Crop-row detection algorithm based on Random Hough Transformation

• Published in: Mathematical and computer modelling Vol. 54; no. 3; pp. 1016 - 1020
• Main Authors: Ji, Ronghua, Qi, Lijun
• Format: Journal Article
• Language: English
• Published: Kidlington Elsevier Ltd 01.08.2011; Elsevier
• Subjects: algorithms; Crop row; Detection algorithm; Exact sciences and technology; Mathematical analysis; Mathematics; Methods of scientific computing (including symbolic computation, algebraic computation); Numerical analysis. Scientific computation; plant density; Random Hough Transform; Sciences and techniques of general use; Random Hough Transform; Detection algorithm; Crop row; Experimental result; Applied mathematics; Distribution function; Mathematical model; Algorithm; Computer aided analysis
• ISSN: 0895-7177; 1872-9479
• DOI: 10.1016/j.mcm.2010.11.030

It is important to detect crop rows accurately for field navigation. In order to spray on line, a variable rate spray system should detect the crop center line accurately. Most existing detection algorithms are slow to detect crop rows because of the complicated calculation. The gradient-based Random Hough Transform algorithm could improve the calculation speed and reduce the computation effectively by the more-to-one merger mapping method. In order to detect the center of the crop row rapidly and effectively, the detection algorithm with gradient-based Random Hough Transform was proposed to detect the center line of crop rows. We tested the center line of crop-row detection for three kinds of plant distribution, being sparse, general and intensive. The experimental results showed that the detection algorithm with gradient-based Random Hough Transform was adaptive to the difference of plant density in the crop row effectively. Contrasted with the detection algorithm based on the Hough transform, the detection algorithm based on the gradient-based Random Hough was faster and had a high detection correction rate.