YOLO POD: a fast and accurate multi-task model for dense Soybean Pod counting
Abstract Background The number of soybean pods is one of the most important indicators of soybean yield, pod counting is crucial for yield estimation, cultivation management, and variety breeding. Counting pods manually is slow and laborious. For crop counting, using object detection network is a co...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2023-01-01
|
Series: | Plant Methods |
Subjects: | |
Online Access: | https://doi.org/10.1186/s13007-023-00985-4 |
_version_ | 1797827513135661056 |
---|---|
author | Shuai Xiang Siyu Wang Mei Xu Wenyan Wang Weiguo Liu |
author_facet | Shuai Xiang Siyu Wang Mei Xu Wenyan Wang Weiguo Liu |
author_sort | Shuai Xiang |
collection | DOAJ |
description | Abstract Background The number of soybean pods is one of the most important indicators of soybean yield, pod counting is crucial for yield estimation, cultivation management, and variety breeding. Counting pods manually is slow and laborious. For crop counting, using object detection network is a common practice, but the scattered and overlapped pods make the detection and counting of the pods difficult. Results We propose an approach that we named YOLO POD, based on the YOLO X framework. On top of YOLO X, we added a block for predicting the number of pods, modified the loss function, thus constructing a multi-task model, and introduced the Convolutional Block Attention Module (CBAM). We achieve accurate identification and counting of pods without reducing the speed of inference. The results showed that the R2 between the number predicted by YOLO POD and the ground truth reached 0.967, which is improved by 0.049 compared to YOLO X, while the inference time only increased by 0.08 s. Moreover, MAE, MAPE, RMSE are only 4.18, 10.0%, 6.48 respectively, the deviation is very small. Conclusions We have achieved the first accurate counting of soybean pods and proposed a new solution for the detection and counting of dense objects. |
first_indexed | 2024-04-09T12:49:31Z |
format | Article |
id | doaj.art-7b4fa9ae01794d238e8c5aa955e96551 |
institution | Directory Open Access Journal |
issn | 1746-4811 |
language | English |
last_indexed | 2024-04-09T12:49:31Z |
publishDate | 2023-01-01 |
publisher | BMC |
record_format | Article |
series | Plant Methods |
spelling | doaj.art-7b4fa9ae01794d238e8c5aa955e965512023-05-14T11:18:09ZengBMCPlant Methods1746-48112023-01-0119111110.1186/s13007-023-00985-4YOLO POD: a fast and accurate multi-task model for dense Soybean Pod countingShuai Xiang0Siyu Wang1Mei Xu2Wenyan Wang3Weiguo Liu4College of Agronomy, Sichuan Agricultural UniversityCollege of Agronomy, Sichuan Agricultural UniversityCollege of Agronomy, Sichuan Agricultural UniversityCollege of Agronomy, Sichuan Agricultural UniversityCollege of Agronomy, Sichuan Agricultural UniversityAbstract Background The number of soybean pods is one of the most important indicators of soybean yield, pod counting is crucial for yield estimation, cultivation management, and variety breeding. Counting pods manually is slow and laborious. For crop counting, using object detection network is a common practice, but the scattered and overlapped pods make the detection and counting of the pods difficult. Results We propose an approach that we named YOLO POD, based on the YOLO X framework. On top of YOLO X, we added a block for predicting the number of pods, modified the loss function, thus constructing a multi-task model, and introduced the Convolutional Block Attention Module (CBAM). We achieve accurate identification and counting of pods without reducing the speed of inference. The results showed that the R2 between the number predicted by YOLO POD and the ground truth reached 0.967, which is improved by 0.049 compared to YOLO X, while the inference time only increased by 0.08 s. Moreover, MAE, MAPE, RMSE are only 4.18, 10.0%, 6.48 respectively, the deviation is very small. Conclusions We have achieved the first accurate counting of soybean pods and proposed a new solution for the detection and counting of dense objects.https://doi.org/10.1186/s13007-023-00985-4SoybeanDeep learningObjection detectionMulti-Task learningYield estimation |
spellingShingle | Shuai Xiang Siyu Wang Mei Xu Wenyan Wang Weiguo Liu YOLO POD: a fast and accurate multi-task model for dense Soybean Pod counting Plant Methods Soybean Deep learning Objection detection Multi-Task learning Yield estimation |
title | YOLO POD: a fast and accurate multi-task model for dense Soybean Pod counting |
title_full | YOLO POD: a fast and accurate multi-task model for dense Soybean Pod counting |
title_fullStr | YOLO POD: a fast and accurate multi-task model for dense Soybean Pod counting |
title_full_unstemmed | YOLO POD: a fast and accurate multi-task model for dense Soybean Pod counting |
title_short | YOLO POD: a fast and accurate multi-task model for dense Soybean Pod counting |
title_sort | yolo pod a fast and accurate multi task model for dense soybean pod counting |
topic | Soybean Deep learning Objection detection Multi-Task learning Yield estimation |
url | https://doi.org/10.1186/s13007-023-00985-4 |
work_keys_str_mv | AT shuaixiang yolopodafastandaccuratemultitaskmodelfordensesoybeanpodcounting AT siyuwang yolopodafastandaccuratemultitaskmodelfordensesoybeanpodcounting AT meixu yolopodafastandaccuratemultitaskmodelfordensesoybeanpodcounting AT wenyanwang yolopodafastandaccuratemultitaskmodelfordensesoybeanpodcounting AT weiguoliu yolopodafastandaccuratemultitaskmodelfordensesoybeanpodcounting |