Detection of the foreign object positions in agricultural soils using Mask-RCNN

Yuanhong Li, Chaofeng Wang, Congyue Wang, Xiaoling Deng, Zuoxi Zhao, Shengde Chen, Yubin Lan

Abstract


Objects in agricultural soils will seriously affect the farming operations of agricultural machinery. At present, it still relies on human experience to judge abnormal Gounrd-penetrting Radar (GPR) signals. It is difficult for traditional image processing technology to form a general positioning method for the randomness and diversity characteristics of GPR signals in soil. Although many scholars had researched a variety of image-processing techniques, most methods lack robustness. In this study, the deep learning algorithm Mask Region-based Convolutional Neural Network (Mask-RCNN) and a geometric model were combined to improve the GPR positioning accuracy. First, a soil stratification experiment was set to classify the physical parameters of the soil and study the attenuation law of electromagnetic waves. Secondly, a SOIL-GPR geometric model was proposed, which can be combined with Mask-RCNN's MASK geometric size to predict object sizes. The results proved the effectiveness and accuracy of the model for position detection and evaluation of objects in soils; then, the improved Mask RCNN method was used to compare the feature extraction accuracy of U-Net and Fully Convolutional Networks (FCN); Finally, the operating speed of agricultural machinery was simulated and designed the A-B survey line experiment. The detection accuracy was evaluated by several indicators, such as the survey line direction, soil depth false alarm rate, Mean Average Precision (mAP), and Intersection over Union (IoU). The results showed that pixel-level segmentation and positioning based on Mask RCNN can improve the accuracy of the position detection of objects in agricultural soil effectively, and the average error of depth prediction is 2.87 cm. The results showed that the detection technology proposed in this study integrates the advantage of soil environmental parameters, geometric models, and artificial intelligence algorithms to provide a high-precision and technical solution for the GPR non-destructive detection of soils.
Keywords: foreign object, soil object, position, agricultural soil, Mask R-CNN, GPR image
DOI: 10.25165/j.ijabe.20231601.7173

Citation: Li Y H, Wang C F, Wang C Y, Deng X L, Zhao Z X, Chen S D, et al. Detection of the foreign object positions in agricultural soils using Mask-RCNN. Int J Agric & Biol Eng, 2023; 16(1): 220–231.

Keywords


foreign object, soil object, position, agricultural soil, Mask R-CNN, GPR image

Full Text:

PDF

References


Li Y H, Zhao X X, Xu W C, Liu Z, Wang X. An effective FDTD model for GPR to detect the material of hard objects buried in tillage soil layer. Soil and Tillage Research, 2019; 195: 104353. doi: 10.1016/j.still. 2019.104353.

Azizi A, Abbaspour-Gilandeh Y, Vannier E, Dusseaux R, Mseri-Gundoshmian T, Moghaddam H A. Semantic segmentation: A modern approach for identifying soil clods in precision farming. Biosystems Engineering, 2020; 196: 172–182.

Xu J J, Zhang H, Tang C S, Cheng Q, Liu B, Shi B. Automatic soil desiccation crack recognition using deep learning. Geotechnique, 2021; pp.1–13.

Ma W P, Wang X D, Liu D. Research on YOLO target detection algorithm in GPR image anomaly recognition. Bulletin of Surveying and Mapping, 2019; S1: 72–76. (in Chinese)

Dou Q, Wei L, Magee D R, Cohn A G. Real-time hyperbola recognition and fitting in GPR data. IEEE Transactions on Geoscience and Remote Sensing, 2017; 55(1): 51–62.

Pham M T, Lefèvre S. Buried object detection from B-scan ground penetrating radar data using Faster-RCNN. In: IGARSS 2018-2018 IEEE International Geoscience and Remote Sensing Symposium, Valencia: IEEE, 2018; pp.6804–6807. doi: 10.1109/IGARSS.2018.8517683.

Gong Z M, Zhang H Q. Research on GPR image recognition based on deep learning. In: 2019 International Conference on Computer Science Communication and Network Security (CSCN2019), 2019; 309: 03027. doi: 10.1051/matecconf/202030903027.

Girshick R, Donahue J, Darrell T, Malik J. Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014; pp.580–587.

