Online Detection System for Wheat Machine Harvesting Impurity Rate Based on DeepLabV3+
Abstract
:1. Introduction
1.1. Background
1.2. Literature Review
1.3. Contributions
2. Materials and Methods
2.1. Online Detection Device for Wheat Impurity Rate
2.2. The Network Architecture of DeepLabV3+
2.3. DeepLabV3+ Network Training
2.3.1. Data Annotation and Augmentation
2.3.2. Network Training
2.4. Test Design
2.4.1. Bench Test Design
2.4.2. Field Trial Design
2.5. Performance Evaluation
2.5.1. Network Recognition and Segmentation Performance Evaluation Index
2.5.2. Performance Evaluation of Wheat Impurity Content Detection Based on Image Information
3. Results and Discussion
3.1. Comparison of Different Backbones
3.2. ResNet-50 Online Recognition and Segmentation Effect Analysis
3.3. Analysis of the Detection Effect of Impurity Rate
4. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Geng, D.Y.; Mu, X.D.; Zhang, G.D.; Wang, Z.Y.; Zhu, J.k.; Xu, H.G. Analysis and optimization of cleaning mechanism of wheat combine harvester. J. Jilin Univ. (Eng. Technol. Ed.) 2022, 52, 219–230. [Google Scholar] [CrossRef]
- Zhou, Y.H.; Yi, Z.X.; Luo, C.H.; Li, L.W.; An, X.F.; Zhang, A.Q. Error dynamic self-calibration method for grain yield monitoring based on combine harvester. Trans. Chin. Soc. Agric. Mach. 2020, 51, 147–153. [Google Scholar] [CrossRef]
- Jin, C.Q.; Li, Q.L.; Ni, Y.L.; Wang, T.E.; Yin, X. Experimental study on double air outlet multi-ducts cleaning device of wheat combine harvester. Trans. Chin. Soc. Agric. Eng. (Trans. CSAE) 2020, 36, 26–34. [Google Scholar] [CrossRef]
- Chen, M.; Ni, Y.L.; Jin, C.Q.; Xu, J.S.; Zhang, G.Y. Online monitoring method f mechanized soybean harvest quality based on machine vision. Trans. Chin. Soc. Agric. Mach. 2021, 52, 91–98. [Google Scholar] [CrossRef]
- Chen, J.; Zhang, S.; Li, Y.M.; Zhu, L.J.; Xia, H.; Zhu, Y.H. Research on online identification system of rice broken impurities in combine harvester. J. Chin. Agric. Mech. 2021, 42, 137–144. [Google Scholar] [CrossRef]
- Wu, T.R.; Chen, Y.J.; Yang, S.H.; Shi, W.S.; Li, M.H.; Xia, B. Detection and experiment on seed cotton impurity rate based on image analysis. J. Xi’an Univ. Technol. 2021, 37, 235–241. [Google Scholar] [CrossRef]
- Feng, J.K.; Zheng, Y.; Li, P.; Li, Y.C.; Zhang, Z.Y.; Guo, X.J. Research on the identification of wheat grain varieties based on feature selection. J. Chin. Agric. Mech. 2022, 43, 116–123. [Google Scholar] [CrossRef]
- Yan, N.; Zhang, H.; Dong, H.T.; Kang, K.; Luo, B. Wheat variety recognition method based on same position segmentation of transmitted light and reflected light images. Acta Agric. Zhejiangensis 2022, 34, 590–598. [Google Scholar] [CrossRef]
- Zeng, H.W.; Lei, J.B.; Tao, J.F.; Liu, C.L. Yield monitoring for grain combine harvester based on monocular vision. Trans. Chin. Soc. Agric. Mach. 2021, 52, 281–289. [Google Scholar]
- Chen, J.; Han, M.N.; Lian, Y.; Zhang, S. Segmentation of impurity rice grain images based on U-Net model. Trans. Chin. Soc. Agric. Eng. (Trans. CSAE) 2020, 36, 174–180. [Google Scholar] [CrossRef]
