Agricultural and Biosystems Engineering Department, North Dakota State University, Fargo, ND 58105, USA.
Department of Plant Sciences, North Dakota State University, Fargo, ND 58105, USA.
Sensors (Basel). 2023 Jul 18;23(14):6506. doi: 10.3390/s23146506.
Improving soybean ( 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.
提高大豆（L. (Merr.））产量对于加强国家粮食安全至关重要。预测大豆产量对于最大限度地发挥作物品种的潜力至关重要。需要在作物成熟前使用非破坏性方法来估计产量。已经使用了各种方法，包括荚计数法，来预测大豆产量，但它们通常面临作物背景颜色的问题。为了解决这个挑战，我们探索了使用深度相机实时过滤 RGB 图像的应用，旨在增强荚计数分类模型的性能。此外，本研究旨在比较目标检测模型（YOLOV7 和 YOLOv7-E6E）并选择最适合计数大豆荚的深度学习（DL）模型。在确定最佳架构后，我们通过对具有和不具有图像背景去除的 DL 模型进行训练，对模型的性能进行了比较分析。结果表明，与存在背景时相比，使用深度相机去除背景可将 YOLOv7 的荚检测性能提高 10.2%的精度、16.4%的召回率、13.8%的 mAP@50 和 17.7%的 mAP@0.5:0.95 分数。使用深度相机和 YOLOv7 算法进行荚检测和计数可实现 mAP@0.5 为 93.4%和 mAP@0.5:0.95 为 83.9%。这些结果表明，当背景被分割并且使用更大的数据集来训练 YOLOv7 时，DL 模型的性能有了显著提高。
