Sugarcane crop line detection from UAV images using genetic algorithm and Radon transform

Unmanned aerial vehicle (UAV) has become a popular technology, and it has promoted the development of many applications in different areas. In the context of precision agriculture, UAV’s images enable us to identify the location of planting rows in order to plan and to estimate the crop production and the number of plants, as well as early identification and correction of failures in sowing. As these applications deal with low- or medium-altitude imagery, new image processing techniques are necessary to process these images. This paper proposes an automatic segmentation approach that uses a genetic algorithm (GA) and Radon transform to detect sugarcane crop lines from images obtained using a UAV assembled with an RGB sensor.

[1]  A. E. Eiben,et al.  Introduction to Evolutionary Computing , 2003, Natural Computing Series.

[2]  Josef Kittler,et al.  A survey of the hough transform , 1988, Comput. Vis. Graph. Image Process..

[3]  Payel Ghosh,et al.  Incorporating priors for medical image segmentation using a genetic algorithm , 2016, Neurocomputing.

[4]  Raphael Canals,et al.  CRowNet: Deep Network for Crop Row Detection in UAV Images , 2020, IEEE Access.

[5]  C. Daughtry,et al.  What good are unmanned aircraft systems for agricultural remote sensing and precision agriculture? , 2018 .

[6]  Edison Pignaton de Freitas,et al.  A UAV Guidance System Using Crop Row Detection and Line Follower Algorithms , 2019, Journal of Intelligent & Robotic Systems.

[7]  Daniel Duarte Abdala,et al.  A curve completion algorithm for agricultural planning , 2018, SAC.

[8]  Lijun Qi,et al.  Crop-row detection algorithm based on Random Hough Transformation , 2011, Math. Comput. Model..

[9]  Vincent Leemans,et al.  Line cluster detection using a variant of the Hough transform for culture row localisation , 2006, Image Vis. Comput..

[10]  Daniel Duarte Abdala,et al.  Plantation Rows Identification by Means of Image Tiling and Hough Transform , 2018, VISIGRAPP.

[11]  Salvatore Tabbone,et al.  Amplitude-only log Radon transform for geometric invariant shape descriptor , 2014, Pattern Recognit..

[12]  Gonzalo Pajares,et al.  Curved and straight crop row detection by accumulation of green pixels from images in maize fields , 2018, Precision Agriculture.

[13]  Salvatore Tabbone,et al.  Histogram of Radon transform with angle correlation matrix for distortion invariant shape descriptor , 2016, Neurocomputing.

[14]  Sadiq M. Sait,et al.  Evolutionary algorithms, simulated annealing and tabu search: a comparative study , 2001 .

[15]  Gonzalo Pajares,et al.  Automatic detection of crop rows in maize fields with high weeds pressure , 2012, Expert Syst. Appl..

[16]  Ivan Vidovic,et al.  Crop row detection by global energy minimization , 2016, Pattern Recognit..

[17]  Gonzalo Pajares,et al.  Crop rows and weeds detection in maize fields applying a computer vision system based on geometry , 2017, Comput. Electron. Agric..

[18]  Robert Stanton,et al.  Radiological Imaging: The Theory of Image Formation, Detection, and Processing , 1983 .

[19]  J. Anitha,et al.  Modified Genetic Algorithm approaches for classification of abnormal Magnetic Resonance Brain tumour images , 2019, Appl. Soft Comput..

[20]  Gonzalo Pajares,et al.  Automatic expert system for weeds/crops identification in images from maize fields , 2013, Expert Syst. Appl..

[21]  Dana H. Ballard,et al.  Generalizing the Hough transform to detect arbitrary shapes , 1981, Pattern Recognit..

[22]  Fan Guo,et al.  Genetic algorithm-based parameter selection approach to single image defogging , 2016, Inf. Process. Lett..

[23]  Melanie Mitchell,et al.  An introduction to genetic algorithms , 1996 .