How Can a Little AI Chip Become The "Eye" of a Smart City?

DIY MAKER 於 09/07/2020 發表 收藏文章
In order to realize the true potential of a "smart city", artificial intelligence processing must be transferred from the cloud to a secure local device to protect personal privacy, reduce data transmission rates, and speed up the response time of critical systems.
Occupancy Detection
With Coral, architectural spaces can detect the presence of people and protect privacy, thereby optimizing lighting. And it also make full use of climate and energy, thereby greatly reducing their operating costs and playing an environmental role.
Pedestrian Safety
Coral can use cameras and image classification technology to help pedestrians at intersections and help drivers better understand their surroundings. Coral on public buses and vehicles can also monitor pedestrians and cyclists while parking or driving doors.
Traffic Flow Forecast
Coral enables sensors on roads and key gateways, which can help optimize traffic flow within the city to optimize traffic during peak hours, special events, weather conditions, and accidents.
Migration
A distributed network of Coral-enabled sensors can help urban planners understand the movement of people in physical spaces such as parks, streets, workplaces, or retail centers in a privacy-protected manner. Feeding data into a larger model can help effectively allocate shared resources and improve incident response.
Air Quality Monitoring
Governments and companies can use Coral to establish fast and effective solutions to identify air pollution problems and develop preventive measures to limit emissions.
Google Coral hardware devices for Edge AI have been put on the market. Google Coral has many international agents, Mouser, Gravitylink, etc.
AI Hardware and Software Supporting Google Edge TPU
The Model Play and Tiorb AIX (Gravitylink) developed by Gravitylink can perfectly support Edge TPU. AIX is an artificial intelligence hardware that integrates the two core functions of computer vision and intelligent voice interaction. The built-in AI acceleration chip (Coral Edge TPU/intel movidius) supports edge deep learning inference and provides a reliable Performance support.
Model Play is an AI model resource platform for global developers, built-in diversified AI models, combined with Tiorb AIX, based on Google open source neural network architecture and algorithms, to build autonomous transfer learning functions without writing code, by selecting pictures, defining models and the category name to complete the AI model training.

留言


請按此登錄後留言。未成為會員? 立即註冊
    快捷鍵:←
    快捷鍵:→