您好,欢迎来到login_星欧(官方)代理招商直营娱乐!

首页> 《中国测试》期刊 >本期导读>基于机器视觉的苹果体积测算研究

基于机器视觉的苹果体积测算研究

344    2024-06-26

¥0.50

全文售价

作者:赵树昌, 庞茂, 张紫建

作者单位:浙江科技学院机械与能源工程学院,浙江 杭州 310023


关键词:机器视觉;积分法;位姿矫正;投影变换


摘要:

针对苹果分级中的体积测量问题,提出一种基于机器视觉和积分法求苹果体积的方法。该方法将苹果轮廓细分为薄片进行积分求取其体积。并探究苹果位姿倾斜时,该方法的误差情况;通过仿射变换求出苹果垂向倾斜角度,采用投影变换对位姿倾斜的苹果进行位姿矫正。结果表明,该方法与实际苹果体积相对误差低于2 %,最大绝对误差绝对值不超过6 cm3,检测准确性较高;苹果沿垂向倾斜角度达到15°时,该方法与实际体积绝对误差绝对值大于6 cm3,该方法失效;位姿矫正后误差小于6 cm3,证明位姿矫正满足该方法测算体积。该文提出的方法可极大提高苹果体积测量精度,可为苹果分级提供有利的技术参考。


Research on apple volumetric calculation based on machine vision
ZHAO Shuchang, PANG Mao, ZHANG Zijian
School of Mechanical and Energy Engineering, Zhejiang University of Science and Technology,Hangzhou 310023, China
Abstract: Aiming at the problem of volume measurement in apple grading, a method to find apple volume based on machine vision and integral method is proposed. This method subdivides the apple profile into thin slices and integrates to obtain its volume. The error of the method when the apple pose is tilted is also explored. The vertical tilt angle of the apple was obtained by affine transformation, and the projection transformation was used to correct the posture of the apple tilted in posture. The results show that the relative error between this method and the actual apple volume is less than 2%, the absolute maximum absolute error is not more than 6 cm3, and the detection accuracy is high. When the vertical inclination angle of apples reaches 15°, the absolute absolute error between the method and the actual volume is greater than 6 cm3, and the method fails. The error after posture correction is less than 6 cm3, which proves that posture correction meets the volume measured by this method. The method proposed in this paper can greatly improve the accuracy of apple volume measurement and provide a favorable technical reference for apple grading.
Keywords: machine vision; integral method; posture correction; projection transform
2024, 50(6):49-55 收稿日期: 2022-07-02;收到修改稿日期: 2022-12-30
基金项目: 浙江省自然科学基金资助项目(LQY19E050001)
作者简介: 赵树昌(1993-),男,河南濮阳市人,硕士研究生,专业方向为机器视觉与智能检测。
参考文献
[1] 高辉, 马国峰, 刘伟杰. 基于机器视觉的苹果缺陷快速检测方法研究[J]. 食品与机械, 2020, 36(10): 125.
GAO H, MA G F, LIU W J. Research on rapid detection of apple defects based on machine vision [J].Food and Machinery, 2020, 36 (10): 125.
[2] 汤钦林. 禽蛋食品在线智能品质检测控制系统研究与设计[J]. 食品工业, 2020, 41(5): 223.
TANG Q L. Research and design of online intelligent quality detection and control system for poultry egg food [J].The Food Industry, 2020, 41 (5): 223.
[3] 赵丹丹, 艾医. 基于计算机视觉的苹果大小检测方法研究[J]. 农机化研究, 2022, 44(7): 206.
ZHAO D D, AI Y. Research on apple size detection method based on computer vision [J].Journal of Agricultural Mechanization Research, 2022, 44 (7): 206.
[4] 王心悦, 迟馨, 杜晓云, 等. 苹果商品性状的表观指标及影响因素[J]. 中国果菜, 2019, 39(5): 28-31.
WANG X Y, CHI X, DU X Y, et al.The epigenetic indicators and influencing factors of apple product traits [J].China Fruit & Vegetable, 2019, 39 (5): 28-31.
[5] 倪云峰, 叶健, 樊娇娇. 基于图像识别的水果分拣系统[J]. 江苏农业科学, 2021, 49(10): 170-176.
NI Y F, YE J, FAN J J. A fruit sorting system based on image recognition [J]. Jiangsu Agricultural Science, 2021, 49 (10): 170-176.
[6] TAO Y, HEINEMANN P H, VARGHESE Z, et al. Machine vision for color inspection of potatoes and apples[J]. Transactions of the ASAE, 1995, 38(5): 1555-1561.
[7] BAIGVAND M, BANAKAR A, MINAEI S, et al. Machine vision system for grading of dried figs[J]. Computers and Electronics in Agriculture, 2015, 119: 158-165.
[8] VENKATESH G V, IQBAL S M, GOPAL A, et al. Estimation of volume and mass of axi-symmetric fruits using image processing technique[J]. International Journal of Food Properties, 2014, 18(3): 608-626.
[9] 吴明清, 弋晓康, 罗华平, 等. 基于多轮廓模型的红枣体积和表面积在线测量方法[J]. 农业工程学报, 2019, 35(19): 283-90.
WU M Q, YI X K, LUO H P, et al.Online measurement method for volume and surface area of red dates based on multi contour model [J].Transactions of the Chinese Society of Agricultural Engineering, 2019, 35 (19): 283-90.
[10] 刘云, 杨建滨, 王传旭. 基于卷积神经网络的苹果缺陷检测算法[J]. 电子测量技术, 2017, 40(3): 108-112.
LIU Y, YANG J B, WANG C X. Apple defect detection algorithm based on convolutional neural network [J].Electronic Measurement Technology, 2017, 40 (3): 108-112.
[11] 林静, 徐月华. 水果姿态图像自动采集训练检测仪设计[J]. 中国测试, 2021, 47(7): 119-124.
LIN J, XU Y H. An instrument designed for automatic image acquisition and training and detection of fruit posture[J]. China Measurement & Testing, 2021, 47 (7): 119-124.
[12] 谢洪起. 基于RGB-D相机的猕猴桃外形和体积检测方法研究[D]. 杨凌: 西北农林科技大学, 2018.
XIE H Q. Research on kiwifruit shape and volume detection method based on RGB-D camera [D]. Yang Ling: Northwest A&F University, 2018.
[13] 谈杰, 范乃吉, 白斌, 等. 高斯滤波对规则斑点图像的亚像素匹配精度影响研究[J]. 中国测试, 2022, 48(4): 6-11.
TAN J, FAN N J, BAI B, et al.Research on the influence of Gaussian filtering on the sub-pixel matching accuracy of regular spot image[J] China Measurement & Test, 2022, 48 (4): 6-11.
[14] 丰远远, 高贤君, 杨元维, 等. 改进对数变换联合局部增强的高分遥感影像阴影自动补偿方法[J]. 激光与光电子学进展, 2020, 57(20): 67-75.
FENG Y, GAO X J, YANG Y W, et al.Improved logarithmic transform combined with local enhancement for automatic shadow compensation in high resolution remote sensing images [J].Laser & Optoelectronics Progress, 2020, 57 (20): 67-75.
[15] 周志宇, 刘迎春, 张建新. 基于自适应Canny算子的柑橘边缘检测[J]. 农业工程学报, 2008(3): 21-24.
ZHOU Z Y, LIU Y C, ZHANG J X. Orange edge detection based on adaptive Canny operator [J].Transactions of the Chinese Society of Agricultural Engineering, 2008 (3): 21-24.