Intel RealSense

Intel RealSense Technology, is a suite of depth and tracking technologies designed to give machines and devices depth perceptions capabilities that will enable them to “see” and understand the world. There are many uses for these computer vision capabilities including autonomous drones, robots, AR/VR, smart home devices amongst many others broad market products. RealSense technology is made of Vision Processors, Depth and Tracking Modules, and Depth Cameras, supported by an open source, cross-platform SDK called librealsense that simplifies supporting cameras for third party software developers, system integrators, ODMs and OEMs.[1]

As of January 2018, new Intel RealSense D400 Product Family was launched with the Intel RealSense Vision Processor D4, Intel RealSense Depth Module D400 Series, and 2 ready to use depth cameras: Intel RealSense Depth Cameras D435 and D415.

Previous generations of Intel RealSense depth cameras (F200, R200 and SR300) were implemented in multiple laptop and tablet computers by Asus, HP, Dell, Lenovo, and Acer.[2] Additionally, Razer and Creative offered consumer ready standalone webcams with the Intel RealSense camera built into the design.:[3] Razer Stargazer and the Creative BlasterX Senz3D.[4]

Technology Overview

Intel RealSense Group supports multiple depth and tracking technologies: Coded Light Depth, Stereo Depth and Positional Tracking.[5]

Products

Intel RealSense D400 Product Family

Intel RealSense Vision Processor D4 Series

The Intel RealSense Vision Processor D4 series are vision processors based on 28 nanometer (nm) process technology to compute real-time stereo depth data. It features a new and advanced stereo depth algorithm that enables more accurate and longer range depth perception than Intel’s previous generation. There are two products in this family: RealSense Vision processor D4 and RealSense Vision Processor D4m.

Specifications:

D4 Vision Processor D4M Vision Processor
Depth Technology Stereo Stereo
Form Factor ASIC BGA ASIC BGA
Package Size 6.4mm x 6.4mm x 1mm 4.7mm x 3.8mm x 0.55mm
Process Technology 28 nm 28 nm
Depth Max Throughput 36.6 MP/sec (848×480@90fps)
Depth Stream Output Resolution Up to 1280×720 Up to 720×720
Depth Stream Output Frame Rate Up to 90fps
RGB Sensor Max Resolution & Max Frame Rate 1920×1080, Up to 60fps 720×720, Up to 30 fps
IR Projector Controls Yes Yes
Host Interface USB 3.0 2x MIPI
Multi Camera Support Yes, up to 5 Up to 30fps
I/O 5x MIPI CSI-2, 5x I2C, 1x SPI, GPIO, Timer 2x MIPI 1x I2C, 1x SPI, GPIO, Timer

Intel RealSense Depth Module D400 Series

The Intel RealSense Depth Module D400 Series includes 5 calibrated imaging sub-system that features active or passive IR stereo depth technology, rolling or global shutter image sensor technology, wide or standard FOV, and in some offerings an RGB sensor. When paired with a RealSense™ Vision Processor D4, these modules can output depth data over USB 3.0 and is designed for easy integration to bring 3D into devices and machines.

Specifications:

D400 D410 D415 D420 D430
Depth technology Passive IR Stereo Active IR Stereo Active IR Stereo Passive IR Stereo Active IR Stereo
Image Sensor technology Rolling Shutter Rolling Shutter Rolling Shutter Global Shutter Global Shutter
Depth FOV (HxV for HD 16:9) 63.4degx 40.4deg 63.4degx 40.4deg 63.4degx 40.4deg 85.2degx 58deg 85.2degx 58deg
RGB Frame Rate and Resolution - - Up to 60FPS - -
Depth Resolution Up to 1280x720 Up to 1280x720 Up to 1280x720 Up to 1280x720 Up to 1280x720
Depth Frame Rate Up to 90fps Up to 90fps Up to 90fps Up to 90fps Up to 90fps
Range 0.16-10m+ 0.16-10m+ 0.16-10m+ 0.11-10m+ 0.11-10m+

Intel RealSense Depth Camera D400 Series

Intel launched 2 new depth cameras in January 2018: D415 and D435. Both cameras feature the RealSense Vision processor D4 and camera sensors. They are supported by the cross-platform and open source Intel RealSense SDK 2.0 or librealsense on GitHub.

Intel RealSense Depth Camera D415

The Intel RealSense Depth Camera D415 includes the Intel RealSense Vision Processor D4 featuring high depth resolution - up to 1280x720 at 30 frames per second (fps), long-range capabilities, rolling shutter technology and a narrow field of view ideal for precise measurements. It is designed for easy setup with USB 3.0 and is in a sleek form factor for portability. With the rolling image shutter and narrow field of view, the Intel RealSense Depth Camera D415 offers high-depth resolution when the object size is small and more precise measurements are required. The D415 Camera is for sale now at several distributors.

Product Brief Available here.

