research-article

Detecting volunteer cotton plants in a corn field with deep learning on UAV remote-sensing imagery

Authors:

Pappu Kumar Yadav,

J. Alex Thomasson,

Stephen W. Searcy,

Ulisses Braga-Neto,

Sorin C. Popescu,

Daniel E Martin,

Roberto Rodriguez,

Jorge Solorzano Diaz,

Tianyi WangAuthors Info & Claims

Volume 204, Issue C

https://doi.org/10.1016/j.compag.2022.107551

Published: 01 January 2023 Publication History

Abstract

Volunteer cotton (VC) plants growing in the fields of inter-seasonal and rotated crops, like corn, can serve as hosts to boll weevil pests once they reach pin-head square stage (5–6 leaf stage). The VC plants therefore need to be detected, located, and destroyed or sprayed. In this paper, we present a study on using deep learning (DL) to detect VC plants in a corn field using RGB images collected with an unmanned aerial vehicle (UAV). The objectives were (i) to determine whether the YOLOv3 DL algorithm could be used for VC detection in a corn field based on UAV-derived RGB images, and (ii) to investigate the behavior of YOLOv3 on images at three different pixel scales (320 × 320, S1; 416 × 416, S2; and 512 × 512, S3). The metrics used to evaluate the results were average precision (AP), mean average precision (mAP) and F1-score at 95 % confidence level. It was found that YOLOv3 was able to detect VC plants in corn field at an average detection accuracy of more than 80 %, F1-score of 78.5 % and mAP of 80.38 %. With respect to images size, no significant differences existed for mAP among the three scales, but a significant difference was found for AP between S1 and S3 (p = 0.04) and between S2 and S3 (p = 0.02). A significant difference was also found for F1-score between S2 and S3 (p = 0.02). The overall goal of this study was to minimize boll weevil pest infestation by maximizing the true positive detection of VC plants in a corn field which is represented by the mAP values. The lack of significant differences of these at all three scales indicated that the trained YOLOv3 model can be used for VC detection irrespective of the three input image sizes. The capability of YOLOv3 to detect VC plants demonstrates the potential of DL algorithms for real-time detection and mitigation using computer vision and a spot-spray capable UAV.

References

[1]

AlexeyAB, 2020. Yolo v4, v3 and v2 for Windows and Linux [WWW Document]. URL https://github.com/AlexeyAB/darknet.

[2]

A. Ammar, A. Koubaa, M. Ahmed, A. Saad, B. Benjdira, Aerial images processing for car detection using convolutional neural networks: comparison between faster R-CNN and YoloV3, J. Not Specified 1 (2021),.

[3]

S.L. Anderson, S.C. Murray, L. Malambo, C. Ratcliff, S. Popescu, D. Cope, A. Chang, J. Jung, J.A. Thomasson, Prediction of maize grain yield before maturity using improved temporal height estimates of unmanned aerial systems, Plant Phenome J. 2 (2019) 1–15,.

[4]

Bojarski, M., Choromanska, A., Choromanski, K., Firner, B., Jackel, L., Muller, U., Zieba, K., 2016. VisualBackProp: efficient visualization of CNNs. arXiv Prepr. arXiv1611.05418.

[5]

M. Buzzy, V. Thesma, M. Davoodi, J.M. Velni, Real-time plant leaf counting using deep object detection networks, Sensors (Switzerland) 20 (2020) 1–14,.

[6]

G. Carlson A; Sappie, G., Hammig, M., Economic Returns to Boll Weevil Eradication 1989 Washington D.C. USDA Agricultural Economic Report No.621.

[7]

Y. Chen, W.S. Lee, H. Gan, N. Peres, C. Fraisse, Y. Zhang, Y. He, Strawberry yield prediction based on a deep neural network using high-resolution aerial orthoimages, Remote Sens. 11 (2019) 1–21,.

[8]

Choi, J., Chun, D., Kim, H., Lee, H.J., 2019. Gaussian YOLOv3: An Accurate and Fast Object Detector Using Localization Uncertainty for Autonomous Driving, in: Proceedings of the IEEE International Conference on Computer Vision. pp. 502–511.

[9]

The SciPy Community, 2021. Statistical functions (scipy.stats) [WWW Document]. URL https://docs.scipy.org/doc/scipy/reference/stats.html.

[10]

F.M.C. Corporation, FYFANON ULV AG, FYFANON ULV AG (2001),.

