acm-header
Sign In

Communications of the ACM

ACM TechNews

Researchers Use AI to Dramatically Increase Image Clarity Under Severe Conditions


View as: Print Mobile App Share:
Proposed multi-modal image fusion.

A new technology uses artificial intelligence to improve image visibility by automatically selecting highly visible parts from multiple images and combining them, while enhancing the smallest characteristics contained in non-visible images.

Credit: NEC Corporation

Researchers at the Tokyo Institute of Technology in Japan have developed technology that uses artificial intelligence (AI) to derive greater image visibility from devices such as thermal and x-ray cameras.

The researchers say the technology automatically selects highly visible parts from multiple images and combines them, while enhancing the smallest characteristics contained in non-visible images.

After the AI carries out a detailed examination of each image in order to assess the degree of visibility of each part, the system automatically extracts the best areas from each image, taking environmental characteristics such as brightness, the direction of light, and obstacles, into account.

"This technology eliminates the need for...manual work, using AI to effectively and automatically combine images taken by different cameras," says Tokyo Institute professor Masatoshi Okutomi. "This also increases visibility by actively utilizing the strong points of each visible image and non-visible image, even when the images are difficult to visualize."

From Tokyo Institute of Technology
View Full Article

 

Abstracts Copyright © 2017 Information Inc., Bethesda, Maryland, USA


 

No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account