AI-powered camera compatible with Raspberry Pi improves ability through every click
Published : Tuesday, August 20, 2019, 3:33 pm
ACROFAN=Seunghee Shin | email@example.com | SNS
(Shanghai, August 19th)--Robotics and open source hardware provider DFRobot announced the company surpassing its crowdfunding goal by 300% of HuskyLens, an easy-to-use, powerful artificial intelligence vision sensor compatible with microcontrollers including Arduino, Raspberry Pi, LattePanda, and micro:bit.
HuskyLens is driven by the power of image processing algorithms and is constantly learning new objects, faces, and colours at the click of a button. It is based on the Kendryte K210 SoC with a dual-core RISC-V 64-bit processor designed with AI applications in mind. The AI camera continuously learns and improves its abilities with each click of the button and has an algorithmic processing speed that is 1,000 times faster than most similar products on the market, reading up to 30 frames per second.
Unlike other similar products on the market, HuskyLens is a time-saving device with several built-in algorithms that allow creators to make projects without previous algorithmic knowledge. HuskyLens is equipped with algorithms of facial recognition, object recognition, object tracking, line following, colour detection, and tag detection. Users can also switch between algorithms with one single click.
The HuskyLens team indicated that the main framework of the HuskyLens will be licensed under LGPL-2.1. The repository of the project will have multiple licenses. There will be a file in each algorithm folder indicating the original author and its license type.
HuskyLens is currently crowdfunding on Kickstarter, with pledges starting at around $20 for the standard early bird version, and approximately $50 for an enhanced version with a 5-megapixel camera. Other options can be found on its KickStarter page and it is available for backing till September 7th.
Copyright ⓒ Acrofan All Right Reserved