Yang F, Qiao X, Zhang Y Y, Xu X L. Prediction method of underground pipeline based on hyperbolic asymptote of GPR image. In: Proceedings of the 15th International Conference on Ground Penetrating Radar, IEEE, 2014; pp.674–678. doi: 10.1109/ICGPR.2014.6970511

Gkioxari G, Girshick R, Malik J. Contextual action recognition with R* CNN. In 2015 IEEE International Conference on Computer Vision (ICCV), Santiago: IEEE, 2015; pp.1080–1088. doi: 0.1109/ICCV.2015.129.

He K, Gkioxari G, Dollár P, Girshick R. Mask R-CNN. In: Proceedings of the IEEE international conference on computer vision 2017; pp.2961–2969.

Ren S, He K, Girshick R, Sun J. Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017; 39(6): 1137–1149.

Rice W, Omwenga M, Wu D L, Liang Y. Enhanced underground object detection with conditional adversarial networks. In: ISSAT International Conference on Data Science & Intelligent Systems, 2019.

Gribbon K T, Bailey D G. A novel approach to real-time bilinear interpolation. In: Proceedings. DELTA 2004. Second IEEE International Workshop on Electronic Design, Test and Applications, Perth: IEEE, 2004; pp.126–131. doi: 10.1109/DELTA.2004.10055.

Janning R, Busche A, Horváth T, Schmidt-Thieme L. Buried pipe localization using an iterative geometric clustering on GPR data. Artificial Intelligence Review, 2014; 42(3): 403–425.

Savelyev T G, van Kempen L, Sahli H, Sachs J, Sato M. Investigation of time–frequency features for GPR landmine discrimination. IEEE Transactions on Geoscience and Remote Sensing, 2006; 45(1): 118–129.

Valueva M V, Nagornov N N, Lyakhov P A, Valuev G V, Chervyakov N I. Application of the residue number system to reduce hardware costs of the convolutional neural network implementation. Mathematics and Computers in Simulation, 2020; 177: 232–243.

Nuzzo L. Coherent noise attenuation in GPR data by linear and parabolic Radon Transform techniques. Annals of Geophysics, 2003; 46(3): 3426. doi: 10.4401/ag–3426.

Benedetto F, Tosti F. GPR spectral analysis for clay content evaluation by the frequency shift method. Journal of Applied Geophysics, 2013; 97: 89–96.

Lachowicz J, Rucka M. Application of GPR method in diagnostics of reinforced concrete structures. Diagnostyka, 2015; 16(2): 31–36.

Tang P, Wang X, Wang A, Yan Y, Liu W, Huang J, et al. Weakly supervised region proposal network and object detection. In: Proceedings of the European conference on computer vision (ECCV), 2018; pp.352–368.

Li J Q, Wu Y, Zhao J Q, Guan L T, Ye C, Yang T. Pedestrian detection with dilated convolution, region proposal network and boosted decision trees. In: 2017 International Joint Conference on Neural Networks (IJCNN), Anchorage: IEEE, 2017; pp.4052–4057.

Lei T, Zhang Q, Xue D H, Chen T, Meng H Y, Nandi A K. End-to-end change detection using a symmetric fully convolutional network for landslide mapping. In: ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton: IEEE, 2019; pp.3027–3031. doi: 10.1109/ICASSP.2019. 8682802.

Yan C, Chen W W, Chen P C, Kendrick Amezquita S, Wu X M. A new two-stage object detection network without RoI-Pooling. In: Proceedings of the 30th Chinese Control And Decision Conference (2018 CCDC), 2018; pp.1680–1685.

Freund Y, Schapire R E. A decision-theoretic generalization of on-line learning and an application to boosting. Journal of Computer and System Sciences, 1997; 55(1): 119–139.

Li X C, Wang L, Sung E. A study of AdaBoost with SVM based weak learners. In: 2005 IEEE International Joint Conference on Neural Networks, Montreal: IEEE, 2005; 1: 196–201. doi: 10.1109/IJCNN.2005.1555829.

Lin T Y, Maire M, Belongie S, Hay J, Perona P, Ramanan D, et al. Microsoft COCO: Common objects in context. In: European Conference on Computer Vision, 2014; pp.740–755.

