Film identification method based on improved deeplabv3+ for full-film double-ditch corn seedbed

Fei Dai, Xiangzhou Li, Ruijie Shi, Fengwei Zhang, Wuyun Zhao, Wenjuan Guo

Abstract


This study aimed to investigate the task demand of intelligent unmanned fertilizer application in seedling stage of corn planted in full-film double-ditch seedbed, a film identification method based on improved DeepLabv3+ identification method for full-film double-ditch corn seedbed was proposed. The differences in performance indicators of the original Deeplabv3+ network taking Xception as the backbone network and the network model that replaced three lightweight backbone networks, MobileNetV2, MobileNetV3 and GhostNet were tested. At the same time, the network models, classical semantic segmentation was introduced to PSPNet and UNet for comparative test. The MIoU of DeepLabv3+ network model that replaced its backbone network increased by 5.01%, and FPS improved by 206% compared with original network, and the model size reduced by 90.3%. The three DeepLabv3+ models after replacing the backbone network were further compressed, and the two-layer expansion convolution with low expansion rate in ASPP was deleted, and the common convolution after feature fusion was replaced by the depthwise separable convolution to obtain a lightweight network model. After testing the improved network model, it was found that the average decline of precision indicators was only 0.17%, FPS raised to 66.5, with an average increase of 25.5%, and the size of the model was compressed to 10.53MB. Test results showed that, the improved model showed excellent performance, and could provide important technology and method support for the research and development of intelligent topdressing and field management on full-film double-ditch corn seedbed during seedling stage.
Keywords: fertilizer application, intelligent unmanned machine, full-film double-ditch corn seedbed, film identification method, deep learning, semantic segmentation, DeepLabv3+
DOI: 10.25165/j.ijabe.20231605.8288

Citation: Dai F, Li X Z, Shi R J, Zhang F W, Zhao W Y, Guo W J. Film identification method based on improved DeepLabV3+ for full-film double-ditch corn seedbed. Int J Agric & Biol Eng, 2023; 16(5): 165–172.

Keywords


fertilizer application, intelligent unmanned machine, full-film double-ditch corn seedbed, film identification method, deep learning, semantic segmentation, DeepLabv3+

Full Text:

PDF

References


Zhou L M, Jin S L, Liu C A, Xiong Y C, Si J T, Li X G, et al. Ridge-furrow and plastic-mulching tillage enhances maize-soil interactions: opportunities and challenges in a semiarid agroecosystem. Field Crops Research, 2012; 126: 181–188.

Dai F, Zhao W Y, Zhang F W, Ma H J, Xin S L, Ma M Y. Research progress analysis of furrow sowing with whole plastic-film mulching on double ridges technology and machine in northwest rainfed area. Transactions of the CSAM, 2019; 50(5): 1–16. (in Chinese)

Dai F, Guo W J, Song X F, Zhang Y, Shi R J, Wang F, Zhao W Y. Optimization of mechanized soil covering path based on the agronomic mode of full-film double-ditch with double-width filming. Int J Agric & Biol Eng, 2022; 15(1): 139–146.

Luo X W, Liao J, Hu L, Zhou Z Y, Zhang Z G, Zang Y, et al. Research progress of intelligent agricultural machinery and practice of unmanned farm in China. Journal of South China Agricultural University, 2021; 42(6): 8–17. (in Chinese)

Tang H, Xu C S, Wang Z M, Wang Q, Wang J W. Optimized design, monitoring system development and experiment for a long-belt finger-clip precision corn seed metering device. Frontiers in Plant Science, 2022; 13: 814747.

Liu C L, Lin H Z, Li Y M, Gong L, Miao Z H. Analysis on status and development trend of intelligent control technology for agricultural equipment. Transactions of the CSAM, 2020; 51(1): 1–18. (in Chinese)

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. Journal of Chinese Agricultural Mechanization, 2021; 42(9): 209–215. (in Chinese)

Zhou J, He Y Q. Research progress on navigation path planning of agricultural machinery. Transactions of the CSAM, 2021; 52(9): 1–14. (in Chinese)

Mu R H, Zeng X Q. A review of deep learning research. KSII Transactions on Internet and Information Systems, 2019; 13: 1738–1764.

Wan S H, Goudos S. Faster R-CNN for multi-class fruit detection using a robotic vision system. Computers Networks, 2020; 168: 107036.

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+. Transactions of the CSAE, 2022; 38(7): 229–236. (in Chinese)

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. Journal of China Agricultural University, 2022; 27(2): 143–154. (in Chinese)

Rao X Q, Zhu Y H, Zhang Y N, Yang H T, Zhang X M, Lin Y Y, et al. Navigation path recognition between crop ridges based on semantic segmentation. Transactions of the Chinese Society of Agricultural Engineering, 2021; 37(20): 179–186. (in Chinese)

Yang Y, Zhang Y L, Miao W, Zhang T, Chen L Q, Huang L L. Accurate identification and location of corn rhizome based on faster R-CNN. Transactions of the CSAM, 2018; 49(10): 46–53. (in Chinese)

Meng Q K, Yang X X, Zhang M, Guan H O. Recognition of unstructured field road scene based on semantic segmentation model. Transactions of the Chinese Society of Agricultural Engineering, 2021; 37(22): 152–160. (in Chinese)

Shorten C, Khoshgoftaar T M. A survey on image data augmentation for deep learning. Journal of big data, 2020; 6: 1–48.

Chen L C, Papandreou G, Kokkinos L, Murphy K, Yuille A L. DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018; 40: 834–848.

Ji J, Li S T, Xiong J, Chen P, Miao Q G. Semantic image segmentation with propagating deep aggregation. IEEE Transactions on Instrumentation and Measurement, 2020; 69: 1.

Li Z Y, Wang R, Zhang W, Hu F M, Meng L K. Multiscale features supported DeepLabV3 optimization scheme for accurate water semantic segmentation. IEEE Access, 2019; 7: 155787–155804.

Fu H X, Meng D, Li W H, Wang Y C. Bridge Crack Semantic Segmentation Based on Improved Deeplabv3+. Journal of Marine Science and Engineering, 2021; 9: 671.

Zhang X F, Bian H N, Cai Y H, Zhang K Y, Li H. An improved tongue image segmentation algorithm based on Deeplabv3+ framework. IET Image Process, 2022; 16: 1473–1485.

Hu Z F, Zhao J, Luo Y, Ou J F. Semantic SLAM based on improved DeepLabv3+ in dynamic scenarios. IEEE Access, 2022; 10: 21160–21168.

Liao J, Chen M H, Zhang K, Zou Y, Zhang S, Zhu D Q. Segmentation of crop plant seedlings based on regional semantic and edge information fusion. Transactions of the CSAM, 2021; 52(12): 171–181. (in Chinese)

Buiu C, Dănăilă V R, Răduţă C N. MobileNetV2 ensemble for cervical precancerous lesions classification. Processes, 2020; 8: 595.

Yin X, Li W H, Li Z, Yi L L. Recognition of grape leaf diseases using MobileNetV3 and deep transfer learning. Int J Agric & Biol Eng, 2022; 15(3): 184–194.

Yuan X G, Li D, Sun P, Wang G, Ma Y L. Real-time counting and height measurement of nursery seedlings based on Ghostnet-YoloV4 network and binocular vision technology. Forests, 2022; 13: 1459.




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