Fast motion detection from airborne videos using graphics processing unit
Mississippi State University, Department of Electrical and Computer Engineering, Mississippi State, Mississippi 39762
Journal of Applied Remote Sensing 6(01), 061505, 2012
@article{liu2012fast,
title={Fast motion detection from airborne videos using graphics processing unit},
author={Liu, K. and Ma, B. and Du, Q. and Chen, G.},
journal={Journal of Applied Remote Sensing},
volume={6},
number={1},
pages={061505–061505},
year={2012},
publisher={Society of Photo-Optical Instrumentation Engineers}
}
In our previous work, we proposed a joint optical flow and principal component analysis (PCA) approach to improve the performance of optical flow based detection, where PCA is applied on the calculated two-dimensional optical flow image, and motion detection is accomplished by a metric derived from the two eigenvalues. To reduce the computational time when processing airborne videos, parallel computing using graphic processing unit (GPU) is implemented on NVIDIA GeForce GTX480. Experimental results demonstrate that our approach can efficiently improve detection performance even with dynamic background, and processing time can be greatly reduced with parallel computing on GPU.
June 23, 2012 by hgpu
