Type | Product Line |
---|---|
Industry | Artificial intelligence, Camera, Depth perception, 3D reconstruction |
Founded | 2015 |
Headquarters | Santa Clara, California |
Products | Intel RealSense |
Parent | Intel |
Website | www |
Developer | Intel RealSense |
---|---|
Manufacturer | Intel |
Type | Cameras, Technology |
Intel RealSense Technology, formerly known as Intel Perceptual Computing, is a product range of depth and tracking technologies designed to give machines and devices depth perception capabilities. The technologies, owned by Intel are used in autonomous drones, robots, AR/VR, smart home devices amongst many others broad market products.
The RealSense products are made of Vision Processors, Depth and Tracking Modules, and Depth Cameras, supported by an open source, cross-platform SDK in an attempt to simplify supporting cameras for third party software developers, system integrators, ODMs and OEMs. [1]
Intel began producing hardware and software that utilized depth tracking, gestures, facial recognition, eye tracking, and other technologies under the branding Perceptual Computing in 2013. [2] [3] According to Intel, much of their research into the technologies is focused around "sensory inputs that make [computers] more human like". They initially hoped to begin including 3D cameras that could support their Perceptual Computing as opposed to traditional 2D cameras by late 2014. [4]
In 2013, Intel ran a competition among seven teams to create software highlighting the capabilities of its Perceptual Computing technology entitled "Intel Ultimate Coder Challenge: Going Perceptual". [3] [5]
In 2014, Intel rebranded their Perceptual Computing line of technology as Intel RealSense. [2] [6]
Intel RealSense Group supports multiple depth and tracking technologies including Coded Light Depth, Stereo Depth and Positional Tracking. [7]
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. [8]
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.
The Intel RealSense Vision Processor D4 series are vision processors based on 28 nanometer (nm) process technology to compute real-time stereo depth data. They utilise a depth algorithm that enables more accurate and longer range depth perception than previously available. There are two products in this family: RealSense Vision processor D4 and RealSense Vision Processor D4m.[ citation needed ]
The Intel RealSense Depth Module D400 Series is designed for easy integration to bring 3D into devices and machines. Intel also released the D415 and D435 in 2018. 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. The Intel D415 is designed for more precise measurements.[ citation needed ]
The Intel RealSense Depth Camera D435 is ideal for capturing stereo depth in a variety of applications that help perceive the world in 3D. [9] [10] [11] [12] [13] [14] [15] [16] [17] [18] [19] [20] [21] [22]
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. [23] Additionally, Razer and Creative offered consumer ready standalone webcams with the Intel RealSense camera built into the design.: [24] Razer Stargazer and the Creative BlasterX Senz3D. [25]
This is a stand-alone camera that can be attached to a desktop or laptop computer. [26] It is intended to be used for natural gesture-based interaction, face recognition, immersive, video conferencing and collaboration, gaming and learning and 3D scanning. [27] There was also version of this camera to be embedded into laptop computers. [23]
Snapshot is a camera system 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 depth photo filters. [28] 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. The Dell Venue 8 and 10 7000 Series Android tablets are equipped with this camera. [29]
Rear-mounted camera for Microsoft Surface or a similar tablet, like the HP Spectre X2. [30] 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. The R200 is a stereo camera and is able to obtain accurate depth outdoors as well as indoors. [31]
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. [32]
Specifications: Intel RealSense Depth Camera D415, D435 and D455 [33] [34] [35] [36]
D415 | D435 | D455 | |
---|---|---|---|
Use Environment | Indoor/Outdoor | ||
Depth Technology | Active infrared (IR) stereo | ||
IR Projector & Left/Right Camera Type | Standard | Wide | |
