作者: Deepak Khosla , David J. Huber , Rajan Bhattacharyya
DOI: 10.1117/12.2262911
关键词: Computation 、 Decoding methods 、 Computer vision 、 Rapid serial visual presentation 、 Motion (physics) 、 Computer science 、 Surprise 、 Contextual image classification 、 Artificial intelligence
摘要: In this paper, we describe an algorithm and system for optimizing search detection performance “items of interest” (IOI) in large-sized images videos that employ the Rapid Serial Visual Presentation (RSVP) based EEG paradigm and surprise algorithms incorporate motion processing to determine whether static or video RSVP is used. The system works by first computing a surprise map on image sub-regions (chips) incoming sensor data then uses those maps label chips as either “static” “moving”. This information tells use a static presentation decoding order optimize IOI each chip. Using method, are able demonstrate classification series regions from with azimuth value of 1, indicating perfect classification, over range display frequencies speeds.