Combined Use of FCN and Harris Corner Detection for Counting Wheat Ears in Field Conditions
Accurate counting of wheat ears in field conditions is vital to predict yield and for crop breeding. To quickly and accurately obtain the number of wheat ears in a field, we propose herein a method to count wheat ears based on fully convolutional network (FCN) and Harris corner detection. The techni...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8930513/ |
| _version_ | 1819276488105525248 |
|---|---|
| author | Daoyong Wang Yuanyuan Fu Guijun Yang Xiaodong Yang Dong Liang Chengquan Zhou Ning Zhang Hongya Wu Dongyan Zhang |
| author_facet | Daoyong Wang Yuanyuan Fu Guijun Yang Xiaodong Yang Dong Liang Chengquan Zhou Ning Zhang Hongya Wu Dongyan Zhang |
| author_sort | Daoyong Wang |
| collection | DOAJ |
| description | Accurate counting of wheat ears in field conditions is vital to predict yield and for crop breeding. To quickly and accurately obtain the number of wheat ears in a field, we propose herein a method to count wheat ears based on fully convolutional network (FCN) and Harris corner detection. The technical procedure consists essentially of 1) constructing a dataset of wheat-ear images from acquired red-green-blue (RGB) images; 2) training a FCN as the wheat-ear segmentation model by using the constructed image dataset; 3) preparing testing images and inputting them into the segmentation model to get the initial segmentation results; 4) binarizing the initial segmentation by using the Otsu algorithm (to facilitate subsequent processing); and 5) applying Harris corner detection after extracting the wheat-ear skeleton to obtain the number of wheat ears in the images. The segmentation results show that the proposed FCN-based segmentation model segments wheat ears with an average accuracy of 0.984 and at low computational cost. An average of only 0.033 s is required to segment a 256× 256 -pixel wheat-ear image. Moreover, the segmentation result is improved by nearly 10% compared with the previous segmentation methods under conditions of wheat-ear occlusion, leaf occlusion, uneven illumination, and soil disturbance. Subsequently, the proposed counting method achieves good results, with an average accuracy of 0.974, a coefficient of determination (R<sup>2</sup>) of 0.983, and a root mean square error (RMSE) of 14.043. These metrics are all improved by 10% compared with the previous methods. These results show that the proposed method accurately counts wheat ears even under conditions of wheat-ear adhesion. Furthermore, the results provide an important technique for studying wheat phenotyping. |
| first_indexed | 2024-12-23T23:41:01Z |
| format | Article |
| id | doaj.art-1734a08c76854a6d85a5315570073350 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-23T23:41:01Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-1734a08c76854a6d85a53155700733502022-12-21T17:25:39ZengIEEEIEEE Access2169-35362019-01-01717893017894110.1109/ACCESS.2019.29588318930513Combined Use of FCN and Harris Corner Detection for Counting Wheat Ears in Field ConditionsDaoyong Wang0https://orcid.org/0000-0001-7427-0888Yuanyuan Fu1https://orcid.org/0000-0002-8096-4082Guijun Yang2https://orcid.org/0000-0002-8309-254XXiaodong Yang3https://orcid.org/0000-0002-5975-6510Dong Liang4https://orcid.org/0000-0002-3166-4235Chengquan Zhou5Ning Zhang6Hongya Wu7Dongyan Zhang8Key Laboratory of Quantitative Remote Sensing in Agriculture of Ministry of Agriculture, Beijing Research Center for Information Technology in Agriculture, Beijing Academy of Agriculture and Forestry Sciences, Beijing, ChinaKey Laboratory of Quantitative Remote Sensing in Agriculture of Ministry of Agriculture, Beijing Research Center for Information Technology in Agriculture, Beijing Academy of Agriculture and Forestry Sciences, Beijing, ChinaKey Laboratory of Quantitative Remote Sensing in Agriculture of Ministry of Agriculture, Beijing Research Center for Information Technology in Agriculture, Beijing Academy of Agriculture and Forestry Sciences, Beijing, ChinaKey Laboratory of Quantitative Remote Sensing in Agriculture of Ministry of Agriculture, Beijing Research Center for Information Technology in Agriculture, Beijing Academy of Agriculture and Forestry Sciences, Beijing, ChinaNational Engineering Research Center for Agro-Ecological Big Data Analysis and Application, Anhui University, Hefei, ChinaInstitute of Agricultural Equipment, Zhejiang Academy