Instance Segmentation of Sugar Apple (<i>Annona squamosa</i>) in Natural Orchard Scenes Using an Improved YOLOv9-seg Model
Sugar apple (<i>Annona squamosa</i>) is prized for its excellent taste, rich nutrition, and diverse uses, making it valuable for both fresh consumption and medicinal purposes. Predominantly found in tropical regions of the Americas and Asia, its harvesting remains labor-intensive in orch...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | Agriculture |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0472/15/12/1278 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850158087384596480 |
|---|---|
| author | Guanquan Zhu Zihang Luo Minyi Ye Zewen Xie Xiaolin Luo Hanhong Hu Yinglin Wang Zhenyu Ke Jiaguo Jiang Wenlong Wang |
| author_facet | Guanquan Zhu Zihang Luo Minyi Ye Zewen Xie Xiaolin Luo Hanhong Hu Yinglin Wang Zhenyu Ke Jiaguo Jiang Wenlong Wang |
| author_sort | Guanquan Zhu |
| collection | DOAJ |
| description | Sugar apple (<i>Annona squamosa</i>) is prized for its excellent taste, rich nutrition, and diverse uses, making it valuable for both fresh consumption and medicinal purposes. Predominantly found in tropical regions of the Americas and Asia, its harvesting remains labor-intensive in orchard settings, resulting in low efficiency and high costs. This study investigates the use of computer vision for sugar apple instance segmentation and introduces an improved deep learning model, GCE-YOLOv9-seg, specifically designed for orchard conditions. The model incorporates Gamma Correction (GC) to enhance image brightness and contrast, improving target region identification and feature extraction in orchard settings. An Efficient Multiscale Attention (EMA) mechanism was added to strengthen feature representation across scales, addressing sugar apple variability and maturity differences. Additionally, a Convolutional Block Attention Module (CBAM) refined the focus on key regions and deep semantic features. The model’s performance was evaluated on a self-constructed dataset of sugar apple instance segmentation images captured under natural orchard conditions. The experimental results demonstrate that the proposed GCE-YOLOv9-seg model achieved an F1 score (<i>F1</i>) of 90.0%, a precision (<i>P</i>) of 89.6%, a recall (<i>R</i>) level of 93.4%, a mAP@0.5 of 73.2%, and a mAP@[0.5:0.95] of 73.2%. Compared to the original YOLOv9-seg model, the proposed GCE-YOLOv9-seg showed improvements of 1.5% in the F1 score and 3.0% in recall for object detection, while the segmentation task exhibited increases of 0.3% in mAP@0.5 and 1.0% in mAP@[0.5:0.95]. Furthermore, when compared to the latest model YOLOv12-seg, the proposed GCE-YOLOv9-seg still outperformed with an F1 score increase of 2.8%, a precision (P) improvement of 0.4%, and a substantial recall (R) boost of 5.0%. In the segmentation task, mAP@0.5 rose by 3.8%, while mAP@[0.5:0.95] demonstrated a significant enhancement of 7.9%. This method may be directly applied to sugar apple instance segmentation, providing a promising solution for automated sugar apple detection in natural orchard environments. |
| format | Article |
| id | doaj-art-de83a46427be4e7a954ca542cf215b60 |
| institution | OA Journals |
| issn | 2077-0472 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agriculture |
| spelling | doaj-art-de83a46427be4e7a954ca542cf215b602025-08-20T02:23:59ZengMDPI AGAgriculture2077-04722025-06-011512127810.3390/agriculture15121278Instance Segmentation of Sugar Apple (<i>Annona squamosa</i>) in Natural Orchard Scenes Using an Improved YOLOv9-seg ModelGuanquan Zhu0Zihang Luo1Minyi Ye2Zewen Xie3Xiaolin Luo4Hanhong Hu5Yinglin Wang6Zhenyu Ke7Jiaguo Jiang8Wenlong Wang9School of Mathematics and Information Science, Guangzhou University, Guangzhou 510006, ChinaSchool of Electronics and Communication Engineering, Guangzhou University, Guangzhou 510006, ChinaSchool of Mathematics and Information Science, Guangzhou University, Guangzhou 510006, ChinaSchool of Physics and Materials Science, Guangzhou University, Guangzhou 510006, ChinaSchool of Electronics and Communication Engineering, Guangzhou University, Guangzhou 510006, ChinaSchool of Mechanical and Electrical Engineering, Guangzhou University, Guangzhou 510006, ChinaSchool of Life Sciences, South China Normal University, Guangzhou 510631, ChinaSchool of Mechanical and Electrical Engineering, Guangzhou University, Guangzhou 510006, ChinaSchool of Mathematics and Information Science, Guangzhou University, Guangzhou 510006, ChinaSchool of Mechanical and Electrical Engineering, Guangzhou University, Guangzhou 510006, ChinaSugar apple (<i>Annona squamosa</i>) is prized for its excellent taste, rich