[11]

Davis, J., Goadrich, M., 2006. The relationship between Precision-Recall and ROC curves, in: Proceedings of the 23rd International Conference on Machine Learning. pp. 233–240.

[12]

O.J. Dunn, Multiple Comparisons among Means, J. Am. Stat. Assoc. 56 (1961) 52–64,.

[13]

Foster, R.N., 2009. Boll Weevil. Encycl. Insects. https://doi.org/10.1016/B978-0-12-374144-8.00039-4.

[14]

R. Gajjar, N. Gajjar, V.J. Thakor, N.P. Patel, S. Ruparelia, Real-time detection and identification of plant leaf diseases using convolutional neural networks on an embedded platform, Vis. Comput. 38 (2022) 2923–2938,.

Digital Library

[15]

Grefenstette, B., El-Lissy, O., 2003. Boll weevil eradication update, in: Proceedings of the Beltwide Cotton Conferences. pp. 131–141.

[16]

X. Han, J.A. Thomasson, G.C. Bagnall, N.A. Pugh, D.W. Horne, W.L. Rooney, J. Jung, A. Chang, L. Malambo, S.C. Popescu, I.T. Gates, D.A. Cope, Measurement and Calibration of Plant-Height from Fixed-Wing UAV Images, Sensors 18 (2018),.

[17]

T.V. Hecke, Power study of anova versus Kruskal-Wallis test, J. Stat. Manag. Syst. 15 (2012) 241–247,.

[18]

Texas Boll Weevil Eradictaion Foundation Inc., 2020. TWEF.pdf [WWW Document].

[19]

Texas Boll Weevil Eradictaion Foundation Inc, 2020. Texas Boll Weevil Eradication Quarantine Status.

[20]

T. Jintasuttisak, E. Edirisinghe, A. Elbattay, Deep neural network based date palm tree detection in drone imagery, Comput. Electron. Agric. 192 (2022) 1–11,.

Digital Library

[21]

A.M. Kist, Glottis Analysis Tools - Deep Neural Networks, Zenodo (2021),.

[22]

F. Kraus, K. Dietmayer, Uncertainty Estimation in One-Stage Object Detection. 2019 IEEE Intell, Transp. Syst. Conf. ITSC 2019 (2019) 53–60,.

Digital Library

[23]

D.K. Lee, J. In, S. Lee, Standard deviation and standard error of the mean, Korean J. Anesthesiol. 68 (2015) 220–223,.

[24]

V. Mazzia, A. Khaliq, F. Salvetti, M. Chiaberge, Real-time apple detection system using embedded systems with hardware accelerators: An edge AI application, IEEE Access 8 (2020) 9102–9114,.

[25]

D. Mccorkle, J.R.C. Robinson, D. Hanselka, S.L. Klose, T.W. Fuchs, C.T. Allen, The Economic Impact of Boll Weevil Eradication in Texas, Texas J. Agric. Nat. Resour. 23 (2010) 50–63.

[26]

Morgan, G.D., Fromme, D.A., Baumann, P.A., Grichar, J., Bean, B., Matocha, M.E., Mott, D.A., 2011. Managing Volunteer Cotton in Grain Crops.

[27]

Morgan, G.D., McGinty, J., Nolte, S., Matocha, M., 2019. Managing Volunteer Cotton in Grain Crops.

[28]

National Cotton Council of America, 2012. Protocol for the Eradication of the Boll Weevil in the Lower Rio Grande Valley in Texas and Tamaulipas, Mexico, cotton.org.

[29]

A.I.B. Parico, T. Ahamed, Real Time Pear Fruit Detection and Counting Using YOLOv4 Models and Deep SORT, Sensors (2021) 1–32.

[30]

V. Partel, S. Charan Kakarla, Y. Ampatzidis, Development and evaluation of a low-cost and smart technology for precision weed management utilizing artificial intelligence, Comput. Electron. Agric. 157 (2019) 339–350,.

Digital Library

[31]

M. Pimenta, R.A. Mata, M. Venzon, D.N.C. Cunha, E.M.G. Fontes, C.S.S. Pires, E.R. Sujii, Survival and preference of cotton boll weevil adults for alternative food sources, Brazilian J. Biol. 76 (2016) 387–395,.

[32]

Redmon, J., Farhadi, A., 2018. YOLOv3:An Incremental Improvement, in: Computer Vision and Pattern Recognition. arXiv preprint arXiv:1804.02767, Berlin/Heidelberg, Germany.

