A quantitative evaluation method for postharvest banana characteristic browning based on the three-dimensional point cloud
-
摘要:目的
研究采后香蕉的表征褐变并评估其衰老程度对香蕉保鲜管理至关重要，本研究致力于解决传统人工测量香蕉表征褐变存在的劳动强度大、效率低下的问题。
方法提出一种基于三维点云的采后香蕉表征褐变过程定量评估方法。首先利用三维扫描仪获取香蕉的三维点云模型，重构出香蕉的几何模型；然后使用欧式聚类对香蕉几何模型进行点云滤波降噪处理；再结合图像阈值分割法与散点轮廓算法(Alpha Shapes)求出香蕉的体积、表面积和黑斑面积；最后利用傅里叶函数对香蕉表面黑斑变化过程进行模拟，确定香蕉表征褐变过程的评估模型。设计本算法与溢水法测量实际香蕉体积、手绘测量面积的对比试验。
结果拟合香蕉的生长函数，回归直线对观测值的拟合程度R2 =0.9816>0.75，验证了算法的有效性。对比试验结果表明，本算法与实际测量值的平均相对误差小于1%，验证了该算法的准确性和可行性。
结论本研究可为香蕉的保鲜管理提供数据及技术支撑。
Abstract:ObjectiveTo study the characteristic browning of postharvest bananas and evaluate the degree of senescence is very important for their fresh-keeping management. This study aims to solve the problems of high labor intensity and low efficiency of traditional methods for measuring the characteristic browning of bananas.
MethodA quantitative evaluation method of postharvest banana characteristic browning process based on three-dimensional point cloud was proposed. Firstly, three-dimensional point cloud model of banana was obtained by 3D scanner, and the geometric model of banana was reconstructed. Then the banana geometry model was denoised by point cloud filtering using euclidean clustering. The volume, surface area and dark spot area of banana were obtained by combining the image threshold segmentation method and Alpha Shapes. Finally, Fourier function was used to simulate the changing process of banana surface dark spots and determine the evaluation model of banana characteristic browning process. A comparison test was designed between the algorithm and the overflow method to measure the actual banana volume and the hand-drawn measurement area.
ResultBy fitting the growth functions of different bananas, the fitting degree R2 of the regression line to the observed values was 0.9816>0.75, indicating the effectiveness of the algorithm. The comparison results showed that the average relative error between the proposed algorithm and the actual measured value was less than 1%, which verified the accuracy and feasibility of the proposed algorithm.
ConclusionThis study can provide data and technical support for banana preservation management.
-
Keywords:
- Three-dimensional point cloud /
- Data fitting /
- Banana /
- Browning /
- Fresh-keeping
-
-
![]()
图 5 RGB阈值分割处理前(a)、后(b)
Figure 5. Before (a) and after (b) RGB threshold segmentation processing
![]()
图 6 10根香蕉表面黑斑占比随时间变化的拟合曲线
Figure 6. The fitting curves of the proportion of dark spots on the surface of ten bananas with time
![]()
图 7 香蕉表面黑斑占比随时间变化的傅里叶函数拟合曲线
Figure 7. The fourier function fitting curves of the proportion of dark spots on banana surface with time
![]()
图 8 香蕉表面积、体积、黑斑面积和黑斑占比折线图
Figure 8. Line charts of banana surface area, volume, dark spot area and dark spot proportion
表 1 不同香蕉样本的面积与体积1)
Table 1 Areas and volumes of different banana samples
样本
SampleM1/
mm2V1/
cm3M2/
mm2V2/
cm3相对误差/%
Relative errorM2 V2 1 100 189 98.87 189.21 1.13 0.11 2 100 203 98.93 202.16 1.07 0.42 3 225 187 224.46 188.16 0.24 0.62 4 225 174 224.65 171.13 0.16 1.65 5 400 186 397.17 184.16 0.71 0.99 1)M1 为实际测量的手绘正方形的表面积，V1 为溢水法记录的香蕉的体积；M2 为本文算法得出的手绘正方形的表面积，V2 为本文算法得出的香蕉体积
1)M1 is the actually measured surface area of the hand-drawn square, V1 is the volume of the banana recorded by the overflow method; M2 is the surface area of the hand-drawn square obtained by this algorithm, V2 is the volume of the banana obtained by this algorithm
下载: 导出CSV
-
[1] MIAO Y L, WANG L Y, PENG C, et al. Banana plant counting and morphological parameters measurement based on terrestrial laser scanning[J]. Plant Methods, 2022, 18(1): 66. doi: 10.1186/s13007-022-00894-y.
[2] 杨凤, 刘灿灿, 邓贵明, 等. 香蕉营养品质与功能特性研究紧张[J]. 广东农业科学, 2022, 49(10): 146-154. [3] WANG S W, YANG Y, XIAO D, et al. Polysaccharides from banana (Musa spp. ) blossoms: Isolation, identification and anti-glycation effects[J]. International Journal of Biological Macromolecules, 2023, 236: 123957. doi: 10.1016/j.ijbiomac.2023.123957.
[4] 王顺. 水果成熟度检测的机器视觉和嗅觉可视化技术研究[D]. 镇江: 江苏大学, 2019. [5] MAGALHÃES D B, DONATO S L R, DOS SANTOS M R, et al. Yield of ‘Prata-Anã’banana plants under water deficit and high plant density[J]. Revista Brasileira De Fruticultura, 2020, 42(5): 29452020046. doi: 10.1590/0100-29452020046.
[6] FANG Y, QIU X, GUO T, et al. An automatic method for counting wheat tiller number in the field with terrestrial LiDAR[J]. Plant Methods, 2020, 16(1): 132. doi: 10.1186/s13007-020-00672-8.
