|
Accession Number
|
ADA565269
|
|
Title
|
Parallel Flux Tensor Analysis for Efficient Moving Object Detection.
|
|
Publication Date
|
Jul 2011
|
|
Media Count
|
9p
|
|
Personal Author
|
G. Seetharaman I. Ersoy K. Palaniappan P. Kumar S. R. Davis
|
|
Abstract
|
The flux tensor motion flow algorithm is a versatile computer vision technique for robustly detecting moving objects in cluttered scenes. The flux tensor calculation has a high computational workload consisting of 3-D spatiotemporal filtering operations combined with 3-D weighted integration operations for estimating local averages of the flux tensor matrix trace. In order to achieve efficient real-time processing of high bandwidth video streams a data parallel multicore algorithm was developed for the Cell Broadband Engine (Cell/B.E.) processor and evaluated in terms of the energy to computation efficiency compared to a fast sequential CPU implementation. Our multicore implementation is 12 to 40 times faster than the sequential version for HD video using a single PS-3 Cell/B.E. processor and is faster than realtime for a range of filter configurations and video frame sizes. We report on the power efficiency measured in terms of performance per watt for the Cell/B.E. implementation which is at least 50 times better than the sequential version.
|
|
Keywords
|
Algorithms
Bandwidth
Broadband
Computations
Computer applications
Computer vision
Configurations
Detection
Efficiency
Energy
Engines
Flux(Rate)
High rate
Image processing
Motion
Moving targets
Parallel orientation
Parallel processing
Processing
Processing equipment
Real time
Sequences
Symposia
Tensor analysis
Tensors
Video frames
Video signals
|
|
|
Source Agency
|
Non Paid ADAS
|
|
NTIS Subject Category
|
72B - Algebra, Analysis, Geometry, & Mathematical Logic
62 - Computers, Control & Information Theory
|
|
Corporate Author
|
Missouri Univ.-Columbia. Dept. of Computer Science.
|
|
Document Type
|
Technical report
|
|
Title Note
|
Conference paper.
|
|
NTIS Issue Number
|
1304
|
|
Contract Number
|
FA8750-09-2-0198 FA8750-10-1-0182
|
