Based on AIO-3399ProC AI open-source platform, industrial-grade metal case and fanless design configured, with high-efficiency
heat dissipation ability, supports for multiple operating systems which can run stable and reliable. EC-A3399ProC has ultra-strong
AI performance and rich expansion interfaces,which can be applied to various intelligent products easily.
Rockchip RK3399Pro processor adopts the architecture of dual-core Cortex-A72 and quad-core Cortex-A53 with its frequency up to 1.8GHz, showing an ultra-strong general-purpose computing performance. Quad-core ARM high-end GPU Mali-T860 integrates more bandwidth compression techniques and therefore has an excellent overall performance.
CPU internally integrates AI neural network unit NPU and supports 8bit/16bit operation with its computing performance
up to 3.0TOPS. Compared with using the traditional GPU as the large chip scheme of AI computing unit, the power
consumption of NPU is merely 1% of that of GPU. Therefore, NPU has an extremely high computing-power
t provides Rock-X SDK AI visual recognition API component library to realize machine vision recognition quickly, supports
TensorFlow/Caffe/Mxnet general-purpose model and provides AI development tools like model transformation and
end-to-side API. It also supports the development interfaces of Android NN API, RKNN cross-platform API and TensorFlow.
It has powerful hardware decoding and encoding capability, supports 4K VP9, 4K 10bits H265/H264 and 1080P multi-format
(VC-1, MPEG-1/2/4, VP8) video decoding, supports 1080P (H.264/VP8 format) video encoding.
With stable and reliable performance, EC-A3399ProC supports multiple operating systems including Android、Linux+QT and Ubuntu.
High-quality metal case and fanless design configured, with the concealed lead hole, heat-conducting aluminum alloy structure for high-efficiency heat dissipation, It can support 60℃high-temperature aging and stable operation for 7x24 hours.
Open SDK, tutorials, technical materials and development tools to make development easier and more convenient.
HDMI2.0, RS485, RS232, USB3.0 Host, Type-C（USB3.0+DP）and other interfaces owned to make it possible to be widely applied in various industries.
EC-A3399ProC can be used for AI driving monitoring, Industrial computer, AI server, Self-service retail shelves,
Face-scanning payment devices, Face recognition, Vending machine,
Smart education, etc.
AI dirving monitoring
Self-service retail shelves
Face-scanning payment devices
Rockchip RK3399Pro, Dual-core Cortex-A72+ Quad-core Cortex-A53 big.LITTLE core CPU architecture,
frequency up to 1.8G Hz
ARM® Mali-T860 MP4 Quad-core GPU
Support OpenGL ES1.1/2.0/3.0/3.1, OpenVG1.1, OpenCL, DX11
Support AFBC (frame buffer compression)
Built-in neural network processor NPU, powerful AI computing performance:
- Support 8bit/16bit operation, computing performance up to 3.0TOPS.
- Compared with using the traditional GPU as the large chip scheme of AI computing unit, the power consumption
of NPU is merely 1% of that of GPU.
- Load Caffe / Mxnet / TensorFlow models directly.
- Provide AI development tools: Support model fast conversion, support end-to-side API, support
TensorFlow / TF Lite / Caffe / ONNX / Darknet models.
- Provide AI application development interface: Support Android NN API, provide RKNN cross-platform API,
Linux support for TensorFlow development.
LPDDR3 3GB (NPU 1GB + CPU 2GB), LPDDR3 6GB (NPU 2GB + CPU 4GB)
High-speed eMMC 5.1 (16GB/32GB/64GB/128GB)
Support TF card expansion
Gigabit Ethernet Interface (RJ45)
On-board WIFI / BT module, support 2.4GHz / 5GHz dual-band WiFi, 802.11a/b/g/n/ac protocol
Support Bluetooth 4.1
Mini PCIe (Used to expand 3G/4G modules for use with Micro SIM card slots)
Support 4K VP9 and 4K 10bits H265/H264 video decoding, up to 60fps
1080P multi-format video decoding (VC-1, MPEG-1/2/4, VP8)
1080P video coding, support H.264, VP8 format
Video post processor, de-interlacing, de-noising, edge/detail/color optimization
- 1 x HDMI 2.0, support 4K@60HZ output and HDCP 1.4/2.2
- 1 x MIPI-DSI , support single-channel 1080P@60fps output and dual-channel LVDS output
(The board defaults to dual LVDS and supports 1920x1200@60fps)
- 1 x eDP 1.3 ( 4 lanes with 10.8Gbps )
- Support dual-screen identical display/dual-screen differential display
SPI×1, UART×2, Debug×1, RS485×1(CANx1 and RS485 share the same interface), RS232×1,
ADCx1, TPx1, IRx1, I2C, PWM, GPIOt
1 x HDMI 2.0 Audio output
1 x I2SFor audio input and output
1 x Speaker Dual-channel speaker（4Ω，10W 8Ω，5W）
1 x Headset output
1 x Mic Audio input
3 x USB2.0 Hub, 1 x USB3.0, 1xTYPE-C(OTG)
With a one-way infrared receiver, Support infrared remote control
Support Android, Linux, Ubuntu system
DC 12V-2A（DC5.5 × 2.1mm）
|Operating Temperature||-20 ℃||25 ℃||60 ℃|
|Storage Temperature||-40 ℃||25 ℃||125 ℃|
160 x 94 x 26 mm
AL6063 aluminum profile