Abstract
In-field pest identification is an important prerequisite for timely adopting corresponding strategies for pest control. However, traditional manual observation measures or classification models that directly use support vector machines cannot meet actual application demands with high-efficiency, fast and low cost. Therefore, a lightweight convolutional neural network can be adopted to solve this problem. Specifically, a new lightweight convolutional neural network model based on asymmetric and depthwise separable convolution cal-led ACEDSNet has been proposed, involving asymmetric convolution enhance depthwise separable module and skip connections. To evaluate the robustness and accuracy of the ACEDSNet method, experiments have been conducted on three public pest datasets. It is observed that asymmetric convolution enhances depthwise separable module and skip connection can effectively improve classification accuracy. Extensive experiments show that our proposed ACEDSNet outperforms most state-of-the-art approaches with the highest overall average accuracy and faster network convergence. Compared with recent lightweight pest classification networks, ACEDSNet can reduce FLOPs by 77.6%, and the accuracy is increased by 2.85%.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Ana A, Wsrs A, Dlba B (2020) Cotton pests classification in field-based images using deep residual networks. Comput Electron Agric. https://doi.org/10.1016/j.compag.2020.105488
Aruna P, P A, Bansode R (2021) Explore and analysis of methods to train cnn in machine learning environment. Ann Romanian Soci Cell Biol 25:14750–14761
Ayan E, Erbay H, Varn F (2020) Crop pest classification with a genetic algorithm-based weighted ensemble of deep convolutional neural networks. Comput Electron Agric 179(4):105809. https://doi.org/10.1016/j.compag.2020.105809
Cai Y, Wang W, Chen Y, Ye Q (2020) Ios-net: an inside-to-outside supervision network for scale robust text detection in the wild. Pattern Recogn 103:107304. https://doi.org/10.1016/j.patcog.2020.107304
Cheng X, Zhang Y, Chen Y, Wu Y, Yue Y (2017) Pest identification via deep residual learning in complex background. Comput Electron Agric 141:351–356. https://doi.org/10.1016/j.compag.2017.08.005
Ding X, Guo Y, Ding G, Han J (2019) Acnet: Strengthening the kernel skeletons for powerful cnn via asymmetric convolution blocks. In: 2019 IEEE/CVF International Conference on Computer Vision (ICCV), pp 1911–1920, https://doi.org/10.1109/ICCV.2019.00200
Ebroul KSAAPK (2020) Dataset for pest classification in mango farms from indonesia. Mendeley Data. https://doi.org/10.17632/94jf97jzc8.1
Fina F, Birch P, Young R, Obu J, Chatwin C (2013) Automatic plant pest detection and recognition using k-means clustering algorithm and correspondence filters. Int J Adv Biotechnol Res 4:189–199
Gross M (2021) How locusts become a plague. Curr Biol 31(10):R459–R461. https://doi.org/10.1016/j.cub.2021.05.007
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 770–778, https://doi.org/10.1109/CVPR.2016.90
He F, Liu T, Tao D (2019) Control batch size and learning rate to generalize well: Theoretical and empirical evidence. In: Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada, pp 1141–1150
Howard A, Sandler M, Chen B, Wang W, Chen LC, Tan M, Chu G, Vasudevan V, Zhu Y, Pang R, Adam H, Le Q (2019) Searching for mobilenetv3. In: 2019 IEEE/CVF International Conference on Computer Vision (ICCV), pp 1314–1324, https://doi.org/10.1109/ICCV.2019.00140
Huynh-The T, Hua CH, Pham QV, Kim DS (2020) Mcnet: an efficient cnn architecture for robust automatic modulation classification. IEEE Commun Lett. https://doi.org/10.1109/LCOMM.2020.2968030
Jayachitra S, Prasanth A (2020) Multi-feature analysis for automated brain stroke classification using weighted gaussian naive baye’s classifier. J Circuits Syst Comput. https://doi.org/10.1142/S0218126621501784
Jia S, Gao H (2020) Review of crop disease and pest image recognition technology. IOP Conf Ser: Mater Sci Eng 799(1):012045. https://doi.org/10.1088/1757-899X/799/1/012045 (6pp)
Kkfak A, Sss B, Asa A, Imaaa A, Hph C, Kck D, Eie D (2020) Data augmentation for automated pest classification in mango farms. Comput Electron Agric. https://doi.org/10.1016/j.compag.2020.105842
Kohler M, Langer S (2020) Statistical theory for image classification using deep convolutional neural networks with cross-entropy loss. arXiv e-prints , https://arxiv.org/abs/2011.13602
