基于双侧图像识别的单株苹果树产量估测模型
利用普通数码相机获取成熟期苹果树图像进行产量估测,具有成本低、操作简单等特点,其关键是估测模型的建立。该文分别按东南和西北2个方向获取富士苹果成熟期的40株果树的80幅图像,通过果实特征提取,获取东南方向识别出的图斑数量（参数1）、西北方向识别出的图斑数量（参数2）、东南方向识别出的图斑像素面积（参数3）、西北识别出的图斑像素面积（参数4）,分别以识别出的4个参数及双方向图斑数量之和（参数5）、双方向图斑像素面积之和（参数6）共6个参数为自变量,以获取的单株产量信息为因变量,以奇数组20株果树为建模数据集建立线性回归模型。结果表明以参数5构建的产量估测模型的决定系数R2最高为0.81,相对均方...
Saved in:
| Published in | 农业工程学报 Vol. 29; no. 11; pp. 132 - 138 |
|---|---|
| Main Author | |
| Format | Journal Article |
| Language | Chinese |
| Published |
北京市农林科学院国家农业信息化工程技术研究中心,北京 100097%北京林业大学信息学院,北京100083%山东农业大学生命科学学院,泰安 271018
2013
|
| Subjects | |
| Online Access | Get full text |
| ISSN | 1002-6819 |
| DOI | 10.3969/j.issn.1002-6819.2013.11.017 |
Cover
| Abstract | 利用普通数码相机获取成熟期苹果树图像进行产量估测,具有成本低、操作简单等特点,其关键是估测模型的建立。该文分别按东南和西北2个方向获取富士苹果成熟期的40株果树的80幅图像,通过果实特征提取,获取东南方向识别出的图斑数量（参数1）、西北方向识别出的图斑数量（参数2）、东南方向识别出的图斑像素面积（参数3）、西北识别出的图斑像素面积（参数4）,分别以识别出的4个参数及双方向图斑数量之和（参数5）、双方向图斑像素面积之和（参数6）共6个参数为自变量,以获取的单株产量信息为因变量,以奇数组20株果树为建模数据集建立线性回归模型。结果表明以参数5构建的产量估测模型的决定系数R2最高为0.81,相对均方根差（NRMSE）值最低为0.11,说明以该参数构建的模型其估测效果最好;进一步利用以参数5构建的估测模型对偶数组20株果树进行验证,其NRMSE值为0.16,估测结果较好,但也存在估测产量较大波动的情况。深入讨论引起估测偏差的情况,后期研究应重点提高逆光、弱光照条件下的成熟期苹果的识别率,及解决由于单果因遮挡被分离而被识别为多果的情况和多果因重叠被识别为单果的情况,以提高识别效果,进而提高产量模型估测效果。 |
|---|---|
| AbstractList | 利用普通数码相机获取成熟期苹果树图像进行产量估测,具有成本低、操作简单等特点,其关键是估测模型的建立。该文分别按东南和西北2个方向获取富士苹果成熟期的40株果树的80幅图像,通过果实特征提取,获取东南方向识别出的图斑数量（参数1）、西北方向识别出的图斑数量（参数2）、东南方向识别出的图斑像素面积（参数3）、西北识别出的图斑像素面积（参数4）,分别以识别出的4个参数及双方向图斑数量之和（参数5）、双方向图斑像素面积之和（参数6）共6个参数为自变量,以获取的单株产量信息为因变量,以奇数组20株果树为建模数据集建立线性回归模型。结果表明以参数5构建的产量估测模型的决定系数R2最高为0.81,相对均方根差（NRMSE）值最低为0.11,说明以该参数构建的模型其估测效果最好;进一步利用以参数5构建的估测模型对偶数组20株果树进行验证,其NRMSE值为0.16,估测结果较好,但也存在估测产量较大波动的情况。深入讨论引起估测偏差的情况,后期研究应重点提高逆光、弱光照条件下的成熟期苹果的识别率,及解决由于单果因遮挡被分离而被识别为多果的情况和多果因重叠被识别为单果的情况,以提高识别效果,进而提高产量模型估测效果。 TP242.62; 利用普通数码相机获取成熟期苹果树图像进行产量估测,具有成本低、操作简单等特点,其关键是估测模型的建立.该文分别按东南和西北2个方向获取富士苹果成熟期的40株果树的80幅图像,通过果实特征提取,获取东南方向识别出的图斑数量(参数1)、西北方向识别出的图斑数量(参数2)、东南方向识别出的图斑像素面积(参数3)、西北识别出的图斑像素面积(参数4),分别以识别出的4个参数及双方向图斑数量之和(参数5)、双方向图斑像素面积之和(参数6)共6个参数为自变量,以获取的单株产量信息为因变量,以奇数组20株果树为建模数据集建立线性回归模型.结果表明以参数5构建的产量估测模型的决定系数R2最高为0.81,相对均方根差(NRMSE)值最低为0.11,说明以该参数构建的模型其估测效果最好;进一步利用以参数5构建的估测模型对偶数组20株果树进行验证,其NRMSE值为0.16,估测结果较好,但也存在估测产量较大波动的情况.深入讨论引起估测偏差的情况,后期研究应重点提高逆光、弱光照条件下的成熟期苹果的识别率,及解决由于单果因遮挡被分离而被识别为多果的情况和多果因重叠被识别为单果的情况,以提高识别效果,进而提高产量模型估测效果. |
| Abstract_FL | Apples yield estimation with a common digital camera to get mature fruits, has the advantages of low lost, simple operation and other characteristics. Key to the estimation is the establishment of an estimation model. In this paper, 80 images from 40 Fuji trees were acquired from the southeast and northwest directions using a Cannon G7 camera. By fruit feature extraction, 4 parameters were identified, which were identification patch number from southeast direction (parameter 1), identification patch number from northwest direction (parameter 2), patch pixels area from southeast direction (parameter 3) and