Ginger Seeding Detection and Shoot Orientation Discrimination Using an Improved YOLOv4-LITE Network
A consistent orientation of ginger shoots when sowing ginger is more conducive to high yields and later harvesting. However, current ginger sowing mainly relies on manual methods, seriously hindering the ginger industry’s development. Existing ginger seeders still require manual assistance in placin...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Agronomy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4395/11/11/2328 |
| _version_ | 1827677665598898176 |
|---|---|
| author | Lifa Fang Yanqiang Wu Yuhua Li Hongen Guo Hua Zhang Xiaoyu Wang Rui Xi Jialin Hou |
| author_facet | Lifa Fang Yanqiang Wu Yuhua Li Hongen Guo Hua Zhang Xiaoyu Wang Rui Xi Jialin Hou |
| author_sort | Lifa Fang |
| collection | DOAJ |
| description | A consistent orientation of ginger shoots when sowing ginger is more conducive to high yields and later harvesting. However, current ginger sowing mainly relies on manual methods, seriously hindering the ginger industry’s development. Existing ginger seeders still require manual assistance in placing ginger seeds to achieve consistent ginger shoot orientation. To address the problem that existing ginger seeders have difficulty in automating seeding and ensuring consistent ginger shoot orientation, this study applies object detection techniques in deep learning to the detection of ginger and proposes a ginger recognition network based on YOLOv4-LITE, which, first, uses MobileNetv2 as the backbone network of the model and, second, adds coordinate attention to MobileNetv2 and uses Do-Conv convolution to replace part of the traditional convolution. After completing the prediction of ginger and ginger shoots, this paper determines ginger shoot orientation by calculating the relative positions of the largest ginger shoot and the ginger. The mean average precision, Params, and giga Flops of the proposed YOLOv4-LITE in the test set reached 98.73%, 47.99 M, and 8.74, respectively. The experimental results show that YOLOv4-LITE achieved ginger seed detection and ginger shoot orientation calculation, and that it provides a technical guarantee for automated ginger seeding. |
| first_indexed | 2024-03-10T05:47:08Z |
| format | Article |
| id | doaj.art-7c816dfc4f1549ea8abefe849e1a9e46 |
| institution | Directory Open Access Journal |
| issn | 2073-4395 |
| language | English |
| last_indexed | 2024-03-10T05:47:08Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agronomy |
| spelling | doaj.art-7c816dfc4f1549ea8abefe849e1a9e462023-11-22T22:03:56ZengMDPI AGAgronomy2073-43952021-11-011111232810.3390/agronomy11112328Ginger Seeding Detection and Shoot Orientation Discrimination Using an Improved YOLOv4-LITE NetworkLifa Fang0Yanqiang Wu1Yuhua Li2Hongen Guo3Hua Zhang4Xiaoyu Wang5Rui Xi6Jialin Hou7Shandong Academy of Agricultural Machinery Sciences, Jinan 250100, ChinaCollege of Mechanical & Electronic Engineering, Shandong Agricultural University, Tai’an 271018, ChinaCollege of Mechanical & Electronic Engineering, Shandong Agricultural University, Tai’an 271018, ChinaShandong Academy of Agricultural Machinery Sciences, Jinan 250100, ChinaShandong Academy of Agricultural Machinery Sciences, Jinan 250100, ChinaShandong Academy of Agricultural Machinery Sciences, Jinan 250100, ChinaCollege of Mechanical & Electronic Engineering, Shandong Agricultural University, Tai’an 271018, ChinaShandong Academy of Agricultural Machinery Sciences, Jinan 250100, ChinaA consistent orientation of ginger shoots when sowing ginger is more conducive to high yields and later harvesting. However, current ginger sowing mainly relies on manual methods, seriously hindering the ginger industry’s development. Existing ginger seeders still require manual assistance in placing ginger seeds to achieve consistent ginger shoot orientation. To address the problem that existing ginger seeders have difficulty in automating seeding and ensuring consistent ginger shoot orientation, this study applies object detection techniques in deep learning to the detection of ginger and proposes a ginger recognition network based on YOLOv4-LITE, which, first, uses MobileNetv2 as the backbone network of the model and, second, adds coordinate attention to MobileNetv2 and uses Do-Conv convolution to replace part of the traditional convolution. After completing the prediction of ginger and ginger shoots, this paper determines ginger shoot orientation by calculating the relative positions of the largest ginger shoot and the ginger. The mean average precision, Params, and giga Flops of the proposed YOLOv4-LITE in the test set reached 98.73%, 47.99 M, and 8.74, respectively. The experimental results show that YOLOv4-LITE achieved ginger seed detection and ginger shoot orientation calculation, and that it provides a technical guarantee for automated ginger seeding.https://www.mdpi.com/2073-4395/11/11/2328image recognitiondeep learningYOLOattention mechanismMobileNetv2ginger |
| spellingShingle | Lifa Fang Yanqiang Wu Yuhua Li Hongen Guo Hua Zhang Xiaoyu Wang Rui Xi Jialin Hou Ginger Seeding Detection and Shoot Orientation Discrimination Using an Improved YOLOv4-LITE Network Agronomy image recognition deep learning YOLO attention mechanism MobileNetv2 ginger |
| title | Ginger Seeding Detection and Shoot Orientation Discrimination Using an Improved YOLOv4-LITE Network |
| title_full | Ginger Seeding Detection and Shoot Orientation Discrimination Using an Improved YOLOv4-LITE Network |
| title_fullStr | Ginger Seeding Detection and Shoot Orientation Discrimination Using an Improved YOLOv4-LITE Network |
| title_full_unstemmed | Ginger Seeding Detection and Shoot Orientation Discrimination Using an Improved YOLOv4-LITE Network |
| title_short | Ginger Seeding Detection and Shoot Orientation Discrimination Using an Improved YOLOv4-LITE Network |
| title_sort | ginger seeding detection and shoot orientation discrimination using an improved yolov4 lite network |
| topic | image recognition deep learning YOLO attention mechanism MobileNetv2 ginger |
| url | https://www.mdpi.com/2073-4395/11/11/2328 |
| work_keys_str_mv | AT lifafang gingerseedingdetectionandshootorientationdiscriminationusinganimprovedyolov4litenetwork AT yanqiangwu gingerseedingdetectionandshootorientationdiscriminationusinganimprovedyolov4litenetwork AT yuhuali gingerseedingdetectionandshootorientationdiscriminationusinganimprovedyolov4litenetwork AT hongenguo gingerseedingdetectionandshootorientationdiscriminationusinganimprovedyolov4litenetwork AT huazhang gingerseedingdetectionandshootorientationdiscriminationusinganimprovedyolov4litenetwork AT xiaoyuwang gingerseedingdetectionandshootorientationdiscriminationusinganimprovedyolov4litenetwork AT ruixi gingerseedingdetectionandshootorientationdiscriminationusinganimprovedyolov4litenetwork AT jialinhou gingerseedingdetectionandshootorientationdiscriminationusinganimprovedyolov4litenetwork |