Railway inspection and maintenance in uninhabited high-cold areas are facing great challenges according to the rapid development of Sino-Russian railway. In this paper, an algorithm is proposed, which is image edge detection track structure recognition and damage detection based on improved convolution model. This paper use image acquisition method and improved two-dimensional convolution to image filtering, thus the original image matrix is processed by determinant transformation to enhance image boundary elements. On the basis of the linear characteristics obtained from edge detection, the fastener cartridge and steel rails are identified. The damage and position of steel rails are judged by the sharp change of alignment. The image recognition and verification of the existing railway demonstrates that the method has the following advantages: It improves the rate of recognition structure and has certain adaptability. At the same time, the corresponding position of the structure can be determined, which is beneficial to the identification of structural damage. Besides, it plays an important role in the daily operation and maintenance of track.
IOS Press, Inc.
6751 Tepper Drive
Clifton, VA 20124
Tel.: +1 703 830 6300
Fax: +1 703 830 2300 firstname.lastname@example.org
(Corporate matters and books only) IOS Press c/o Accucoms US, Inc.
For North America Sales and Customer Service
West Point Commons
Lansdale PA 19446
Tel.: +1 866 855 8967
Fax: +1 215 660 5042 email@example.com