One of the key aspects of artificial intelligence (AI) and machine learning (ML) applications is image processing and computer vision. As the complexity and demands of AI and ML applications increase, it is important to develop efficient, cutting-edge tools for image processing and visual data analysis.
e-con Systems has partnered with Qualcomm to launch a ready-to-deploy AI Vision kit based on the Qualcomm QCS processor, the qSmartAI80_CUQ610, which has powerful AI processing capabilities and is therefore suitable for a wide range of computing applications. To support interconnects and external components in the ecosystem, the Qualcomm Vision Kit includes an e-con Sony STARVIS IMX415-based 4K MIPI CSI-2 camera module, a Qualcomm® QCS610 SoC-based VVDN SoM, and a carrier board.
The Sony STARVIS IMX415 ultra-low light sensor is used in the 4K camera module to capture incredibly clear photos even in low light conditions. The Sony STARVIS® IMX415 camera module has a viewing range of 115.9°. The camera is capable of working at a frame rate of 30fps while capturing images in 4K (3840 x 2160) resolution for precise high-quality image capture.
The carrier board is powered by 12V DC and provides three 4-lane MIPI CSI for camera interface, one 4-lane MIPI DSI display interface, one USB3.1, USB2.0 (Type-C) and one USB 2.0 and 4-bit Secure Digital Interface (SDIO). Additionally, it offers WiFi (2.4GHz/5GHz), Bluetooth and Ethernet connectivity, and 50 Ohm coaxial connectors to enhance its connectivity.
This kit is designed to provide powerful computing power for image processing with excellent power and thermal efficiency. In addition to offering a complete vision suite, e-con Systems will expand its custom support for cameras, carrier boards, software and housings. This enables customers to focus on their end application.
With this ready-to-deploy AI vision kit and extensive customization services for cameras, BSPs, carrier boards, software and housings, product developers can develop AI-based smart camera systems more efficiently and faster, reducing time to market .
In addition to providing comprehensive customization support, another key added value of e-con Systems is the fine-tuned Image Signal Processor (ISP). The default Qualcomm ISP is further developed to provide top-notch image quality and color reproduction, making it adaptable to various lighting conditions.
The kit's small form factor makes it ideal for compact embedded systems. Additionally, it can perform all image processing and analysis locally without the need for a cloud connection.
Features such as small size, low power consumption, low light performance, high resolution, and the ability to run image-based machine learning and deep learning models at the edge make the product ideal for service robots, telemedicine robots, telepresence robots, smart checkout, and shopping car, intelligent transportation, driving recorder, etc.
In addition to the complete vision suite, e-con Systems provides a Yocto-built Linux image and a GStreamer-based camera application for HDMI streaming, H.264 network streaming over Ethernet and WiFi, JPEG and RAW image capture, H.264 video recording, and adjustments for white balance, gain, and exposure. Engineers can take advantage of Qualcomm's AI Neural Processing SDK, Neural Network API (TFLite model), GStreamer plugin (DLC model), and GStreamer TFLite plugin to take full advantage of the suite's AI capabilities.
