A New Edge Detection Algorithm Applied in Obstacle Identification of Unmanned Vehicle

Abstract:

Obstacle identification is one of the critical technologies of unmanned vehicle, edge detection is the basic step of obstacle identification based on video sensor and the magnitude guarantee of identification effect. In order to meet the demand of accuracy, real-time and stability of obstacle identification, a new multiple order morphology edge detection algorithm is proposed. We adopt two-dimensional histogram oblique segmentation to locate edge, then detected edge by improving the existing mathematical morphology edge detection operators and using appropriate structuring elements and percentile. Experimental results showed the edge detected is exquisite, continuous and intact. The algorithm possesses good robustness for different noised images, cuts operation time by nearly half compared with algorithm without edge location, then makes a good foundation for subsequent processing of obstacle identification.

• Periodical: Applied Mechanics and Materials (Volumes 635-637)
• Pages: 981-984
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.635-637.981
• Online since: September 2014
• Authors: Hai Long Huang*, Jie Guo, Zhong Yi Zhao
• Keywords: Edge Detection, Multiple Order Morphology, Obstacle Identification, Two-Dimensional Histogram, Unmanned Vehicle

References

[1] REN Y H. About the research to information identification and processing system of obstacle for unmanned vehicle[D]. Lanzhou university of technology, 2011: 32-41(In Chinese).

[2] GONZALEZ R C. Digital Image Processing (second Edition) [M]. Beijing：Publishing House of Electronics Industry, 2003：474-479.

[3] MARAGOS P. Differential morphology and image processing [J]. IEEE Trans Image Processing , 1996, 5(6): 922-937.

DOI: 10.1109/83.503909

[4] SERRA J. Mathematical morphology and its applications to image and signal processing [M]. Boston: Kluwer Academic Publishers, 1996：234-251.

[5] MARIA C M. Fuzzy mathematical morphology：concepts and applications [J]. Vistas in Astronomy, 1996, 40(4)：469-477.

[6] LIU J ZH. A fuzzy clustering method for image segmentation based on two-dimensional histogram [J]. ACTA ELECTORONICA SINICA, 1992, 20（9）: 40-46(In Chinese).

[7] WU Y Q, PAN ZH, WU W Y. Image thresholding based on two-dimensional histogram oblique segmentation and its fast recurring algorithm[J] . Journal on Communications, 2008, 29（4）: 77-83(In Chinese).

[8] NAEGEL B. Using mathematical morphology for the anatomical labeling of vertebrae from 3D CT-scan images [J]. Computerized Medical Imaging and Graphics, 2007, 3: 141-156.

DOI: 10.1016/j.compmedimag.2006.12.001

[9] LEE C K, WONG S P. A mathematical morphological approach for segmenting heavily noise-corrupted images [J]. Pattern Recognition, 1996, 29(8): 1347-135.

DOI: 10.1016/0031-3203(96)86888-9