Li Y H, Wang X, Zhao Z X, Han S, Liu Z. Lagoon water quality monitoring based on digital image analysis and machine learning estimators. Water Research, 2020; 172: 115471. doi: 10.1016/j.watres. 2020.115471.

Sun L Q, Zou Y B, Li Y, Cai Z D, Li Y, Luo B, et al. Multi target pigs tracking loss correction algorithm based on Faster R-CNN. Int J Agric & Biol Eng, 2018; 11(5): 192–197.

Johnson J W. Adapting Mask-RCNN for automatic nucleus segmentation. arXiv preprint, 2018; arXiv:1805.00500.

Shaodan L, Chen F, Zhide C. A ship target location and mask generation algorithms base on Mask RCNN. International Journal of Computational Intelligence Systems, 2019; 12(2): 1134–1143.

Huang Z D, Zhong Z Y, Sun L, Huo Q. Mask R-CNN with pyramid attention network for scene text detection. In: 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), Waikoloa: IEEE, 2019; pp.764–772.

LeCun Y, Bengio Y, Hinton G. Deep learning. Nature, 2015; 521(7553): 436–444.

Schmidhuber J. 2015. Deep learning in neural networks: An overview. Neural Networks, 2015; 61: 85–117.

Chen Y S, Lin Z H, Zhao X, Wang G, Gu Y F. Deep learning-based classification of hyperspectral data. IEEE Journal of Selected Topics in Applied Earth Obserbvations and Remote Sensing, 2014; 7(6): 2094–2107.

He K M, Zhang X Y, Ren S Q, Sun J. Identity mappings in deep residual networks. In European Conference on Computer Vision 2016; pp.630–645.

Zagoruyko S, Komodakis N. Wide residual networks. arXiv, 2016; arXiv preprint arXiv:1605.07146.

Li S, Yuan C X, Cai H B. Integrated processing of image and GPR data for automated pothole detection. Journal of Computing in Civil Engineering, 2016; 30(6): 04016015. doi:10.1061/(ASCE)CP.1943-5487.0000582.

Fu C Y, Liu W, Ranga A, Tyagi A, Berg A C. DSSD: Deconvolutional Single Shot Detector. arXiv preprint, 2017; arXiv:1701.06659.

Lempitsky V, Kohli P, Rother C, Sharp T. Image segmentation with a bounding box prior. In: 2009 IEEE 12th International Conference on Computer Vision, IEEE, 2009; pp.277–284.

Wang G B, Lan Y B, Qi H X, Chen P C, Hewitt A, Han Y X. Field evaluation of an unmanned aerial vehicle (UAV) sprayer: effect of spray volume on deposition and the control of pests and disease in wheat. Pest Management Science, 2019; 75(6): 1546–1555.

Mu G, Chen Y, Wu D, Zhan Y, Zhou X S, Gao Y. Relu Cascade of Feature Pyramid Networks for CT pulmonary nodule detection. In: International Workshop on Machine Learning in Medical Imaging, 2019; pp.444–452.

Ghiasi G, Lin T Y, Le Q V. NAS-FPN: Learning scalable feature pyramid architecture for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2019; pp.7036–7045.

Chiao J Y, Chen K Y, Liao K Y K, Hsieh P H, Zhang G, Huang T C. Detection and classification the breast tumors using mask R-CNN on sonograms. Medicine, 2019; 98(19): e15200. doi: 10.1097/MD. 0000000000015200.

Chen L C, Papandreou G, Schroff F, Adam H. Rethinking atrous convolution for semantic image segmentation. arXiv preprint, 2017; arXiv:1706.05587.

Chen P C, Douzals J P, Lan Y B, Cotteux E, Delpuech X, Pouxviel G, et al. Characteristics of unmanned aerial spraying systems and related spray drift: A review. Frontiers in Plant Science, 2022; 13: 870956. doi: 10.3389/fpls.2022.870956.

Zhan Y L, Chen P C, Xu W C, Chen S D, Han Y F, Lan Y B, et al. Influence of the downwash airflow distribution characteristics of a plant protection UAV on spray deposit distribution. Biosystems Engineering, 2022; 216: 32–45.




Copyright (c) 2023 International Journal of Agricultural and Biological Engineering

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.

2023-2026 Copyright IJABE Editing and Publishing Office