Smart Agriculture ›› 2024, Vol. 6 ›› Issue (5): 128-138.doi: 10.12133/j.smartag.SA202406012
• Technology and Method • Previous Articles Next Articles
LUO Youlu, PAN Yonghao(), XIA Shunxing, TAO Youzhi
Received:
2024-06-25
Online:
2024-09-30
Foundation items:
About author:
LUO Youlu, E-mail: 1632373384@qq.com
corresponding author:
CLC Number:
LUO Youlu, PAN Yonghao, XIA Shunxing, TAO Youzhi. Lightweight Apple Leaf Disease Detection Algorithm Based on Improved YOLOv8[J]. Smart Agriculture, 2024, 6(5): 128-138.
Add to citation manager EndNote|Ris|BibTeX
URL: https://www.smartag.net.cn/EN/10.12133/j.smartag.SA202406012
Table 4
Ablation experiments on apple leaf disease object detection
试验 | SPD-Conv | MSDA | RepHead | 准确率/% | 召回率/% | mAP50/% | mAP50:95/% | 浮点运算次数FLOPs/ G | 模型大小/MB |
---|---|---|---|---|---|---|---|---|---|
1 | √ | 82.9 | 78.5 | 85.9 | 36.3 | 7.4 | 5.6 | ||
2 | √ | 83.6 | 81.7 | 87.3 | 36.6 | 8.4 | 8.3 | ||
3 | √ | 84.2 | 78.7 | 86.5 | 35.9 | 8.4 | 8.2 | ||
4 | √ | √ | 82.9 | 83.0 | 87.7 | 37.7 | 7.9 | 5.9 | |
5 | √ | √ | 81.9 | 80.4 | 86.7 | 36.6 | 7.7 | 7.6 | |
6 | √ | √ | 84.0 | 80.1 | 87.5 | 37.0 | 8.8 | 8.6 | |
7 | √ | √ | √ | 83.1 | 80.2 | 88.2 | 37.0 | 8.0 | 7.8 |
Table 5
Experimental results of apple leaf disease detection using different network models
模型 | 准确率/% | 召回率/% | mAP50/% | mAP50:95/% | 浮点运算次数FLOPs/G | 模型大小/MB | 参数量/M |
---|---|---|---|---|---|---|---|
YOLOv8n-SMR | 83.1 | 80.2 | 88.2 | 37.0 | 8.0 | 7.8 | 3.7 |
YOLOv9-c | 83.8 | 81.0 | 86.9 | 36.8 | 102.3 | 51.6 | 25.5 |
YOLOv7-tiny | 82.8 | 81.8 | 86.8 | 34.2 | 13.2 | 12.3 | 6.0 |
RetinaNet | 78.3 | 78.2 | 80.4 | 33.0 | 191.4 | 139.0 | 36.3 |
Faster-RCNN | 73.5 | 74.3 | 76.6 | 31.4 | 370.2 | 108.0 | 136.7 |
Table 8
Model training results before and after data class balancing in apple leaf disease detection
类别 | 准确率 (平衡前) | 准确率 (平衡后) | 召回率 (平衡前) | 召回率 (平衡后) | mAP50 (平衡前) | mAP50 (平衡后) | mAP50:95 (平衡前) | mAP50:95 (平衡后) |
---|---|---|---|---|---|---|---|---|
总体 | 83.1 | 85.8 | 80.2 | 83.6 | 88.2 | 88.9 | 37.0 | 39.4 |
褐纹病 | 91.3 | 90.2 | 86.6 | 95.7 | 96.2 | 97.1 | 39.2 | 50.3 |
褐腐病 | 79.9 | 92.2 | 85.6 | 82.5 | 89.9 | 93.4 | 39.6 | 39.2 |
黑星病 | 74.7 | 77.3 | 62.7 | 69.9 | 74.8 | 76.6 | 30.8 | 32.0 |
锈病 | 86.5 | 83.5 | 85.7 | 86.2 | 91.9 | 88.7 | 38.4 | 36.3 |
1 |
田有文, 程怡, 王小奇, 等. 基于高光谱成像的苹果虫害检测特征向量的选取[J]. 农业工程学报, 2014, 30(12): 132-139.
|
|
|
2 |
|
3 |
王帅, 王利众, 朱丽平, 等. 基于改进YOLOv5s的苹果病害检测技术研究[J]. 山西农业大学学报(自然科学版), 2024, 44(4): 118-129.
|
|
|
4 |
王君婵, 洪俐, 朱少龙, 等. 基于深度学习的病害识别方法研究[J]. 农业展望, 2023, 19(8): 90-99.
|
|
|
5 |
|
6 |
WOO S,
|
7 |
|
8 |
|
9 |
|
10 |
|
11 |
|
12 |
|
13 |
|
14 |
|
15 |
|
16 |
陆丽娜, 于啸. 深度学习在大豆叶片图像数据管理中的识别与分类研究[J].农业图书情报学报,2023,35(2):87-94.
|
|
|
17 |
|
18 |
|
19 |
|
20 |
|
21 |
|
22 |
|
23 |
石展鲲, 杨风, 韩建宁, 等. 基于Faster-RCNN的自然环境下苹果识别[J]. 计算机与现代化, 2023(2): 62-65.
