YOLOv8-RBean: Runner Bean Leaf Disease Detection Model Based on YOLOv8 DOI Creative Commons
Hongbing Chen,

Hengxiao Zhai,

Jinghuan Hu

и другие.

Agronomy, Год журнала: 2025, Номер 15(4), С. 944 - 944

Опубликована: Апрель 13, 2025

Runner bean is an important food source worldwide, and effective disease prevention control are crucial to ensuring security. However, runner vulnerable various diseases during its growth, which significantly affect both yield quality. Despite the continuous advancement of detection technologies, existing legume models still face significant challenges in identifying small-scale, irregular, visually insignificant types, limiting their practical application. To address this issue, study proposes improved model, YOLOv8_RBean, based on YOLOv8n object framework, specifically designed for leaf detection. The model enhances performance through three key innovations: (1) BeanConv module, integrates depthwise separable convolution pointwise improve multi-scale feature extraction; (2) a lightweight LA attention mechanism that incorporates spatial, channel, coordinate information enhance representation; (3) BLBlock structure built upon DWConv attention, optimizes computational efficiency while maintaining high accuracy. Experimental results dataset demonstrate proposed achieves precision 88.7%, with mAP50 mAP50-95 reaching 83.5% 71.3%, respectively. Moreover, reduces number parameters 2.71 M cost 7.5 GFLOPs, representing reductions 10% 7.4% compared baseline model. Notably, method shows clear advantages detecting morphologically subtle such as viral infections, providing efficient technical solution intelligent monitoring diseases.

Язык: Английский

RTR_Lite_MobileNetV2: A Lightweight and Efficient Model for Plant Disease Detection and Classification DOI Creative Commons
Sangeeta Duhan, Preeti Gulia, Nasib Singh Gill

и другие.

Current Plant Biology, Год журнала: 2025, Номер unknown, С. 100459 - 100459

Опубликована: Фев. 1, 2025

Язык: Английский

Процитировано

0
Exploring Nutrient Deficiencies in Lettuce Crops: Utilizing Advanced Multidimensional Image Analysis for Precision Diagnosis DOI Creative Commons

Xie Ji-long,

Shanshan Lv, Xihai Zhang

и другие.

Sensors, Год журнала: 2025, Номер 25(7), С. 1957 - 1957

Опубликована: Март 21, 2025

In agricultural production, lettuce growth, yield, and quality are impacted by nutrient deficiencies caused both environmental human factors. Traditional detection methods face challenges such as long processing times, potential sample damage, low automation, limiting their effectiveness in diagnosing managing crop nutrition. To address these issues, this study developed a deficiency system using multi-dimensional image analysis Field-Programmable Gate Arrays (FPGA). The first applied dynamic window histogram median filtering algorithm to denoise captured images. An adaptive integrating global local contrast enhancement was then used improve detail contrast. Additionally, combining threshold segmentation, improved Canny edge detection, gradient-guided segmentation enabled precise of healthy nutrient-deficient tissues. quantitatively assessed analyzing the proportion tissue Experimental results showed that achieved an average precision 0.944, recall rate 0.943, F1 score 0.943 across different growth stages, demonstrating significant improvements accuracy, efficiency while minimizing interference. This provides reliable method for rapid diagnosis lettuce.

Язык: Английский

Процитировано

0
Machine Learning and Deep Learning Approaches for Guava Disease Detection DOI
K Paramesha,

Shruti Jalapur,

Shalini Hanok

и другие.

SN Computer Science, Год журнала: 2025, Номер 6(4)

Опубликована: Апрель 7, 2025

Язык: Английский

Процитировано

0
Application of deep learning models for pest detection and identification DOI Creative Commons

Ayesha Rafique,

Madiha Abbasi,

Noreen Akram

и другие.

Mehran University Research Journal of Engineering and Technology, Год журнала: 2025, Номер 44(2), С. 117 - 128

Опубликована: Апрель 9, 2025

The quality and productivity of crops are seriously threatened by insect infestations, which is the primary focus this research. Traditional monitoring methodologies tend to be ineffective incorrect, resulting in wasted resources loss money. By incorporating cutting-edge AI deep learning technologies, study unveils a fresh method for rapid precisely identifying pests agricultural settings. This research makes use high-resolution image technologies Convolutional Neural Networks (CNNs) showcase promise models automated pest detection. generalizability model performance may improved using transfer techniques leading more efficient available resources. Key goals include extensive testing across varied types environmental settings, combined with design refinement CNN specifically engineered accurate identification. gap between traditional practices data-driven procedures filled suggested ensures significant increase that will contribute greater food security overall economic prosperity. strengthens influential effects on agriculture, including enhancement control, increasing security, boosting expansion. To promote continuous cooperation academics, businesses, farmers essential.

Язык: Английский

Процитировано

0
YOLOv8-RBean: Runner Bean Leaf Disease Detection Model Based on YOLOv8 DOI Creative Commons
Hongbing Chen,

Hengxiao Zhai,

Jinghuan Hu

и другие.

Agronomy, Год журнала: 2025, Номер 15(4), С. 944 - 944

Опубликована: Апрель 13, 2025

Runner bean is an important food source worldwide, and effective disease prevention control are crucial to ensuring security. However, runner vulnerable various diseases during its growth, which significantly affect both yield quality. Despite the continuous advancement of detection technologies, existing legume models still face significant challenges in identifying small-scale, irregular, visually insignificant types, limiting their practical application. To address this issue, study proposes improved model, YOLOv8_RBean, based on YOLOv8n object framework, specifically designed for leaf detection. The model enhances performance through three key innovations: (1) BeanConv module, integrates depthwise separable convolution pointwise improve multi-scale feature extraction; (2) a lightweight LA attention mechanism that incorporates spatial, channel, coordinate information enhance representation; (3) BLBlock structure built upon DWConv attention, optimizes computational efficiency while maintaining high accuracy. Experimental results dataset demonstrate proposed achieves precision 88.7%, with mAP50 mAP50-95 reaching 83.5% 71.3%, respectively. Moreover, reduces number parameters 2.71 M cost 7.5 GFLOPs, representing reductions 10% 7.4% compared baseline model. Notably, method shows clear advantages detecting morphologically subtle such as viral infections, providing efficient technical solution intelligent monitoring diseases.

Язык: Английский

Процитировано

0