- Guo, M.; Ma, Y.T.; Yang, X.J.; Mankin, R.W. Detection of damaged wheat kernels using an impact acoustic signal processing technique based on Gaussian modelling and an improved extreme learning machine algorithm. Biosyst. Eng. 2019, 184, 37–44. [Google Scholar] [CrossRef]
- Moghimia, A.; Yanga, C.; Andersonb, J.A. Aerial hyperspectral imagery and deep neural networks for high-throughput yield phenotyping in wheat. Comput. Electron. Agric. 2020, 172, 105299. [Google Scholar] [CrossRef] [Green Version]
- Laabassi, K.; Belarbi, M.A.; Mahmoudi, S.; Mahmoudi, S.A.; Ferhat, K. Wheat varieties identification based on a deep learning approach. J. Saudi Soc. Agric. Sci. 2021, 20, 281–289. [Google Scholar] [CrossRef]
- Ferreira, M.B.; Almeidab, D.R.; Papac, D.; Minervinod, J.B.; Verase, H.F.; Formighierid, A.; Santosc, C.A.; Ferreiraf, M.A.; Figueiredoc, E.O.; Ferreirag, E.J. Individual tree detection and species classification of Amazonian palms using UAV images and deep learning. For. Ecol. Manag. 2020, 475, 118397. [Google Scholar] [CrossRef]
- Zhao, Y.Y.; Wu, W.; Zhou, Y.Z.; Zhu, B.; Yang, T.L.; Yao, Z.S.; Ju, C.X.; Sun, C.M.; Liu, T. A backlight and deep learning based method for calculating the number of seeds per silique. Biosyst. Eng. 2022, 213, 182–194. [Google Scholar] [CrossRef]
- Zhang, D.Y.; Ding, Y.; Chen, P.F.; Zhang, X.Q.; Pan, Z.G.; Liang, D. Automatic extraction of wheat lodging area based on transfer learning method and deeplabv3+ network. Comput. Electron. Agric. 2020, 179, 105845. [Google Scholar] [CrossRef]
- Bhagat, S.; Kokare, M.; Haswani, V.; Hambarde, P.; Kamble, R. Eff-UNet++: A novel architecture for plant leaf segmentation and counting. Ecol. Inform. 2022, 68, 101583. [Google Scholar] [CrossRef]
- Yang, Q.; She, B.; Huang, L.S.; Yang, Y.Y.; Zhang, G.; Zhang, M.; Huang, L.S.; Hong, Q.; Zhang, D.Y. Extraction of soybean planting area based on feature fusion technology of multi-source low altitude unmanned aerial vehicle images. Ecol. Inform. 2022, 70, 101715. [Google Scholar] [CrossRef]
- Shen, Y.; Yin, Y.X.; Lin, B.; Zhao, C.J.; Li, G.L. Detection of impurities in wheat using terahertz spectral imaging and convolutional neural networks. Comput. Electron. Agric. 2021, 181, 105931. [Google Scholar] [CrossRef]
- Chen, M.; Ni, Y.L.; Jin, C.Q.; Xu, J.S.; Yuan, W.S. High spectral inversion of wheat impurities rate for grain combine harvester. Trans. Chin. Soc. Agric. Eng. (Trans. CSAE) 2019, 35, 22–29. [Google Scholar] [CrossRef]
- Wu, Z.C.; Yang, R.C.; Gao, F.F.; Wang, W.Q.; Fu, L.S.; Li, R. Segmentation of abnormal leaves of hydroponic lettuce based on DeepLabV3+ for robotic sorting. Comput. Electron. Agric. 2021, 190, 106443. [Google Scholar] [CrossRef]
- Sun, Z.T.; Zhu, S.N.; Gao, Z.J.; Gu, M.Y.; Zhang, G.L.; Zhang, H.M. Recognition of grape growing areas in multispectral images based on band enhanced DeepLabv3+. Trans. Chin. Soc. Agric. Eng. (Trans. CSAE) 2022, 38, 229–236. [Google Scholar] [CrossRef]
