Estimation of rapeseed crop density at the two-leaf stage based on image processing and using a combination of Gaussian Mixture Model and k-means clustering algorithms

Rezaee, Alireza; Khalili, Seyed Morteza; Asadpour, Milad

doi:10.22092/amsr.2021.354218.1381

Document Type : Original Article

Authors

¹ Assistant Professor, Intelligent mobile robot lab, Interdisciplinary Technology group, Mechatronics and Mems part, faculty of new sciences and technologies, university of Tehran, Tehran, Iran,

² post-graduate student, Interdisciplinary Technology group, Mechatronics and mems part, faculty of new sciences and technologies, university of Tehran, Tehran, Iran

³ tehran , tehran univesity , mechatronic department

https://doi.org/10.22092/amsr.2021.354218.1381

Abstract

Today, with the expansion of industrial agriculture, the use of new sciences and technologies such as artificial intelligence has a significant role in increasing productivity and smartening of agricultural methods. These methods include estimating seedling density using image processing methods. In addition to helping agricultural land management, this is also effective in assessing the amount of fertilizer and chemicals and determining the storage space required. In this paper, a new method for estimating rapeseed crop density at the two-leaf stage is proposed. To prepare the images, first, images were taken from several random areas of the rapeseed field in the two-leaf stage located in the village of Mohammadabad, Qazvin, using square frames one meter long to meet the usual standards; Then the Gaussian mixed model with the Expectation Maximization algorithm is used to segment the images. In order to improve the segmentation of the images, the k-mean clustering algorithm was used and finally, when the leaves were separated from the other components of the image, morphological operators were used to count the number of products in the images. The number of rapeseed products in the images is also averaged manually and used as reference values to evaluate the performance of the proposed algorithm. The results of the proposed method have a correlation of R=0.96 with the manual counting method and have an accuracy of 96.5%. The results of the proposed method are also compared with two common methods called the Normalized Difference Index (NDI) and the Otsu threshold methods which are based on the color characteristics of the images and used in recent studies, and it is observed that the proposed method works better. Although the images were taken in different environmental conditions and with different light intensities, the error rate of the proposed method for the images used was only less than four percent, which shows the efficiency of the proposed method in estimating canola density. Therefore, the proposed method can be used in estimating canola seedlings in practice in agricultural fields.

Keywords

References

Bairwa, N., Agrawal, N. K., & Gupta, S. (2017). Development of counting algorithm for overlapped agricultural products. International Journal of Computer Applications, 975, 16-19.

Bishop, C. M. (2006). Pattern recognition and machine learning. eBook, Springer.

Carré, P., & Pouzet, A. (2016). Rapeseed market, worldwide and in Europe. Ocl, 21(1), D102- D113.

Chabok, F., Rezaee, A., & Asadpour, M. (2021). Sensor data fusion for positioning of agriculture mobile robotusing dempster-shafer method. Agricultural Mechanization and Systems Research, 22(78), 89-106.

Cordill, C., & Grift, T. E. (2016). Design and testing of an intra-row mechanical weeding machine for corn. Biosystems Engineering, 110(3), 247-252.

Dorj, U. O., Lee, M., & Lee, K. K. (2018). A computer vision algorithm for tangerine yield estimation. International Journal of Bio-Science and Bio-Technology, 5(5), 101-110.

Ehlert, D., Adamek, R., & Horn, H. J. (2013). Vehicle based laser range finding in crops. Sensors, 9(5), 3679-3694.

Karbasi, A., Mohammadzade, S., & Hendizade, H. (2019). Analysis of effective factors on increasing the area under rapeseed cultivation in rural areas. Journal of Space Economics and Rural Development, 8(3), 187-202.

Lenaerts, B., Craessaerts, G., Baerdemaeker, J. D., & Saeys, W. (2015). Crop stand density prediction using LIDAR-sensors. Proceedings of the Agricultural and biosystems engineering for a sustainable world. International Conference on Agricultural Engineering, 23-25 June, 2008. European Society of Agricultural Engineers (AgEng). Hersonissos, Crete, Greece.

Maertens, K., Reyns, P., De Clippel, J., & De Baerdemaeker, J. (2003). First experiments on ultrasonic crop density measurement. Journal of sound and Vibration, 266(3), 655-665.

Mavaddati, S. (2021). Rice classification with fractal-based features based on sparse structured principal component analysis and Gaussian mixture model. Journal of AI and Data Mining. 9(2), 235-244.

Payne, A. B., Walsh, K. B., Subedi, P. P., & Jarvis, D. (2019). Estimation of mango crop yield using image analysis–segmentation method. Computers and Electronics in Agriculture, 91, 57-64.

Rezaei, Y., Rezaee, A., Darakeh, F., & Azarakhsh, Z. (2021). Classification of polarimetric radar images based on SVM and BGSA. Signal and Data Processing, 18(1) :102-87. (in Persian)

Wang, Q., Nuske, S., Bergerman, M., & Singh, S. (2013). Automated crop yield estimation for apple orchards. Proceedings of the The 13^th International Symposium on Experimental Robotics, June 18-21. Québec City, Canada.

Wang, Z., Ritou, M., Da Cunha, C., & Furet, B. (2020). Contextual classification for smart machining based on unsupervised machine learning by Gaussian mixture model. International Journal of Computer Integrated Manufacturing, 33(10-11), 1042-1054.

Yamamoto, K., Guo, W., Yoshioka, Y., & Ninomiya, S. (2017). On plant detection of intact tomato fruits using image analysis and machine learning methods. Sensors, 14(7), 12191-12206.

Zeng, S., Huang, R., Kang, Z., & Sang, N. (2014). Image segmentation using spectral clustering of Gaussian mixture models. Neurocomputing, 144, 346-356.

Estimation of rapeseed crop density at the two-leaf stage based on image processing and using a combination of Gaussian Mixture Model and k-means clustering algorithms

References

References

Volume 22, Issue 80 - Serial Number 80March 2022Pages 33-50

Volume 22, Issue 80 - Serial Number 80
March 2022
Pages 33-50