Recognizing human motions (IMAGE)

University of Massachusetts Amherst

Recognizing human motions

Caption

Recognizing human motions in sophisticated environments is a classic computer vision challenge. Xu and colleagues found that their analog technology was able to perform the task with 90% accuracy, outperforming its digital counterparts.

Credit

Guangyu Xu, UMass Amherst

Usage Restrictions

Image to be used in covering the study "Parallelizing analog in-sensor visual processing with arrays of gate-tunable silicon photodetectors"

License

Original content

Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.