Title :
An intelligent high-frame-rate video logging system with real-time image processing at 1000 fps
Author :
Ishii, Idaku ; Wang, Yaodong ; Takaki, Takeshi
Author_Institution :
Hiroshima Univ., Higashi-Hiroshima, Japan
Abstract :
This paper introduces an intelligent high-frame-rate video logging system that can automatically detect high-speed unpredictable behavior and record video comprising images with dimensions of 512 × 512 pixels at 1000 fps. To capture high-frame-rate video of crucial moments of abnormal behavior in high-speed periodic motion, a real-time abnormal behavior detection algorithm is implemented on a highspeed vision platform, IDP Express, which can record both input images and processed results at 1000 fps for video logging. Several experiments were performed using a machine with repetitive operation at a frequency of 15 Hz and video of the abnormal behavior was automatically recorded to verify the effectiveness of our system.
Keywords :
artificial intelligence; image processing; real-time systems; video signal processing; 1000 fps; intelligent high frame rate video logging system; real-time image processing; video comprising images; Cameras; Detection algorithms; Head; Metals; Pixel; Streaming media; Synchronization; abnormal behavior detection; high-frame-rate video recording; real-time vision;
Conference_Titel :
Multimedia and Expo (ICME), 2010 IEEE International Conference on
Conference_Location :
Suntec City
Print_ISBN :
978-1-4244-7491-2
DOI :
10.1109/ICME.2010.5582583