Fast motion detection from airborne videos using graphics processing unit

Kui Liu; Ben Ma; Qian Du; Genshe Chen

doi:10.1117/1.JRS.6.061505

Translator Disclaimer

10 May 2012 Fast motion detection from airborne videos using graphics processing unit

Kui Liu, Ben Ma, Qian Du, Genshe Chen

Author Affiliations +

J. of Applied Remote Sensing, 6(1), 061505 (2012). https://doi.org/10.1117/1.JRS.6.061505

Abstract

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.

Citation Download Citation

Kui Liu, Ben Ma, Qian Du, and Genshe Chen "Fast motion detection from airborne videos using graphics processing unit," Journal of Applied Remote Sensing 6(1), 061505 (10 May 2012). https://doi.org/10.1117/1.JRS.6.061505

Published: 10 May 2012

ACCESS THE FULL ARTICLE