基于机器视觉的海鲜菇恢复期生长特征识别

沈嘉骊; 杨淑珍; 杜万和; 张东剑; 李培超

doi:10.12299/jsues.24-0286

基于机器视觉的海鲜菇恢复期生长特征识别

doi: 10.12299/jsues.24-0286

1.
上海工程技术大学机械与汽车工程学院, 上海 201620
2.
上海第二工业大学智能制造与控制工程学院, 上海 201209

基金项目: 浦东新区科技发展基金事业单位民生科研专项（PKJ2023-N13）

详细信息

作者简介:
沈嘉骊（1999 − ），女，硕士生，研究方向为机器视觉。E-mail：sjl5476@126.com

通讯作者:
李培超（1976 − ），男，教授，博士，研究方向为多场耦合力学和人工智能。E-mail：wiselee18@163.com

中图分类号: TP391.4
计量
- 文章访问数: 18
- HTML全文浏览量: 12
- PDF下载量: 1
- 被引次数: 0
出版历程
- 收稿日期: 2024-09-29
- 网络出版日期: 2026-08-19
- 刊出日期: 2026-06-30

Recognition of growth characteristics during recovery of seafood mushroom based on machine vision

1.
School of Mechanical and Automotive Engineering, Shanghai University of Engineering Science, Shanghai 201620, China
2.
School of Intelligent Manufacturing and Control Engineering, Shanghai Polytechnic University, Shanghai 201209, China

摘要

摘要: 在实际菇房环境中，背景和蓝光干扰对海鲜菇恢复期菌丝识别效果的影响很大。因此，提出一种基于机器视觉的改进阈值处理的智能计算方法。针对上述问题，首先采用高斯平滑处理去除图像噪声，再通过顶帽自适应二值化方法（TH-ATB）结合最大面积轮廓检测技术，提取无背景的菌丝图像；接着，结合改进的自动白平衡算法（IAWB-GWPR）与对比度受限自适应直方图均衡化（CLAHE）算法处理蓝光。最后，通过灰度直方图计算菌丝浓白程度和覆盖率，并用二维高斯拟合评估其分布均匀度。实验结果显示，本研究算法在蓝光环境下识别效果的决定系数达到0.94，较蓝光无处理、IAWB-GWPR和CLAHE方法分别提高0.15、0.14和0.35，浓白程度和覆盖率的区间比例分别为83.64%和88.98%，相对偏差也在允许范围内。
- 图像识别 /
- 机器视觉 /
- 改进的自动白平衡算法 /
- 改进的顶帽自适应二值化算法 /
- 对比度受限自适应直方图均衡化
Abstract: In the actual mushroom house environment, the interference from background and blue light has a significant impact on the identification effect of seafood mushroom mycelium in the recovery period. Therefore, an intelligent computation method based on improved threshold processing using machine vision was proposed. To address the above problems, image noise was first removed by Gaussian smoothing, and then the background-free mycelium image was extracted by top-hat adaptive binarization method (TH-ATB) combined with maximum area contour detection. Subsequently, the improved automatic white balance algorithm (IAWB-GWPR) is integrated with contrast limited adaptive histogram equalization (CLAHE) to address blue light interference. Finally, the gray histogram is used to calculate mycelium density and coverage, while two-dimensional Gaussian fitting assesses distribution uniformity. Experimental results demonstrate that the proposed algorithm achieves a coefficient of determination of 0.94 under blue light conditions, improving by 0.15, 0.14, and 0.35 compared to the no treatment, IAWB-GWPR, and CLAHE methods, respectively. The interval ratios for density and coverage are 83.64% and 88.98%, with relative deviations remaining within acceptable limits.

HTML全文

图 1 海鲜菇菌丝不同浓白程度图像示例

Figure 1. Examples of images of seafood mushroom mycelium with different degrees of whiteness

下载: 全尺寸图片幻灯片

图 2 菇房实地与相机架的摆放图片

Figure 2. Pictures of mushroom field and camera rack placement

下载: 全尺寸图片幻灯片

图 3 原图与各二值化结果的对比

Figure 3. Comparison between original image and binarization results

下载: 全尺寸图片幻灯片

图 4 不同蓝光强度下的两种蓝光处理算法效果的对比

Figure 4. Comparison of the effect of two blue light processing algorithms under different blue light intensities

下载: 全尺寸图片幻灯片

图 5 不同蓝光强度图像使用所提蓝光处理方法后的菌丝提取结果对比

Figure 5. Comparison of mycelium extraction results of images with different blue light intensities using the blue light processing method proposed