of Agricultural Sciences (ZAAS), Hangzhou, ChinaKey Laboratory of Quantitative Remote Sensing in Agriculture of Ministry of Agriculture, Beijing Research Center for Information Technology in Agriculture, Beijing Academy of Agriculture and Forestry Sciences, Beijing, ChinaInstitute of Agricultural Sciences of Lixiahe District, Yangzhou, ChinaNational Engineering Research Center for Agro-Ecological Big Data Analysis and Application, Anhui University, Hefei, ChinaAccurate counting of wheat ears in field conditions is vital to predict yield and for crop breeding. To quickly and accurately obtain the number of wheat ears in a field, we propose herein a method to count wheat ears based on fully convolutional network (FCN) and Harris corner detection. The technical procedure consists essentially of 1) constructing a dataset of wheat-ear images from acquired red-green-blue (RGB) images; 2) training a FCN as the wheat-ear segmentation model by using the constructed image dataset; 3) preparing testing images and inputting them into the segmentation model to get the initial segmentation results; 4) binarizing the initial segmentation by using the Otsu algorithm (to facilitate subsequent processing); and 5) applying Harris corner detection after extracting the wheat-ear skeleton to obtain the number of wheat ears in the images. The segmentation results show that the proposed FCN-based segmentation model segments wheat ears with an average accuracy of 0.984 and at low computational cost. An average of only 0.033 s is required to segment a 256× 256 -pixel wheat-ear image. Moreover, the segmentation result is improved by nearly 10% compared with the previous segmentation methods under conditions of wheat-ear occlusion, leaf occlusion, uneven illumination, and soil disturbance. Subsequently, the proposed counting method achieves good results, with an average accuracy of 0.974, a coefficient of determination (R<sup>2</sup>) of 0.983, and a root mean square error (RMSE) of 14.043. These metrics are all improved by 10% compared with the previous methods. These results show that the proposed method accurately counts wheat ears even under conditions of wheat-ear adhesion. Furthermore, the results provide an important technique for studying wheat phenotyping.https://ieeexplore.ieee.org/document/8930513/Wheat-ear countingfully convolutional networkwheat-ear adhesionHarris corner detectionfield conditions |
| spellingShingle | Daoyong Wang Yuanyuan Fu Guijun Yang Xiaodong Yang Dong Liang Chengquan Zhou Ning Zhang Hongya Wu Dongyan Zhang Combined Use of FCN and Harris Corner Detection for Counting Wheat Ears in Field Conditions IEEE Access Wheat-ear counting fully convolutional network wheat-ear adhesion Harris corner detection field conditions |
| title | Combined Use of FCN and Harris Corner Detection for Counting Wheat Ears in Field Conditions |
| title_full | Combined Use of FCN and Harris Corner Detection for Counting Wheat Ears in Field Conditions |
| title_fullStr | Combined Use of FCN and Harris Corner Detection for Counting Wheat Ears in Field Conditions |
| title_full_unstemmed | Combined Use of FCN and Harris Corner Detection for Counting Wheat Ears in Field Conditions |
| title_short | Combined Use of FCN and Harris Corner Detection for Counting Wheat Ears in Field Conditions |
| title_sort | combined use of fcn and harris corner detection for counting wheat ears in field conditions |
| topic | Wheat-ear counting fully convolutional network wheat-ear adhesion Harris corner detection field conditions |
| url | https://ieeexplore.ieee.org/document/8930513/ |
| work_keys_str_mv | AT daoyongwang combineduseoffcnandharriscornerdetectionforcountingwheatearsinfieldconditions AT yuanyuanfu combineduseoffcnandharriscornerdetectionforcountingwheatearsinfieldconditions AT guijunyang combineduseoffcnandharriscornerdetectionforcountingwheatearsinfieldconditions AT xiaodongyang combineduseoffcnandharriscornerdetectionforcountingwheatearsinfieldconditions AT dongliang combineduseoffcnandharriscornerdetectionforcountingwheatearsinfieldconditions AT chengquanzhou combineduseoffcnandharriscornerdetectionforcountingwheatearsinfieldconditions AT ningzhang combineduseoffcnandharriscornerdetectionforcountingwheatearsinfieldconditions AT hongyawu combineduseoffcnandharriscornerdetectionforcountingwheatearsinfieldconditions AT dongyanzhang combineduseoffcnandharriscornerdetectionforcountingwheatearsinfieldconditions |