[1]车金庆,王帆,王艺洁,等.基于视觉注意机制的黄绿色苹果图像分割[J].江苏农业学报,2018,(06):1347-1353.[doi:doi:10.3969/j.issn.1000-4440.2018.06.021]
　CHE Jin-qing,WANG Fan,WANG Yi-jie,et al.A segmentation method of yellow and green apple images based on visual attention mechanism[J].,2018,(06):1347-1353.[doi:doi:10.3969/j.issn.1000-4440.2018.06.021]
点击复制

基于视觉注意机制的黄绿色苹果图像分割()
分享到：

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2018年06期
页码:
1347-1353
栏目:
园艺
出版日期:
2018-12-25

文章信息/Info

Title:
A segmentation method of yellow and green apple images based on visual attention mechanism
作者:
车金庆1; 王帆2; 王艺洁2; 吕继东2; 马正华2
（1.常州工程职业技术学院智能装备与信息工程学院，江苏常州213000；2.常州大学信息科学与工程学院，江苏常州213164)
Author(s):
CHE Jin-qing1; WANG Fan2; WANG Yi-jie2; LYU Ji-dong2; MA Zheng-hua2
(1.School of Intelligent Equipment and Information Engineering, Changzhou Vocational Institute of Engineering, Changzhou 213000, China;2.School of Information Science and Engineering, Changzhou University, Changzhou 213164, China)
关键词:
苹果; 视觉注意机制; 图像分割; 图像处理
Keywords:
apple; visual attention mechanism; image segmentation; image processing
分类号:
TP391.4
DOI:
doi:10.3969/j.issn.1000-4440.2018.06.021
文献标志码:
A
摘要:
针对近色背景黄、绿色苹果图像难以分割的问题，设计了一种基于视觉注意机制的分割方法。首先基于RGB（Red，Green，Blue）采集图像将R-B、2R-G-B色差分量分别作为黄、绿色苹果图像的颜色特征分量，采用基于频率调谐的显著检测模型（Frequency-tuned salient region detection，FT）算法提取以光线正常区域为主的显著图,然后通过基于标记的分水岭算法处理原图像，再用FT算法提取以高亮区域为主的显著图,将2部分显著图分别进行自适应阈值分割,去除小面积等操作获取其二值图像，最后将2个二值图像合并，由此获得黄色和绿色苹果的果实区域。最后进行本研究方法效果图的主观判断和基于分割误差（Af）、假阳性率（FPR）、假阴性率（FNR） 3个评价指标的定量分析。结果表明该方法能更有效地分割出黄、绿色苹果果实， Af、FPR、FNR分别为81%、1056%和1018%。
Abstract:
Aiming at the problem that the yellow and green apple images in similar background were difficult to be segmented, a segmentation method based on visual attention mechanism was designed. The components of R, G and B in RGB color space were extracted, and the R-B and 2R-G-B color difference were used as color characteristic components of yellow and green apple images, respectively. The salient graphs of the normal light region oriented fruit based on frequency-tuned salient region detection (FT) were extracted. The watershed algorithm based on the mark was used to deal with the original image, and FT algorithm was used to extract the salient map of the highlighted region oriented fruit. Two parts of salient graphs were segmented using adaptive threshold method, respectively. After the removal of small area and boundary object, two partial binary images were obtained and merged to get the fruit target area of yellow and green apple. Finally, the subjective judgment of experimental results and the quantitative analysis of three evaluation indicators based on segmentation error (Af), false positive rate (FPR) and false negative rate (FNR) were carried cut. This method can more effectively segment yellow and green apple fruits, Af, FPR, FNR were 81%, 1056% and 1018%, respectively.

