The Qualcomm QCS6490 is a system-on-chip (SoC) designed for industrial and commercial iot applications that supports Wi-Fi 6E connectivity for advanced iot devices, as well as advanced cameras, Artificial Intelligence, and computing capabilities for powerful performance at low power consumption.The chip combines a Qualcomm Kryo™ 670 CPU and a Qualcomm Hexagon processor with a converged AI accelerator architecture that delivers powerful connectivity and computing performance. In addition to supporting Android, the Qualcomm QCS6490 can also run Linux, Ubuntu, and Microsoft Windows IoT Enterprise operating systems.

The following is an introduction to the use of Qualcomm QCS6490 application in AI smart electronic fence display:

Real-time monitoring and intrusion detection:

- Using the QCS6490's high-performance AI engine, Smart electronic fencing can instantly monitor the environment to detect and identify suspicious activity.

For example, people, vehicles and animals can be identified and distinguished to improve safety and alert accuracy.

Multi-scenario application integration:

- Supports the integration of multiple sensors and cameras for different scenarios, such as home security, industrial surveillance and smart city infrastructure.

- Can work with other smart city systems, such as smart transportation and smart lighting, to improve overall performance.

►Thundercomm Turbox C6490 Introduction

The Thunderconn Turbox C6490 development board is based on the Qualcomm QCS6490 processor, a 6-nanometer process processor with superior performance and energy efficiency, and up to 12.5 TOPS of AI computing power. The board supports Wi-Fi 6E, long range Bluetooth, and optional 5G NR connectivity, and comes with five 4-channel MIPI CSI D-PHY interfaces (two of which support 3-channel MIPI CSI C-PHY for up to 48M cameras). In addition, the C6490 development board also has a rich set of peripheral interfaces, including concurrent use of USB 3.1 and USB 2.0 and PCIE interfaces, making it a high-performance AIoT development board. 

The main components of the development board include the main IO board, the adapter board, the audio board and the sensor board, which are all designed to meet different development needs. The main I/O board supports multiple ports to connect the LCD panel, camera module, SD card, SIM card, and USB devices.

►Executive Program

This scheme uses the Yolo-NAS pedestrian recognition AI model and sets the warning area manually. 

When the AI makes an inference about the pedestrian, it gives a mark. When the pedestrian's mark is in the warning area for about 1 second, 

the system will issue a warning and send pictures. For the part of sending alerts, you can use the API of the back-end Server 

of Line Notify and other third-party communication apps to connect in series. Through the communication software, 

relevant personnel can receive the alerts and current photo.You can make judgments based on the photos, for example, on the right of the scene application diagram.

The left hand side of the scene application diagram is the main screen of the electronic fence APP. 

The light blue area in the screen is the warning area. Use gestures to drag and move to adjust the warning area scope. 

The right hand side of the screen is the control setting, which controls different hardware inference and screen enlargement 

and reduction.

►References

1. Thundercomm TurboX C6490 Development Kit

2. 高通QCS6490

►Frequent Q&A

►Scene application diagram

►Display Board Photo

►Solution Bolck Diagram

►Core Technical Advantages

1. High-performance computing: multi-core Kryo CPU and Adreno GPU provide powerful computing and graphics processing capabilities

2. AI computing power: Integrate Hexagon DSP and Qualcomm AI engine to provide AI computing power of up to 12 TOPS

3. Low power consumption design: high energy consumption ratio and intelligent power management, suitable for equipment that runs for a long time

4. Scalability and flexibility: supports a variety of interfaces and peripherals, and provides a wealth of software development tools and SDKs

►Solution specifications

1. AI : 6th gen Qualcomm AI Engine 2. Connectivity WLAN : Wi-Fi 6 (802.11ax) and Wi-Fi 6E (6 GHz), Bluetooth® 5.2 and FM supported. Uplink/Downlink MU-MIMO, 4K QAM, 160MHz channels (5 & 6 GHz) 3. CPU : 8x Kryo 670 CPU from 1.9 up to 2.7 GHz 4. GPU : Adreno GPU 643 with support for Open GL ES 3.2, Open CL 2.0, Vulkan 1.x, DX FL 12 5. DSP : Compute Hexagon DSP with dual HVX and 4K HMX 6. Memory & Storage : Dual channel, non-PoP LPDDR5/LPDDR4X SDRAM, UFS 2.x/3.1, two-lane HS gear 4, SD v3.0, eMMC 5.1, PCIe two-lane NVMe Display Support : Adreno 1075 DPU 7. Camera Support : Qualcomm Spectra™ ISP 570L 64 MP / 36 + 22 MP / 3x22 MP at 30fps ZSL 192 MP non-ZSL 8. Video : Up to 4K60 decode for H.264/H.265/VP9, Up to 4K30 encode for H.264/H.265; Support for HDR10 and HDR10+ playback 9. Location : GPS, GLONASS, NavIC, BeiDou, Galileo, QZSS, and SBAS 10. Operating System : Android, Ubuntu, Yocto, Windows