Leopard Imaging, a global provider of embedded camera design and manufacturing, is collaborating with three leading companies to deliver EdgeTuring: a next-generation artificial intelligence (AI) processing solution for video analytics.
Leopard Imaging, a global provider of embedded camera design and manufacturing, is collaborating with three leading companies to deliver EdgeTuring: a next-generation artificial intelligence (AI) processing solution for video analytics. Leopard is working with Hailo, an AI chipmaker for edge devices, Socionext, a provider of advanced system-on-chip (SoC) solutions for imaging and video systems; and Amazon Web Services (AWS), one of the world’s most comprehensive and broadly adopted cloud platforms, to launch their transformative solution. The venture produces high image quality and high energy efficiency for AI inference nodes, benefiting a wide range of applications in industrial automation, smart devices, smart retail, and others.
Innovative AI Edge Device Cuts Costs and Delivers Faster Performance
Leopard Imaging has been working to address the need for affordable multiprocessing power in deep learning applications. Using Socionext’s SC2000 image signal processor and the Hailo-8 M.2 AI acceleration module, Leopard Imaging’s EdgeTuring consumes less power, performs at a higher level, and ensures greater reliability for video analytics and privacy at the edge than alternative solutions. Leveraging AWS services such as Amazon Kinesis Video Streams and Amazon Kinesis Data Streams (Amazon KDS), EdgeTuring creates a seamless experience for customers to stream and analyze videos using a simple internet connection.
"EdgeTuring has an accuracy ranging from 95% to 99% for several state of the art deep learning - based computer vision applications, such as object detection, image classification and others. Additionally, it processes frames much faster, supports more functions, consumes less power, and costs much less than any comparable solution—all with the ability to stream inputs in real time," said Bill Pu, President and Co-Founder of Leopard Imaging. "We believe that this strategic collaboration will help us carve a new path forward in the AI-driven camera industry. We want to break away from the status quo and embrace these opportunities to adopt new AI solutions.”
Launched just last year, the Hailo-8 enables customers to integrate high performance AI capabilities of 26 Tera Operations Per Second (TOPS) into edge devices, providing a more flexible solution for accelerating a wide range of deep learning-based applications with high efficiency—optimizing time to market with a standard form factor. A comparison between the Hailo-8’s average Frames Per Second (FPS) with competitors across multiple standard NN benchmarks (based on the latest published figures) shows that Hailo’s AI modules achieve up to 26x higher FPS rate.
Leopard Imaging has previously launched various high-definition embedded camera products with AI solutions. By creating more efficient processes and solutions, their products have helped significantly reduce operating costs—increasing precision and improving reliability.
“We are excited to work with Leopard Imaging, Socionext, and AWS to bring unprecedented AI-based products to the edge market,” said Orr Danon, CEO and Co-Founder of Hailo. “As demand for AI at the edge grows, our innovative AI processor and acceleration modules, together with the solutions created by these industry leaders, will help usher in a new generation of AI that is more powerful, more scalable, and more cost-efficient.”
"It’s a pleasure to announce our strategic collaboration with three global leaders in the AI solutions space," said Takuji Nukiwa, President at Socionext America. “When it comes to edge technology, our new generation of chips enables more capabilities, and these new capabilities lead to new opportunities. The transformation of edge technology ushers in a new wave of smart industries that will continue to evolve and grow with the changing technologies.”
AWS provides coverage connected by high throughput, low latency, and highly redundant networking, which allows EdgeTuring to combine the advantages of both edge computing and cloud computing to achieve more functions in more applications.
The field of AI computing solutions is thriving and involves applications for broader markets that rely on high data rate, fast processing, low power consumption, and low latency. For example, smart cities need numerous cameras to produce video streams that need to be quickly processed, meaning every millisecond counts. Presenting in real time on the production floor means a more effective and efficient process—leading to higher quality outputs and reducing operational costs.