nutrition, and diverse uses, making it valuable for both fresh consumption and medicinal purposes. Predominantly found in tropical regions of the Americas and Asia, its harvesting remains labor-intensive in orchard settings, resulting in low efficiency and high costs. This study investigates the use of computer vision for sugar apple instance segmentation and introduces an improved deep learning model, GCE-YOLOv9-seg, specifically designed for orchard conditions. The model incorporates Gamma Correction (GC) to enhance image brightness and contrast, improving target region identification and feature extraction in orchard settings. An Efficient Multiscale Attention (EMA) mechanism was added to strengthen feature representation across scales, addressing sugar apple variability and maturity differences. Additionally, a Convolutional Block Attention Module (CBAM) refined the focus on key regions and deep semantic features. The model’s performance was evaluated on a self-constructed dataset of sugar apple instance segmentation images captured under natural orchard conditions. The experimental results demonstrate that the proposed GCE-YOLOv9-seg model achieved an F1 score (<i>F1</i>) of 90.0%, a precision (<i>P</i>) of 89.6%, a recall (<i>R</i>) level of 93.4%, a mAP@0.5 of 73.2%, and a mAP@[0.5:0.95] of 73.2%. Compared to the original YOLOv9-seg model, the proposed GCE-YOLOv9-seg showed improvements of 1.5% in the F1 score and 3.0% in recall for object detection, while the segmentation task exhibited increases of 0.3% in mAP@0.5 and 1.0% in mAP@[0.5:0.95]. Furthermore, when compared to the latest model YOLOv12-seg, the proposed GCE-YOLOv9-seg still outperformed with an F1 score increase of 2.8%, a precision (P) improvement of 0.4%, and a substantial recall (R) boost of 5.0%. In the segmentation task, mAP@0.5 rose by 3.8%, while mAP@[0.5:0.95] demonstrated a significant enhancement of 7.9%. This method may be directly applied to sugar apple instance segmentation, providing a promising solution for automated sugar apple detection in natural orchard environments.https://www.mdpi.com/2077-0472/15/12/1278deep learningcomputer visionYOLOv9-segsugar apple (<i>Annona squamosa</i>) |
| spellingShingle | Guanquan Zhu Zihang Luo Minyi Ye Zewen Xie Xiaolin Luo Hanhong Hu Yinglin Wang Zhenyu Ke Jiaguo Jiang Wenlong Wang Instance Segmentation of Sugar Apple (<i>Annona squamosa</i>) in Natural Orchard Scenes Using an Improved YOLOv9-seg Model Agriculture deep learning computer vision YOLOv9-seg sugar apple (<i>Annona squamosa</i>) |
| title | Instance Segmentation of Sugar Apple (<i>Annona squamosa</i>) in Natural Orchard Scenes Using an Improved YOLOv9-seg Model |
| title_full | Instance Segmentation of Sugar Apple (<i>Annona squamosa</i>) in Natural Orchard Scenes Using an Improved YOLOv9-seg Model |
| title_fullStr | Instance Segmentation of Sugar Apple (<i>Annona squamosa</i>) in Natural Orchard Scenes Using an Improved YOLOv9-seg Model |
| title_full_unstemmed | Instance Segmentation of Sugar Apple (<i>Annona squamosa</i>) in Natural Orchard Scenes Using an Improved YOLOv9-seg Model |
| title_short | Instance Segmentation of Sugar Apple (<i>Annona squamosa</i>) in Natural Orchard Scenes Using an Improved YOLOv9-seg Model |
| title_sort | instance segmentation of sugar apple i annona squamosa i in natural orchard scenes using an improved yolov9 seg model |
| topic | deep learning computer vision YOLOv9-seg sugar apple (<i>Annona squamosa</i>) |
| url | https://www.mdpi.com/2077-0472/15/12/1278 |
| work_keys_str_mv | AT guanquanzhu instancesegmentationofsugarappleiannonasquamosaiinnaturalorchardscenesusinganimprovedyolov9segmodel AT zihangluo instancesegmentationofsugarappleiannonasquamosaiinnaturalorchardscenesusinganimprovedyolov9segmodel AT minyiye instancesegmentationofsugarappleiannonasquamosaiinnaturalorchardscenesusinganimprovedyolov9segmodel AT zewenxie instancesegmentationofsugarappleiannonasquamosaiinnaturalorchardscenesusinganimprovedyolov9segmodel AT xiaolinluo instancesegmentationofsugarappleiannonasquamosaiinnaturalorchardscenesusinganimprovedyolov9segmodel AT hanhonghu instancesegmentationofsugarappleiannonasquamosaiinnaturalorchardscenesusinganimprovedyolov9segmodel AT yinglinwang instancesegmentationofsugarappleiannonasquamosaiinnaturalorchardscenesusinganimprovedyolov9segmodel AT zhenyuke instancesegmentationofsugarappleiannonasquamosaiinnaturalorchardscenesusinganimprovedyolov9segmodel AT jiaguojiang instancesegmentationofsugarappleiannonasquamosaiinnaturalorchardscenesusinganimprovedyolov9segmodel AT wenlongwang instancesegmentationofsugarappleiannonasquamosaiinnaturalorchardscenesusinganimprovedyolov9segmodel |