参考文献/References:

[1]JI W, ZHAO D, CHENG F Y, et al. Automatic recognition vision system guided for apple harvesting robot[J]. Computers and Electrical Engineering, 2012,38:1186-1195.
[2]MALIK Z, ZIAUDDIN S, AHMAD R, et al. Detection and counting of on-tree citrus fruit for crop yield estimation[J]. International Journal of Advanced Computer Science & Applications, 2016, 7(5): 519-523.
[3]VITZRABIN E, EDAN Y. Changing task objectives for improved sweet pepper detection for robotic harvesting[J]. IEEE Robotics and Automation Letters,2016, 1(1):578-583.
[4]牟丽莎，彭莉娟．基于视觉图像处理的农业机械自主导航方案[J]．江苏农业科学，2017,45(4):159-162.
[5]罗陆锋,邹湘军,熊俊涛,等. 自然环境下葡萄采摘机器人采摘点的自动定位[J]. 农业工程学报, 2015, 31(2):14-21.
[6]冯娟,刘刚,司永胜,等. 苹果采摘机器人激光视觉系统的构建[J]. 农业工程学报, 2013, 29(1):32-37.
[7]王丹丹,宋怀波,何东健. 苹果采摘机器人视觉系统研究进展[J]. 农业工程学报, 2017, 33(10):59-69.
[8]王风云，郑纪业，唐研，等. 机器视觉在我国农业中的应用研究进展分析[J]．山东农业科学，2016,48(4):139-144.
[9]PAYNE A, WALSH K, SUBEDI P, et al. Estimating mango crop yield using image analysis using fruit at ‘stone hardening’ stage and night time imaging[J]. Computers & Electronics in Agriculture, 2014, 100:160-167.
[10]王冰心,王孙安,于德弘. 基于选择性注意机制的果实簇识别与采摘顺序规划[J]. 农业机械学报, 2016, 47(11):1-7.
[11]陈科尹,邹湘军,熊俊涛,等. 基于视觉显著性改进的水果图像模糊聚类分割算法[J]. 农业工程学报, 2013, 29(6):157-165.
[12]贺付亮,郭永彩,高潮,等. 基于视觉显著性和脉冲耦合神经网络的成熟桑葚图像分割[J]. 农业工程学报, 2017, 33(6):148-155.
[13]荀一,陈晓,李伟,等.基于轮廓曲率的树上苹果自动识别[J].江苏大学学报（自然科学版）, 2007, 28(6):461-464.
[14]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.
[15]RAKUN J, STAJNKO D, ZAZULA D. Detecting fruits in natural scenes by using spatial-frequency based texture analysis and multiview geometry[J]. Computers and Electronics in Agriculture, 2011 , 76 (1) :80-88.
[16]张志强,张惠莉. 基于神经网络和图像颜色、形状特征的绿色苹果图像分割[J].农业网络信息, 2013(10):20-23.
[17]ACHANTA R, HEMAMI S, ESTRADA F, et al. Frequency-tuned salient region detection[C]//MIAMI F L. IEEE Conference on Computer Vision and Pattern Recognition(CVPR). USA: IEEE, 2009: 1597-1604.
[18]吕继东,赵德安,姬伟. 苹果采摘机器人目标果实快速跟踪识别方法[J]. 农业机械学报, 2014, 45(1):65-72.
[19]宋怀波，张卫园，张欣欣，等. 基于模糊集理论的苹果表面阴影去除方法[J]. 农业工程学报，2014, 30(3): 135-141.

相似文献/References:

