Akraino Edge StackBlog

Akraino Edge Stack Use Cases: Baidu’s End User Story

By February 18, 2020No Comments

Written by Baidu representatives who actively participate in Akraino’s TSC

Edge scenarios are very important commercial scenarios for AI applications. There are many type of hardware, OSes, etc. It is hard for AI application providers to adapt their products to all these edge components. Fortunately, the Akraino community and LF Edge member companies can help to do the validation/development or to support their products. The AI application providers need to state their requirements or cooperate with member companies in their Blueprint validation/integration labs. In this way, the AI application providers  are more likely to find potential partners and potential commercial market.

The AI Edge Blueprint Family

LF Edge member Baidu has deployed School/Education Video Security Monitoring blueprint. With this blueprint, teachers and school authorities could conduct a full evaluation of the overall class and the concentration of individual students, helping to fully understand the real time teaching situation. According to the concentration data of each course, teachers and school authorities can conduct knowledge test and strengthen. And the School/Education Video Security Monitoring blueprint has been deployed in Beijing, Shanghai, Hangzhou(Zhejiang Province), and many other cities in China.

The AI Edge Blueprint mainly focuses on establishing an open source MEC platform combined with AI capacities at the Edge, which could be used for safety, security, and surveillance sectors. Currently it has been highly supported by partners like Arm and Intel. And both Arm and Intel infrastructures, such as Servers and GPU cards,  have been implemented in respective scenarios.

A picture of the architecture

The AI Edge: RoboTaxi blueprint proposal has been deployed in Changsha, Hunan province, China. Commercial code is being run. The community version of code will be available in Q1 of 2020.

For more information about the Akraino blueprints or end user case stories, please visit the wiki: https://wiki.akraino.org.