Back to Blog

Nvidia/Sophon + FPGA + AI High-Performance Edge Computing Box: Smart Robot for Power Inspection

#人工智能#fpga开发#边缘计算

Focusing on the digital economy and dual-carbon economy tracks, we specialize in providing integrated digital and intelligent solutions for centralized new energy power stations and distributed integrated energy systems, adhering to a dual-driven development model of power station digitalization and integrated energy digitalization. Relying on a professional talent team and rich research experience from practical bases, we have built a mature and advanced digital and intelligent new energy R&D platform. In the field of centralized new energy power stations, we focus on the research, innovation, and application of technologies such as machine vision, artificial intelligence, digital twin, big data, and IoT, to uncover the data value of photovoltaic power stations and improve power station operation and maintenance efficiency. We independently develop software products and intelligent equipment such as regional integrated smart O&M platforms, photovoltaic power station production management systems, wind-solar-line integrated drone intelligent diagnostic platforms, IV&CV fusion diagnostic systems, photovoltaic monitoring systems, drone hangars, cleaning robots, and inspection robots, providing efficient, safe, and multi-dimensional integrated solutions for new energy power stations.

In the field of distributed integrated energy, relying on the national smart microgrid demonstration projects approved by the National Development and Reform Commission and the National Energy Administration, we conduct research on "source-grid-load-storage-charge" smart microgrid integration technology. We have successively developed key systems and equipment such as integrated energy management systems, distributed photovoltaic operation management platforms, microgrid central control units, and integrated PV-storage-charging systems. We deeply cultivate DC flexible distribution technology, launching solutions such as AC/DC hybrid microgrids, PV-storage-DC flexible, PV-storage-charging, and low-voltage area flexible interconnection. Integrating optimization and intelligent allocation to build an efficient, reliable, and safe new power system. Using technology to reduce carbon and gather energy, sharing a green and beautiful life. In the future, Shangtejie will continue to deeply cultivate the energy sector, continuously create value for customers, and strive to become a leader in digital and intelligent new energy power.

    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, its INT8 computing power reaches up to 17.6 TOPS. It can process 16 channels of high-definition video simultaneously and supports 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 video intelligent comprehensive management platform. The AI intelligent algorithms cover various algorithms for scenarios such as parks, communities, construction sites, and campuses, which can be combined on demand and configured by scenario. The video intelligent comprehensive management platform supports front-end device management, real-time video preview, alarm push, forensic snapshot, online algorithm loading and optimization, data trend analysis large screen display, etc. The device is easy to operate, plug-and-play, and also features rich northbound API interfaces, enabling upper-layer business application platforms.

    1. Product Features

Ultra-High Performance Computing and Codec Capabilities

  • Supports peak INT8 computing power of up to 17.6 TOPS or high-precision FP32 computing power of 2.2 TFLOPS;
  • 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.

Rich Built-in AI Algorithms

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

(Supports Personnel Structuring / Face Recognition / Vehicle Structuring / License Plate Recognition / Flame Detection / Smoke Detection / Smoking Detection / Phone Call Detection / Mobile Phone Play Detection / Mask Non-wearing Detection / Personnel Absenteeism Detection / Personnel Sleeping on Duty Detection / Personnel Fall Detection / Personnel Static Elimination / 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 Passenger Flow Statistics / Perimeter Intrusion Detection / Personnel Cross-border 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 Movement 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 simultaneously; when exceeding 16 AI analysis tasks, polling analysis can be performed.

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, supports fanless cooling (subject to specific model);
  • Adapts to support SATA storage, supports 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, supports 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

17.6TOPS

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 Functionality

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 Functionality (Non-Optional)

5G Wireless Module

M2.5G Module

Physical Specifications

Dimensions

LengthWidthHeight

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 functionality are optional features, not standard product configurations. Typical power consumption does not include hard drive and wireless module power consumption.