Lawn weed recognition based on improved fuzzy C-means clustering algorithm
-
摘要:目的
为了实现草坪杂草管理的精准化施药,针对自然环境中杂草与草坪颜色相近导致杂草难以分割的问题,提出一种改进模糊C均值(Fuzzy C-means, FCM)聚类的分割算法。
方法利用超绿算子提取感兴趣区域,融合HSV空间的多通道信息进行图像预处理,扩大杂草与草坪的特征差异。使用区域面积约束滤波范围,去除预处理图像中的草坪背景噪声,降低中值滤波造成的目标区域灰度级损失。提出一种各向灰度分布差异(Difference of gray distribution, DGD)检测算子,在聚类过程中引入像素周围不同方向的灰度分布差异特征实现草坪杂草分割。
结果与传统FCM、FCM-S2、FCMNLS以及RSFCM算法相比,本文算法对大多数噪声区域抑制效果较好,可以实现较为理想的杂草分割效果。本文算法能有效分割草坪杂草,平均分割准确率达到91.45%,比FCM、FCM-S2、FCMNLS和RSFCM算法分别提高16.35%、4.12%、6.80%和8.06%。
结论本文算法可有效地分割自然环境中的草坪杂草,为草坪杂草精准化施药提供了条件,具有实际应用价值。
Abstract:ObjectiveIn order to realize the precise application of herbicides for lawn weed management, an improved fuzzy C-means (FCM) clustering segmentation algorithm was proposed to solve the problem that it is difficult to segment weeds due to the similar color between weeds and lawns in natural environment.
MethodThe region of interest was extracted by extra-green operator, and the multi-channel information in HSV space was incorporated for image preprocessing to expand the feature difference between weeds and lawns. The filtering range was constrained using region area to remove the lawn background noise in the preprocessed image and reduce the gray level loss in the target region caused by median filtering. An anisotropic detection operator of difference of gray distribution(DGD) was proposed. In the clustering process, the gray distribution difference characteristics in different directions around pixels were introduced to realize lawn weed segmentation.
ResultCompared with the traditional FCM, FCM-S2, FCMNLS and RSFCM algorithms, the algorithm in this paper (DGDFCM) had better suppression effect on most noise areas and could achieve ideal weed segmentation effect. The DGDFCM algorithm could effectively segment lawn weeds, and the average segmentation accuracy was 91.45%, which was 16.35%, 4.12%, 6.80% and 8.06% higher than FCM, FCM-S2, FCMNLS and RSFCM algorithms, respectively.
ConclusionThe DGDFCM algorithm can effectively segment lawn weeds in natural environment, provides the condition of precise application of herbicides for lawn weeds, and has a practical application value.
-
Keywords:
- Precision spraying /
- Image processing /
- Image segmentation /
- Fuzzy C-means clustering /
- Fawn weed
-
-
表 1 草坪和杂草样本表型
Table 1 Phenotypes of lawn and weed samples
样本编号
Sample number草坪表型
Lawn phenotype杂草表型
Weed phenotype叶片颜色
Leaf color生长状态
Growth state叶片形状
Leaf shape叶片颜色
Leaf color生长状态
Growth state1 青绿 密集 细叶 青绿 丛生 2 黄绿 密集 大阔叶 黄绿 单株 3 黄绿 密集 小阔叶 黄绿 单株 4 青绿 密集 大阔叶 青绿 丛生 5 嫩绿 密集 细叶 青绿 单株 6 嫩绿 稀疏 大阔叶 青绿 丛生 7 青绿 密集 小阔叶 青绿 单株 8 嫩绿 稀疏 大阔叶 嫩绿 单株 表 2 不同算法的图像分割质量评价
Table 2 Quality evaluation for image segmentation of different algorithm
% 样本编号 Sample number 指标1) Index FCM FCM-S2 FCMNLS RSFCM DGDFCM 1 SA 59.07 72.11 54.14 62.81 85.78 UR 11.83 11.27 11.44 9.34 7.41 OR 13.23 3.05 2.14 23.43 1.69 2 SA 95.21 95.74 95.67 96.01 95.87 UR 2.51 2.55 2.53 2.47 2.51 OR 1.29 0.85 0.80 1.12 0.88 3 SA 67.75 86.07 82.99 77.80 87.57 UR 8.40 8.42 8.43 7.08 7.36 OR 12.02 2.49 2.46 10.03 2.61 4 SA 89.21 92.59 92.67 91.71 93.34 UR 3.86 3.84 3.86 3.71 3.76 OR 3.69 1.57 1.13 2.72 1.32 5 SA 79.07 83.79 86.58 83.79 91.61 UR 9.75 8.17 8.33 5.25 6.13 OR 9.47 2.78 1.60 10.35 1.39 6 SA 84.37 93.77 93.98 90.96 94.60 UR 4.11 3.51 3.53 3.20 3.34 OR 6.43 1.07 0.71 3.92 0.73 7 SA 83.81 90.74 90.20 87.84 92.23 UR 5.88 5.00 5.03 4.66 4.80 OR 6.08 1.99 1.58 4.50 1.53 8 SA 70.29 87.84 88.73 86.08 90.60 UR 8.24 5.91 5.96 4.85 5.33 OR 12.17 1.21 0.71 7.26 0.19 平均
AverageSA 78.60 87.83 85.62 84.63 91.45 UR 6.82 6.08 6.14 5.07 5.08 OR 8.05 1.88 1.39 7.92 1.09 1) SA: 分割准确率,UR: 欠分割率,OR: 过分割率
1) SA: Segmentation accuracy, UR: Under segmentation rate, OR: Over segmentation rate -
[1] IGNATIEVA M, ERIKSSON F, ERIKSSON T, et al. The lawn as a social and cultural phenomenon in Sweden[J]. Urban Forestry & Urban Greening, 2017, 21: 213-223.
