Abstract: fusarium head blight (FHB), a frequent disease in wheat cultivation, can lead to substantial yield losses and the production of mycotoxins in grains. Therefore, the development of wheat varieties resistant to FHB is an important strategy to reduce related losses. In this respect, manual surveys of FHB are time-consuming and labor-intensive. To overcome this issue, this paper proposes a method for detecting and evaluating wheat FHB using color imaging and deep learning. Initially, a lightweight convolutional neural network model based on the you Only Look Once (YOLO) v8s artificial intelligence (AI) model was designed to detect wheat spikes from color images. Testing revealed that the model’s mean average precision in spike detection reached 0.964. Moreover, another lightweight model was developed for detecting wheat spikelet and FHB. To enhance the detection capability of the model for small objects, space-to-depth convolution (SPD-Conv) and BiFormer attention modules were integrated. The results indicated that the model can accurately detect spikelet and FHB, with a mean average precision of 0.936. Finally, based on the wheat spikelet detection results, the rate of diseased wheat spikes (RD_S) and the disease index for wheat (DI_W) were calculated to evaluate the severity of wheat FHB. For RD_S and DI_W, the coefficients of determination between phytologists’ evaluations and the estimates derived from the proposed method were 0.71 and 0.93, respectively. These results demonstrate that the proposed method facilitates the accurate and efficient detection of wheat FHB and contributes to the quantitative evaluation of FHB in the field.

基于轻量化卷积神经网络改进模型的小麦赤霉病检测与评估方法

[1]AbduAM, MokjiMM, SheikhUU, 2020. Automatic vegetable disease identification approach using individual lesion features. Comput Electron Agric, 176:105660.

[2]AgarwalM, GuptaSK, BiswasKK, 2020. Development of efficient CNN model for tomato crop disease identification. Sustain Comput Infor Syst, 28:100407.

[3]AhlgrenP, KekäläinenJ, 2007. Indexing strategies for Swedish full text retrieval under different user scenarios. Inform Process Manag, 43:81-102.

[4]AlmoujahedMB, RangarajanAK, WhettonRL, et al., 2022. Detection of Fusarium head blight in wheat under field conditions using a hyperspectral camera and machine learning. Comput Electron Agric, 203:107456.

[5]AQSIQ (General Administration of Quality Supervision, Inspection and Quarantine), 2011. Rules for monitoring and forecast of the wheat head blight, GB 15796-2011. National Standards of People’s Republic of China.

[6]BasavaiahJ, Arlene AnthonyA, 2020. Tomato leaf disease classification using multiple feature extraction techniques. Wireless Pers Commun, 115:633-651.

[7]ChenJD, ZhangDF, ZebA, et al., 2021. Identification of rice plant diseases using lightweight attention networks. Expert Syst Appl, 169:114514.

[8]ChenJR, KaoSH, HeH, et al., 2023. Run, don’t walk: chasing higher FLOPS for faster neural networks. IEEE/CVF Conference on Computer Vision and Pattern Recognition, p.12021-12031.

[9]ChenYY, WangXC, ZhangXL, et al., 2023. Spectral quantitative analysis and research of Fusarium head blight infection degree in wheat canopy visible areas. Agronomy, 13(3):933.

[10]ChenZR, ZhangYJ, WangYQ, et al., 2023. Robust image inpainting forensics by using an attention-based feature pyramid network. Appl Sci, 13(16):9196.

[11]FangT, ChenP, ZhangJ, et al., 2020. Crop leaf disease grade identification based on an improved convolutional neural network. J Electron Imag, 29(1):013004.

[12]FerentinosKP, 2018. Deep learning models for plant disease detection and diagnosis. Comput Electron Agric, 145:311-318.

[13]FigueroaM, Hammond-KosackKE, SolomonPS, 2018. A review of wheat diseases—a field perspective. Mol Plant Pathol, 19(6):1523-1536.

[14]GaoCF, GuoW, YangCH, et al., 2024. A fast and lightweight detection model for wheat Fusarium head blight spikes in natural environments. Comput Electron Agric, 216:108484.

[15]HellemansT, LandschootS, DewitteK, et al., 2018. Impact of crop husbandry practices and environmental conditions on wheat composition and quality: a review. J Agric Food Chem, 66(11):2491-2509.

[16]HongQQ, JiangL, ZhangZH, et al., 2022. A lightweight model for wheat ear Fusarium head blight detection based on RGB images. Remote Sens, 14(14):3481.

[17]HowardA, SandlerM, ChenB, et al., 2019. Searching for MobileNetV3. IEEE/CVF International Conference on Computer Vision, p.1314-1324.

[18]HuJ, XieLH, GuXA, et al., 2022. Information-interaction feature pyramid networks for object detection. IEEE 34th International Conference on Tools with Artificial Intelligence, p.1301-1306.

[19]KhanMS, UandaiSB, SrinivasanH, 2019. Anthracnose disease diagnosis by image processing, support vector machine and correlation with pigments. J Plant Pathol, 101(3):749-751.