Intel RealSense Depth Camera D435

The Intel RealSense Depth Camera D435 is ideal for capturing stereo depth in a variety of applications that help perceive the world in 3D. The camera includes the Intel RealSense Vision Processor D4 featuring high depth resolution - up to 1280x720 at 30 frames per second (fps), long-range capabilities, global shutter technology and a wide field of view. With the global image shutter and wide field of view (91.2° x 65.5° x 100.6°), the Intel RealSense Depth Camera D435 offers accurate depth perception when the object is moving or the device is in motion, and it covers more field of view, minimising blind spots. It is designed for easy setup with USB 3.0 and is in a sleek form factor for portability. The D435 Camera is for sale now at several distributors.

Specifications:

D415 D435
Use Environment Indoor/Outdoor Indoor/Outdoor
Depth Technology Active infared (IR) stereo Active IR stereo
Image Sensor Technology Rolling shutter, 1.4umx1.4 um pixel size Global Shutter, 3 um X 3 um pixel size
Components Included Realsense Vision Processor D4

Realsense Module D410

Realsense Vision Processor D4

Realsense Module D430

Depth Field of View 63.4deg x 40.4deg (+/-3deg) 85.2deg x 58deg (+/-3deg)
Depth Stream Output Resolution Up to 1280x720 Up to 1280x720
Depth Stream Output Frame Rate Up to 90fps Up to 90fps
Minimum Depth Distance (MinZ) 0.16m 0.11m
Max Range ~10meters

Varies depending on calibration, scene, lighting condition

 ~10meters

Varies depending on calibration, scene, lighting condition

RGB Sensor Resolution & Frame Rate 1920x1080 at 30fps 1920x1080 at 30fps
RGB Sensor FOV 69.4deg x 42.5deg (+/- 3deg) 69.4deg x 42.5deg (+/- 3deg)
Camera Dimension 99mm X 20mm X 23mm 90mm x 25mm x 25 mm
Connectors USB 3.0 Type-C USB 3.0 Type-C
Mounting Mechanism One 1/4 -20 UNC thread mounting point

Two M3 thread mounting points

One 1/4 -20 UNC thread mounting point

Two M3 thread mounting points

Intel Euclid Robotics Development Kit

A stick computer with :[6][7][8][9][10][11][12][13][14][15][16][17][18][19]

  • Intel Atom x7-Z8700 Quad Core
  • 4GB LPDDR3-1600
  • 32GB eMMC MLC 5.0
  • Intel RealSense ZR300 Depth Camera
  • Wi-Fi : 802.11 a/b/g/n, 1x1 DB
  • Bluetooth 4.0
  • USB 3.0
  • Micro HDMI
  • Microphone : D-MIC, X3, Noise Cancellation
  • USB OTG/Charging ports
  • inertial measurement unit
  • barometric pressure sensor
  • GPS : GNS, GLONASS, Beidou, Galileo, QZSS, WAAS, EGNOS
  • proximity sensor
  • Battery
  • Power Adapter
  • USB cable
  • HDMI cable
  • Pre-installed Ubuntu 16.04 operating system
  • Pre-installed Robotics Operating System

Previous Generations

Intel RealSense 3D Camera (Front F200)

This is a stand-alone camera that can be attached to a desktop or laptop computer.[20] It is intended to be used for natural gesture-based interaction, face recognition, immersive, video conferencing and collaboration, gaming and learning and 3D scanning.[21]

There is a version of this camera to be embedded into laptop computers.[22]

Specifications

  • Full VGA depth resolution
  • 1080p RGB camera
  • 0.2–1.2 meter range (Specific algorithms may have different range and accuracy)
  • USB 3.0 interface

Intel RealSense Snapshot

Snapshot is a camera intended to be built into tablet computers and possibly smartphones. Its intended uses include taking photographs and performing after the fact refocusing, distance measurements, and applying motion photo filters.[23]

The refocus feature differs from a plenoptic camera in that RealSense Snapshot takes pictures with large depth of field so that initially the whole picture is in focus and then in software it selectively blurs parts of the image depending on their distance.

Dell Venue 8 7000 Series Android tablet is equipped with this camera.[24]

Intel RealSense 3D Camera (Rear R200)

Rear-mounted camera for Microsoft Surface or a similar tablet, like the HP Spectre X2.[25] This camera is intended for augmented reality applications, content creation, and object scanning. Its depth accuracy is on the order of millimeters and its range is up to 6.0 meters. This makes it the more accurate and longer range of the Intel RealSense 3D cameras. Also unlike the F200 and SR300, the R200 is a stereo camera and is able to obtain accurate depth outdoors as well as indoors.[26]

Intel RealSense 3D Camera (Front SR300)

The SR300 camera is the next generation of the Front F200 camera. It improves in various respects over its predecessor,[27] notably with

  • 60% improved range
  • >5X reduction in standby power
  • 2X improvement in gesture speed (up to 2 m/s)
  • >8X improvement in depth/RGB latency

App Challenge

To address the lack of applications built on the RealSense platform and to promote the platform among software developers, in 2014 Intel organized the Intel RealSense App Challenge. The winners were awarded large sums of money.[28]

Software Developer Kit: Librealsense

Intel launched their open source cross platform software developer kit with the Intel RealSense depth cameras D435 and D415. It is available on GitHub.