Shutter Type | Rolling | Global | |
Image Sensor Module | OV2740 (OV02740-H34A-Z) [37] | OV9782 (OV09782-GA4A) [38] | |
Image Sensor Technology | PureCel HDR [37] | OmniPixel3-GS [38] | |
Image Sensor Size | 1⁄6 inch, 3855 µm × 2919 µm [37] | 1⁄4 inch, 3896 µm × 2453 µm [38] | |
Image Sensor Pixel Size | 1.4 µm × 1.4 µm [37] | 3 µm × 3 µm [38] | |
Vision Processor Board | RealSense Vision Processor D4 | ||
Depth Sensor Module | RealSense Module D415 | RealSense Module D430 + RGB Camera | RealSense Module D450 |
Depth Field of View for HD | H:65°±2 V:40°±1 D:72°±2 | H:87°±3 V:58°±1 D:95°±3 | |
Depth Field of View for VGA | H:50°±2 V:40°±1 D:61°±2 | H:75°±3 V:62°±1 D:89°±3 | |
Depth Resolution and Framerate | Up to 1280px × 720px @ 90fps | ||
Minimum Depth Distance at Maximum Resolution | 45 cm / 17.7" | 28 cm / 11.0" | 52 cm / 20.5" |
Depth Accuracy | <2% at 2.0m / 2.2yd | <2% at 4.0m / 4.4yd | |
Ideal and Maximum Range | 0.5m to 3m / 0.6yd to 3.3yd | 0.3m to 3m / 0.3yd to 3.3yd | 0.6m to 6m / 0.3yd to 6.6yd |
RGB Resolution, Framerate and Aspect Ratio | 1920px × 1080px @ 30fps (16:9) | 1280px × 800px @ 30fps (8:5) | |
RGB Field of View | H:69.4° V:42.5° D:77.0° | H:91.2° V:65.5° D:100.6° | |
RGB Lens Distortion | ≤1.5% | ||
Device Dimensions | 99mm × 20mm × 23mm | 90mm × 25mm × 25mm | 124mm × 26mm × 29mm |
Connector | USB Type-C 3.1 Gen 1 | ||
Mounting Mechanisms | One 1/4-20UNC thread mounting point | ||
Two M3 thread mounting points | Two M4 thread mounting points |
Specifications: Intel RealSense Vision Processor D4 Series [39]
(Not available separately as these are just the bare PCB Vision Processor boards, only used as basis for the RealSense Depth Camera series)
RealSense Vision Processor D4 | RealSense Vision Processor D4M | |
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 |
Specifications: Intel Stereo DepthModule SKUs [40]
(Not available separately as these are just the bare PCB Depth Sensor Modules, only used as basis for the RealSense Depth Camera series)
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+ |
Havok is a middleware software suite developed by the Irish company Havok. Havok provides a physics engine component and related functions to video games.
A stereo camera is a type of camera with two or more lenses with a separate image sensor or film frame for each lens. This allows the camera to simulate human binocular vision, and therefore gives it the ability to capture three-dimensional images, a process known as stereo photography. Stereo cameras may be used for making stereoviews and 3D pictures for movies, or for range imaging. The distance between the lenses in a typical stereo camera is about the distance between one's eyes and is about 6.35 cm, though a longer base line produces more extreme 3-dimensionality.
OpenCV is a library of programming functions mainly for real-time computer vision. Originally developed by Intel, it was later supported by Willow Garage, then Itseez. The library is cross-platform and licensed as free and open-source software under Apache License 2. Starting in 2011, OpenCV features GPU acceleration for real-time operations.
Communications servers are open, standards-based computing systems that operate as a carrier-grade common platform for a wide range of communications applications and allow equipment providers to add value at many levels of the system architecture.
The Classmate PC, formerly known as Eduwise, is Intel's entry into the market for low-cost personal computers for children in the developing world. It is in some respects similar to the One Laptop Per Child (OLPC) trade association's Children's Machine (XO), which has a similar target market. Although made for profit, the Classmate PC is considered an Information and Communication Technologies for Development project (ICT4D). Introduced in 2006, the device falls into the then popular category of netbooks.
Microsoft PixelSense was an interactive surface computing platform that allowed one or more people to use and touch real-world objects, and share digital content at the same time. The PixelSense platform consists of software and hardware products that combine vision based multitouch PC hardware, 360-degree multiuser application design, and Windows software to create a natural user interface (NUI).
