‘Intel RealSense’ – gives machines and devices depth perceptions capabilities

Intel RealSense Technology is a product range of depth and tracking technologies designed to give machines and devices depth perceptions capabilities. The technology, owned by Intel are used in autonomous drones, robots, AR/VR, smart home devices amongst many others broad market products.

The RealSense product is made of Vision Processors, Depth and Tracking Modules, and Depth Cameras, supported by an open source, cross-platform SDK, simplifying supporting cameras for third party software developers, system integrators, ODMs and OEMs.

Stereo Depth

Intel® RealSense™ Stereo depth technology brings 3D to devices and machines that only see 2D today. Compare what the human eye sees to what Intel® RealSense™ depth technology sees.

Stereo depth works both indoors and outdoors in a wide variety of lighting conditions and can also be used in multiple camera configurations without the need for custom calibration. The onboard Intel® RealSense™ Vision Processor D4 performs all the depth calculations on the camera, allowing for low power, platform agnostic devices.

Stereo depth solutions

Designed for easy setup and portability, Intel® RealSense™ D400 series cameras feature high depth resolution and include active infrared (IR) stereo with standard or wide field of view. For high-precision applications, choose the D415 with rolling shutter. If your application is fast‑moving or outdoors, select either the D435 or D435i camera which feature a global shutter. For longer range applications, the D455 features wide field of view and global shutter on the depth and RGB sensors.

Stereo image sensing technologies use two cameras to calculate depth and enable devices to see, understand, interact with, and learn from their environment. Depth cameras in the Intel RealSense D400 family work both indoors and outdoors in a wide variety of lighting conditions and can also be used in multiple camera configurations without the need for custom calibration.

Intel RealSense™ ID – Facial Authentication

 on-device solution combines an active depth sensor with a specialized neural network to deliver secure and accurate facial authentication for everyone, everywhere.

Rapid authentication. Privacy is key.

Every piece of our facial authentication solution is engineered to work together — for security, privacy, reliability and speed. With a fast and easy enrollment, only registered users are authenticated — and the whole process takes less than a second.

Using TensorFlow with Intel RealSense Depth Cameras

There are many situations where using a depth camera as input into a machine learning system can offer additional benefits and features – as we previously discussed in a prior blog post “What does Depth Bring to Machine Learning.” Depth cameras have a number of advantages for a variety of machine learning problems, including lightning invariance. Depth cameras can easily adapt to a wide variety of lighting conditions, something that 2D models must be trained to compensate for. A depth camera also allows differentiation between items of different size as well as easier background segmentation, allowing the separation of individual items regardless of how complicated the background is.

Image of a small child with a bounding box showing approximated height using TensorFlow and Intel RealSense Depth cameras

Trusted and Secure.

Intel RealSense ID enables you to build a facial authentication solution with built in anti‑spoofing technology which protects against attacks using photographs, videos or high‑quality 3D masks.

Intel RealSense ID is open‑source, created with the developer in mind. It is designed to plug into your user authentication systems.

Facial authentication code samples

Code Samples

Check out how easy it is to get started with Intel RealSense ID.