Detection and threshold-adaptive segmentation of farmland residual plastic film images based on CBAM-DBNet

Lijian Xiong, Can Hu, Xufeng Wang, Hongbiao Wang, Xiuying Tang, Xingwang Wang

Abstract


Robust, accurate, and fast monitoring of residual plastic film (RPF) pollution in farmlands has great significance. Based on CBAM-DBNet, this study proposed a threshold-adaptive joint framework for identifying the RPF on farmland surfaces and estimating its coverage rate. UAV imaging was used to gather images of the RPF from several locations with various soil backgrounds. RPFs were manually labeled, and the degree of RPF pollution was defined based on the RPF coverage rate. Combining differentiable binarization network (DBNet) with the convolutional block attention module (CBAM), whose feature extraction module was improved. A dynamic adaptive binarization threshold formula was defined for segmenting the RPF’s approximate binary map. Regarding the RPF image detection branch, the CBAM-DBNet exhibited a precision (P) value of 85.81%, a recall (R) value of 82.69%, and an F1-score (F1) value of 84.22%, which was 1.09 percentage points higher than the DBNet in the comprehensive index F1 value. For the RPF image segmentation branch, using CBAM-DBNet to segment the RPF image combined with an adaptive binarization threshold formula. Subsequently, the mean absolute percentage error (MAPE), root mean square error (RMSE), and mean absolute error (MAE) of the prediction of RPF’s coverage rate were 0.276, 0.366, and 0.605, respectively, outperforming the DBNet and the Iterative Threshold method. This study provides a theoretical reference for the further development of evaluation technology for RPF pollution based on UAV imaging.
Keywords: binarization threshold adaptive, residual plastic film, object detection, image segmentation, UAV remote sensing
DOI: 10.25165/j.ijabe.20241705.8069

Citation: Xiong L J, Hu C, Wang X F, Wang H B, Tang X Y, Wang X W. Detection and threshold-adaptive segmentation of farmland residual plastic film images based on CBAM-DBNet. Int J Agric & Biol Eng, 2024; 17(5): 231-238.

Keywords


binarization threshold adaptive, residual plastic film, object detection, image segmentation, UAV remote sensing

Full Text:

PDF

References


Sun D B, Li H G, Wang E L, He W Q, Hao W P, Yan C R, et al. An overview of the use of plastic-film mulching in China to increase crop yield and water-use efficiency. National Science Review, 2020; 7（10）: 1523–1526.

Hu C, Lu B, Guo W S, Tang X Y, Wang X F, Xue Y H, et al. Distribution of microplastics in mulched soil in Xinjiang, China. Int J Agric & Biol Eng, 2021; 14（2）: 196–204.

Hu C, Wang X F, Chen X G, Tang X Y, Zhao Y, Yan C R, Current situation and control strategies of residual film pollution in Xinjiang. Transactions of the CSAE, 2019; 35（24）: 223–234. （in Chinese）

Hu C, Wang X F, Wang S G, Lu B, Guo W S, Liu C J, et al. Impact of agricultural residual plastic film on the growth and yield of drip-irrigated cotton in arid region of Xinjiang, China. Int J Agric & Biol Eng, 2020; 13（1）: 160–169.

Zhao Y, Chen X G, Wen H J, Zheng X, Niu Q, Kang J M. Research status and prospect of control technology for residual plastic film pollution in farmland. Transactions of the CSAM, 2017; 48（6）: 1–14. （in Chinese）

Niu R K, Wang X F, Hu C, Hou S L, Lu B, Li J B. Analysis of the current situations of plastic films residue pollution of cotton field in Xinjiang Aksu Area. Xinjiang Agricultural Sciences, 2016; 53（2）: 283–288. （in Chinese）

Zhang D, Liu H B, Hu W L, Qin X H, Ma X W, Yan C R, et al. The status and distribution characteristics of residual mulching film in Xinjiang. Journal of Integrative Agriculture, 2016; 15（11）: 2639–2646.

He H J, Wang Z H, Guo L, Zheng X R, Zhang J Z, Li W H, et al. Distribution characteristics of residual film over a cotton field under long-term film mulching and drip irrigation in an oasis agroecosystem. Soil and Tillage Research, 2018; 180: 194–203.