|
|
|
24 |
|
25 |
杨锋, 姚晓通. 基于改进YOLOv8的小麦叶片病虫害检测轻量化模型[J].智慧农业(中英文), 2024, 6(1): 147-157.
|
|
|
26 |
郑宇达, 陈仁凡, 杨长才, 等. 基于改进YOLOv5s模型的柑橘病虫害识别方法[J]. 华中农业大学学报, 2024, 43(2): 134-143.
|
|
|
27 |
陈禹, 吴雪梅, 张珍, 等. 基于改进YOLOv5s的自然环境下茶叶病害识别方法[J]. 农业工程学报, 2023, 39(24): 185-194.
|
|
[1] | CUI Jiale, ZENG Xiangfeng, REN Zhengwei, SUN Jian, TANG Chen, YANG Wanneng, SONG Peng. Detection Method of Effective Tillering of Rice in Field Based on Lightweight Ghost-YOLOv8 and Smart Phone [J]. Smart Agriculture, 2024, 6(5): 98-107. |
[2] | LIU Yi, ZHANG Yanjun. ReluformerN: Lightweight High-Low Frequency Enhanced for Hyperspectral Agricultural Lancover Classification [J]. Smart Agriculture, 2024, 6(5): 74-87. |
[3] | NIAN Yue, ZHAO Kaixuan, JI Jiangtao. Cow Hoof Slippage Detecting Method Based on Enhanced DeepLabCut Model [J]. Smart Agriculture, 2024, 6(5): 153-163. |
[4] | ZHANG Yanqi, ZHOU Shuo, ZHANG Ning, CHAI Xiujuan, SUN Tan. A Regional Farming Pig Counting System Based on Improved Instance Segmentation Algorithm [J]. Smart Agriculture, 2024, 6(4): 53-63. |
[5] | LI Minghuang, SU Lide, ZHANG Yong, ZONG Zheying, ZHANG Shun. Automatic Measurement of Mongolian Horse Body Based on Improved YOLOv8n-pose and 3D Point Cloud Analysis [J]. Smart Agriculture, 2024, 6(4): 91-102. |
[6] | WENG Zhi, FAN Qi, ZHENG Zhiqiang. Automatic Measurement Method of Beef Cattle Body Size Based on Multimodal Image Information and Improved Instance Segmentation Network [J]. Smart Agriculture, 2024, 6(4): 64-75. |
[7] | YANG Lin, LIU Shuangyin, XU Longqin, HE Min, SHENG Qingfeng, HAN Jiawei. Dynamic Prediction Method for Carbon Emissions of Cold Chain Distribution Vehicle under Multi-Source Information Fusion [J]. Smart Agriculture, 2024, 6(4): 138-148. |
[8] | HOU Yiting, RAO Yuan, SONG He, NIE Zhenjun, WANG Tan, HE Haoxu. A Rapid Detection Method for Wheat Seedling Leaf Number in Complex Field Scenarios Based on Improved YOLOv8 [J]. Smart Agriculture, 2024, 6(4): 128-137. |
[9] | WENG Zhi, LIU Haixin, ZHENG Zhiqiang. CSD-YOLOv8s: Dense Sheep Small Target Detection Model Based on UAV Images [J]. Smart Agriculture, 2024, 6(4): 42-52. |
[10] | LI Hao, DU Yuqiu, XIAO Xingzhu, CHEN Yanxi. Remote Sensing Identification Method of Cultivated Land at Hill County of Sichuan Basin Based on Deep Learning [J]. Smart Agriculture, 2024, 6(3): 34-45. |
[11] | NIE Ganggang, RAO Honghui, LI Zefeng, LIU Muhua. Severity Grading Model for Camellia Oleifera Anthracnose Infection Based on Improved YOLACT [J]. Smart Agriculture, 2024, 6(3): 138-147. |
[12] | XU Ruifeng, WANG Yaohua, DING Wenyong, YU Junqi, YAN Maocang, CHEN Chen. Shrimp Diseases Detection Method Based on Improved YOLOv8 and Multiple Features [J]. Smart Agriculture, 2024, 6(2): 62-71. |
[13] | ZHANG Ronghua, BAI Xue, FAN Jiangchuan. Crop Pest Target Detection Algorithm in Complex Scenes:YOLOv8-Extend [J]. Smart Agriculture, 2024, 6(2): 49-61. |
[14] | ZHANG Jing, ZHAO Zexuan, ZHAO Yanru, BU Hongchao, WU Xingyu. Oilseed Rape Sclerotinia in Hyperspectral Images Segmentation Method Based on Bi-GRU and Spatial-Spectral Information Fusion [J]. Smart Agriculture, 2024, 6(2): 40-48. |
[15] | WU Xiaoyan, GUO Wei, ZHU Yiping, ZHU Huaji, WU Huarui. Transplant Status Detection Algorithm of Cabbage in the Field Based on Improved YOLOv8s [J]. Smart Agriculture, 2024, 6(2): 107-117. |
Viewed | ||||||
Full text |
|
|||||
Abstract |
|
|||||