TOKYO, Sep 10, 2020 – (JCN Newswire) – Fujitsu today announced the launch of the FUJITSU Future Mobility Accelerator Digital Twin Analyzer, an AI-powered in-vehicle camera image analysis platform, delivering a powerful new tool for businesses offering services that rely on big data collected from connected cars. Sales begin in Japan from September 25th, with availability to follow in the North American and European markets from February 2021.
The new platform leverages technologies developed by Fujitsu Laboratories Ltd., including AI image-recognition technology for image analysis, as well as high-precision 3D positioning technology for the vehicle and surrounding objects to analyze images taken by in-vehicle cameras and convert them into valuable data to support customers’ digital transformation. The platform enables the highly-accurate estimation of 3D position and trajectory information of potential obstacles in the real world, including pedestrians, other vehicles, roads, and buildings, which are constantly changing, to deliver rapid analysis and prediction of vehicle conditions and traffic conditions. With the addition of analysis logic, the technology also offers new use cases, including feature detection and accident situation analysis, demonstrating a wide range of potential applications for a variety of services.
The Future of Mobility is Connected
In the near future, the number of connected cars will increase exponentially. Big data from connected vehicles, including images collected from car sensors, and CAN(1) data, will play a key role in making mobility services like traffic monitoring, maps, and insurance, as well as advanced vehicle design a reality.
An AI-Powered Big Data Platform to Digitally Transform Mobility
FUJITSU Future Mobility Accelerator Digital Twin Analyzer is an in-vehicle camera image analysis platform powered by AI image recognition technology for analyzing in-vehicle camera images and high-precision 3D position estimation technology for the vehicle and surrounding objects. Fujitsu’s AI image recognition technology not only recognizes objects like vehicles, road markings, and traffic signals from video, but can also detect detailed attributes to differentiate between vehicle types (cars, buses, and trucks) and road markings like crosswalks and center lines. For objects that change over time, like traffic lights, the platform can effectively detect and record changes in color, etc. by tracking objects. The high-precision 3D position estimation technology accurately grasps objects detected by the image recognition technology and the position of the user’s own vehicle. The platform even makes it possible to achieve highly accurate estimates with consumer-grade drive recorders, regardless of installation conditions or type of on-board camera.
Improving the efficiency and sophistication of automotive insurance claims/processing
By analyzing images taken by in-vehicle cameras at the time of an accident, it becomes possible to automatically analyze the surrounding circumstances. This includes information like the trajectory of the vehicle, changes in the color of traffic signals, and the presence or absence of pedestrian crossings. This would help the insurance company to provide automobile insurance services with a more efficient response to accident cases.
Upgrading road management services
The system can automatically detect events occurring on the road, such as accidents or falling obstacles, together with accurate positional information from in-vehicle camera data, enabling the provision of detailed traffic control services including individual lane regulations.
Dynamic information service
The platform could support an information service that reflect changes in the real world, including the replacement of a building or a store, with data drawn from in-vehicle cameras, displaying information on a map in a timely manner according to user preferences.
The basic service provides data that can be analyzed from in-vehicle camera data, including the position and speed of the vehicle and the 3D position of surrounding vehicles, signs, and buildings. Other supported services include requirements definition support services for the creation of systemization requirements definition documents to meet customer needs, as well as setup services to configure user environments in accordance with these.
(1) Controller Area Network (CAN) This is a type of communication method in an in-vehicle network, and is mainly used for data transmission and reception for dashboard meters, body control, engine control, etc.
About Fujitsu Ltd
Fujitsu is the leading Japanese information and communication technology (ICT) company offering a full range of technology products, solutions and services. Approximately 130,000 Fujitsu people support customers in more than 100 countries. We use our experience and the power of ICT to shape the future of society with our customers. Fujitsu Limited (TSE:6702) reported consolidated revenues of 3.9 trillion yen (US$35 billion) for the fiscal year ended March 31, 2020. For more information, please see www.fujitsu.com.
Copyright 2020 JCN Newswire. All rights reserved. www.jcnnewswire.com