Liang C J, Wu X M, Wang F, Song Z J, Zhang F G. Research on recognition algorithm of field mulch film based on unmanned aerial vehicle. Acta Agriculturae Zhejiangensis, 2019; 31（6）: 1005–1011. （in Chinese）

Zhu X F, Li S B, Xiao G F. Method on extraction of area and distribution of plastic-mulched farmland based on UAV images. Transactions of the CSAE, 2019; 35（4）: 106–113. （in Chinese）

Wu X M, Liang C J, Zhang D B, Yu L H, Zhang F G. Identification method of plastic film residue based on UAV remote sensing images. Transactions of the CSAM, 2020; 51（8）: 189–195. （in Chinese）

Jiang S Q, Zhang H D, Hua Y J. Research on location of residual plastic film based on computer vision. Journal of Chinese Agricultural Mechanization, 2016; 37（11）: 150–154. （in Chinese）

Yang K, Liu H, Wang P, Meng Z J, Chen J P. Convolutional neural network-based automatic image recognition for agricultural machinery. Int J Agric & Biol Eng, 2018; 11（4）: 200–206.

Zhao J, Pan F J, Li Z M, Lan Y B, Lu L Q, Yang D J, et al. Detection of cotton waterlogging stress based on hyperspectral images and convolutional neural network. Int J Agric & Biol Eng, 2021; 14（2）: 167–174.

Ma Z, Wang Y, Zhang T S, Wang H G, Jia Y J, Gao R, et al. Maize leaf disease identification using deep transfer convolutional neural networks. Int J Agric & Biol Eng, 2022; 15（5）: 187–195.

Zhang X J, Huang S, Jin W, Yan J S, Shi Z L, Zhou X C, et al. Identification method of agricultural film residue based on improved faster R-CNN. Journal of Hunan University （Natural Sciences）, 2021; 48（8）: 161–168. （in Chinese）

Zhai Z Q, Chen X G, Qiu F S, Meng Q J, Wang H Y, Zhang R Y. Detecting surface residual film coverage rate in pre-sowing cotton fields using pixel block and machine learning. Transactions of the CSAE, 2022; 38（6）: 140–147. （in Chinese）

Zhai Z Q, Chen X G, Zhang R Y, Qiu F S, Meng Q J, Yang J K, et al. Evaluation of residual plastic film pollution in pre-sowing cotton field using UAV imaging and semantic segmentation. Frontiers in Plant Science, 2022; 13: 991191.

Qiu F S, Zhai Z Q, Li Y L, Yang J K, Wang H Y, Zhang R Y. UAV imaging and deep learning based method for predicting residual film in cotton field plough layer. Frontiers in Plant Science, 2022; 13: 1010474.

Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks. Communications of the ACM, 2012; 60（6）: 84–90.

Burgos-Artizzu X P, Ribeiro A, Guijarro M, Pajares G. Real-time image processing for crop/weed discrimination in maize fields. Computers and Electronics in Agriculture, 2011; 75（2）: 337–346.

Liao M H, Wan Z Y, Yao C, Chen K, Bai X. Real-time scene text detection with differentiable binarization. In: Proceedings of the AAAI Conference on Artificial Intelligence, 2019; 34（7）: 11474–11481.

Woo S, Park J, Lee J-Y, Kweno I S. CBAM: Convolutional Block Attention Module. In: Proceedings of the European Conference on Computer Vision – ECCV 2018, 2018; pp.3-19. doi: 10.1007/978-3-030-01234-2_1.

Lin T-Y, Dollar P, Girishick R, He K M, Hariharan B, Belongie S. Feature pyramid networks for object detection. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition （CVPR）, Honolulu: IEEE, 2017; pp.936-944.

Shrivastava A, Gupta A, Girshick R. Training region-based object detectors with online hard example mining. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition （CVPR）, Las Vegas: IEEE, 2016; pp.761-769.

He K M, Zhang X Y, Ren S Q, Sun J. Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition （CVPR）, Las Vegas: IEEE, 2016; pp.770–778. doi:10.1109/CVPR.2016.90.

Girshick R, Donahue J, Darrell T, Malik J. Rich feature hierarchies for accurate object detection and semantic segmentation. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus: IEEE, 2014; pp.580–587. doi: 10.1109/cvpr.2014.81.

Sun F, Tian X D. Lecture video automatic summarization system based on DBNet and Kalman filtering. Mathematical Problems in Engineering, 2022; 2022（1）: 5303503.

Vatti B R. A generic solution to polygon clipping. Communications of the ACM, 1992; 35（7）: 56–63.

De Myttenaere A, Golden B, Le Grand B, Rossi Fabrice. Mean absolute percentage error for regression models. Neurocomputing, 2016; 192: 38–48.

Karunasingha D S K. Root mean square error or mean absolute error? Use their ratio as well. Information Sciences, 2022; 585: 609–629.

Willmott C J, Matsuura K. Advantages of the mean absolute error （MAE） over the root mean square error （RMSE） in assessing average model performance. Climate Research, 2005; 30（1）: 79–82.




Copyright (c) 2024 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