CEVA, Inc. has announced that iCatch Technology, Inc. has licensed theCEVA imaging and vision DSPfor its next-generation SoCs targeting the automotive, drone, surveillance camera markets. iCatch will leverage the powerful computer vision and image enhancement capabilities of the DSP to significantly enhance the feature set offered in their smart camera SoCs.
“iCatch is committed to developing highly innovative SoCs that excel in performance and cost-efficiency with ultra-low power consumption,” said Tek Wei, executive vice president at iCatch Technology. The CEVA imaging and vision DSP enables us to add leading-edge computer vision-based functions to our SoCs, allowing our customers to create differentiated and sophisticated smart camera products.
Our leadership in imaging and vision processing allows for innovative companies to develop feature-rich, exciting products that incorporate state-of-the-art computer vision functions, said Eran Briman, vice president of marketing and corporate development at CEVA. iCatch has a strong heritage in digital video and imaging SoCs and were pleased that our imaging and vision DSP forms an integral part of their latest smart camera product line.
CEVAs imaging and vision DSP addresses the extreme processing requirements of the most sophisticated computational photography and computer vision applications such as video analytics, augmented reality and advanced driver assistance systems (ADAS). By offloading these performance-intensive tasks from the CPUs and GPUs, the highly-efficient DSP dramatically reduces the power consumption of the overall system, while providing complete flexibility.
The platform includes a vector processor developed specifically to deal with the complexities of such applications and an extensiveApplication Development Kit(ADK) to enable easy development environment. The CEVA ADK includes anAndroid Multimedia Framework(AMF) that streamlines software development and integration effort, a set of advanced software development tools and a range of software products and libraries optimized for the DSP. For embedded systems targeting deep learning, theCEVA Deep Neural Network (CDNN)real-time neural network software framework streamlines machine learning deployment at a fraction of the power consumption of the leading GPU-based systems.