下载: 全尺寸图片幻灯片

图 6 蓝光开启时不同算法对浓白程度测量结果可视化

Figure 6. Visualization of different algorithms for measuring whiteness when blue light is on

下载: 全尺寸图片幻灯片

图 7 生长特征测量结果可视化

Figure 7. Visualization of growth characteristic measurements

下载: 全尺寸图片幻灯片

参考文献(18)

[1]	李玉, 杨仁智, 郑雪平. 画说真姬菇优质高效生产技术[M] . 北京: 中国农业科学技术出版社, 2020.
[2]	Jang M J, Lee Y H. The suitable mixed LED and light intensity for cultivation of oyster mushroom[J] . Journal of Mushroom, 2014, 12(4): 258 − 262.
[3]	杜尚丰, 何耀枫, 梁美惠, 等. 物联网温室环境调控系统[J] . 农业机械学报, 2017, 48(增刊1): 296 − 301.
[4]	冀荣华, 李豹, 陈振海, 等. 基于模糊推理的多因素兔舍环境调控方法研究[J] . 农业机械学报, 2019, 50(增刊1): 361 − 365.
[5]	张帆. 食用菌生长库研发及智能化研究[J] . 农业装备技术, 2012, 38(2): 22 − 24.
[6]	Marim R A, Avelino K V, Halabura M I W, et al. Lentinus crinitus response to blue light on carbohydrate-active enzymes[J] . Bioscience Journal, 2020, 36(3): 924 − 931. doi: 10.14393/bj-v36n3a2020-49986
[7]	袁晓辉, 付永平, 肖世俊, 等. 食用菌表型组技术研究进展[J] . 菌物学报, 2021, 40(4): 721 − 742. doi: 10.13346/j.mycosystema.21007
[8]	Sten O, Del Dottore E, Pugno N, et al. A ridge-based detection algorithm with filament overlap identification for 2D mycelium network analysis[J] . Ecological Informatics, 2024, 82: 102670. doi: 10.1016/j.ecoinf.2024.102670
[9]	胡冬, 袁涛, 于海龙, 等. 基于数字图像处理技术的猪肚菇菌落表型性状分析[J] . 食用菌学报, 2022, 29(3): 32 − 40. doi: 10.16488/j.cnki.1005-9873.2022.03.005
[10]	陈燕, 陆嘉豪, 胡小春, 等. 基于VGG-UNet的食用菌菌丝体表型参数自动测量方法[J] . 农业机械学报, 2024, 55(1): 233 − 240.
[11]	谭硕果, 王盈, 孙颖慧. 海鲜菇的人工栽培、营养成分及加工利用研究进展[J] . 中国食用菌, 2024, 43(3): 1 − 5. doi: 10.13629/j.cnki.53-1054.2024.03.001
[12]	Feng Y, Xu H R, Sun Y, et al. Effect of light on quality of preharvest and postharvest edible mushrooms and its action mechanism: A review[J] . Trends in Food Science & Technology, 2023, 139: 104119. doi: 10.1016/j.tifs.2023.104119
[13]	徐晓昭, 蔡轶珩, 刘长江, 等. 基于图像分析的偏色检测及颜色校正方法[J] . 测控技术, 2008, 27(5): 10 − 12,21. doi: 10.3969/j.issn.1000-8829.2008.05.003
[14]	化春键, 郭金花, 陈莹. 低对比度下手机膜缺陷图像的分割研究[J] . 激光与光电子学进展, 2020, 57(20): 201013. doi: 10.3788/LOP57.201013
[15]	胡张颖, 周全, 陈明举, 等. 图像去模糊研究综述[J] . 中国图象图形学报, 2024, 29(4): 841 − 861.
[16]	Wang Z Y, Huang X Q, Cheng Z Q. Automatic spot identification method for high throughput surface Plasmon resonance imaging analysis[J] . Biosensors, 2018, 8(3): 85. doi: 10.3390/bios8030085
[17]	Li Y S, Li Z Z, Li J, et al. Robust small infrared target detection using weighted adaptive ring top-hat transformation[J] . Signal Processing, 2024, 217: 109339. doi: 10.1016/j.sigpro.2023.109339
[18]	Wang X W, Zhou Z Y, Chen B Q, et al. Distribution uniformity improvement methods of a large discharge rate disc spreader for UAV fertilizer application[J] . Computers and Electronics in Agriculture, 2024, 220: 108928. doi: 10.1016/j.compag.2024.108928