patch pixels area from northwest direction (parameter 4). A total of 6 parameters, including the above-mention 4 parameters along with the sum of patch number from two directions (parameter 5) and the sum of patch pixels area from two directions (parameter 6) acted as independent variables and single tree yield information acted as the dependent variable. With 20 fruit trees used as the modeling data set, the linear regression model was constructed based on the independent variables and dependent variable. The results showed that the yield estimation model with parameter 5 had the best effects with the highest R2 of 0.81 and the lowest NRMSE (Normal Root Mean Squared Error) value of 0.43. Further, additional 20 fruit trees were verified using the yield estimation model with parameter 5. The estimation result was good with a NRMSE value of 0.59, but there were also fluctuations between estimation yield and actual yield. In the verified 20 fruit trees, there were 10 trees whose estimated yield was higher than the actual yield, and the deviation value of No. 2 tree was maximum of 14.02. There were also 10 trees whose estimated yield was lower than the actual yield, and the deviation value of No. 30 was maximum of 17.79. The reason of estimation errors was discussed. Later studies should focus on improving mature apple recognition rates in conditions of backlighting and weak light, and solve the error recognition in conditions of single apple occlusion and multi apples overlapping. The research will help improve recognition effects and then improve model estimation effects. |
| Author | 钱建平 李明 杨信廷 吴保国 张勇 王衍安 |
| AuthorAffiliation | 北京市农林科学院国家农业信息化工程技术研究中心,北京100097 北京林业大学信息学院,北京100083 山东农业大学生命科学学院,泰安271018 |
| AuthorAffiliation_xml | – name: 北京市农林科学院国家农业信息化工程技术研究中心,北京 100097%北京林业大学信息学院,北京100083%山东农业大学生命科学学院,泰安 271018 |
| Author_xml | – sequence: 1 fullname: 钱建平 李明 杨信廷 吴保国 张勇 王衍安 |
| BookMark | eNo9jz9Lw0Achm-oYK39EILglHi_XHK5Axcp_oOCg-7lLsnVFL1qg2hnxQpVi4OLSq1TRQddHCzST5OL9VtYqTi98PLwvLwzKKfrOkJoHrBNOOWLNTtOEm0Dxo5FGXDbwUBsABuDn0P5_34aFZMkltgD4mPsQh4tmYdBOrgynYt02Dd3Q3PSGb2emfOXr9tTc3mT9Z5H7Y-se5_1rtNB_7vVST_fsvd29vRouu1ZNKXEbhIV_7KAtlZXtkvrVnlzbaO0XLYCj3GLSSKxL5kfecpxIioDxljoKhGGAntKUSUDAOmGRAgWCFcS5mIehb5PeMglKaCFifVIaCV0tVKrHzb0eK-im9XgWP5-BcDAx-TchAx26rp6EI_Z_Ua8JxrNiksdSgnH5Ac7NG8T |
| ClassificationCodes | TP242.62 |
| ContentType | Journal Article |
| Copyright | Copyright © Wanfang Data Co. Ltd. All Rights Reserved. |
| Copyright_xml | – notice: Copyright © Wanfang Data Co. Ltd. All Rights Reserved. |
| DBID | 2RA 92L CQIGP W95 ~WA 2B. 4A8 92I 93N PSX TCJ |
| DOI | 10.3969/j.issn.1002-6819.2013.11.017 |
| DatabaseName | 维普期刊资源整合服务平台 中文科技期刊数据库-CALIS站点 中文科技期刊数据库-7.0平台 中文科技期刊数据库-农业科学 中文科技期刊数据库- 镜像站点 Wanfang Data Journals - Hong Kong WANFANG Data Centre Wanfang Data Journals 万方数据期刊 - 香港版 China Online Journals (COJ) China Online Journals (COJ) |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Agriculture |
