An Improved YOLOv5s-Based <i>Agaricus bisporus</i> Detection Algorithm
This study aims to improve the <i>Agaricus bisporus</i> detection efficiency and performance of harvesting robots in the complex environment of the mushroom growing house. Based on deep learning networks, an improved YOLOv5s algorithm was proposed for accurate <i>A. bisporus</i&...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-07-01
|
| Series: | Agronomy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4395/13/7/1871 |
| _version_ | 1797590683131838464 |
|---|---|
| author | Chao Chen Feng Wang Yuzhe Cai Shanlin Yi Baofeng Zhang |
| author_facet | Chao Chen Feng Wang Yuzhe Cai Shanlin Yi Baofeng Zhang |
| author_sort | Chao Chen |
| collection | DOAJ |
| description | This study aims to improve the <i>Agaricus bisporus</i> detection efficiency and performance of harvesting robots in the complex environment of the mushroom growing house. Based on deep learning networks, an improved YOLOv5s algorithm was proposed for accurate <i>A. bisporus</i> detection. First, <i>A. bisporus</i> images collected in situ from the mushroom growing house were preprocessed and augmented to construct a dataset containing 810 images, which were divided into the training and test sets in the ratio of 8:2. Then, by introducing the Convolutional Block Attention Module (CBAM) into the backbone network of YOLOv5s and adopting the Mosaic image augmentation technique in training, the detection accuracy and robustness of the algorithm were improved. The experimental results showed that the improved algorithm had a recognition accuracy of 98%, a single-image processing time of 18 ms, an <i>A. bisporus</i> center point locating error of 0.40%, and a diameter measuring error of 1.08%. Compared with YOLOv5s and YOLOv7, the YOLOv5s-CBAM has better performance in recognition accuracy, center positioning, and diameter measurement. Therefore, the proposed algorithm is capable of accurate <i>A. bisporus</i> detection in the complex environment of the mushroom growing house. |
| first_indexed | 2024-03-11T01:24:01Z |
| format | Article |
| id | doaj.art-ecb568419d424bca8dac4d46f4647601 |
| institution | Directory Open Access Journal |
| issn | 2073-4395 |
| language | English |
| last_indexed | 2024-03-11T01:24:01Z |
| publishDate | 2023-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agronomy |
| spelling | doaj.art-ecb568419d424bca8dac4d46f46476012023-11-18T17:57:30ZengMDPI AGAgronomy2073-43952023-07-01137187110.3390/agronomy13071871An Improved YOLOv5s-Based <i>Agaricus bisporus</i> Detection AlgorithmChao Chen0Feng Wang1Yuzhe Cai2Shanlin Yi3Baofeng Zhang4School of Mechanical Engineering, Yangzhou University, Yangzhou 225127, ChinaSchool of Mechanical Engineering, Yangzhou University, Yangzhou 225127, ChinaSchool of Mechanical Engineering, Yangzhou University, Yangzhou 225127, ChinaSchool of Mechanical Engineering, Yangzhou University, Yangzhou 225127, ChinaSchool of Mechanical Engineering, Yangzhou University, Yangzhou 225127, ChinaThis study aims to improve the <i>Agaricus bisporus</i> detection efficiency and performance of harvesting robots in the complex environment of the mushroom growing house. Based on deep learning networks, an improved YOLOv5s algorithm was proposed for accurate <i>A. bisporus</i> detection. First, <i>A. bisporus</i> images collected in situ from the mushroom growing house were preprocessed and augmented to construct a dataset containing 810 images, which were divided into the training and test sets in the ratio of 8:2. Then, by introducing the Convolutional Block Attention Module (CBAM) into the backbone network of YOLOv5s and adopting the Mosaic image augmentation technique in training, the detection accuracy and robustness of the algorithm were improved. The experimental results showed that the improved algorithm had a recognition accuracy of 98%, a single-image processing time of 18 ms, an <i>A. bisporus</i> center point locating error of 0.40%, and a diameter measuring error of 1.08%. Compared with YOLOv5s and YOLOv7, the YOLOv5s-CBAM has better performance in recognition accuracy, center positioning, and diameter measurement. Therefore, the proposed algorithm is capable of accurate <i>A. bisporus</i> detection in the complex environment of the mushroom growing house.https://www.mdpi.com/2073-4395/13/7/1871mushroom detectioncomputer visioncenter point positioningdiameter measurementattention mechanism |
| spellingShingle | Chao Chen Feng Wang Yuzhe Cai Shanlin Yi Baofeng Zhang An Improved YOLOv5s-Based <i>Agaricus bisporus</i> Detection Algorithm Agronomy mushroom detection computer vision center point positioning diameter measurement attention mechanism |
| title | An Improved YOLOv5s-Based <i>Agaricus bisporus</i> Detection Algorithm |
| title_full | An Improved YOLOv5s-Based <i>Agaricus bisporus</i> Detection Algorithm |
| title_fullStr | An Improved YOLOv5s-Based <i>Agaricus bisporus</i> Detection Algorithm |
| title_full_unstemmed | An Improved YOLOv5s-Based <i>Agaricus bisporus</i> Detection Algorithm |
| title_short | An Improved YOLOv5s-Based <i>Agaricus bisporus</i> Detection Algorithm |
| title_sort | improved yolov5s based i agaricus bisporus i detection algorithm |
| topic | mushroom detection computer vision center point positioning diameter measurement attention mechanism |
| url | https://www.mdpi.com/2073-4395/13/7/1871 |
| work_keys_str_mv | AT chaochen animprovedyolov5sbasediagaricusbisporusidetectionalgorithm AT fengwang animprovedyolov5sbasediagaricusbisporusidetectionalgorithm AT yuzhecai animprovedyolov5sbasediagaricusbisporusidetectionalgorithm AT shanlinyi animprovedyolov5sbasediagaricusbisporusidetectionalgorithm AT baofengzhang animprovedyolov5sbasediagaricusbisporusidetectionalgorithm AT chaochen improvedyolov5sbasediagaricusbisporusidetectionalgorithm AT fengwang improvedyolov5sbasediagaricusbisporusidetectionalgorithm AT yuzhecai improvedyolov5sbasediagaricusbisporusidetectionalgorithm AT shanlinyi improvedyolov5sbasediagaricusbisporusidetectionalgorithm AT baofengzhang improvedyolov5sbasediagaricusbisporusidetectionalgorithm |