Communications of the ACM
Computer Scientists Combine Computer Vision and Brain Computer Interface For Faster Mine Detection
Researchers at the University of California, San Diego have developed a new method to speed detection of landmines in sonar images of the ocean floor, through the use of computer-vision algorithms in combination with a brain-computer interface.
Credit: Neuromatters
University of California, San Diego researchers have developed a new method, combining computer-vision algorithms with a brain-computer interface, to speed the detection of landmines in sonar images of the ocean floor.
The researchers collected a dataset of 450 sonar images containing 150 inert, bright-orange mines placed in test fields. The researchers also trained the computer-vision algorithms on a data set of 975 images of mine-like objects.
As part of the study, the researchers showed six volunteers a complete dataset, before it had been analyzed by the computer-vision algorithms. They then ran the image dataset through mine-detection algorithms, which flagged images that most likely included mines. The researchers showed the results to subjects outfitted with an EEG system, which was programmed to detect brain activity. The system demonstrated that subjects reacted to an image thought to contain a mine much faster when the images had already been processed by the algorithms.
The algorithms are a series of classifiers, working in succession to improve speed and accuracy. The system's goal is to detect 99.5 percent of true positives and only generate 50 percent of false positives during each run through a classifier, which means the number of false positives will reduce with each pass.
From UCSD News (CA)
View Full Article
Abstracts Copyright © 2015 Information Inc., Bethesda, Maryland, USA
No entries found