Convolutional Neural Networks for Image-Based Corn Kernel Detection and Counting
Precise in-season corn grain yield estimates enable farmers to make real-time accurate harvest and grain marketing decisions minimizing possible losses of profitability. A well developed corn ear can have up to 800 kernels, but manually counting the kernels on an ear of corn is labor-intensive, time...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-05-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/9/2721 |
| _version_ | 1827717127529824256 |
|---|---|
| author | Saeed Khaki Hieu Pham Ye Han Andy Kuhl Wade Kent Lizhi Wang |
| author_facet | Saeed Khaki Hieu Pham Ye Han Andy Kuhl Wade Kent Lizhi Wang |
| author_sort | Saeed Khaki |
| collection | DOAJ |
| description | Precise in-season corn grain yield estimates enable farmers to make real-time accurate harvest and grain marketing decisions minimizing possible losses of profitability. A well developed corn ear can have up to 800 kernels, but manually counting the kernels on an ear of corn is labor-intensive, time consuming and prone to human error. From an algorithmic perspective, the detection of the kernels from a single corn ear image is challenging due to the large number of kernels at different angles and very small distance among the kernels. In this paper, we propose a kernel detection and counting method based on a sliding window approach. The proposed method detects and counts all corn kernels in a single corn ear image taken in uncontrolled lighting conditions. The sliding window approach uses a convolutional neural network (CNN) for kernel detection. Then, a non-maximum suppression (NMS) is applied to remove overlapping detections. Finally, windows that are classified as kernel are passed to another CNN regression model for finding the <inline-formula> <math display="inline"> <semantics> <mrow> <mo>(</mo> <mi>x</mi> <mo>,</mo> <mi>y</mi> <mo>)</mo> </mrow> </semantics> </math> </inline-formula> coordinates of the center of kernel image patches. Our experiments indicate that the proposed method can successfully detect the corn kernels with a low detection error and is also able to detect kernels on a batch of corn ears positioned at different angles. |
| first_indexed | 2024-03-10T19:55:19Z |
| format | Article |
| id | doaj.art-406297b901244f1fba89aa7dd3b0285b |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T19:55:19Z |
| publishDate | 2020-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-406297b901244f1fba89aa7dd3b0285b2023-11-19T23:58:13ZengMDPI AGSensors1424-82202020-05-01209272110.3390/s20092721Convolutional Neural Networks for Image-Based Corn Kernel Detection and CountingSaeed Khaki0Hieu Pham1Ye Han2Andy Kuhl3Wade Kent4Lizhi Wang5Industrial and Manufacturing Systems Engineering, Iowa State University, Ames, IA 50011-3611, USASyngenta, Slater, IA 50244, USASyngenta, Slater, IA 50244, USASyngenta, Slater, IA 50244, USASyngenta, Slater, IA 50244, USAIndustrial and Manufacturing Systems Engineering, Iowa State University, Ames, IA 50011-3611, USAPrecise in-season corn grain yield estimates enable farmers to make real-time accurate harvest and grain marketing decisions minimizing possible losses of profitability. A well developed corn ear can have up to 800 kernels, but manually counting the kernels on an ear of corn is labor-intensive, time consuming and prone to human error. From an algorithmic perspective, the detection of the kernels from a single corn ear image is challenging due to the large number of kernels at different angles and very small distance among the kernels. In this paper, we propose a kernel detection and counting method based on a sliding window approach. The proposed method detects and counts all corn kernels in a single corn ear image taken in uncontrolled lighting conditions. The sliding window approach uses a convolutional neural network (CNN) for kernel detection. Then, a non-maximum suppression (NMS) is applied to remove overlapping detections. Finally, windows that are classified as kernel are passed to another CNN regression model for finding the <inline-formula> <math display="inline"> <semantics> <mrow> <mo>(</mo> <mi>x</mi> <mo>,</mo> <mi>y</mi> <mo>)</mo> </mrow> </semantics> </math> </inline-formula> coordinates of the center of kernel image patches. Our experiments indicate that the proposed method can successfully detect the corn kernels with a low detection error and is also able to detect kernels on a batch of corn ears positioned at different angles.https://www.mdpi.com/1424-8220/20/9/2721corn kernel countingobject detectionconvolutional neural networksdigital agriculture |
| spellingShingle | Saeed Khaki Hieu Pham Ye Han Andy Kuhl Wade Kent Lizhi Wang Convolutional Neural Networks for Image-Based Corn Kernel Detection and Counting Sensors corn kernel counting object detection convolutional neural networks digital agriculture |
| title | Convolutional Neural Networks for Image-Based Corn Kernel Detection and Counting |
| title_full | Convolutional Neural Networks for Image-Based Corn Kernel Detection and Counting |
| title_fullStr | Convolutional Neural Networks for Image-Based Corn Kernel Detection and Counting |
| title_full_unstemmed | Convolutional Neural Networks for Image-Based Corn Kernel Detection and Counting |
| title_short | Convolutional Neural Networks for Image-Based Corn Kernel Detection and Counting |
| title_sort | convolutional neural networks for image based corn kernel detection and counting |
| topic | corn kernel counting object detection convolutional neural networks digital agriculture |
| url | https://www.mdpi.com/1424-8220/20/9/2721 |
| work_keys_str_mv | AT saeedkhaki convolutionalneuralnetworksforimagebasedcornkerneldetectionandcounting AT hieupham convolutionalneuralnetworksforimagebasedcornkerneldetectionandcounting AT yehan convolutionalneuralnetworksforimagebasedcornkerneldetectionandcounting AT andykuhl convolutionalneuralnetworksforimagebasedcornkerneldetectionandcounting AT wadekent convolutionalneuralnetworksforimagebasedcornkerneldetectionandcounting AT lizhiwang convolutionalneuralnetworksforimagebasedcornkerneldetectionandcounting |