[20]LiuGL, RedaFA, ShihKJ, et al., 2018. Image inpainting for irregular holes using partial convolutions. Proceedings of 15th European Conference on Computer Vision‒ECCV 2018, p.89-105.

[21]LiuST, HuangD, WangYH, 2019. Learning spatial fusion for single-shot object detection. arXiv:1911.09516.

[22]LiuT, ZhaoYY, SunY, et al., 2024. High-throughput identification of Fusarium head blight resistance in wheat varieties using field robot-assisted imaging and deep learning techniques. J Clean Prod, 480:144024.

[23]MaoR, WangZC, LiFL, et al., 2023. GSEYOLOX-s: an improved lightweight network for identifying the severity of wheat Fusarium head blight. Agronomy, 13:242.

[24]MehtaS, RastegariM, 2021. MobileViT: light-weight, general-purpose, and mobile-friendly vision transformer. arXiv:2110.02178.

[25]MustafaG, ZhengHB, KhanIH, et al., 2024. Enhancing Fusarium head blight detection in wheat crops using hyperspectral indices and machine learning classifiers. Comput Electron Agric, 218:108663.

[26]OuyangDL, HeS, ZhangGZ, et al., 2023. Efficient multi-scale attention module with cross-spatial learning. ICASSP IEEE International Conference on Acoustics, Speech and Signal Processing, p.1-5.

[27]PantaziXE, MoshouD, TamouridouAA, 2019. Automated leaf disease detection in different crop species through image features analysis and One Class Classifiers. Comput Electron Agric, 156:96-104.

[28]ParkJ, KimJ, KimCS, 2023. BiFormer: learning bilateral motion estimation via bilateral transformer for 4K video frame interpolation. IEEE/CVF Conference on Computer Vision and Pattern Recognition, p.1568-1577.

[29]QiuRC, YangC, MoghimiA, et al., 2019. Detection of Fusarium head blight in wheat using a deep neural network and color imaging. Remote Sens, 11(22):2658.

[30]RedmonJ, DivvalaS, GirshickR, et al., 2016. You only look once: unified, real-time object detection. IEEE Conference on Computer Vision and Pattern Recognition, p.779-788.

[31]RößleD, PreyL, RamgraberL, et al., 2023. Efficient noninvasive FHB estimation using RGB images from a novel multiyear, multirater dataset. Plant Phenomics, 5:0068.

[32]SacconFAM, ParceyD, PaliwalJ, et al., 2017. Assessment of Fusarium and deoxynivalenol using optical methods. Food Bioprocess Tech, 10:34-50.

[33]SampathkumarS, RajeswariR, 2022. An automated crop and plant disease identification scheme using Cognitive Fuzzy C-Means algorithm. IETE J Res, 68(5):3786-3797.

[34]SuWH, ZhangJJ, YangC, et al., 2021. Automatic evaluation of wheat resistance to Fusarium head blight using dual mask-RCNN deep learning frameworks in computer vision. Remote Sens, 13:26.

[35]SunkaraR, LuoT, 2022. No more strided convolutions or pooling: a new CNN building block for low-resolution images and small objects. arXiv:2208.03641.

[36]TanMX, LeQV, 2019. EfficientNet: rethinking model scaling for convolutional neural networks. arXiv:1905.11946.

[37]VinckeD, EylenboschD, JacqueminG, et al., 2023. Near infrared hyperspectral imaging method to assess Fusarium head blight infection on winter wheat ears. Microchem J, 191:108812.

[38]WangGQ, ChenMS, LinYC, et al., 2024. Efficient multi-branch dynamic fusion network for super-resolution of industrial component image. Displays, 82:102633.

[39]WangYH, LiJJ, SuWH, 2023. An integrated multi-model fusion system for automatically diagnosing the severity of wheat Fusarium head blight. Agriculture, 13(7):1381.

[40]ZhangDY, LuoHS, WangDY, et al., 2022. Assessment of the levels of damage caused by Fusarium head blight in wheat using an improved YoloV5 method. Comput Electron Agric, 198:107086.

[41]ZhangDY, LuoHS, ChengT, et al., 2023. Enhancing wheat Fusarium head blight detection using rotation Yolo wheat detection network and simple spatial attention network. Comput Electron Agric, 211:107968.

[42]ZhaoYS, LiuL, XieCJ, et al., 2020. An effective automatic system deployed in agricultural internet of things using Multi-Context Fusion Network towards crop disease recognition in the wild. App Soft Comput, 89:106128.

[43]ZhengL, ShenLY, TianL, et al., 2015. Scalable person re-identification: a benchmark. IEEE International Conference on Computer Vision, p.1116-1124.

[44]ZhuL, WangXJ, KeZH, et al., 2023. BiFormer: vision transformer with bi-level routing attention. IEEE/CVF Conference on Computer Vision and Pattern Recognition, p.10323-10333.

Similar articles