Li Z, Nie F, Chang X, Nie L, Yi Y (2018a) Rank-constrained spectral clustering with flexible embedding. IEEE Trans Neural Netw Learn Syst. https://doi.org/10.1109/TNNLS.2018.2817538
Li Z, Nie F, Chang X, Yang Y, Zhang C, Sebe N (2018b) Dynamic affinity graph construction for spectral clustering using multiple features. IEEE Trans Neural Netw Learn Syst. https://doi.org/10.1109/TNNLS.2018.2829867
Li G, Jiang S, Yun I, Kim J, Kim J (2020) Depth-wise asymmetric bottleneck with point-wise aggregation decoder for real-time semantic segmentation in urban scenes. IEEE Access 8:27495–27506. https://doi.org/10.1109/ACCESS.2020.2971760
Li Y, Li X, Xiao C, Li H, Zhang W (2021) Eacnet: enhanced asymmetric convolution for real-time semantic segmentation. IEEE Signal Process Lett 28:234–238. https://doi.org/10.1109/LSP.2021.3051845
Ma N, Zhang X, Zheng HT, Sun J (2018) Shufflenet v2: practical guidelines for efficient cnn architecture design. In: Ferrari V, Hebert M, Sminchisescu C, Weiss Y (eds) Computer vision—ECCV 2018. Springer International Publishing, Cham, pp 122–138. https://doi.org/10.1007/978-3-030-01264-98
Martineau M, Conte D, Raveaux R, Arnault I, Munier D, Venturini G (2017) A survey on image-based insect classification. Pattern Recogn 65:273–284. https://doi.org/10.1016/j.patcog.2016.12.020
Mei-Ling Chuang TC (2020) A database of eight common tomato pest images. Mendeley Data. https://doi.org/10.17632/s62zm6djd2.1
Sandler M, Howard A, Zhu M, Zhmoginov A, Chen LC (2018) Mobilenetv2: inverted residuals and linear bottlenecks. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 4510–4520, https://doi.org/10.1109/CVPR.2018.00474
Selvam L, Kavitha P (2020) Classification of ladies finger plant leaf using deep learning. J Ambient Intell Hum Comput 5:1–9. https://doi.org/10.1007/s12652-020-02671-y
Thenmozhi K, Reddy US (2019) Crop pest classification based on deep convolutional neural network and transfer learning—sciencedirect. Comput Electron Agric 164:104906. https://doi.org/10.1016/j.compag.2019.104906
Turkoglu MHD, A S, (2019) Multi-model lstm-based convolutional neural networks for detection of apple diseases and pests. J Ambient Intell Hum Comput. https://doi.org/10.1007/s12652-019-01591-w
Wang J, Li Y, Feng H, Ren L, Wu J (2020) Common pests image recognition based on deep convolutional neural network. Comput Electron Agric 179(1):105834. https://doi.org/10.1016/j.compag.2020.105834
Wu B, Wan A, Yue X, Jin P, Zhao S, Golmant N, Gholaminejad A, Gonzalez J, Keutzer K (2018) Shift: A zero flop, zero parameter alternative to spatial convolutions. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 9127–9135, https://doi.org/10.1109/CVPR.2018.00951
Xie C, Zhang J, Li R, Li J, Hong P, Xia J, Chen P (2015) Automatic classification for field crop insects via multiple-task sparse representation and multiple-kernel learning. Comput Electron Agric 119:123–132. https://doi.org/10.1016/j.compag.2015.10.015
Xie C, Wang R, Jie Z, Chen P, Wei D, Rui L, Chen T, Chen H (2018) Multi-level learning features for automatic classification of field crop pests. Comput Electron Agric 152:233–241. https://doi.org/10.1016/j.compag.2018.07.014
Xie C, Rui L, Wei D, Song L, Zhang J, Chen H, Chen T (2016) Recognition for insects via spatial pyramid model using sparse coding. Trans Chin Soc Agric Eng. https://doi.org/10.11975/j.issn.1002-6819.2016.17.020
Zl A, Ly A, Xc B, Kz C, Js D, Hz D (2019) Zero-shot event detection via event-adaptive concept relevance mining. Pattern Recogn 88:595–603. https://doi.org/10.1016/j.patcog.2018.12.010
Acknowledgements
The authors would like to thank the Wuxi Institute of Radio Science and Technology for devising and providing the facilities and equipment and the agrometeorological observers F.S. Qin, G.X. Yang, Z.H. Zhang, J.Y. Peng, Q.Y. Ma, R.G. Yang, J.L. Zhou and B. Qi for their painstaking work to record the valuable data.
Funding
This work is supported in part by National Natural Science Foundation of China under Grant 61906139, and in part by Science Foundation of Wuhan Institute of Technology under Grant K202031.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Li, Y., Sun, M. & Qi, Y. Common pests classification based on asymmetric convolution enhance depthwise separable neural network. J Ambient Intell Human Comput 14, 8449–8457 (2023). https://doi.org/10.1007/s12652-021-03611-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12652-021-03611-0