| DocumentTitleAlternate | Yield estimation model of single tree of Fuji apples based on bilateral image identification |
| DocumentTitle_FL | Yield estimation model of single tree of Fuji apples based on bilateral image identification |
| EndPage | 138 |
| ExternalDocumentID | nygcxb201311019 46266390 |
| GroupedDBID | -04 2B. 2B~ 2RA 5XA 5XE 92G 92I 92L ABDBF ABJNI ACGFO ACGFS AEGXH AIAGR ALMA_UNASSIGNED_HOLDINGS CCEZO CHDYS CQIGP CW9 EOJEC FIJ IPNFZ OBODZ RIG TCJ TGD TUS U1G U5N W95 ~WA 4A8 93N ACUHS PSX |
| ID | FETCH-LOGICAL-c589-8b3b07b87e5f22e6bc888d4fadda05ff6fbc11b4d3aa8ca4b38409ed7739d9b3 |
| ISSN | 1002-6819 |
| IngestDate | Thu May 29 04:04:17 EDT 2025 Wed Feb 14 10:41:46 EST 2024 |
| IsPeerReviewed | false |
| IsScholarly | true |
| Issue | 11 |
| Keywords | yield estimation image identification models 模型 linear regression 富士苹果 Fuji apples 图像识别 线性回归 产量估测 |
| Language | Chinese |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c589-8b3b07b87e5f22e6bc888d4fadda05ff6fbc11b4d3aa8ca4b38409ed7739d9b3 |
| Notes | 11-2047/S Apples yield estimation with a common digital camera to get mature fruits, has the advantages of low lost, simple operation and other characteristics. Key to the estimation is the establishment of an estimation model. In this paper, 80 images from 40 Fuji trees were acquired from the southeast and northwest directions using a Cannon G7 camera. By fruit feature extraction, 4 parameters were identified, which were identification patch number from southeast direction （parameter 1）, identification patch number from northwest direction （parameter 2）, patch pixels area from southeast direction （parameter 3） and patch pixels area from northwest direction （parameter 4）. A total of 6 parameters, including the above-mention 4 parameters along with the sum of patch number from two directions （parameter 5） and the sum of patch pixels area from two directions （parameter 6） acted as independent variables and single tree yield information acted as the dependent variable. With 20 fruit trees used as the modeling dat |
| PageCount | 7 |
| ParticipantIDs | wanfang_journals_nygcxb201311019 chongqing_primary_46266390 |
| PublicationCentury | 2000 |
| PublicationDate | 2013 |
| PublicationDateYYYYMMDD | 2013-01-01 |
| PublicationDate_xml | – year: 2013 text: 2013 |
| PublicationDecade | 2010 |
| PublicationTitle | 农业工程学报 |
| PublicationTitleAlternate | Transactions of the Chinese Society of Agricultural Engineering |
| PublicationTitle_FL | Transactions of the Chinese Society of Agricultural Engineering |
| PublicationYear | 2013 |
| Publisher | 北京市农林科学院国家农业信息化工程技术研究中心,北京 100097%北京林业大学信息学院,北京100083%山东农业大学生命科学学院,泰安 271018 |
| Publisher_xml | – name: 北京市农林科学院国家农业信息化工程技术研究中心,北京 100097%北京林业大学信息学院,北京100083%山东农业大学生命科学学院,泰安 271018 |
| SSID | ssib051370041 ssib017478172 ssj0041925 ssib001101065 ssib023167668 |
