion
The Inertial Measurement Unit, allows for accurate
measurement of rotation and acceleration of the device, to feed into the
USB 3.1 Gen 1 Micro-B
USB 2.0 and USB-C 3.1 Gen1 supported for pure pose data, or a combination of pose and
images. Connection on the camera is
108 x 24.5 x 12.5 mm
Small form factor designed to mount on any device with
2 x M3 0.5mm post mounting sockets
Securely attach the camera to your device with these
standard mounting points on the rear of the camera