Hyperspectral Detection of Soybean Heart-Eating Insect Pests Based on Image Retrieval
GUI Jiang-sheng1, HE Jie1, FU Xia-ping2
1. School of Information Science and Technology, Zhejiang Sci-Tech University, Hangzhou 310018, China
2. Faculty of Mechanical Engineering & Automation, Zhejiang Sci-Tech University, Hangzhou 310018, China
Abstract：To reduce the impact of insect pests on soybeans, first use the corresponding hyperspectral instrument to collect samples. The samples are divided into 4 categories: those with tiny eggs, those with larvae, those with nibbling marks, and those with entirely normal soybeans. 20 Then, a hyperspectral detection method of soybean borer based on three-dimensional image retrieval (3D-RD, 3D Resnet18 DCH) was proposed. The application of video retrieval inspires this method. Considering the analogy relationship between different frames of the video and the different layers of the hyper spectrum, the classification model trained on the large-scale video retrieval data set is used as a predictive model. Train the 3D convolution model for training. Same as the known literature method, the public spectral data set is used for formal training and fine-tuning to obtain a 3D convolutional network that can perform feature extraction. Image retrieval is used to achieve indirect classification, and the feature distance between samples is used to achieve classification in new categories. In order to be able to adapt to the task, the final classification layer of the model is turned into a commonly used hash layer for image retrieval, thereby obtaining the binary code representing the feature. This method completes the detection of soybean types in different situations and solves the problem of insufficient samples during training. In order to explore a good similarity matching loss function, this article uses a variety of newer methods to explore and finally found that the Cauchy distribution is integrated into the loss function, which can be effectively applied in this experiment. Experiments have proved that the classification accuracy of the final model is 86%±1.00%. Compared with the latest small sample method in detecting soybean borer, the 3D-RD method improves the accuracy by about 3.5%, which shows that the method is effective. The method also provides a new way of thinking for hyperspectral research.
Key words：Image retrieval; Soybean heartworm; Hyperspectral; 3DCNN; Pest detection
[1] Li L, Zhang S, Wang B. IEEE Access, 2021, 9: 56683.
[2] Ma J, Pang L, Yan L, et al. AgriEngineering, 2020, 2(4): 556.
[3] Nguyen C, Sagan V, Maimaitiyiming M, et al. Sensors, 2021, 21(3): 742.
[4] Yan T, Xu W, Lin J, et al. Frontiers in Plant Science, 2021, 12: 74.
[5] Chen H, Hu C, Lee F, et al. Sensors, 2021, 21(9): 3094.
[6] GUI Jiang-sheng, FEI Jing-yi, FU Xia-ping, et al(桂江生，费婧怡，傅霞萍，等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2021, 41(7): 2171.
[7] Zhang Z, Zou Q, Lin Y, et al. IEEE Transactions on Multimedia, 2019, 22(2): 540.
[8] Liu H, Wang R, Shan S, et al. Deep Supervised Hashing for Fast Image Retrieval, IEEE Conference on Computer Vision and Pattern Recognition，2016.
[9] Cao Y, Long M, Liu B, et al. Deep Cauchy Hashing for Hamming Space Retrieval, IEEE Conference on Computer Vision and Pattern Recognition，2018.
[10] Wu L, Ling H, Li P, et al. IEEE Access, 2019, 7: 36489 (doi: 10.1109/ACCESS.2019.2900489).
[11] Yuan L, Wang T, Zhang X, et al. Central Similarity Quantization for Efficient Image and Video Retrieval, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020.
[12] Vinyals O, Blundell C, Lillicrap T, et al. Matching Networks for One Shot Learning, Proceedings of the Neural Information Processing Systems Conference, 2016.
[13] Finn C, Abbeel P, Levine S. Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks, Proceedings of International Conference on Machine Learning, 2017.
[14] Sung F, Yang Y, Zhang L, et al. Learning to Compare: Relation Network for Few-Shot Learning, CVPR 2018, doi: 10.1109/CVPR.2018.00131.
