Qualcomm continues to announce new product families purpose-built for IoT applications. One of the first additions to the IoT chipset family was QCS605, along with software and reference designs. The 10nm SoCs include advanced camera processing software, machine learning, and computer vision software development kits (SDKs), plus proven connectivity and security technologies — all of which are designed explicitly for next-generation IoT devices.

AI capabilities on the edge device reduces the stringent cloud and connectivity bandwidth requirements and also enhances security and system performance. Processing this data at the edge requires significant computing and processing capabilities, which Qualcomm Snapdragon Vision intelligence platform delivers by leveraging their signature heterogeneous computing, which is enabled through the following features:

• Powerful 8-core, 64-bit Qualcomm Kryo 300 CPU
• Qualcomm Adreno 615 GPU
• Qualcomm Hexagon 685 Vector Processor
• Qualcomm Spectra 270 ISP, DSPs for sensors and audio

The processor supports multiple connectivity options through 2×2 802.11ac Wi-Fi with MU-MIMO, and Bluetooth 5.1. It also offers enhanced multimedia experience by leveraging Qualcomm 3D Audio Suite, Qualcomm Aqstic Audio technologies, and Qualcomm aptX audio – exactly what is needed to build intelligent IoT applications for different end applications.

It also includes an integrated DSP that is capable of up to WQHD resolution touch display with hardware accelerated composition, 3D overlays, and support for major graphics APIs, including OpenGL, OpenCL, and Vulkan.

The QCS605 is capable of handling dual image streams – a 5.7k stream at 30 fps or 4k stream at 60 fps and a secondary 1080p stream at 60 fps – that can be used for data analytics. If we talk about AI interference processing, the chipset can perform 2.1 tera-operations per second. In addition, the Image Signal Processor is optimized for low light environments.

The Vision Intelligence platform can be used for a wide range of applications including but not limited to security, industrial and consumer robots, 360-degree cameras, virtual reality, sports, smart displays, and more. Qualcomm also provides extended lifecycle support for industrial applications. Integrated with Azure IoT Edge and working with the Microsoft Azure Machine Learning service (AML), QCS605-based VR360 camera reference design kit enables developers to build a vision AI solution and run their AI models on the device. For more information: https://www.arrow.com/en/products/eic-ms-vision-500/einfochips-limited

In partnership with Qualcomm and Microsoft, eInfochips helps developers in building AI solutions and offerings using the vision kit. This includes creating customizable models or building new AI models and deploying directly to the cloud or to the new hardware-accelerated device.

eInfochips is also a Qualcomm Snapdragon Technology Partner and we have enabled and enhanced multiple products by leveraging strong expertise in Snapdragon processor technology and latest Qualcomm SDKs.

We provide customized IoT solutions to enterprises and help clients to implement a highly scalable, reliable, and cost-efficient infrastructure with custom solutions for IoT on the Microsoft Azure platform. To help AI Vision kit users with their development, we are offering technical support. This package includes:

•             MS Azure and ML related support

•             Qualcomm Snapdragon related support for hardware and BSP

To learn more about our solution, please get in touch with us.