Back to Blog

Nvidia/Sophon + FPGA + High-Performance AI Edge Computing Box: Measurement, Control, and Inspection Smart Robot

#人工智能#边缘计算#机器人

We are a high-tech enterprise integrating R&D, production, manufacturing, and sales, and a technological leader in the field of "conveyor belt intelligent inspection" in China. The company has successively obtained honorary qualifications such as National High-tech Enterprise, Taiyuan Municipal Enterprise Technology Center, Taiyuan Technology Innovation Demonstration Enterprise, Shanxi Private Technology Enterprise, Shanxi "Specialized, Refined, Unique, and Innovative" SME, Shanxi "Four New" SME, Taiyuan Small and Micro Credit Enterprise, Taiyuan High-tech Zone "Double Hundred" Enterprise, and Shanxi Comprehensive Reform Zone Innovation and Entrepreneurship Enterprise. The company currently holds 3 trademark registrations, 4 software copyright patents, and 51 national patent certificates, continuously achieving breakthroughs in the intelligent inspection of conveyor belt safe operation, with its technological level consistently leading the industry's development.

Smart inspection robots can perform functional monitoring such as infrared temperature measurement, meter recognition, vibration measurement, and sound recognition, uploading the recognition results to a data center to ensure data accuracy and timeliness, while also adapting to more complex working environments. It is a complex system integrating robot body technology, non-contact power equipment detection technology, multi-sensor fusion technology, and navigation and behavior planning technology. It features reliable autonomous path planning, high-precision and highly flexible autonomous driving capabilities in complex environments, and rich I/O options for enhanced scalability.

    1. Product Overview

The XM-AIBOX-32 Smart Edge Analysis All-in-One Machine is a high-performance, low-power edge computing product. Equipped with the BM1684X main chip, it boasts INT8 computing power up to 32 TOPS, FP16/BF16 computing power up to 16 TFLOPS, and FP32 computing power up to 2 TFLOPS. It can simultaneously process 32 channels of high-definition video, supporting hardware decoding for 32 channels of 1080P HD video and encoding for 12 channels.

This product highly integrates high-precision AI intelligent algorithms based on computer vision and deep learning networks, as well as a comprehensive video intelligent management platform. The AI intelligent algorithms cover various scenarios such as industrial parks, communities, construction sites, and campuses, allowing for on-demand combination and scenario-based configuration. The comprehensive video intelligent 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 situational analysis. The device is easy to operate, plug-and-play, and features rich northbound API interfaces to empower upper-layer business applications.

    1. Product Features

Ultra-High Performance Computing and Encoding/Decoding Capabilities

  • Supports peak INT8 computing power up to 32 TOPS;
  • Supports FP16/BF16 half-precision computing power up to 16 TFLOPS;
  • Supports FP32 high-precision computing power of 2 TFLOPS;
  • Supports hardware decoding for up to 32 channels of H.264/H.265 1080P@25FPS video;
  • Supports hardware encoding for up to 12 channels of H.264/H.265 1080P@25FPS video.

Rich Built-in 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 Play Detection / Mask Not Worn Detection / Personnel Absenteeism Detection / Personnel Sleeping on Duty Detection / Personnel Fall Detection / Personnel Electrostatic Discharge / Area People Counting / Area Underpopulation / Area Overpopulation / Area Abnormal Population / Area Intrusion Detection / Work Uniform Detection / Safety Helmet Detection / Reflective Vest Detection / Electric Bicycle Detection / Standardized Parking (Illegal Parking) / Entrance/Exit Flow Statistics / Perimeter Crossing Intrusion / Personnel Boundary Crossing Detection / Area 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 32 video AI analysis tasks running simultaneously; if more than 32 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 rating, fanless cooling (subject to specific model);
  • Adapts to support SATA storage, supporting 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/secondary 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 classification and detection network models, supports custom operator development;

Supports Docker containerization for rapid deployment of algorithm applications.

    1. Technical Specifications

Specifications

XM-AIBOX-32

Technical Specifications

Chip

SOC

BM1684X

CPU

8-core A53@2.3GHz

AI Computing Power

INT8

32 TOPS

BF16/FP16

16 TFLOPS

FP32

2 TFLOPS

Video/Image Encoding & Decoding

Video Decoding Capability

H.264/H.265: 1080P @800fps

Video Decoding Resolution

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

Video Encoding Capability

H.264/H.265:1080P @300fps

Video Encoding Resolution

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

Image Encoding/Decoding Capability

600 images/sec (JPEG)

Max Image Decoding Resolution

32768 * 32768

Memory & Storage

Memory

16 GB

eMMC

64 GB

External Interfaces

Ethernet Port

10/100/1000Mbps Adaptive *2

USB

USB3.0 *2, USB2.0 *2

Storage

MicroSD *1

Display

HDMI *1

Serial Port

RS232 *1/RS485 *1

Extended Storage

SSD (Optional)

M.2 SSD

Wireless Function

4G/5G Wireless Module (Optional)

Mini-PCIe 4G Module/M.2 5G Module

Antenna

SMA Female *1 (LTE)

SMA Female *4 (5G), requires motherboard replacement

SMA Female *2 (Wi-Fi)

SMA Female *1 (BT)

SIM

Standard SIM Card Slot

Wi-Fi/BT

Wi-Fi supports 802.11a/b/g/n/ac

BT5.0

Physical Specifications

Dimensions

LengthWidthHeight

210 mm * 130 mm * 44.5 mm

Power Supply & Consumption

Power Supply

DC 12V

Typical Power Consumption

≤20W

Note: Hard drive, 4G/5G functions are optional and not standard product configurations. Typical power consumption does not include hard drive or wireless module power consumption.