Optimizing AI for embedded applications
In my previous blog I talked about how demand for AI-based interfaces has become almost unavoidable—and that adding an AI-based interface …
Home Surveillance and Security Without the Hassle
Fisheye dewarping with no need to install an app: this solution works directly with the WebGL API and on popular …
SLAM and Multi-Sensing Robots: Soon in Every Home
Robotics, for many of us, is still an application mostly limited to the factory or warehouse floor. We see media …
Easing the development of visual SLAM applications
Simultaneous Localization and Mapping (SLAM) describes the process by which a device, such as a robot, uses sensor data to build …
Ultra-Wide is Ultra-Hot, and a Lot of Work
Wide angle cameras are hot in smartphones, cars, VR and surveillance, for convenience, cost or safety. Turning wide-angle, high-res input …
Image Processing and Computer Vision in One Package: A Logical Next Step
Computer vision on the edge is a good start but it isn’t enough. It needs to deal with distorted images …
Smart AI Assistants are the Real Enabler for Edge AI
AI at the edge will reduce overwhelming volumes of data to useful and relevant information on which we can act. A recent …
DMS Given Green Light to Increase Road Safety
The “Vision Zero” approach from the European Union (EU) includes the goal of bringing automotive fatalities and serious injuries down …
The Challenges for AR/VR to Go Mainstream
The right combination of image-processing performance and low power consumption is best achieved by specialized on-device vision and neural-network processors Some …
Browse
Browse posts by categories
-
Audio / Voice / Speech -
Automotive -
Bluetooth -
Communication -
Connectivity -
Deep Learning -
Development tools -
DSP cores -
Financial -
Imaging & vision -
Sensor fusion -
Wireless