铁道科学与工程学报2018，Vol.15Issue(4)：1043-1049,7.
基于相对位置不变性的接触网鸟巢识别检测
Detection of birds' nest in catenary based on relative position invariance
摘要
Abstract
Combined with the features of platform of bird nesting, a novel foreign body detection method was proposed based on relative position invariance between hard beam and birds' nest. The proposed method aimed to overcome the difficulties in recognizing and locating the birds' nest in the various global images of the high speed railway contact net. Firstly, the image edge was obtained by using the horizontal Sobel edge detection operator. Secondly, the image was corrected by the method of probability Hough transform line detection, and the most front hard beam was analyzed by combining with the length of lines in the image. Thirdly, the image was processed through Otsu binarization processing and the existence of any birds' nest can be detected by computing the white area between two beams. The experiments show that the method can exactly recognize and locate the birds' nest between the beams. The algorithm has the characteristics of good accuracy, high automatic recognition rates and efficiency, and it can be provided for the safety inspection of railway contact network.关键词
鸟巢检测/相对位置不变/Sobel检测/概率Hough变换/OtsuKey words
birds' nest detection/relative position invariance/Sobel detection/probabilistic Hough transform/Otsu分类
信息技术与安全科学引用本文复制引用
祝振敏,谢亮凯..基于相对位置不变性的接触网鸟巢识别检测[J].铁道科学与工程学报,2018,15(4):1043-1049,7.基金项目
江西省杰出青年资助项目(20162BCB23047) （20162BCB23047）
江西省发明专利产业化重点资助项目(20161BBM26037) （20161BBM26037）
江西省科技支撑计划资助项目(20151BBE50116) （20151BBE50116）
