Intelligent Agrobots for Crop Yield Estimation using Computer Vision

D. Bini; D. Pamela; Thusnavis Bella Mary I.; D. Shamia; Shajin Prince

doi:10.24423/cames.419

D. Bini Karunya Institute of Technology and Sciences
D. Pamela Karunya Institute of Technology and Sciences
Thusnavis Bella Mary I. Karunya Institute of Technology and Sciences
D. Shamia V.S.B. College of Engineering Technical Campus
Shajin Prince Karunya Institute of Technology and Sciences

DOI: http://dx.doi.org/10.24423/cames.419

Abstract

The machine vision-based autonomous intelligent robots perform precise farm tasks such as robot harvesting, weeding, pest or fertilizer spraying, monitoring, and pruning. Estimating crop yield is an essential assignment on a regional or federal scale. For a long time the estimation measures were based on the statistics from manual counting of plants in a specific zone. The computer vision algorithms have addressed the technical drawbacks of the conventional image processing techniques and established an autonomous discipline and yielded new approaches to crop planning. A method for quantitative assessment of a tomato crop has been developed in this research using color thresholding in MATLAB using the RGB color model. Converting an RGB image to a grayscale image is one of the steps involved in detecting red color in a taken image. After subtracting the two images, a median filter is employed to filter the noisy pixels to produce a two-dimensional black and white image. The bounding boxes are used to label the binary digital images to detect related components, and the parameters of the labeled regions are computed to measure the number of tomatoes in a crop. The obtained R² correlation coefficient between the tomato berry counting algorithm and human counting was 0.98. Furthermore, the color of each pixel in the acquired image is evaluated by examining RGB values for pixel intensities in the obtained image. The performance of the berry counting algorithm was evaluated, and the technique was determined to have a high precision and recognition ratio of 96%. The research indicates that this technique may be used to estimate the crop yield, which is helpful information for forecasting yields, planning harvest plans, and generating prescription maps for field-specific management strategies. The proposed model performed exceptionally well in estimating yield with each tomato (Solanum lycopersicum) crop.

Keywords

computer vision, real-time images, autonomous agricultural robots, digital image processing, object detection, crop yield estimation,

References

1. J. Massah, K. Asefpour Vakilian, M. Shabanian, S.M. Shariatmadari, Design, development, and performance evaluation of a robot for yield estimation of kiwifruit, Computers and Electronics in Agriculture, 185(April), p. 106132, 2021, doi: 10.1016/j.compag.2021.106132.
2. R. Zhou, L. Damerow, Y. Sun, M.M. Blanke, Using colour features of cv. ‘Gala’ apple fruits in an orchard in image processing to predict yield, Precision Agriculture, 13(5): 568–580, 2012, doi: 10.1007/s11119-012-9269-2.
3. R. Xiang, Y. Ying, H. Jiang, Research on image segmentation methods of tomato in natural conditions, 2011 4th International Congress on Image and Signal Processing, 2011, pp. 1268–1272, doi: 10.1109/CISP.2011.6100424.
4. H. Li, W.S. Lee, K. Wang, Immature green citrus fruit detection and counting based on fast normalized cross correlation (FNCC) using natural outdoor colour images, Precision Agriculture, 17(6): 678–697, 2016, doi: 10.1007/s11119-016-9443-z.
5. D.M. Bulanon, T. Kataoka, Y. Ota, T. Hiroma, AE–Automation and emerging technologies: A segmentation algorithm for the automatic recognition of Fuji apples at harvest, Biosystems Engineering, 83(4): 405–412, 2002, doi: 10.1006/bioe.2002.0132.
6. S. Bargoti, J.P. Underwood, Image segmentation for fruit detection and yield estimation in apple orchards, Journal of Field Robotics, 34(6): 1039–1060, 2017, doi: 10.1002/rob.21699.
7. D. Font, M. Tresanchez, D. Martínez, J. Moreno, E. Clotet, J. Palacín, Vineyard yield estimation based on the analysis of high resolution images obtained with artificial illumination at night, Sensors, 15(4): 8284–8301, 2015, doi: 10.3390/s150408284.
8. D. Bini, D. Pamela, S. Prince, Machine vision and machine learning for intelligent agrobots: A review, 2020 5th International Conference on Devices, Circuits and Systems (ICDCS), pp. 12–16, 2020, doi: 10.1109/ICDCS48716.2020.243538.
9. M. Tripathi, Analysis of convolutional neural network based image classification techniques, Journal of Innovative Image Processing, 3(2): 100–117, 2021, doi: 10.36548/jiip.2021.2.003.
10. R. Sharma, A. Sungheetha, An efficient dimension reduction based fusion of CNN and SVM model for detection of abnormal incident in video surveillance, Journal of Soft Computing Paradigm, 3(2): 55–69, 2021, doi: 10.36548/jscp.2021.2.001.
11. R. Dhaya, R. Kanthavel, A. Ahilan, Developing an energy-efficient ubiquitous agriculture mobile sensor network-based threshold built-in MAC routing protocol (TBMP), Soft Computing, 25(18): 12333–12342, 2021, doi: 10.1007/s00500-021-05927-7.
12. K. Kottursamy, Multi-scale CNN Approach for Accurate Detection of Underwater Static Fish Image, Journal of Artificial Intelligence and Capsule Networks, 3(3): 230–242, 2021, doi: 10.36548/jaicn.2021.3.006.
13. A. Gong, J. Yu, Y. He, Z. Qiu, Citrus yield estimation based on images processed by an Android mobile phone, Biosystems Engineering, 115(2): 162–170, 2013, doi: 10.1016/j.biosystemseng.2013.03.009.
14. P. Annamalai, T.F. Burks, F.C. Laurier, Color Vision System for Estimating Citrus Yield in Real-time Written for presentation at the 2004 ASAE/CSAE Annual International Meeting Sponsored by ASAE/CSAE, 2004, https://elibrary.asabe.org/abstract.asp?JID=5&AID=16714&CID=can2004&T=1.
15. X. Liu et al., Monocular camera based fruit counting and mapping with semantic data association, IEEE Robotics and Automation Letters, 4(3): 2296–2303, 2019, doi: 10.1109/LRA.2019.2901987.
16. B. Darwin, P. Dharmaraj, S. Prince, D.E. Popescu, D.J. Hemanth, Recognition of bloom/yield in crop images using deep learning models for smart agriculture: A review, Agronomy, 11(4): 1–22, 2021, doi: 10.3390/agronomy11040646.
17. A.D. Aggelopoulou, D. Bochtis, S. Fountas, K.C. Swain, T.A. Gemtos, G.D. Nanos, Yield prediction in apple orchards based on image processing, Precision Agriculture, 12(3): 448–456, 2011, doi: 10.1007/s11119-010-9187-0.
18. M.A. Shaikh, S.B. Sayyad, Color image enhancement filtering techniques for agricultural domain using Matlab, [in:] ISRS Proceeding Papers on Sort Interactive Session. ISPRS TC VIII International Symposium on “Operational Remote Sensing Applications: Opportunities, Progress and Challenges”, Hyderabad, India, December 9–12, 2014, no. 224, 6 pages.
19. A.L. Tabb, D.L. Peterson, J. Park, Segmentation of apple fruit from video via background modeling, American Society of Agricultural and Biological Engineers, 2016, no. December, doi: 10.13031/2013.20873.
20. F. Yi, I. Moon, Image segmentation: A survey of graph-cut methods, International Conference on Systems and Informatics (ICSAI 2012), Yantai, China, 2012, pp. 1936–1941, doi: 10.1109/ ICSAI.2012.6223428.