Mobileye's System-on-Chip Delivers 2nd Generation Solution for Visual Recognition and Interpretation
Amstelveen, Netherlands -- February 27, 2008 - The Mobileye EyeQ2™ reflects a new philosophy of vision based processing platform, includes optimal combination for Vision Scalar and Vector processing on a single die, based on Mobileye algorithm knowledge.
EyeQ2™, Mobileye's System-on-Chip (SoC) delivers a 2nd generation solution for computationally intensive applications for real-time visual recognition and scene interpretation and has cabin-grade automotive qualification for use in intelligent vehicle systems. The Mobileye EyeQ2™ reflects a new Philosophy of Vision based processing platform, includes optimal combination for Vision Scalar and Vector processing on a single die, based on Mobileye algorithm knowledge.
Mobileye EyeQ2™ will be launched in 2009 start of production involving a consolidated feature package with lanes, vehicles, pedestrian and fusion. Manufactured by STMicroelectronics, the concept behind the EyeQ2 is twofold:
- Mobileye EyeQ2™ is six times more powerful than the first generation Mobileye EyeQ™, thus allowing a higher degree of feature consolidation
- Mobileye EyQ2™ is multi-threaded thus allowing for an easier combination of different IPs, some from Mobileye and others from 3rd parties working in tandem with Mobileye software.
• Programmable ASIC
• Parallelism, 11 computing processors working simultaneously
• On chip 1M Byte of SRAM
• Vision application minded design
• Automotive qualified
The chip architecture is designed to run a full-fledged application on a single chip, and is completely programmable to accommodate a wide range of visual processing applications beyond automotive specific applications.
Mobileye EyeQ2™ is manufactured using the leading STMicroelectronics CMOS 90nm-micron technology, operating at 332Mhz. To optimize costp erformance, all peripheral interfaces are integrated in to the SoC, including dual CAN Controllers; dual UART, I2C, Mobile DDR SDRAM controller, parallel I/O, dual Video image data capture and video out units.
Mobileye’s SDK (System Development Kit) for Mobileye EyeQ2™ provides a well defined working environment for use by developers and programmers of applications based on the Mobileye EyeQ2™ SW and is highly suited also for inexperienced developers. Provided with Mobileye Vision algorithms as libraries.
The Mobileye EyeQ2™ architecture consists of two floating point, hyper-thread 64bit RISC 34KMIPS CPUs, five Vision Computing Engines (VCE), three Vector Microcode Processors (VMP™), Denali 64bit Mobile DDR Controller, 128bit internal Sonics Interconnect, dual 16bit Video input and 18bit Video output controllers, 16 channels DMA and several peripherals. The MIPS34K CPU manages the five VCEs, three VMP™ and the DMA, the second MIPS34K CPU and the multi-channel DMA as well as the other Peripherals. The five VCEs, three VMP™ and the MIPS34K CPU perform all the intensive vision computations required by the applications such as tracking and pattern classification.
EyeQ2™, Mobileye's System-on-Chip (SoC) delivers a 2nd generation solution for computationally intensive applications for real-time visual recognition and scene interpretation and has cabin-grade automotive qualification for use in intelligent vehicle systems. The Mobileye EyeQ2™ reflects a new Philosophy of Vision based processing platform, includes optimal combination for Vision Scalar and Vector processing on a single die, based on Mobileye algorithm knowledge.
Mobileye EyeQ2™ will be launched in 2009 start of production involving a consolidated feature package with lanes, vehicles, pedestrian and fusion. Manufactured by STMicroelectronics, the concept behind the EyeQ2 is twofold:
- Mobileye EyeQ2™ is six times more powerful than the first generation Mobileye EyeQ™, thus allowing a higher degree of feature consolidation
- Mobileye EyQ2™ is multi-threaded thus allowing for an easier combination of different IPs, some from Mobileye and others from 3rd parties working in tandem with Mobileye software.
• Programmable ASIC
• Parallelism, 11 computing processors working simultaneously
• On chip 1M Byte of SRAM
• Vision application minded design
• Automotive qualified
The chip architecture is designed to run a full-fledged application on a single chip, and is completely programmable to accommodate a wide range of visual processing applications beyond automotive specific applications.
Mobileye EyeQ2™ is manufactured using the leading STMicroelectronics CMOS 90nm-micron technology, operating at 332Mhz. To optimize costp erformance, all peripheral interfaces are integrated in to the SoC, including dual CAN Controllers; dual UART, I2C, Mobile DDR SDRAM controller, parallel I/O, dual Video image data capture and video out units.
Mobileye’s SDK (System Development Kit) for Mobileye EyeQ2™ provides a well defined working environment for use by developers and programmers of applications based on the Mobileye EyeQ2™ SW and is highly suited also for inexperienced developers. Provided with Mobileye Vision algorithms as libraries.
The Mobileye EyeQ2™ architecture consists of two floating point, hyper-thread 64bit RISC 34KMIPS CPUs, five Vision Computing Engines (VCE), three Vector Microcode Processors (VMP™), Denali 64bit Mobile DDR Controller, 128bit internal Sonics Interconnect, dual 16bit Video input and 18bit Video output controllers, 16 channels DMA and several peripherals. The MIPS34K CPU manages the five VCEs, three VMP™ and the DMA, the second MIPS34K CPU and the multi-channel DMA as well as the other Peripherals. The five VCEs, three VMP™ and the MIPS34K CPU perform all the intensive vision computations required by the applications such as tracking and pattern classification.
Related Semiconductor IP
- 5G-NTN Modem IP for Satellite User Terminals
- 14-bit 12.5MSPS SAR ADC - Tower 65nm
- 5G-Advanced Modem IP for Edge and IoT Applications
- TSN Ethernet Endpoint Controller 10Gbps
- 13ns High-Speed Comparator with no Hysteresis
Related News
- NeuriCam chooses ARC microprocessor for automotive and fingerprint recognition applications
- Bops discloses new cores targeted at improving 3D graphics and visual realism
- Altera Endorses Summit Design's Visual IP as the Platform for Delivering Protected Simulation Models for Its IP MegaCore Functions
- Summit Design Launches Visual IP Version 3.0 for PC Platform Support
Latest News
- MIPS, GlobalFoundries Bet on Physical AI
- IPrium releases LunaNet AFS LDPC Encoder and Decoder for Lunar Navigation Satellite Systems
- Quintauris Introduces Altair: The Unified RISC-V Profile for Embedded Systems
- IAR accelerates SDV development with Infineon DRIVECORE bundles and AURIX™ RISC-V Debug capabilities
- Ceva Launches PentaG-NTN™ 5G Advanced Modem IP, Enabling Satellite-Native Innovators to Rapidly Deploy Differentiated LEO User Terminals