Algolux's CNA is the 2018 Vision Product of the Year Award Winner in the Automotive Solutions category. CANA is a novel end-to-end deep neural network (DNN) for much more robust perception in challenging imaging conditions, such as low light, adverse weather, or lens issues found in the real world. RAW or lightly processed image sensor data is directly input into the CANA DNN, bypassing traditional ISP pre-processing. Lens and sensor characteristics are fused into the early levels of the DNN to understand how the image is being formed, while the upper layers address the perception task, such as object detection, classification, or segmentation. The network is trained end-to-end with a tailored training approach that leverages a combination of captured and synthetic annotated data. This results in significantly improved perception in difficult imaging conditions, typically 20-30% versus current state of the art and higher in more extreme scenarios.
“We are honored to win the ‘Best Automotive Solution’ award. Our CANA perception stack represents a reimagining of traditional imaging architectures with the end goal of producing far greater robustness than can be achieved with today’s vision systems. The Embedded Vision Alliance has been an ideal vehicle for Algolux to meet with key stakeholders in the industry, showcase our technology, and bring it to market.”
Allan Benchetrit, President and CEO, Algolux
Algolux provides groundbreaking technologies that enable the smart optimization of computer vision systems, transforming the development and accuracy of machines that can “see”. Computer vision is at the heart of autonomous cars, ADAS, AR/VR, robotics, drones, IoT, medical equipment, and mobile devices…leading the next wave of market growth and social impact. Developed by an industry-recognized team of machine learning, computer vision, and image processing researchers, our patented CRISP technology addresses the cost, schedule, and expertise challenges that product development teams face in optimizing their imaging and vision systems. To learn more about Algolux, please visit www.algolux.com.
Applications for the 2019 Vision Product of the Year Awards are now being accepted, until March 8, 2019. If you're an employee of an Embedded Vision Alliance member company, please see here for an online application form. If you're interested in becoming a member of the Embedded Vision Alliance, please see here for more information!