| Score | 2.013428 |
| Snippet | 利用普通数码相机获取成熟期苹果树图像进行产量估测,具有成本低、操作简单等特点,其关键是估测模型的建立。该文分别按东南和西北2个方向获取富士苹果成熟期的40株果树的80幅... TP242.62; 利用普通数码相机获取成熟期苹果树图像进行产量估测,具有成本低、操作简单等特点,其关键是估测模型的建立.该文分别按东南和西北2个方向获取富士苹果成熟期的40株... |
| SourceID | wanfang chongqing |
| SourceType | Aggregation Database Publisher |
| StartPage | 132 |
| SubjectTerms | 产量估测 图像识别 富士苹果 模型 线性回归 |
| Title | 基于双侧图像识别的单株苹果树产量估测模型 |
| URI | http://lib.cqvip.com/qk/90712X/201311/46266390.html https://d.wanfangdata.com.cn/periodical/nygcxb201311019 |
| Volume | 29 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVALS databaseName: IngentaConnect Open Access Journals issn: 1002-6819 databaseCode: FIJ dateStart: 20090101 customDbUrl: isFulltext: true dateEnd: 20151231 titleUrlDefault: http://www.ingentaconnect.com/content/title?j_type=online&j_startat=Aa&j_endat=Af&j_pagesize=200&j_page=1 omitProxy: true ssIdentifier: ssj0041925 providerName: Ingenta |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV07bxQxELaSICFAQjxFwkNXxFW0YR_2ri3ReO_2FFLQEKR0p_U-LtUFQiJBWhAgBThR0AAKoQqCAhoKIpRfc3uEf8GMz7mcUBQBzcr3eTwz9uzZY689JmRaBrnHNcucQPuZw8qIO0KE2mFZxNI8Y3lamt0Wt8K5O2x-kS-OjZ8a2bW0tqpns_VDz5X8j1UBA7viKdl_sOyQKQCQBvvCEywMz7-yMU04lU0aK5owfIoEEdGkom6QhKrI0MSYxqwAcxNBFdCEBoF0TJOISijODNKgktMkpMqlSiGxgOISEZlQWbdZ0rNCUYSkIjKcAanT2EWamGNBJAYRnlEjAWTUGzbiQsMTCgrUAZA4ooqjSsqIBkQ1qAqRlQBxfP8dQbHSp7HhHcemGThqGgczRtuGaRBIAJ9kHwKmKKxpdcJy0YzRzqUxs3lAZ5utYfKgUlDlxNRIIHmErFE5UzdhyBUgcnQVZXD81Xb5OCaEwnbcdkywqzD23fdGenjPLscW9pc4bBwKZCjNOIQSZocScCdhMItBYwfnVf-I9M1gcgkOoztOjvm4uoRBS2_OHzi3Hs7fh72vhzcfeAennn2MaRAeTB65F-DVBcMNT_i5n5tv_1ab42Taqnr9KEUx6MjScqd9D1wpc7KtU6ad9ogTtnCGnLazp5oa_BXOkrH1pXPkpGqv2AgyxXlyo3q_09t5WXWf93a3q7e71aPu3pcn1bPPP988rl687m992tv43t9819961dvZ_vW02_vxtf9to__xQ7W5cYHcbiYL9TnHXhHiZFxIR-hAu5EWUcFL3y9CnQkhclbCoJ26vCzDUmeep1kepKnIUqYDXM8o8igKZC51cJFMdJY7xSVSy6CbKjTGJtIp-OiFFG5QgnfrlnkpCl9MkqlhK7TuDgLBtPYNNklqtllatne43-o8bGcPtG_CWcE0auqo8pfJCd_csoIre1fIxOrKWnEVfN1Vfc28Ar8BHDyBnQ |
| linkProvider | Ingenta |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=%E5%9F%BA%E4%BA%8E%E5%8F%8C%E4%BE%A7%E5%9B%BE%E5%83%8F%E8%AF%86%E5%88%AB%E7%9A%84%E5%8D%95%E6%A0%AA%E8%8B%B9%E6%9E%9C%E6%A0%91%E4%BA%A7%E9%87%8F%E4%BC%B0%E6%B5%8B%E6%A8%A1%E5%9E%8B&rft.jtitle=%E5%86%9C%E4%B8%9A%E5%B7%A5%E7%A8%8B%E5%AD%A6%E6%8A%A5&rft.au=%E9%92%B1%E5%BB%BA%E5%B9%B3+%E6%9D%8E%E6%98%8E+%E6%9D%A8%E4%BF%A1%E5%BB%B7+%E5%90%B4%E4%BF%9D%E5%9B%BD+%E5%BC%A0%E5%8B%87+%E7%8E%8B%E8%A1%8D%E5%AE%89&rft.date=2013&rft.issn=1002-6819&rft.volume=29&rft.issue=11&rft.spage=132&rft.epage=138&rft_id=info:doi/10.3969%2Fj.issn.1002-6819.2013.11.017&rft.externalDocID=46266390 |
| thumbnail_s | http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fimage.cqvip.com%2Fvip1000%2Fqk%2F90712X%2F90712X.jpg http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fwww.wanfangdata.com.cn%2Fimages%2FPeriodicalImages%2Fnygcxb%2Fnygcxb.jpg |