Abstract
For the benefits of productivity, efficiency and sustainability, the adoption of machine vision with robotics in applications has become essential in agriculture industry; for example, outdoor tender-tealeaf harvesting, where tasks are highly repetitive and laborious. As machine vision must cope with changing daylight conditions, among the challenges is an efficient technique to accurately detect/locate randomly distributed targets in natural background that has closely similar color as the targets of interests. The success of developing a harvesting machine depends on robust, accurate, and efficient target-detection, which is the first step of the automation. Built upon the concept of an artificial color contrast (ACC) model developed for color-feature classification using principal component analysis (PCA), this paper presents an improved ACC/PCA method to overcome commonly encountered target-detection problems for outdoor agriculture applications where targets in a closely similar background must be identified/located in real time for subsequent robotic handling. Specifically, several methods have been developed to determine an optimal feature-set boundary for effective target detection, which require only a limited set of training data. The effectiveness of the methods is evaluated using experimentally obtained samples in terms of three practical measures (% detection error, % numerical noise and computation time) by comparing results with commonly used methods.
Similar content being viewed by others
Abbreviations
- [A]:
-
Conversion matrix of tender PCA
- [B]:
-
Conversion matrix of old PCA
- [C]:
-
Covariance matrix of tender leaf samples
- D −, D + :
-
% Noise, % error
- G σc , G σs :
-
2D symmetric Gaussian kernels (zero-mean, width σc or σs)
- I d :
-
(Ir − If) image difference
- I e , I n :
-
(Error, noise) image
- I f :
-
Filtered binary images (with a range of widths)
- I r, I s :
-
(Reference, sample) image pixels
- P i :
-
Pixel value of ith principal component
- f i, i = 1, 2, 3:
-
The ith channel of RGB image
- f j :
-
Linear combination of RGB channels
- h (.,.,.) :
-
ACC image
- v :
-
Eigenvectors of [C]
- w(σ):
-
Width in terms of σ
- λ :
-
Eigenvalues of [C]
- (σA σB):
-
Standard deviations of (IA2,IB2) sample distribution
References
Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., Süsstrunk, S.: SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Trans. Pattern Anal. Mach. Intell. 34(11), 2274–2282 (2012)
Bu, R., Xiong, J., Chen, S., Zheng, Z., Guo, W., Yang, Z., Lin, X.: A Shadow detection and removal method for fruit recognition in natural environments. Precis. Agric. 21, 782–801 (2020)
Cabrera, C., Artacho, R., Giménez, R.: Beneficial effects of green tea—a review. J. Am. Coll. Nutr. 25(2), 79–99 (2006)
Chen, Y.T., Chen, S.F.: Localizing plucking points of tea leaves using deep convolutional neural networks. Comput. Electron. Agric. 171, 105298 (2020)
Christina, E.C., John, R.: Functional characteristics and diversity of Cat Retinal Ganglion cells. Invest. Ophthalmol. vis. Sci. 25, 250–267 (1984)
Fathi, K.M., Mohammed, S.N., Kuhnert, K.-D.: Fully-automatic natural plant recognition system using deep neural network for dynamic outdoor environments. SN Appl. Sci. 1, 756 (2019)
Han, Y., Xiao, H., Qin, G., Song, Z., Ding, W., Mei, S.: Developing situations of tea plucking machine. Engineering 06, 268–273 (2014)
Hering, E.: Outlines of a theory of light sense (translated by Hurvich and Jameson). Harvard University Press, Cambridge (1964)
Huang, H., Wu, M., Wang, X., Liu, S., Zhou, J.: Image recognition of tender leaves based on improved watershed algorithm in tea. Guizhou Agric. Sci. 46(4), 136–138 (2018)
Ikeda, T., Kanaya, S., Yonetani, T., Kobayashi, A., Fukusaki, E.: Prediction of Japanese green tea ranking by fourier transform near-infrared reflectance spectroscopy. J. Agric. Food Chem. 55, 9908–9912 (2007)
Krahe, J., Krahe, M., Roach, P.: Development of an objective measure of quality and commercial value of Japanese-styled green tea (Camellia L. sinensis): the Quality Index Tool. J. Food Sci. Technol. 55, 2926–2934 (2018)
Lee K.-M., Daley W. and Li Q.: Artificial Color Contrast for Machine Vision and its Effects on Feature Detection. IEEE/ASME International Conference on Advanced Intelligent Mechatronics. Monterey, California, USA, (2005).