[2] 杭楠, 王翔宇, 张蕴薇, 等. 结缕草草坪杂草化学防除策略[J]. 草业科学, 2019, 36(9): 2259-2269. [3] HOCKEMEYER K, KOCH P L. Alternative and low‐use‐rate herbicides offer similar levels of weed control to current standards in turfgrass lawns in the upper midwest[J]. Crop, Forage & Turfgrass Management, 2019, 5(1): 1-6.
[4] MARTELLONI L, FONTANELLI M, CATUREGLI L, et al. Flaming to control weeds in seashore paspalum (Paspalum vaginatum Sw. ) turfgrass[J]. Journal of Agricultural Engineering, 2019, 50(3): 105-112. doi: 10.4081/jae.2019.904
[5] JIN X, CHE J, CHEN Y. Weed identification using deep learning and image processing in vegetable plantation[J]. IEEE Access, 2021, 9: 10940-10950. doi: 10.1109/ACCESS.2021.3050296
[6] YU J, SCHUMANN A W, SHARPE S M, et al. Detection of grassy weeds in bermudagrass with deep convolutional neural networks[J]. Weed Science, 2020, 68(5): 1-31. doi: 10.1017/wsc.2020.76
[7] WATCHAREERUETAI U, MATSUMOTO Y T T, KUDO H, et al. Computer vision based methods for detecting weeds in lawns[J]. Machine Vision & Applications, 2006, 17(5): 287-296.
[8] PARRA L, MARIN J, YOUSFI S, et al. Edge detection for weed recognition in lawns[J]. Computers and Electronics in Agriculture, 2020, 176(2): 105684.
[9] TONGBRAM S, SHIMRAY B A, SINGH L S, et al. A novel image segmentation approach using fcm and whale optimization algorithm[J]. Journal of Ambient Intelligence and Humanized Computing, 2021(1): 1-15.
[10] 兰蓉, 林洋. 抑制式非局部空间直觉模糊C−均值图像分割算法[J]. 电子与信息学报, 2019, 41(6): 1472-1479. [11] 赵泉华, 王春畅, 李玉. 基于混合邻域约束项的改进FCM算法[J]. 控制与决策, 2021, 36(6): 1457-1464. [12] 张春龙, 张楫, 张俊雄, 等. 近色背景中树上绿色苹果识别方法[J]. 农业机械学报, 2014, 45(10): 277-281. doi: 10.6041/j.issn.1000-1298.2014.10.043 [13] 张田, 田勇, 王子, 等. 基于清晰度评价的自适应阈值图像分割法[J]. 东北大学学报(自然科学版), 2020, 41(9): 1231-1238. doi: 10.12068/j.issn.1005-3026.2020.09.003 [14] 王宁, 殷长春, 高玲琦, 等. 基于曲波变换的航空电磁数据去噪方法研究[J]. 地球物理学报, 2020, 63(12): 4592-4603. doi: 10.6038/cjg2020N0365 [15] CAI W, CHEN S, ZHANG D. Fast and robust fuzzy C-means clustering algorithms incorporating local information for image segmentation[J]. Pattern Recognition, 2007, 40(3): 825-838. doi: 10.1016/j.patcog.2006.07.011
[16] 毛林, 赵利强, 于明安, 等. 基于图像局部熵的混合水平集模型甲状旁腺分割[J]. 光学学报, 2019, 39(12): 256-264. [17] 徐金东, 赵甜雨, 冯国政, 等. 基于上下文模糊C均值聚类的图像分割算法[J]. 电子与信息学报, 2021, 43(7): 2079-2086. doi: 10.11999/JEIT200263 -
期刊类型引用(3)
1. 秦国峰,刘根林. 84消毒液对非洲猪瘟病毒的杀灭效果. 上海畜牧兽医通讯. 2025(02): 19-20+24 . 百度学术
2. 王量,刘敏,郭星辉,姚帆,段聪康,姚军. 猪场外围环境非洲猪瘟病毒阳性率的影响因素分析. 上海畜牧兽医通讯. 2024(01): 15-19 . 百度学术
3. 邓毅,漆信桥,张继甫,张勋,周娜娜,徐志文,刘天强. 养猪场烟雾消毒机消毒效果评价. 中国猪业. 2024(04): 37-43 . 百度学术
其他类型引用(1)