Vision processor IP expert CEVA has announced its CEVA-XM4 intelligent vision DSP is used by vision SOC chip developer Inuitive in its next-generation AR/VR and computer vision SoC NU4000.
Inuitive to use CEVA-XM4 DSP IP for real-time depth sensing, feature tracking, object recognition, deep learning and other vision-related algorithms in mobile devices including augmented and virtual reality headsets, drones, consumer robots, 360 degree cameras and depth sensors.
CEVA says "Developers and OEMs will be able to leverage the open, programmable nature of the CEVA-XM4 in the Inuitive SoC to add their own differentiating features and algorithms via software, including their own neural networks which can be implemented via the CEVA Deep Neural Network (CDNN) framework."
Shlomo Gadot, co-founder & CEO at Inuitive said "The CEVA-XM4 provides the software infrastructures by which product builders can add their own algorithms and introduce revolutionary applications for vision-based systems."
The new NU4000 SoC is developed by Inuitive after the success of its previous NU3000 multi-core image processor which utilized the third-generation CEVA-MM3101 imaging and vision DSP for stereoscopic vision. NU3000 was used in Google Project Tango ecosystem for real-time depth generation, mapping, localization, navigation and other complex signal processing algorithms.
"We are delighted to extend our close relationship with Inuitive as they continue to innovate in the areas of 3D computer vision and image processing," said Eran Briman, vice president of marketing at CEVA. "Our CEVA-XM4 intelligent vision DSP delivers the power-efficiency and the flexibility that allows Inuitive and its customers implement a range of advanced machine-vision technologies on any mobile device, from neural network-based systems to highly-accurate depth sensing."
CEVA vision processor IP uses vector processor developed specifically to deal with the complexities of such applications and an extensive Application Development Kit (ADK) to enable easy development environment. The CEVA ADK includes an Android 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, the CEVA 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, says Ceva.