Back to Blog

Sophgo BM1684 + FPGA + AI + Camera Inference Edge Computing Box

#人工智能#大数据

Powered by the Sophgo AI computing chip BM1684, this edge computing box is designed for AI inference. It efficiently supports all mainstream AI algorithms on the market, enabling applications such as video structuring, facial recognition, behavior analysis, and status monitoring. It delivers AI empowerment to smart city, intelligent transportation, smart energy, smart finance, smart telecom, and smart industrial fields.

Product Specifications

Processor

Chip

Sophgo BM1684

CPU

8-core ARM A53, 2.3GHz clock frequency

AI Computing Power

INT8

17.6 TOPS

FP32

2.2 TFLOPS

Video/Image Codec

Video Decoding Capability

960fps 1080p (32 channels 1080P@30FPS)

Video Encoding Capability

50fps 1080p (2 channels 1080P@25FPS)

Image Codec Capability

480 images/sec 1080P

Expansion Slots

Memory

12GB

eMMC

32GB

External Interfaces

Ethernet

4 x 10/100/1000Mbps adaptive

USB

2 x USB3.0

Debug Port

1 x Type-C debug

Storage

1 x TF Card

Display

1 x HDMI

Phoenix Terminal

Supports 2 x RS-485, 2 x relays, 2 x DI, 2 x DO

Expansion Interface

M.2

3 slots: 1 x SSD, 1 x WIFI, 1 x 4G/5G

SIM

1

Temperature and Humidity

Operating Temperature

-20°C to +65°C

Operating Humidity

5% to 95%

Power

Supply

DC 12V/3A

Operating System

Version

Ubuntu 20.04

Physical Characteristics

Product Dimensions

200 (L) x 133 (W) x 47 (H) mm