- Mu, T.Y.; Zhao, W.; Hu, X.Y.; Li, D. Rice lodging recognition method based on UAV remote sensing combined with the improved DeepLabV3+ model. J. China Agric. Univ. 2022, 27, 143–154. [Google Scholar] [CrossRef]
- Dai, Y.S.; Zhong, X.C.; Sun, C.M.; Yang, J.; Liu, T.; Liu, S.P. Identification of fusarium head blight in wheat based on image processing and Deeplabv3+ model. J. Chin. Agric. Mech. 2021, 42, 209–215. [Google Scholar] [CrossRef]
- Chen, L.C.; Zhu, Y.; Papandreou, G.; Schroff, F.; Adam, H. Encoder-Decoder with atrous separable convolution for semantic image segmentation. Eur. Conf. Comput. Vis. 2018, 11211, 833–851. [Google Scholar] [CrossRef] [Green Version]
- Yin, Q.J.; Yang, W.Z.; Ran, M.G.; Wang, S.L. FD-SSD: An improved SSD object detection algorithm based on feature fusion and dilated convolution. Signal Process. Image Commun. 2021, 98, 116402. [Google Scholar] [CrossRef]
Model Backbone | DeepLabV3+ | ||||
---|---|---|---|---|---|
MobileNetV2 | Xception-65 | ResNet-50 | ResNet-101 | ||
Grains | P (%) | 85.31 | 83.57 | 86.86 | 84.54 |
R (%) | 75.41 | 77.76 | 80.63 | 79.32 | |
F1 (%) | 80.06 | 80.56 | 83.63 | 81.85 | |
FIOU | 0.6674 | 0.6745 | 0.7186 | 0.6927 | |
Impurities | P (%) | 93.72 | 95.03 | 89.91 | 90.78 |
R (%) | 73.70 | 74.39 | 84.61 | 77.93 | |
F1 (%) | 82.51 | 83.45 | 87.18 | 83.87 | |
FIOU | 0.7023 | 0.7160 | 0.7727 | 0.7221 | |
FMIOU | 0.6849 | 0.7060 | 0.7457 | 0.7074 | |
Iv (ms) | 234 | 268 | 256 | 261 |
Index | Bench Test | Field Test | ||||||||
---|---|---|---|---|---|---|---|---|---|---|
P (%) | R (%) | F1 (%) | FIOU | FMIOU | P (%) | R (%) | F1 (%) | FIOU | FMIOU | |
Grains | 0.9625 | 0.5888 | 0.7306 | 0.5756 | 0.6201 | 0.9900 | 0.5162 | 0.6786 | 0.6646 | 0.7104 |
Impurities | 0.9340 | 0.6973 | 0.7985 | 0.6646 | 0.8871 | 0.8366 | 0.8611 | 0.7561 |
Test Type | RScv (%) | RMcv(%) | Raz (%) | Rrz (%) | |||
---|---|---|---|---|---|---|---|
Bench test | 1 | 0.92 | 1.03 | 35.24 | 17.39 | 0.11 | 10.68 |
2 | 0.95 | 1.15 | 31.79 | 12.43 | 0.20 | 17.34 | |
3 | 0.97 | 0.93 | 33.00 | 11.42 | 0.04 | 4.29 | |
Field test | 1 | 1.11 | 1.18 | 33.43 | 28.63 | 0.06 | 5.1 |
2 | 1.15 | 1.28 | 39.33 | 21.94 | 0.13 | 10.16 | |
3 | 1.08 | 0.94 | 46.31 | 21.51 | 0.13 | 13.78 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Chen, M.; Jin, C.; Ni, Y.; Xu, J.; Yang, T. Online Detection System for Wheat Machine Harvesting Impurity Rate Based on DeepLabV3+. Sensors 2022, 22, 7627. https://doi.org/10.3390/s22197627
Chen M, Jin C, Ni Y, Xu J, Yang T. Online Detection System for Wheat Machine Harvesting Impurity Rate Based on DeepLabV3+. Sensors. 2022; 22(19):7627. https://doi.org/10.3390/s22197627
Chicago/Turabian StyleChen, Man, Chengqian Jin, Youliang Ni, Jinshan Xu, and Tengxiang Yang. 2022. "Online Detection System for Wheat Machine Harvesting Impurity Rate Based on DeepLabV3+" Sensors 22, no. 19: 7627. https://doi.org/10.3390/s22197627
APA StyleChen, M., Jin, C., Ni, Y., Xu, J., & Yang, T. (2022). Online Detection System for Wheat Machine Harvesting Impurity Rate Based on DeepLabV3+. Sensors, 22(19), 7627. https://doi.org/10.3390/s22197627