Study on a Real-Time Corner Detection Algorithm

Abstract:

Article Preview

Conventional Harris corner detector is a desirable detector but it requires significantly more computation time. For MIC detector proposed by Trajkovic, the minimal computational demands of its operator make it well-suited for real-time applications, however the Trajkovic’s operator responses too readily to certain diagonal edges. For this reason, the paper proposed a new corner detection algorithm. The new corner detection algorithm adopted multigrid algorithm and preprocessed the lower resolution revision of the original image to obtain the potential corners, subsequently used autocorrelation matrix to get the corner response function for the corresponding points of the potential corner. The test results indicate the new corner detection algorithm can decrease edge responses and the number of textural corners effectively. Furthermore, it can satisfy the demands of real-time applications.

Info:

Periodical:

Edited by:

Dehuai Zeng

Pages:

192-197

DOI:

10.4028/www.scientific.net/AMR.159.192

Citation:

Y. F. Guo et al., "Study on a Real-Time Corner Detection Algorithm", Advanced Materials Research, Vol. 159, pp. 192-197, 2011

Online since:

December 2010

Export:

Price:

$35.00

In order to see related information, you need to Login.

In order to see related information, you need to Login.