DocumentCode :
3061805
Title :
Video-rate pyramid optical flow computation on the linear SIMD array IVIP
Author :
Johannesson, Mattias ; Gökstorp, Mats
Author_Institution :
Dept. of Electr. Eng., Linkoping Univ., Sweden
fYear :
1995
fDate :
18-20 Sep 1995
Firstpage :
280
Lastpage :
287
Abstract :
The IVIP (IR Video Image Processor) signal processor array is used to process a video sequence to obtain its optical flow. Optical flow is the apparent motion of the intensity patterns in image sequences, and it can be used to obtain information about scene structure and object motion. A differential-based method for optical flow using second-order derivatives is implemented. We investigate both one-level and pyramid implementations. A pyramid implementation makes it possible to estimate much larger image velocities than a one-level implementation. IVIP is a row-parallel bit-serial SIMD processor array. The special ALU design which incorporates a serial-parallel multiplier/divider together with good interprocessor communication makes it very effective for large convolutions. In this paper, we show that we can process 5122 image sequences at 50 Hz frame rate for one-level flow and 25 Hz for multi-level pyramid flow
Keywords :
convolution; image sequences; motion estimation; parallel processing; 0.25 Mpixel; 25 Hz; 2nd-order derivatives; 50 Hz; 512 pixel; ALU design; IR Video Image Processor; IVIP signal processor array; convolution; differential-based method; image sequences; image velocities; intensity pattern apparent motion; interprocessor communication; linear SIMD array; multi-level pyramid flow; object motion; one-level implementation; row-parallel bit-serial SIMD processor array; scene structure; serial-parallel multiplier/divider; video sequence processing; video-rate pyramid optical flow computation; Cameras; Image motion analysis; Image processing; Image sensors; Image sequences; Layout; Optical arrays; Optical computing; Optical sensors; Registers;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Architectures for Machine Perception, 1995. Proceedings. CAMP '95
Conference_Location :
Como
Print_ISBN :
0-8186-7134-3
Type :
conf
DOI :
10.1109/CAMP.1995.521051
Filename :
521051
Link To Document :
بازگشت