Add BrightSurf on Google Email

The missing link between event cameras and robot vision

Penn's Fast Feature Field transforms event-camera data into information that many different kinds of robots can use, improving robots' ability to recognize objects, estimate distances and perceive motion. The tool could transform robotics by allowing for the widespread use of event cameras in self-driving cars and drones.

SourceUniversity of Pennsylvania School of Engineering and Applied Science·JournalScience Robotics·TypeComputational simulation/modeling·DateOct 29, 2026

Tiny crop-health sensors could help cut the cost of groceries

Researchers developed a compact sensor system with infrared imaging capabilities that can be fitted to drones for remote crop monitoring. The system can rapidly switch between edge detection and detailed infrared imaging, allowing farmers to pinpoint specific crop needs and boost harvests.

SourceRMIT University·JournalNature Communications·TypeExperimental study·DateJun 5, 2024

Streaming from the future

A team of researchers at Osaka University has created a machine learning system that can virtually remove buildings from a live view, streaming in real-time on a mobile device. This technology can help accelerate the process of urban renewal based on community agreement, reducing conflicts and delays.

SourceOsaka University·JournalJournal of Computational Design and Engineering·TypeComputational simulation/modeling·DateJul 26, 2022

Development of an artificial vision device capable of mimicking human optical illusions

The National Institute for Materials Science in Japan has developed an ionic artificial vision device capable of increasing edge contrast between dark and light areas like human vision. This device uses ionic migration and interaction within solids to mimic human optical illusions without software.

SourceNational Institute for Materials Science, Japan·JournalNano Letters·TypeImaging analysis·DateNov 29, 2021

X-ray street vision

A team of researchers at Osaka University created a custom dataset to train an AI algorithm to digitally remove unwanted objects from building façade images. The algorithm achieved high accuracy in inpainting occluded regions with digital inpainting.

SourceOsaka University·JournalIEEE Access·TypeImaging analysis·DateSep 6, 2021

Paint the town

A team of scientists from Osaka University developed a machine learning method for classifying the type of building and its primary façade color using deep learning models applied to street-level images. This work may assist in fostering neighborhood cohesion and support urban renewal by providing tailored street-view datasets.

SourceOsaka University·JournalISPRS International Journal of Geo-Information·DateAug 31, 2021