Back to Blog

Nvidia/Sophon +FPGA+AI High-Compute Edge Computing Box:

#人工智能#边缘计算

China University of Petroleum (Huadong) is a national key university directly under the Ministry of Education, one of the universities included in "Project 211" and the "Innovation Platform for Advantageous Disciplines under Project 985" initiatives, and equipped with a graduate school. The university is jointly built by the Ministry of Education and five major energy enterprise groups, and by the Ministry of Education and the People's Government of Shandong Province. It is an important base for cultivating high-level talents in the petroleum and petrochemical industries, renowned as "the cradle of petroleum technology and management talents." It has now become a university primarily focused on engineering, with distinct petroleum and petrochemical characteristics, and coordinated development across multiple disciplines. It was included in the national "Double First-Class" Initiative in both 2017 and 2022.

Under the overall framework of a multi-layer closed-loop management system in the oil and gas industry, closely integrating with the development ideas and technological trends of industrial IoT platforms, and focusing on the actual needs of the oil and gas production business, a cloud-deployed big data platform software for the industrial sector has been developed. The platform is entirely based on a B/S (Browser/Server) architecture design, utilizing technologies such as IoT and cloud computing to provide one-stop services including device access, control system operation monitoring, and equipment asset management. It achieves unified data collection, storage, computation, display, and sharing, and builds systems for equipment monitoring, equipment management, and equipment operation and maintenance, centered around equipment operation and management, thereby supporting the construction and rapid deployment of IoT platform applications.

    1. Product Overview

The XM-AIBOX-16 Smart Edge Analysis All-in-One Machine is a high-performance, low-power edge computing product. Equipped with the domestic TPU chip BM1684, it delivers up to 17.6 TOPS of INT8 computing power, capable of processing 16 channels of high-definition video simultaneously, and supporting hardware decoding of 32 channels of 1080P HD video and 2 channels of encoding.

This product highly integrates high-precision AI intelligent algorithms based on computer vision and deep learning networks, as well as a comprehensive intelligent video management platform. The AI intelligent algorithms cover various scenarios such as parks, communities, construction sites, and campuses, and can be combined on demand and configured per scenario. The comprehensive intelligent video management platform supports front-end device management, real-time video preview, alarm push, evidence capture, online algorithm loading and optimization, and large-screen display of data situation analysis. The device is easy to operate and plug-and-play, and also features rich northbound API interfaces to empower upper-layer business application platforms.

    1. Product Features

Ultra-High Performance Computing and Codec Capabilities

  • Supports up to 17.6 TOPS of INT8 peak computing power or 2.2 TFLOPS of FP32 high-precision computing power;
  • Supports full-process handling of up to 16 channels of 1080P HD video;
  • Supports hardware decoding of up to 32 channels of H.264/H.265 1080P@25FPS video;
  • Supports hardware encoding of up to 2 channels of H.264/H.265 1080P@25FPS video.

Built-in Rich AI Algorithms

  • Built-in 30+ AI algorithms, supporting free matching and custom combinations;

(Supports Person Structuring / Face Recognition / Vehicle Structuring / License Plate Recognition / Flame Detection / Smoke Detection / Smoking Detection / Phone Call Detection / Mobile Phone Usage Detection / Mask Non-Compliance Detection / Personnel Absenteeism Detection / Personnel Sleeping on Duty Detection / Personnel Fall Detection / Personnel Static Elimination / Area People Counting / Insufficient People in Area / Area Overcrowding / Abnormal People Count in Area / Area Intrusion Detection / Work Uniform Detection / Safety Helmet Detection / Reflective Vest Detection / Electric Bicycle Detection / Standardized Parking (Illegal Parking) / Entrance/Exit Passenger Flow Statistics / Perimeter Climbing Intrusion / Personnel Cross-Border Detection / Loitering Detection / Fire Lane Occupancy / Fire Escape Route Occupancy / Trash Not in Bin Detection / Overflowing Trash Bin Detection / Trash Disposal Reminder / Camera Abnormal Displacement Detection, and other algorithms.)

  • Each video channel supports up to 3 AI analysis tasks running simultaneously;
  • Supports up to 16 video AI analysis tasks running concurrently; if more than 16 AI analysis tasks are required, they can be analyzed in a polling manner.

Rich Interfaces, Flexible Deployment

  • Supports rich interfaces: 1000M Ethernet port, USB3.0/USB2.0, HDMI, RS-485, RS-232;
  • Supports wide operating temperature range from -20℃ to +60℃;
  • Supports IP30 protection level, fanless cooling (subject to specific model);
  • Adapts to and supports SATA storage, with 2TB storage capacity (subject to specific model);
  • Optional support for LTE wireless backhaul function (subject to specific model);
  • Northbound interfaces: Supports HTTP protocol, MQTT protocol, GB28281;
  • Southbound interfaces: Supports GB28281, Onvif, RTSP.

High Reliability, Encryption Protection

  • Supports high-capacity eMMC with development support for primary and backup partitions;
  • Supports abnormal fault alarm and protection handling mechanisms;
  • Supports programmable encryption chip for privacy information protection.

Easy-to-Use Toolchain, Flexible Development

  • One-stop deep learning development toolkit Sophon SDK;
  • Supports mainstream deep learning frameworks such as Caffe/DarkNet/TensorFlow/PyTorch/MXNet/ONNX/PaddlePaddle;
  • Supports mainstream network models for classification and detection, and custom operator development;

Supports Docker containerization for rapid deployment of algorithm applications.

    1. Technical Specifications

Specifications

Model Version

XM-AIBOX-16

Technical Specifications

Chip

TPU

BM1684

CPU

8-core A53@2.3GHz

AI Computing Power

INT8

17.6 TOPS

FP32

2.2 TFLOPS

Video/Image Codec

Video Decoding Capability

H.264/H.265: 1080P @960fps

Video Decoding Resolution

8K / 4K / 1080P / 720P / D1 / CIF

Video Encoding Capability

H.264/H.265: 1080P @50fps

Video Encoding Resolution

4K / 1080P / 720P / D1 / CIF

Image Encoding/Decoding Capability

480 frames/sec@1080P

Max Image Decoding Resolution

32768 * 32768

Memory and Storage

Memory

12 GB

eMMC

32 GB

External Interfaces

Network Port

10/100/1000Mbps Adaptive *2

USB

USB3.0 *2

N/A

Storage

MicroSD *1

Display

HDMI *1

N/A

Serial Port

RS232 *1/RS485 *1/Custom I/O

Extended Storage

SSD (Optional)

2TB (Optional)

N/A

Wireless Function

4G/5G Wireless Module (Optional)

Mini-PCIe 4G Module

Antenna (Optional)

SMA Female *2 (Wi-Fi)

SMA Female *4 (5G)

SIM

Standard SIM Card Slot

Wireless Function (Non-Optional)

5G Wireless Module

M.2 5G Module

Physical Specifications

Dimensions

LWH

188 mm * 148 mm * 44.5 mm

Power Supply and Consumption

Power Supply

DC 12V

Typical Power Consumption

≤23.5W

≤19W

Note: Hard drive and wireless functions are optional and not standard product configurations. Typical power consumption does not include power consumption of hard drive and wireless modules.