Title :
Accurate Line Detection by Adjusting Hough Transform Threshold Adaptively
Author :
Ma, Yan ; Wang, Junning ; He, Di ; Pang, Jinbo
Author_Institution :
Dept. of Commun. Eng., Xidian Univ., Xi´´an, China
Abstract :
-A method to adjust the Hough transform threshold automatically is proposed in this paper. Straight lines are divided into two categories, parallel lines and intersection lines. Firstly we adjust the thresh roughly depending on the number of the needed lines. Then, the thresh are transformed precisely according to different characteristics of the two kinds of straight lines . Typically, this algorithm is applied to discern the runway in the aerial images of airports and recognize the bridge. Simulation results show that the algorithm requires short time and has a good anti-noise performance. Furthermore, it can solve the problems of "false peak" and "false negative".
Keywords :
Hough transforms; object recognition; parameter estimation; Hough transform threshold; accurate line detection; Algorithm design and analysis; Gaussian noise; Head; Image edge detection; Interference; Transforms;
Conference_Titel :
Wireless Communications Networking and Mobile Computing (WiCOM), 2010 6th International Conference on
Conference_Location :
Chengdu
Print_ISBN :
978-1-4244-3708-5
Electronic_ISBN :
978-1-4244-3709-2
DOI :
10.1109/WICOM.2010.5601319