Rockchip Has Participated @ 2018 Embedded World Exhibition in Germany
From February 27 to March 1, the 2018 Embedded World Exhibition & Conference was held in Nuremberg, Germany. It is one of the world’s most influential exhibitions and the world’s largest embedded system exhibition.
In this exhibition, Rockchip showed its ultra-wide platform applications including embedded AI, industrial control, smart audio, smart vision and other development platforms.
Embedded AI platform
Firefly-RK3399 development kit is based on six-core 64-bit “server class” processor Rockchip RK3399, and with 2GB/4GB DDR3 and 16G/32GB eMMC, as well as PCIe M.2, DP 1.2, Type-C, USB3.0 and other high-performance data transmission and display interfaces. The powerful performance of Firefly-RK3399 is suitable for VR, panorama shooting, visual recognition, server, 3D and so on.
RK3288+RK1608 DEEPEYE 120 Face Recognition Engine. The DEEPEYE120 face recognition embedded engine is a small front-end computing unit developed by IntelliFusion in order to fulfill the complex edge computing needs of the public security system. It is designed using the RK3288+RK1608 embedded engine platform. At the show, the DEEPEYE120’s IFaceEngine® embedded face recognition engine solution shows mobile face recognition with mobile phone deployment.
Industrial Control Platform
RK3288 Asus Tinker board is powered by RK3288 processor, with quad-core Cortex-A17 CPU, up to 1.8GHz, supports 4K H.264 video decoding, has better 24-bit/192K audio playback capability. It is built-in 802.11 b/g/n Wi-Fi, Bluetooth 4.0 + EDR and Gigabit Ethernet. In addition to four USB ports, HDMI and MicroUSB interface for power supply, the board has a HD DSI display interface, CSI camera interface and 40pin interface (28pin GPIO interface), and Micro SD card supporting UHS-I speed.
Visual and audio platforms
RK3229 SOM Module for Android Things. RK3229 SOM module mainly consists of six parts: RK3229 master chip, power management chip, DDR3/3L, eMMC, Wi-Fi/BT, and built-in voltmeter. It is reported that the platform can support product development of both built-in battery and DC direct charge. Global developers and OEM/ODM manufacturers can use the RK3229SOM module to realize the development of intelligent IoT products such as smart voice control speakers, cameras, gateways and home appliances.
RV1108 face recognition platform. It has key technologies such as intelligent iamge processing. It is embedded high-performance CEVA XM4 vision processor DSP, up to 600MHz, 8M ISP; and supports 1440p@30fps/1080p @60fps H.264 video codec. It has built-in 128MByte DDR and is highly integrated. It supports MIPI DSI, HDMI TX, CVBS IN/OUT, 100M Ethernet, and Audio Codec. It has RV1108-based viewing algorithm IP and a completed algorithm matrix. From face detection to human detection, from tracking to recognition, all can be performed in the local computing operation, without relying on computer resources and has low power consumption thus its performance is enhanced several times. Such as face detection, the platform can achieve 120ms detection speed and 90% detection rate under 1080P resolution.