[33]

Robinson, J.R.C.; Vergara, O., 1999. Structural changes to consider in the valuation of boll weevil eradication programs, in: Proceedings of the Beltwide Cotton Conferences. National Cotton Council. pp. 321–324.

[34]

O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A.C. Berg, L. Fei-Fei, ImageNet Large Scale Visual Recognition Challenge, Int. J. Comput. Vis. 115 (2015) 211–252,.

Digital Library

[35]

A.S.S. Shapiro, M.B. Wilk, An Analysis of Variance Test for Normality, Biometrika 52 (1965) 591–611.

[36]

Y. Shi, J. Alex Thomasson, S.C. Murray, N. Ace Pugh, W.L. Rooney, S. Shafian, N. Rajan, G. Rouze, C.L.S. Morgan, H.L. Neely, A. Rana, M.V. Bagavathiannan, J. Henrickson, E. Bowden, J. Valasek, J. Olsenholler, M.P. Bishop, R. Sheridan, E.B. Putman, S. Popescu, T. Burks, D. Cope, A. Ibrahim, B.F. McCutchen, D.D. Baltensperger, R.V. Avant, M. Vidrine, C. Yang, Unmanned Aerial Vehicles for High- Throughput Phenotyping and Agronomic Research, PLoS One 11 (2016) 1–26,.

[37]

Simonyan, K., Vedaldi, A., Zisserman, A., 2014. Deep inside convolutional networks: Visualising image classification models and saliency maps, in: 2nd International Conference on Learning Representations, ICLR 2014 - Workshop Track Proceedings. pp. 1–8.

[38]

Singh, B., Davis, L.S., 2018. An Analysis of Scale Invariance in Object Detection - SNIP, in: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. pp. 3578–3587. https://doi.org/10.1109/CVPR.2018.00377.

[39]

J.W. Smith, Boll Weevil Eradication: Area-Wide Pest Management, Ann. Entomol. Soc. Am. 91 (1998) 239–247,.

[40]

Stanford, 2013. Softmax Regression [WWW Document]. URL http://ufldl.stanford.edu/tutorial/supervised/SoftmaxRegression/.

[41]

P.I. Szmedra, R.W. McClendon, M.E. Wetzstein, Economic Risk Efficiency of Boll Weevil Eradication, South. J. Agric. Econ. 23 (1991) 237–245,.

[42]

C.M. Tribble, C.S. Mcintosh, M.E. Wetzstein, Georgia Cotton Acreage Response to the Boll Weevil Eradication Program, J. Agric. Appl. Econ. 31 (1999) 499–506,.

[43]

J.W. Tukey, Comparing Individual Means in the Analysis of Variance, Int. Biometric Soc. 5 (1949) 99–114.

[44]

Tzutalin, 2015. LabelImg. Git code [WWW Document]. URL https://github.com/tzutalin/labelImg.

[45]

United States Environmental Protection Agency, 2016. Malathion: Human Health Draft Risk Assessment for Registration Review. Washington D.C.

[46]

USDA-Natural Resources Conservation Service, 2020. Web Soil Survey [WWW Document]. URL https://websoilsurvey.sc.egov.usda.gov/App/HomePage.htm.

[47]

A. Veit, M. Wilber, S. Belongie, Residual networks behave like ensembles of relatively shallow networks, Adv. Neural Inf. Process. Syst. 29 (2016) 550–558.

[48]

T. Wang, X. Mei, J. Alex Thomasson, C. Yang, X. Han, P.K. Yadav, Y. Shi, GIS-based volunteer cotton habitat prediction and plant-level detection with UAV remote sensing, Comput. Electron. Agric. 193 (2022) https://doi.org/10.13031/aim.202000219.

[49]

J.K. Westbrook, R.S. Eyster, C. Yang, C.P.C. Suh, Airborne multispectral identification of individual cotton plants using consumer-grade cameras, Remote Sens. Appl. Soc. Environ. 4 (2016) 37–43,.

[50]

Yadav, P., Thomasson, J.A., Enciso, J., Samanta, S., Shrestha, A., 2019. Assessment of different image enhancement and classification techniques in detection of volunteer cotton using UAV remote sensing, in: SPIE Defense + Commercial Sensing. p. 20. https://doi.org/10.1117/12.2518721.

