Visual detection of rice rows based on Bayesian decision theory and robust regression least squares method

Authors

  • Jing He Key Laboratory of Key Technology on Agricultural Machine and Equipment, Ministry of Education, South China Agricultural University, Guangzhou 510642, China
  • Ying Zang Key Laboratory of Key Technology on Agricultural Machine and Equipment, Ministry of Education, South China Agricultural University, Guangzhou 510642, China
  • Xiwen Luo Key Laboratory of Key Technology on Agricultural Machine and Equipment, Ministry of Education, South China Agricultural University, Guangzhou 510642, China
  • Runmao Zhao Key Laboratory of Key Technology on Agricultural Machine and Equipment, Ministry of Education, South China Agricultural University, Guangzhou 510642, China
  • Jie He Key Laboratory of Key Technology on Agricultural Machine and Equipment, Ministry of Education, South China Agricultural University, Guangzhou 510642, China
  • Jinkang Jiao Key Laboratory of Key Technology on Agricultural Machine and Equipment, Ministry of Education, South China Agricultural University, Guangzhou 510642, China

Keywords:

rice rows detection, Bayesian decision theory, clustering, RRLSM, credibility analysis, automatic tracking

Abstract

Paddy field management is complicated and labor intensive. Correct row detection is important to automatically track rice rows. In this study, a novel method was proposed for accurate rice row recognition in paddy field transplanted by machine before the disappearance of row information. Firstly, Bayesian decision theory based on the minimum error was used to classify the period of collected images into three periods (T1: 0-7 d; T2: 7-28 d; T3: 28-45 d), and resulting in the correct recognition rate was 97.03%. Moreover, secondary clustering of feature points was proposed, which can solve some problems such as row breaking and tilting. Then, the robust regression least squares method (RRLSM) for linear fitting was proposed to fit rice rows to effectively eliminate interference by outliers. Finally, a credibility analysis of connected region markers was proposed to evaluate the accuracy of fitting lines. When the threshold of credibility was set at 40%, the correct recognition rate of fitting lines was 96.32%. The result showed that the method can effectively solve the problems caused by the presence of duckweed, high-density inter-row weeds, broken rows, tilting (±60°), wind and overlap. Keywords: rice rows detection, Bayesian decision theory, clustering, RRLSM, credibility analysis, automatic tracking DOI: 10.25165/j.ijabe.20211401.5910 Citation: He J, Zang Y, Luo X W, Zhao R M, He J, Jiao J K. Visual detection of rice rows based on Bayesian decision theory and robust regression least squares method. Int J Agric & Biol Eng, 2021; 14(1): 199–206.

Author Biographies

Jing He, Key Laboratory of Key Technology on Agricultural Machine and Equipment, Ministry of Education, South China Agricultural University, Guangzhou 510642, China

He Jing, PhD, College of engineering, South China Agricultural University, Guangzhou, Guangdong

Ying Zang, Key Laboratory of Key Technology on Agricultural Machine and Equipment, Ministry of Education, South China Agricultural University, Guangzhou 510642, China

Zang Ying, PhD, Professor, College of engineering, South China Agricultural University, Guangzhou, Guangdong

Xiwen Luo, Key Laboratory of Key Technology on Agricultural Machine and Equipment, Ministry of Education, South China Agricultural University, Guangzhou 510642, China

Luo Xiwen, PhD, Professor, College of engineering, South China Agricultural University, Guangzhou, Guangdong

Runmao Zhao, Key Laboratory of Key Technology on Agricultural Machine and Equipment, Ministry of Education, South China Agricultural University, Guangzhou 510642, China

Zhao Runmao, PhD, College of engineering, South China Agricultural University, Guangzhou, Guangdong

Jie He, Key Laboratory of Key Technology on Agricultural Machine and Equipment, Ministry of Education, South China Agricultural University, Guangzhou 510642, China

He Jie, PhD, College of engineering, South China Agricultural University, Guangzhou, Guangdong

Jinkang Jiao, Key Laboratory of Key Technology on Agricultural Machine and Equipment, Ministry of Education, South China Agricultural University, Guangzhou 510642, China

Jiao Jinkang, PhD, College of engineering, South China Agricultural University, Guangzhou, Guangdong

References

Yi Z Y. China Agricultural Mechanization Yearbook 2017. China Agricultural Science and Technology Press, 2017; 136p. (in Chinese)

Yi Z Y. China Agricultural Mechanization Yearbook 2018. China Agricultural Science and Technology Press, 2018; 120p. (in Chinese)

Keicher R, Seufert H. Automatic guidance for agricultural vehicles in Europe. Computers and Electronics in Agriculture, 2000; 25(1-2): 169–194.

Bakker T, Wouters H, Asselt K V, Bontsema J, Tang L, Müller J, et al. A vision based row detection system for sugar beet. Computers and Electronics in Agriculture, 2008; 60(1): 87–95.

Bakker T, Asselt K V, Bontsema J, Müller J, van Straten G. Autonomous navigation using a robot platform in a sugar beet field. Biosystems Engineering, 2011; 109(4): 357–368.

García-Santillán I D, Montalvo M, Guerrero J M, Pajares G. Automatic detection of curved and straight crop rows from images in maize fields. Biosystems Engineering, 2017; 156: 61–79.

Zhang Q, Chen M E S, Li B. A visual navigation algorithm for paddy field weeding robot based on image understanding. Computers & Electronics in Agriculture, 2017; 143: 66–78.

Burgos-Artizzu X P, Ribeiro A, Tellaeche A, Pajares G, Fernández-Quintanilla G. Analysis of natural images processing for the extraction of agricultural elements. Image and Vision Computing, 2010; 28(1): 138–149.