Lee, K.-M., Li, Q., Daley, W.: Effects of classification methods on color-based feature detection with food processing applications. IEEE Trans. Autom. Sci. Eng. 4(1), 40–51 (2007)
Li Q. and Lee K.-M.: Effects of Color Characterization on Computational Efficiency of Feature Detection with Live-object Handling Applications. IEEE/ASME International Conference on Advanced Intelligent Mechatronics. Monterey, California, USA, (2005).
Li, H., Zhao, Q., Li, X., Zhang, X.: Object detection based on color and shape features for service robot in semi-structured indoor environment. Int. J. Intell. Robot. Appl. 3, 430–442 (2019)
Li W., Chen R., Gao Y.: Automatic Recognition of Tea Bud Image Based on Support Vector Machine. International Conference on Advanced Hybrid Information Processing. Springer, Cham, 279–290 (2020).
Liu, Z., Tian, Y., Yang, L., Yang, Q.: Automatic detection of tea shoots under overlapping conditions. Chin. J. Stereo Image Anal. 14(2), 129–132 (2009)
Meyer, G.E., Neto, J.C.: Verification of color vegetation indices for automated crop imaging applications. Comput. Electron. Agric. 63(2), 282–293 (2008)
Nanehkaran Y.A., Zhang D., Chen J., Tian Y. and AI-Nabhan N.: Recognition of Plant Leaf Diseases based on Computer Vision. Journal of Ambient Intelligence and Humanized Computing. 1–18 (2020).
Qian, C., Li, M., Ren, Y.: Tea sprouts segmentation via improved deep convolutional encoder-decoder network. IEICE Trans. Inf. Syst. 103(2), 476–479 (2020)
Slaughter, D., Gilesa, D., Downeya, D.: Autonomous robotic weed control systems: a review. Comput. Electron. Agric. 61, 63–78 (2008)
Verma, T., Dubey, S.: Impact of color spaces and feature sets in automated plant diseases classifier: a comprehensive review based on rice plant images. Arch. Comput. Methods Eng. 27, 1611–1632 (2020)
Wang, J.: Segmentation algorithm of tea combined with the color and region growing. J. Tea Sci. 31(1), 72–77 (2011)
Wu, X., Zhang, F., Lv, J.: Study on the method of tea tender leaf recognition based on image color information. J. Tea Sci. 33(6), 584–589 (2013)
Yang, W., Wang, S., Zhao, X., Zhang, J., Feng, J.: Greenness identification based on HSV decision tree. Inf. Process. Agric. 2(3–4), 149–160 (2015)
Yang, H., Chen, L., Chen, M., Ma, Z., Deng, F., Li, M., Li, X.: Tender tea shoots recognition and positioning for picking robot using improved YOLO-V3 model. IEEE Access. 7, 180998–181011 (2019)
Yao, G., Saltus, R., Dani, A.P.: Shape estimation for elongated deformable object using B-spline chained multiple random matrices model. Int. J. Intell. Robot. Appl. 4, 429–440 (2020)
Acknowledgements
This work was supported in part by the Guangxi Key Lab of Manufacturing System and Advanced Manufacturing Technology (19-050-44-005Z), Guangxi Science and Technology Base Talent Project (Guike-AD19245141), National Natural Science Foundation of China under Grant U1713204, and Innovation-driven Major Development Project of Guangxi (AA20161002-1).
Author information
Authors and Affiliations
Corresponding authors
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendices
Appendix
Principal Component Analysis (PCA)
Given N RGB samples, a covariance matrix [C] can be calculated from (24, 25) where \(i,j \in \{ R,\;G,\;B\}\):
Using (26) where (v1 v2 v3) are the eigenvectors corresponding to the eigenvalues (λ1, λ2, λ3) of [C] in descending order, image IRGB in RGB color space can be transformed to IPCA in the PCA coordinate system:
where \(\left[ {\mathbf{A}} \right] = \left[ {\begin{array}{*{20}c} {{\mathbf{v}}_{{\text{1}}}^{{\text{T}}} } & {{\mathbf{v}}_{2}^{{\text{T}}} } & {{\mathbf{v}}_{3}^{{\text{T}}} } \\ \end{array} } \right]^{{\text{T}}}\) and \( \overline{{\mathbf{I}}} _{{{\text{RGB}}}} = \left[ {\overline{{\text{I}}} _{{\text{R}}} \;\overline{{\text{I}}} _{{\text{G}}} \;\overline{{\text{I}}} _{{\text{B}}} } \right]^{{\text{T}}} \)
Rights and permissions
About this article
Cite this article
Lu, J., Huang, Y. & Lee, KM. Feature-set characterization for target detection based on artificial color contrast and principal component analysis with robotic tealeaf harvesting applications. Int J Intell Robot Appl 5, 494–509 (2021). https://doi.org/10.1007/s41315-021-00187-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s41315-021-00187-y