Cloudian-Powered Vehicle Recognition Advertising Model Now in Production Use

Share Article

Object storage system accelerates machine learning for Tokyo-based targeted roadside advertising

“This technology demonstrates how Cloudian object storage revolutionizes the economics of data-intensive applications such as machine learning, making futuristic solutions now a part of our daily lives,” said Mike Tso, chief executive officer, Cloudian.

Cloudian, Inc., the leading provider of hybrid cloud object storage systems, announced that its HyperStore technology-enabled roadside digital advertising project in Tokyo has transitioned from a proof-of-concept to production use. Spearheaded by Cloudian, Dentsu, Inc., and Intel, the project employs AI-based vehicle recognition using HyperStore’s object storage and deep learning capabilities to present relevant display ads to drivers based on vehicle make and model. The groundbreaking initiative is currently implemented in one smart billboard located in Roppongi, Tokyo, and is projected to expand to other areas within the city in 2017.

“This technology demonstrates how Cloudian object storage revolutionizes the economics of data-intensive applications such as machine learning, making futuristic solutions now a part of our daily lives,” said Mike Tso, chief executive officer, Cloudian. “The world’s data is growing at an exponential rate, a trend that will only accelerate as IoT and machine learning technologies gain momentum. Cloudian strives to leverage the world’s data to create powerful new experiences for businesses and consumers.”

The Cloudian HyperStore-powered system utilizes automatic feature extraction of traffic patterns and volume, and automatic vehicle recognition to enable the targeted advertising via roadside, digital signage. The system currently recognizes over 300 unique car makes and models. Once the system has recognized a target vehicle, the smart billboard then selects an appropriate stored image to present a customized digital advertisement to the driver in just half a second.

Ads are chosen for specific vehicles based on requirements set by advertisement sponsors. For example, if a beverage company is a sponsor, the programmed system will select an image of one of its products from the database when it detects an appropriate vehicle to target—such as a canned coffee or energy drink for truck drivers traveling long distances. The system does not store or archive any of the vehicle photos.

With other possible applications including traffic volume surveys through vehicle differentiation and existing traffic cameras, as well as road monitoring projects for safety and security with license plate recognition, Cloudian HyperStore provides many possible use cases for companies seeking to utilize big data storage and deep learning technology for similar machine learning initiatives.

To see Cloudian HyperStore’s deep learning and storage capabilities in action, view this video. For more information about Cloudian HyperStore, visit: http://www.cloudian.com.

About Cloudian
Based in Silicon Valley, Cloudian is a leading provider of hybrid cloud object storage systems. Our flagship product, Cloudian HyperStore, enables service providers and enterprises to build reliable, affordable and scalable hybrid cloud storage solutions. Join us on LinkedIn, follow us on Twitter (@CloudianStorage) and Facebook, or visit us at http://www.cloudian.com.

Cloudian Media Contacts:
U.S.: McClenahan Bruer
cloudian(at)mcbru(dot)com
+1 503-546-1000

Touchdown PR
cloudian(at)touchdownpr(dot)com
+44 (0)1252 717040

Share article on social media or email:

View article via:

Pdf Print

Contact Author

Erica Harbison
Cloudian, Inc.
+1 (503) 546-1013
Email >

Tam Nguyen
Cloudian
408-510-0132
Email >