Fast Straight Line Detection Method Based on Directional Coding

Abstract

The Standard Hough Transform (SHT) is robust in detecting dashed or broken lines, but the main parts of it, blind vote, can cause excessive consumption of computation. To overcome this disadvantage, a fast straight line detection method based on directional coding(DCHT) is described in this paper. The algorithm turns the exhausted task of voting for all directions into an elegant task by constructing a sniffer and predicting direction of straight lines around the pixels. By using directional coding approach, the algorithm proposed here treats each direction of edge pixels differently, voting for a smaller angle range covering the direction of straight line which contains this edge pixel. In this way, half or more voting is removed. Experimental results show that DCHT algorithm has significant performance in reducing both execution time and the influence of noise on parameter space.

A Fast Gap Detection Algorithm Based on Machine Vision

“…Rafael et al [8] proposed an LSD line segment detection algorithm to detect gaps, but it needs to compute the magnitude and direction of the gradient of all points. Most of the gap detection algorithms are based on the theory of Hough transform [9] proposed by Hough, and there are two drawbacks of Hough transform: one is that the calculation is blind and the operational complexity is high [10] ; the other is that the peaks in the parameter domain are surrounded by many pseudo-peaks, which can easily lead to false detection [11] .…”