[1]张丽颖,冯新新,高晶晶,等.根际浇灌ALA 溶液对苹果叶片生理特性与果实品质的影响[J].江苏农业学报,2015,(01):158.[doi:10.3969/j.issn.1000-4440.2015.01.025]
　ZHANG Li-ying,FENG Xin-xin,GAO Jing-jing,et al.Effects of rhizosphere-applied 5-aminolevulinic acid (ALA) solutions on leaf physiological characteristics and fruit quality of apples[J].,2015,(06):158.[doi:10.3969/j.issn.1000-4440.2015.01.025]
[2]牛鹏飞,申远,李帅,等.苹果中福美胂残留的RP-HPLC检测[J].江苏农业学报,2018,(03):706.[doi:doi:10.3969/j.issn.1000-4440.2018.03.033]
　NIU Peng-fei,SHEN Yuan,LI Shuai,et al.Determination of residual asomate in apple by reversed-phase high-performance liquid chromatography (RP-HPLC)[J].,2018,(06):706.[doi:doi:10.3969/j.issn.1000-4440.2018.03.033]
[3]车金庆,王帆,吕继东,等.重叠苹果果实的分离识别方法[J].江苏农业学报,2019,(02):469.[doi:doi:10.3969/j.issn.1000-4440.2019.02.030]
　CHE Jin-qing,WANG Fan,LYU Ji-dong,et al.Separation and recognition method for overlapped apple fruits[J].,2019,(06):469.[doi:doi:10.3969/j.issn.1000-4440.2019.02.030]
[4]张永超,赵录怀,王昊,等.基于环境气体信息的BP神经网络苹果贮藏品质预测[J].江苏农业学报,2020,(01):194.[doi:doi:10.3969/j.issn.1000-4440.2020.01.027]
　ZHANG Yong-chao,ZHAO Lu-huai,WANG Hao,et al.Prediction of apple storage quality using BP neural network based on environmental gas information[J].,2020,(06):194.[doi:doi:10.3969/j.issn.1000-4440.2020.01.027]
[5]徐臣善,徐爱红,萧蓓蕾,等.授粉品种对红富士苹果果实糖积累及其代谢相关酶活性的影响[J].江苏农业学报,2021,(01):121.[doi:doi:10.3969/j.issn.1000-4440.2021.01.016]
　XU Chen-shan,XU Ai-hong,XIAO Bei-lei,et al.Effects of pollination varieties on sugar accumulation and metabolism related enzyme activities in red Fuji apple fruit[J].,2021,(06):121.[doi:doi:10.3969/j.issn.1000-4440.2021.01.016]
[6]张俊娜,王冲,张东,等.小农户管理行为对苹果园郁闭度的影响[J].江苏农业学报,2021,(01):163.[doi:doi:10.3969/j.issn.1000-4440.2021.01.021]
　ZHANG Jun-na,WANG Chong,ZHANG Dong,et al.Effect of smallholder farmers’ management behavior on the canopy density of apple orchard[J].,2021,(06):163.[doi:doi:10.3969/j.issn.1000-4440.2021.01.021]
[7]王新亮,彭玲,王健,等.苹果Dof转录因子生物信息学及其表达分析[J].江苏农业学报,2021,(02):480.[doi:doi:10.3969/j.issn.1000-4440.2021.02.026]
　WANG Xin-liang,PENG Ling,WANG Jian,et al.Bioinformatics and expression analysis of the Dof transcription factors in apple[J].,2021,(06):480.[doi:doi:10.3969/j.issn.1000-4440.2021.02.026]
[8]陈光明,孔浩然,章永年,等.苹果机器人采摘存在的关键问题及对策[J].江苏农业学报,2022,38(06):1709.[doi:doi:10.3969/j.issn.1000-4440.2022.06.030]
　CHEN Guang-ming,KONG Hao-ran,ZHANG Yong-nian,et al.Key problems and countermeasures of apple machine picking[J].,2022,38(06):1709.[doi:doi:10.3969/j.issn.1000-4440.2022.06.030]
[9]班兆军,高喧翔,马肄恒,等.基于高光谱和深度学习的苹果品质无损检测方法[J].江苏农业学报,2024,(08):1446.[doi:doi:10.3969/j.issn.1000-4440.2024.08.009]
　BAN Zhaojun,GAO Xuanxiang,MA Yiheng,et al.Non-destructive detection method of apple quality based on hyperspectral and deep learning[J].,2024,(06):1446.[doi:doi:10.3969/j.issn.1000-4440.2024.08.009]

备注/Memo

备注/Memo:
收稿日期：2018-03-29 基金项目：江苏省自然科学青年基金项目(BK20140266)；江苏省高等学校自然科学研究项目(17KJB416002)；常州市科技计划资助项目（CJ20179057） 作者简介：车金庆（1979-），男，江苏南京人，硕士，讲师，主要研究方向为图像处理、软件开发，（E-mail）jqche@czie.edu.cn 通讯作者：吕继东，（E-mail） vveaglevv@163.com
更新日期/Last Update: 2018-12-28