Grape Cluster Real-Time Detection in Complex Natural Scenes Based on YOLOv5s Deep Learning Network
Due to differences in planting environment, color, shape, size, and compactness, accurate detection of grape clusters is very difficult. Herein, a real-time detection method for grape clusters based on the YOLOv5s deep learning algorithm was proposed. More specifically, a novel dataset called Grape-...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-08-01
|
| Series: | Agriculture |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0472/12/8/1242 |
| _version_ | 1797432556455460864 |
|---|---|
| author | Chuandong Zhang Huali Ding Qinfeng Shi Yunfei Wang |
| author_facet | Chuandong Zhang Huali Ding Qinfeng Shi Yunfei Wang |
| author_sort | Chuandong Zhang |
| collection | DOAJ |
| description | Due to differences in planting environment, color, shape, size, and compactness, accurate detection of grape clusters is very difficult. Herein, a real-time detection method for grape clusters based on the YOLOv5s deep learning algorithm was proposed. More specifically, a novel dataset called Grape-internet was constructed, which consisted of 8657 grape images and corresponding annotation files in complex scenes. By training and adjusting the parameters of the YOLOv5s model on the data set, and by reducing the depth and width of the network, the lightweight processing of the network was completed, losing only a small amount of accuracy. As a result, the fast and accurate detection of grape clusters was finally realized. The test results showed that the precision, recall, mAP and F1 of the grape cluster detection network were 99.40%, 99.40%, 99.40% and 99.40%, respectively, and the average detection speed per image was 344.83 fps, with a model size of 13.67 MB. Compared with the YOLOv5x, ScaledYOLOv4-CSP and YOLOv3 models, the precision of YOLOv5s was 1.84% higher than that of ScaledYOLOv4-CSP, and the recall rate and mAP were slightly lower than three networks by 0.1–0.3%. The speed was the fastest (4.6 times, 2.83 times and 6.7 times of YOLOv3, ScaledYOLOv4-CSP and YOLOv5x network, respectively) and the network scale was the smallest (1.61%, 6.81% and 8.28% of YOLOv3, ScaledYOLOv4-CSP YOLOv5x, respectively) for YOLOv5s. Moreover, the detection precision and recall rate of YOLOv5s was 26.14% and 30.96% higher, respectively, than those of Mask R-CNN. Further, it exhibited more lightweight and better real-time performance. In short, the detection network can not only meet the requirements of being a high precision, high speed and lightweight solution for grape cluster detection, but also it can adapt to differences between products and complex environmental interference, possessing strong robustness, generalization, and real-time adaptability. |
| first_indexed | 2024-03-09T10:03:15Z |
| format | Article |
| id | doaj.art-355e52fd9f0e410f8aaff8310ee6c557 |
| institution | Directory Open Access Journal |
| issn | 2077-0472 |
| language | English |
| last_indexed | 2024-03-09T10:03:15Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agriculture |
| spelling | doaj.art-355e52fd9f0e410f8aaff8310ee6c5572023-12-01T23:17:00ZengMDPI AGAgriculture2077-04722022-08-01128124210.3390/agriculture12081242Grape Cluster Real-Time Detection in Complex Natural Scenes Based on YOLOv5s Deep Learning NetworkChuandong Zhang0Huali Ding1Qinfeng Shi2Yunfei Wang3School of Mathematics and Computer Application Technology, Jining University, Qufu 273100, ChinaSchool of Mathematics and Computer Application Technology, Jining University, Qufu 273100, ChinaSchool of Mathematics and Computer Application Technology, Jining University, Qufu 273100, ChinaCollege of Mechanical and Electronic Engineering, Northwest A&F University, Xianyang 712100, ChinaDue to differences in planting environment, color, shape, size, and compactness, accurate detection of grape clusters is very difficult. Herein, a real-time detection method for grape clusters based on the YOLOv5s deep learning algorithm was proposed. More specifically, a novel dataset called Grape-internet was constructed, which consisted of 8657 grape images and corresponding annotation files in complex scenes. By training and adjusting the parameters of the YOLOv5s model on the data set, and by reducing the depth and width of the network, the lightweight processing of the network was completed, losing only a small amount of accuracy. As a result, the fast and accurate detection of grape clusters was finally realized. The test results showed that the precision, recall, mAP and F1 of the grape cluster detection network were 99.40%, 99.40%, 99.40% and 99.40%, respectively, and the average detection speed per image was 344.83 fps, with a model size of 13.67 MB. Compared with the YOLOv5x, ScaledYOLOv4-CSP and YOLOv3 models, the precision of YOLOv5s was 1.84% higher than that of ScaledYOLOv4-CSP, and the recall rate and mAP were slightly lower than three networks by 0.1–0.3%. The speed was the fastest (4.6 times, 2.83 times and 6.7 times of YOLOv3, ScaledYOLOv4-CSP and YOLOv5x network, respectively) and the network scale was the smallest (1.61%, 6.81% and 8.28% of YOLOv3, ScaledYOLOv4-CSP YOLOv5x, respectively) for YOLOv5s. Moreover, the detection precision and recall rate of YOLOv5s was 26.14% and 30.96% higher, respectively, than those of Mask R-CNN. Further, it exhibited more lightweight and better real-time performance. In short, the detection network can not only meet the requirements of being a high precision, high speed and lightweight solution for grape cluster detection, but also it can adapt to differences between products and complex environmental interference, possessing strong robustness, generalization, and real-time adaptability.https://www.mdpi.com/2077-0472/12/8/1242grape cluster detectionYOLOv5sobject detectionreal-time detectionlightweight |
| spellingShingle | Chuandong Zhang Huali Ding Qinfeng Shi Yunfei Wang Grape Cluster Real-Time Detection in Complex Natural Scenes Based on YOLOv5s Deep Learning Network Agriculture grape cluster detection YOLOv5s object detection real-time detection lightweight |
| title | Grape Cluster Real-Time Detection in Complex Natural Scenes Based on YOLOv5s Deep Learning Network |
| title_full | Grape Cluster Real-Time Detection in Complex Natural Scenes Based on YOLOv5s Deep Learning Network |
| title_fullStr | Grape Cluster Real-Time Detection in Complex Natural Scenes Based on YOLOv5s Deep Learning Network |
| title_full_unstemmed | Grape Cluster Real-Time Detection in Complex Natural Scenes Based on YOLOv5s Deep Learning Network |
| title_short | Grape Cluster Real-Time Detection in Complex Natural Scenes Based on YOLOv5s Deep Learning Network |
| title_sort | grape cluster real time detection in complex natural scenes based on yolov5s deep learning network |
| topic | grape cluster detection YOLOv5s object detection real-time detection lightweight |
| url | https://www.mdpi.com/2077-0472/12/8/1242 |
| work_keys_str_mv | AT chuandongzhang grapeclusterrealtimedetectionincomplexnaturalscenesbasedonyolov5sdeeplearningnetwork AT hualiding grapeclusterrealtimedetectionincomplexnaturalscenesbasedonyolov5sdeeplearningnetwork AT qinfengshi grapeclusterrealtimedetectionincomplexnaturalscenesbasedonyolov5sdeeplearningnetwork AT yunfeiwang grapeclusterrealtimedetectionincomplexnaturalscenesbasedonyolov5sdeeplearningnetwork |