Montalvo M, Pajares G, Guerrero J M, Romio J, Guijarro M, Ribeiro A, et al. Automatic detection of crop rows in maize fields with high weeds pressure. Expert Systems with Applications, 2012; 39(15): 11889–11897.

Kaizu Y, Imou K. A dual-spectral camera system for paddy rice seedling row detection. Computers and Electronics in Agriculture, 2008; 63(1): 49–56.

Tang L, Tian L F, Steward B L. Classification of broadleaf and grass weeds using Gabor wavelets and an artificial neural network. Transactions of the ASAE, 2003; 46(4): 1247–1254.

Jeon H Y, Tian L F, Zhu H. Robust crop and weed segmentation under uncontrolled outdoor illumination. Sensors, 2011; 11(12): 6270–6283.

Swain K C, NøRremark M, JøRgensen R N, Midtiby H S, Green O. Weed identification using an automated active shape matching (AASM) technique. Biosystems Engineering, 2011; 110(4): 450–457.

Hyyti H, Kalmari J, Visala A. Real-time detection of young spruce using color and texture features on an autonomous forest machine. In: 2013 International Joint Conference on Neural Networks. Dallas: IEEE, 2013; pp.1–8.

Hu L, Lin C X, Luo X W, Yang W W, Xu Y, Zhou H, et al. Design and experiment on auto leveling control system of agricultural implements. Transactions of the CSAE, 2015; 31(8): 15–20. (in Chinese)

Zhao R M, Hu L, Luo X W, Zhou H, Du P, Tang L M, et al. A novel approach for describing and classifying the unevenness of the bottom layer of paddy fields. Computers and Electronics in Agriculture, 2019; 158: 183–188

Søgaard H T, Olsen H J. Determination of crop rows by image analysis without segmentation. Computers and Electronics in Agriculture, 2003; 38(2): 141–158.

Jiang G, Wang Z, Liu H. Automatic detection of crop rows based on multi-ROIs. Expert Systems with Applications, 2015; 42(5): 2429–2441.

Zhang X Y, Li X N, Zhang B H, Zhou J, Tian G Z, Xiong Y J, et al. Automated robust crop-row detection in maize fields based on position clustering algorithm and shortest path method. Computers and Electronics in Agriculture, 2018; 154: 165–175.

Gao G Z, Wang Y Y, Zheng F X. The effect of light intensity on the growth and development of late rice at different closure periods - An empirical study on Chen Yongkang's suitable closure period for high-yield late rice (1). Acta Meteorologica Sinica, 1966; 2: 35–42

Wang W J. Crop cultivation. Science and Technology Literature Publishing House, 1998; 347p. (in Chinese)

Jiang G Q, Yang X Y, Wang Z H, Liu H M. Crop rows detection based on image characteristic point and particle swarm optimization-clustering algorithm. Transactions of CSAE, 2017; 33(11): 173–178. (in Chinese)

Choi K H, Han S K, Han S H, Park K H, Kim K S, Kim S H. Morphology-based guidance line extraction for an autonomous weeding robot in paddy fields. Computers and Electronics in Agriculture, 2015; 113: 266–274.

Liao J, Wang Y, Yin J, Zhang S, Liu L, Zhu D. Detection of seedling row centerlines based on sub-regional feature points clustering. Transactions of CSAM, 2019; 50(11): 34–41. (in Chinese)

Chen Z, Li W, Zhang W Q, Li Y W, Li M, Li H. Vegetable crop row extraction method based on accumulation threshold of Hough Transformation. Transactions of CSAE, 2019; 35(22): 314–322. (in Chinese)

Otsu N. A threshold selection method from gray-level histograms. Automatica, 1975; 11(285-296): 23–27.

Woebbecke D M, Meyer G E, Von Bargen K, Mortensen D A. Color indices for weed identification under various soil, residue, and lighting conditions. Transactions of the ASAE, 1995; 38(1): 259–269.

Bao X M, Wang Y M. Apple image segmentation based on the minimum error Bayes decision. Transactions of the CSAE, 2006; 22(5): 122–124. (in Chinese)

Liu C L. Image processing with MATLAB. Beijing: Tsinghua University press, 2017; 450p. (in Chinese)

Onyango C M, Marchant, J A. Segmentation of row crop plants from weeds using colour and morphology. Computers and Electronics in Agriculture, 2003; 39(3): 141–155.

Hu L, Luo X W, Zeng S, Zhang Z G, Chen X F, Lin C X. Plant recognition and localization for intra-row mechanical weeding device based on machine vision. Transactions of the CSAE, 2013; 29: 12–18. (in Chinese)

Javier G, Daniel P, Romer R. A robust partial least squares regression method with applications. Journal of Chemometrics, 2009; 23(2):78–90.

Huber P J. Robust statistics. Springer Berlin Heidelberg, 2011; 380p.

Lawson C, Keats J B, Montgomery D C. Comparison of robust and least-squares regression in computer-generated probability plot. IEEE Transactions on Reliability, 1997; 46(1): 108–115.

Downloads

Published

2021-02-10

How to Cite

He, J., Zang, Y., Luo, X., Zhao, R., He, J., & Jiao, J. (2021). Visual detection of rice rows based on Bayesian decision theory and robust regression least squares method. International Journal of Agricultural and Biological Engineering, 14(1), 199–206. Retrieved from https://www.ijabe.migration.pkpps06.publicknowledgeproject.org/index.php/ijabe/article/view/5910

Issue

Vol. 14 No. 1 (2021): IJABE

Section

Information Technology, Sensors and Control Systems

License

IJABE is an international peer reviewed, open access journal, adopting Creative Commons Copyright Notices as follows.

Authors who publish with this journal agree to the following terms:

  1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
  2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
  3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).