[7] PACE J, LEE N, NAIK H S, et al. Analysis of maize (Zea mays L. ) seedling roots with the high-throughput image analysis tool ARIA (Automatic root image analysis)[J]. PLoS One, 2014, 9(9): e108255. doi: 10.1371/journal.pone.0108255.
[8] DAS CHOUDHURY S, SAMAL A, AWADA T. Leveraging image analysis for high-throughput plant phenotyping[J]. Frontiers in Plant Science, 2019, 10: 508. doi: 10.3389/fpls.2019.00508.
[9] LIU W Z, LIU C, JIN J Y, et al. High-throughput phenotyping of morphological seed and fruit characteristics using X-ray computed tomography[J]. Frontiers in Plant Science, 2020, 11: 601475. doi: 10.3389/fpls.2020.601475.
[10] JAROLMASJED S, SANKARAN S, MARZOUGUI A, et al. High-throughput phenotyping of fire blight disease symptoms using sensing techniques in apple[J]. Frontiers in Plant Science, 2019, 10: 576. doi: 10.3389/fpls.2019.00576.
[11] AMPATZIDIS Y, PARTEL V. UAV-based high throughput phenotyping in Citrus utilizing multispectral imaging and artificial intelligence[J]. Remote Sensing, 2019, 11(4): 410. doi: 10.3390/rs11040410.
[12] HE J Q, HARRISON R J, LI B. A novel 3D imaging system for strawberry phenotyping[J]. Plant Methods, 2017, 13: 93. doi: 10.1186/s13007-017-0243-x.
[13] MANOLIKAKI I, SERGENTANI C, TUL S, et al. Introducing three-dimensional scanning for phenotyping of olive fruits based on an extensive germplasm survey[J]. Plants, 2022, 11(11): 1501. doi: 10.3390/plants11111501.
[14] 淮永建, 杨丹琦, 蔡东娜. 基于三维点云数据的花瓣形态及生长过程模拟[J]. 农业工程学报, 2019, 35(15): 155-164. [15] KIDER J T Jr, RAJA S, BADLER N I. Fruit senescence and decay simulation[J]. Computer Graphics Forum, 2011, 30(2): 257-266. doi: 10.1111/j.1467-8659.2011.01857.x
[16] 苏宝峰, 刘易雪, 王琮, 等. 基于三维点云的叶面积估算方法[J]. 农业机械学报, 2019, 50(12): 240-254. doi: 10.6041/j.issn.1000-1298.2019.12.027 [17] ZHANG C, ZHANG K, GE L, et al. A method for organs classification and fruit counting on pomegranate trees based on multi-features fusion and support vector machine by 3D point cloud[J]. Scientia Horticulturae, 2021, 278: 109791. doi: 10.1016/j.scienta.2020.109791.
[18] JIANG Y, LI C Y, TAKEDA F, et al. 3D point cloud data to quantitatively characterize size and shape of shrub crops[J]. Horticulture Research, 2019, 6(1): 1-17. doi: 10.1038/s41438-018-0066-6
[19] WANG Y W, CHEN Y F. Non-destructive measurement of three-dimensional plants based on point cloud[J]. Plants, 2020, 9(5): 571. doi: 10.3390/plants9050571.
[20] 高智勇. 基于激光点云技术的园林虚拟植物动态三维模型构建[J]. 信息技术与信息化, 2022(2): 98-101. doi: 10.3969/j.issn.1672-9528.2022.02.025 [21] 徐伟恒, 冯仲科, 苏志芳, 等. 一种基于三维激光点云数据的单木树冠投影面积和树冠体积自动提取算法[J]. 光谱学和光谱分析, 2014, 34(2): 465-471. [22] CHEN M Y, TANG Y C, ZOU X J, et al. Three-dimensional perception of orchard banana central stock enhanced by adaptive multi-vision technology[J]. Computers and Electronics in Agriculture, 2020, 174: 105508. doi: 10.1016/j.compag.2020.105508.
[23] TSOULIAS N, PARAFOROS D S, XANTHOPOULOS G, et al. Apple shape detection based on geometric and radiometric features using a LiDAR laser scanner[J]. Remote Sensing, 2020, 12(15): 2481. doi: 10.3390/rs12152481.
[24] MÉNDEZ V, PÉREZ-ROMERO A, SOLA-GUIRADO R, et al. In-field estimation of orange number and size by 3D laser scanning[J]. Agronomy, 2019, 9(12): 885. doi: 10.3390/agronomy9120885.
[25] HUANG X, ZHENG S Y, ZHU N N. High-throughput legume seed phenotyping using a handheld 3D laser scanner[J]. Remote Sensing, 2022, 14(2): 431. doi: 10.3390/rs14020431.
[26] WANG L M, YU L. Automatic classification of banana ripeness based on deep learning[J]. Food and Machinery, 2022, 38(11): 149-154.
[27] ZHU T Y, MA X D, GUAN H O, et al. A calculation method of phenotypic traits based on three-dimensional reconstruction of tomato canopy[J]. Computers and Electronics in Agriculture, 2023, 204: 107515. doi: 10.1016/j.compag.2022.107515.
[28] 陈柱, 杨君, 基于三维点云的植物叶片重建及其面积估算[J]. 传感技术学报, 2022, 35(3): 349-354. [29] 屈文星, 刘浩, 秦楚, 等. 基于MATLAB傅里叶曲线拟合的天线跟踪精度评估方法[J]. 电子测量技术, 2020, 43(12): 91-95.
计量
- 文章访问数: 149
- HTML全文浏览量: 19
- PDF下载量: 48
