Title :
A QVGA-Size Pixel-Parallel Image Processor for 1,000-fps Vision
Author :
Komuro, Takashi ; Iwashita, Atsushi ; Ishikawa, Masatoshi
Author_Institution :
Univ. of Tokyo, Tokyo, Japan
Abstract :
Massively parallel image processing with as many processing elements as pixels can achieve real-time vision with rates as high as 1,000 frames per second. The authors implemented a QVGA-size pixel-parallel image processor for object identification and pose estimation on a single chip. Bit-serial operation and dynamic logic reduce the circuit area, and pipelining enables high processing speed.
Keywords :
computer vision; microprocessor chips; object recognition; pose estimation; 1,000-fps vision; QVGA-size pixel-parallel image processor; bit-serial operation; high processing speed; object identification; parallel image processing; pose estimation; Cameras; Image sensors; Logic circuits; Manipulators; Pixel; Robot control; Robot sensing systems; Robot vision systems; Robotic assembly; Service robots; high-speed vision; massively parallel processor; smart image sensor; vision chip;
Journal_Title :
Micro, IEEE