OpenCL is a framework for writing programs that execute across heterogeneous platforms consisting of central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), field-programmable gate arrays (FPGAs) and other processors or hardware accelerators. OpenCL specifies programming languages for programming these devices and application programming interfaces (APIs) to control the platform and execute programs on the compute devices. OpenCL provides a standard interface for parallel computing using task- and data-based parallelism.
A time-of-flight camera, also known as time-of-flight sensor, is a range imaging camera system for measuring distances between the camera and the subject for each point of the image based on time-of-flight, the round trip time of an artificial light signal, as provided by a laser or an LED. Laser-based time-of-flight cameras are part of a broader class of scannerless LIDAR, in which the entire scene is captured with each laser pulse, as opposed to point-by-point with a laser beam such as in scanning LIDAR systems. Time-of-flight camera products for civil applications began to emerge around 2000, as the semiconductor processes allowed the production of components fast enough for such devices. The systems cover ranges of a few centimeters up to several kilometers.
Rockchip is a Chinese fabless semiconductor company based in Fuzhou, Fujian province. Rockchip has been providing SoC products for tablets & PCs, streaming media TV boxes, AI audio & vision, IoT hardware since founded in 2001. It has offices in Shanghai, Beijing, Shenzhen, Hangzhou and Hong Kong. It designs system on a chip (SoC) products, using the ARM architecture licensed from ARM Holdings for the majority of its projects.
Nvidia 3D Vision is a discontinued stereoscopic gaming kit from Nvidia which consists of LC shutter glasses and driver software which enables stereoscopic vision for any Direct3D game, with various degrees of compatibility. There have been many examples of shutter glasses. Electrically controlled mechanical shutter glasses date back to the middle of the 20th century. LCD shutter glasses appeared in the 1980s, one example of which is Sega's SegaScope. This was available for Sega's game console, the Master System. The NVIDIA 3D Vision gaming kit introduced in 2008 made this technology available for mainstream consumers and PC gamers.
PrimeSense was an Israeli 3D sensing company based in Tel Aviv. PrimeSense had offices in Israel, North America, Japan, Singapore, Korea, China and Taiwan. PrimeSense was bought by Apple Inc. for $360 million on November 24, 2013.
The Lenovo IdeaCentre is a line of consumer-oriented desktop computers designed, developed and marketed by Lenovo. The first IdeaCentre desktop, the IdeaCentre K210, was announced by Lenovo on June 30, 2008 as a consumer-focussed alternative to the business-oriented ThinkCentre and ThinkStation brandnames acquired from IBM. While the IdeaCentre line consists entirely of desktops, they share a common design language with the IdeaPad line of laptops and hybrids. One such feature is Veriface facial recognition technology.
Omek Interactive was a venture-backed technology company developing advanced motion sensing software for human-computer interaction. Omek was co-founded in 2007 by Janine Kutliroff and Gershom Kutliroff.
Intel Quark is a line of 32-bit x86 SoCs and microcontrollers by Intel, designed for small size and low power consumption, and targeted at new markets including wearable devices. The line was introduced at Intel Developer Forum in 2013, and discontinued in January 2019.
Intel Galileo is the first in a line of Arduino-certified development boards based on Intel x86 architecture and is designed for the maker and education communities. Intel released two versions of Galileo, referred to as Gen 1 and Gen 2. These development boards are sometimes called "Breakout boards".
Tango was an augmented reality computing platform, developed and authored by the Advanced Technology and Projects (ATAP), a skunkworks division of Google. It used computer vision to enable mobile devices, such as smartphones and tablets, to detect their position relative to the world around them without using GPS or other external signals. This allowed application developers to create user experiences that include indoor navigation, 3D mapping, physical space measurement, environmental recognition, augmented reality, and windows into a virtual world.
Movidius is a company based in San Mateo, California, that designs low-power processor chips for computer vision. The company was acquired by Intel in September 2016.
{{cite web}}
: CS1 maint: numeric names: authors list (link){{cite web}}
: CS1 maint: location (link){{cite web}}
: CS1 maint: location (link)