A Novel Approach to Pod Count Estimation Using a Depth Camera in Support of Soybean Breeding Applications
Improving soybean (<i>Glycine max</i> L. (Merr.)) yield is crucial for strengthening national food security. Predicting soybean yield is essential to maximize the potential of crop varieties. Non-destructive methods are needed to estimate yield before crop maturity. Various approaches, i...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/14/6506 |
| _version_ | 1797587553576026112 |
|---|---|
| author | Jithin Mathew Nadia Delavarpour Carrie Miranda John Stenger Zhao Zhang Justice Aduteye Paulo Flores |
| author_facet | Jithin Mathew Nadia Delavarpour Carrie Miranda John Stenger Zhao Zhang Justice Aduteye Paulo Flores |
| author_sort | Jithin Mathew |
| collection | DOAJ |
| description | Improving soybean (<i>Glycine max</i> L. (Merr.)) yield is crucial for strengthening national food security. Predicting soybean yield is essential to maximize the potential of crop varieties. Non-destructive methods are needed to estimate yield before crop maturity. Various approaches, including the pod-count method, have been used to predict soybean yield, but they often face issues with the crop background color. To address this challenge, we explored the application of a depth camera to real-time filtering of RGB images, aiming to enhance the performance of the pod-counting classification model. Additionally, this study aimed to compare object detection models (YOLOV7 and YOLOv7-E6E) and select the most suitable deep learning (DL) model for counting soybean pods. After identifying the best architecture, we conducted a comparative analysis of the model’s performance by training the DL model with and without background removal from images. Results demonstrated that removing the background using a depth camera improved YOLOv7’s pod detection performance by 10.2% precision, 16.4% recall, 13.8% mAP@50, and 17.7% mAP@0.5:0.95 score compared to when the background was present. Using a depth camera and the YOLOv7 algorithm for pod detection and counting yielded a mAP@0.5 of 93.4% and mAP@0.5:0.95 of 83.9%. These results indicated a significant improvement in the DL model’s performance when the background was segmented, and a reasonably larger dataset was used to train YOLOv7. |
| first_indexed | 2024-03-11T00:40:32Z |
| format | Article |
| id | doaj.art-e7109c0147ac47f2baf8ff2656d0b1cd |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T00:40:32Z |
| publishDate | 2023-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-e7109c0147ac47f2baf8ff2656d0b1cd2023-11-18T21:18:40ZengMDPI AGSensors1424-82202023-07-012314650610.3390/s23146506A Novel Approach to Pod Count Estimation Using a Depth Camera in Support of Soybean Breeding ApplicationsJithin Mathew0Nadia Delavarpour1Carrie Miranda2John Stenger3Zhao Zhang4Justice Aduteye5Paulo Flores6Agricultural and Biosystems Engineering Department, North Dakota State University, Fargo, ND 58105, USAAgricultural and Biosystems Engineering Department, North Dakota State University, Fargo, ND 58105, USADepartment of Plant Sciences, North Dakota State University, Fargo, ND 58105, USANorth Dakota Agricultural Weather Network, School of Natural Resource Sciences, North Dakota State University, Fargo, ND 58105, USACollege of Information and Electrical Engineering, China Agricultural University, Beijing 100083, ChinaDepartment of Agronomy, Earth University, San Jose 4442-1000, Costa RicaAgricultural and Biosystems Engineering Department, North Dakota State University, Fargo, ND 58105, USAImproving soybean (<i>Glycine max</i> L. (Merr.)) yield is crucial for strengthening national food security. Predicting soybean yield is essential to maximize the potential of crop varieties. Non-destructive methods are needed to estimate yield before crop maturity. Various approaches, including the pod-count method, have been used to predict soybean yield, but they often face issues with the crop background color. To address this challenge, we explored the application of a depth camera to real-time filtering of RGB images, aiming to enhance the performance of the pod-counting classification model. Additionally, this study aimed to compare object detection models (YOLOV7 and YOLOv7-E6E) and select the most suitable deep learning (DL) model for counting soybean pods. After identifying the best architecture, we conducted a comparative analysis of the model’s performance by training the DL model with and without background removal from images. Results demonstrated that removing the background using a depth camera improved YOLOv7’s pod detection performance by 10.2% precision, 16.4% recall, 13.8% mAP@50, and 17.7% mAP@0.5:0.95 score compared to when the background was present. Using a depth camera and the YOLOv7 algorithm for pod detection and counting yielded a mAP@0.5 of 93.4% and mAP@0.5:0.95 of 83.9%. These results indicated a significant improvement in the DL model’s performance when the background was segmented, and a reasonably larger dataset was used to train YOLOv7.https://www.mdpi.com/1424-8220/23/14/6506background segmentationcomputer visiondeep learningdepth camerahigh throughput phenotypingmachine vision |
| spellingShingle | Jithin Mathew Nadia Delavarpour Carrie Miranda John Stenger Zhao Zhang Justice Aduteye Paulo Flores A Novel Approach to Pod Count Estimation Using a Depth Camera in Support of Soybean Breeding Applications Sensors background segmentation computer vision deep learning depth camera high throughput phenotyping machine vision |
| title | A Novel Approach to Pod Count Estimation Using a Depth Camera in Support of Soybean Breeding Applications |
| title_full | A Novel Approach to Pod Count Estimation Using a Depth Camera in Support of Soybean Breeding Applications |
| title_fullStr | A Novel Approach to Pod Count Estimation Using a Depth Camera in Support of Soybean Breeding Applications |
| title_full_unstemmed | A Novel Approach to Pod Count Estimation Using a Depth Camera in Support of Soybean Breeding Applications |
| title_short | A Novel Approach to Pod Count Estimation Using a Depth Camera in Support of Soybean Breeding Applications |
| title_sort | novel approach to pod count estimation using a depth camera in support of soybean breeding applications |
| topic | background segmentation computer vision deep learning depth camera high throughput phenotyping machine vision |
| url | https://www.mdpi.com/1424-8220/23/14/6506 |
| work_keys_str_mv | AT jithinmathew anovelapproachtopodcountestimationusingadepthcamerainsupportofsoybeanbreedingapplications AT nadiadelavarpour anovelapproachtopodcountestimationusingadepthcamerainsupportofsoybeanbreedingapplications AT carriemiranda anovelapproachtopodcountestimationusingadepthcamerainsupportofsoybeanbreedingapplications AT johnstenger anovelapproachtopodcountestimationusingadepthcamerainsupportofsoybeanbreedingapplications AT zhaozhang anovelapproachtopodcountestimationusingadepthcamerainsupportofsoybeanbreedingapplications AT justiceaduteye anovelapproachtopodcountestimationusingadepthcamerainsupportofsoybeanbreedingapplications AT pauloflores anovelapproachtopodcountestimationusingadepthcamerainsupportofsoybeanbreedingapplications AT jithinmathew novelapproachtopodcountestimationusingadepthcamerainsupportofsoybeanbreedingapplications AT nadiadelavarpour novelapproachtopodcountestimationusingadepthcamerainsupportofsoybeanbreedingapplications AT carriemiranda novelapproachtopodcountestimationusingadepthcamerainsupportofsoybeanbreedingapplications AT johnstenger novelapproachtopodcountestimationusingadepthcamerainsupportofsoybeanbreedingapplications AT zhaozhang novelapproachtopodcountestimationusingadepthcamerainsupportofsoybeanbreedingapplications AT justiceaduteye novelapproachtopodcountestimationusingadepthcamerainsupportofsoybeanbreedingapplications AT pauloflores novelapproachtopodcountestimationusingadepthcamerainsupportofsoybeanbreedingapplications |