The SDK (librealsense) allows depth and color streaming, and provides intrinsic and extrinsic calibration information. The library also offers synthetic streams (pointcloud, depth aligned to color and vice versa), and a built-in support for record and playback of streaming sessions.

Key Features of the SDK (librealsense):

What Description
Intel® RealSense™ Viewer With this application, you can quickly access your Intel® RealSense™ Depth Camera to view the depth stream, visualize point clouds, record and playback streams, configure your camera settings, modify advanced controls, enable depth visualization and post processing and much more.
Depth Quality Tool This application allows you to test the camera’s depth quality, including: standard deviation from plane fit, normalized RMS – the subpixel accuracy, distance accuracy and fill rate. You should be able to easily get and interpret several of the depth quality metrics and record and save the data for offline analysis.
Other Debug Tools Device enumeration, FW logger, etc. as can be seen at the tools directory
Code Samples to Start Prototyping Quickly These simple examples demonstrate how to easily use the SDK to include code snippets that access the camera into your applications. Check some of the C++ examples including capture, pointcloud and more and basic C examples
Wrappers Python, .NET, Node.js API, as well as integration with the following 3rd-party technologies: ROS, LabVIEW, OpenCV, PCL, Unity, and more to come, including Matlab and OpenNI.

Reception

In an early preview article in 2015, PC World's Mark Hachman concluded that RealSense is an enabling technology that will be largely defined by the software that will take advantage of its features. He noted that as of the time the article was written, the technology was new and there was no such software.[29]

See also

References

  1. ↑ "Intel RealSense". Intel RealSense. Retrieved 2018-04-14.
  2. ↑ "Devices with Intel RealSense Technology". Intel.
  3. ↑ "Razer Stargazer Depth-Sensing Webcam". Feb 22, 2016.
  4. ↑ http://www.pcgamesn.com/creative/creative-senz3d-razer-stargazer
  5. ↑ "Intel RealSense". Intel RealSense. Retrieved 2018-04-14.
  6. ↑ https://www.cnx-software.com/2017/05/22/399-intel-euclid-realsense-powered-robotics-devkit-runs-ubuntu-ros-on-intel-atom-x7-z8700-processor/
  7. ↑ http://roscon.ros.org/2016/presentations/ROSCon2016_Intel_RealSense.pdf
  8. ↑ https://fccid.io/2AK6WEUCLID1/RF-Exposure-Info/SAR-Test-Report-1-3339127
  9. ↑ https://newsroom.intel.com/chip-shots/intel-announces-tools-realsense-technology-development/
  10. ↑ https://www.patreon.com/posts/intel-euclid-022-12444963
  11. ↑ https://www.youtube.com/watch?v=tIGvWYMwLzA
  12. ↑ https://www.intel.com/content/www/us/en/support/articles/000024177/emerging-technologies/intel-euclid-development-kit.html
  13. ↑ https://www.euclidcommunity.intel.com/
  14. ↑ https://www.mouser.de/new/Intel/intel-euclid-dev-kit/
  15. ↑ http://wiki.ros.org/IntelEuclid
  16. ↑ https://imvc.co.il/Portals/38/Amit%20Moran.pdf
  17. ↑ https://github.com/inteleuclid
  18. ↑ https://www.intel.com/content/www/us/en/support/products/99400/emerging-technologies/intel-euclid-development-kit.html
  19. ↑ https://www.intel.com/content/dam/support/us/en/documents/emerging-technologies/Euclid_User_Guide.pdf
  20. ↑ "Take Interaction to the Next Level – Intel RealSense Camera F200". Intel.
  21. ↑ "Developing for the Intel RealSense Camera (F200)". Intel.
  22. ↑ "Devices with Intel RealSense Technology". Intel.
  23. ↑ "Developing for the Intel RealSense Snapshot". Intel. Archived from the original on May 14, 2015.
  24. ↑ "Intel RealSense Snapshot". Intel. Archived from the original on May 3, 2015.
  25. ↑ "HP Spectre X2". HP.
  26. ↑ Keselman, Leonid; Woodfill, John Iselin; Grunnet-Jepsen, Anders; Bhowmik, Achintya (2017-05-16). "Intel RealSense Stereoscopic Depth Cameras". arXiv:1705.05548 [cs.CV].
  27. ↑ "Intel®RealSense™ Developer Kit featuring SR300". Retrieved 22 February 2016.
  28. ↑ "Intel RealSense App Challenge Winners". Intel.
  29. ↑ "Hands on: Without apps, Intel's RealSense camera is a puzzle". PC World. Mar 5, 2015. Retrieved 25 March 2015.
This article is issued from Wikipedia. The text is licensed under Creative Commons - Attribution - Sharealike. Additional terms may apply for the media files.