|
|
|
|
|
|
| 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.
|
|
Received: 2021-07-21
Accepted: 2021-10-25
|
|
|
|
[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.
|
| [1] |
WANG Cai-ling1，ZHANG Jing1，WANG Hong-wei2*, SONG Xiao-nan1, JI Tong3. A Hyperspectral Image Classification Model Based on Band Clustering and Multi-Scale Structure Feature Fusion[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(01): 258-265. |
| [2] |
GAO Hong-sheng1, GUO Zhi-qiang1*, ZENG Yun-liu2, DING Gang2, WANG Xiao-yao2, LI Li3. Early Classification and Detection of Kiwifruit Soft Rot Based on
Hyperspectral Image Band Fusion[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(01): 241-249. |
| [3] |
WU Hu-lin1, DENG Xian-ming1*, ZHANG Tian-cai1, LI Zhong-sheng1, CEN Yi2, WANG Jia-hui1, XIONG Jie1, CHEN Zhi-hua1, LIN Mu-chun1. A Revised Target Detection Algorithm Based on Feature Separation Model of Target and Background for Hyperspectral Imagery[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(01): 283-291. |
| [4] |
CHU Bing-quan1, 2, LI Cheng-feng1, DING Li3, GUO Zheng-yan1, WANG Shi-yu1, SUN Wei-jie1, JIN Wei-yi1, HE Yong2*. Nondestructive and Rapid Determination of Carbohydrate and Protein in T. obliquus Based on Hyperspectral Imaging Technology[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(12): 3732-3741. |
| [5] |
HUANG You-ju1, TIAN Yi-chao2, 3*, ZHANG Qiang2, TAO Jin2, ZHANG Ya-li2, YANG Yong-wei2, LIN Jun-liang2. Estimation of Aboveground Biomass of Mangroves in Maowei Sea of Beibu Gulf Based on ZY-1-02D Satellite Hyperspectral Data[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(12): 3906-3915. |
| [6] |
ZHOU Bei-bei1, LI Heng-kai1*, LONG Bei-ping2. Variation Analysis of Spectral Characteristics of Reclaimed Vegetation in an Ionic Rare Earth Mining Area[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(12): 3946-3954. |
| [7] |
YUAN Wei-dong1, 2, JU Hao2, JIANG Hong-zhe1, 2, LI Xing-peng2, ZHOU Hong-ping1, 2*, SUN Meng-meng1, 2. Classification of Different Maturity Stages of Camellia Oleifera Fruit
Using Hyperspectral Imaging Technique[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(11): 3419-3426. |
| [8] |
FU Gen-shen1, LÜ Hai-yan1, YAN Li-peng1, HUANG Qing-feng1, CHENG Hai-feng2, WANG Xin-wen3, QIAN Wen-qi1, GAO Xiang4, TANG Xue-hai1*. A C/N Ratio Estimation Model of Camellia Oleifera Leaves Based on
Canopy Hyperspectral Characteristics[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(11): 3404-3411. |
| [9] |
SHEN Ying, WU Pan, HUANG Feng*, GUO Cui-xia. Identification of Species and Concentration Measurement of Microalgae Based on Hyperspectral Imaging[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(11): 3629-3636. |
| [10] |
XIE Peng, WANG Zheng-hai*, XIAO Bei, CAO Hai-ling, HUANG Yi, SU Wen-lin. Hyperspectral Quantitative Inversion of Soil Selenium Content Based on sCARS-PSO-SVM[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(11): 3599-3606. |
| [11] |
QIAN Rui1, XU Wei-heng2, 3 , 4*, HUANG Shao-dong2, WANG Lei-guang2, 3, 4, LU Ning2, OU Guang-long1. Tea Plantations Extraction Based on GF-5 Hyperspectral Remote Sensing
Imagery in the Mountainous Area[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(11): 3591-3598. |
| [12] |
ZHU Zhi-cheng1, WU Yong-feng2*, MA Jun-cheng2, JI Lin2, LIU Bin-hui3*, JIN Hai-liang1*. Response of Winter Wheat Canopy Spectra to Chlorophyll Changes Under Water Stress Based on Unmanned Aerial Vehicle Remote Sensing[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(11): 3524-3534. |
| [13] |
YANG Lei1, 2, 3, ZHOU Jin-song1, 2, 3, JING Juan-juan1, 2, 3, NIE Bo-yang1, 3*. Non-Uniformity Correction Method for Splicing Hyperspectral Imager Based on Overlapping Field of View[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(11): 3582-3590. |
| [14] |
SUN Lin1, BI Wei-hong1, LIU Tong1, WU Jia-qing1, ZHANG Bao-jun1, FU Guang-wei1, JIN Wa1, WANG Bing2, FU Xing-hu1*. Identification Algorithm of Green Algae Using Airborne Hyperspectral and Machine Learning Method[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(11): 3637-3643. |
| [15] |
TAO Jing-zhe1, 3, SONG De-rui1, 3, SONG Chuan-ming2, WANG Xiang-hai1, 2*. Multi-Band Remote Sensing Image Sharpening: A Survey[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(10): 2999-3008. |
|
|
|
|