[51]

P.K. Yadav, J.A. Thomasson, R.G. Hardin, S.W. Searcy, U.M. Braga-Neto, S.C. Popescu, D.E. Martin, R. Rodriguez, K. Meza, J. Enciso, J. Solorzano, T. Wang, Volunteer cotton plant detection in corn field with deep learning, in: Autonomous Air and Ground Sensing Systems for Agricultural Optimization and Phenotyping VII, SPIE, Orlando, Fl, 2022, p. 3,.

[52]

Yadav, P., 2021. image_splitter [WWW Document]. URL https://github.com/pappuyadav/image_splitter.

[53]

Y. Zhang, J. Yu, Y. Chen, W. Yang, W. Zhang, Y. He, Real-time strawberry detection using deep neural networks on embedded system (rtsd-net): An edge AI application, Comput. Electron. Agric. 192 (2022),.

Digital Library

[54]

L. Zhang, C. Zhang, S. Quan, H. Xiao, G. Kuang, L. Liu, L. Liu, A class imbalance loss for imbalanced object recognition. IEEE J, Sel. Top. Appl. Earth Obs. Remote Sens. 13 (2020) 2778–2792,.

[55]

Y. Zhang, W. Zhang, J. Yu, L. He, J. Chen, Y. He, Complete and accurate holly fruits counting using YOLOX object detection, Comput. Electron. Agric. 198 (2022),.

Digital Library

[56]

Zheng, Y., Wu, S., Liu, D., Wei, R., Li, S., Tu, Z., 2020. Sleeper Defect Detection Based on Improved YOLO V3 Algorithm, in: Proceedings of the 15th IEEE Conference on Industrial Electronics and Applications, ICIEA. pp. 955–960. https://doi.org/10.1109/ICIEA48937.2020.9248299.

[57]

Zhang, X., Wang, W., Zhao, Y., Xie, H., 2021. An improved YOLOv3 model based on skipping connections and spatial pyramid pooling. Systems Science & Control Engineering, 9(sup1), 142-149.

[58]

J. Zhou, Y. Tian, C. Yuan, K. Yin, G. Yang, M. Wen, Improved UAV opium poppy detection using an updated YOLOV3 model, Sensors (Switzerland) 19 (2019) 1–23,.

Cited By

Aierken NYang BLi YJiang PPan GLi S(2024)A review of unmanned aerial vehicle based remote sensing and machine learning for cotton crop growth monitoringComputers and Electronics in Agriculture10.1016/j.compag.2024.109601227:P2Online publication date: 1-Dec-2024
https://dl.acm.org/doi/10.1016/j.compag.2024.109601
Dari STiwaskar SRaja Kumar JLangote VMohadikar GAshtagi R(2023)Enhancing Plant Leaf Disease Identification with a CNN and DenseNet Hybrid ModelProceedings of the 5th International Conference on Information Management & Machine Intelligence10.1145/3647444.3647929(1-6)Online publication date: 23-Nov-2023
https://dl.acm.org/doi/10.1145/3647444.3647929

Index terms have been assigned to the content through auto-classification.

Recommendations

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image Computers and Electronics in Agriculture

Computers and Electronics in Agriculture Volume 204, Issue C

Jan 2023

821 pages

ISSN:0168-1699

Issue’s Table of Contents

The Author(s).

Publisher

Elsevier Science Publishers B. V.

Netherlands

Publication History

Published: 01 January 2023

Author Tags

Qualifiers

Research-article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

2
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 13 Feb 2025

Other Metrics

View Author Metrics

Citations

Cited By

Aierken NYang BLi YJiang PPan GLi S(2024)A review of unmanned aerial vehicle based remote sensing and machine learning for cotton crop growth monitoringComputers and Electronics in Agriculture10.1016/j.compag.2024.109601227:P2Online publication date: 1-Dec-2024
https://dl.acm.org/doi/10.1016/j.compag.2024.109601
Dari STiwaskar SRaja Kumar JLangote VMohadikar GAshtagi R(2023)Enhancing Plant Leaf Disease Identification with a CNN and DenseNet Hybrid ModelProceedings of the 5th International Conference on Information Management & Machine Intelligence10.1145/3647444.3647929(1-6)Online publication date: 23-Nov-2023
https://dl.acm.org/doi/10.1145/3647444.3647929

View Options

View options

Figures

Tables

Media

View Issue’s Table of Contents