DMM-YOLO: A high efficiency soil fauna detection model based on an adaptive dynamic shuffle mechanism
Abstract Soil fauna play a critical role in maintaining ecosystem functions and assessing environmental health, making accurate and efficient detection essential. Therefore, this paper proposes an improved algorithm based on You Only Look Once (YOLO) v9, which enhances feature capture capability whi...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-08-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-12058-8 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849342937338478592 |
|---|---|
| author | Jiehui Ke Renbo Luo Guoliang Xu Yuna Tan Zhifeng Wu Liufeng Xiao |
| author_facet | Jiehui Ke Renbo Luo Guoliang Xu Yuna Tan Zhifeng Wu Liufeng Xiao |
| author_sort | Jiehui Ke |
| collection | DOAJ |
| description | Abstract Soil fauna play a critical role in maintaining ecosystem functions and assessing environmental health, making accurate and efficient detection essential. Therefore, this paper proposes an improved algorithm based on You Only Look Once (YOLO) v9, which enhances feature capture capability while reducing parameters by 33.6%. First, a dynamic local shuffle module (DLSConv) is proposed, which utilizes convolutions and adaptive shuffling, effectively enhancing information interaction and feature richness. Additionally, different efficient modules with multi-branch fusion structures, integrating DLSConv, are adopted for the Backbone and Neck to enhance feature extraction and fusion, while optimizing the feature maps fed into the detection head, thereby improving the network’s ability to extract features and detect targets. Ablation experiments demonstrate that the model achieves a 2.3% improvement in F-score and 1.8% increase in mean average precision (mAP)@50. On the soil fauna dataset, it attains 94.3% in mAP@75, significantly outperforming the baseline in challenging scenarios. These results highlight the model’s efficiency and reliability for soil fauna detection on resource-constrained devices. And this capability can significantly enhance ecological monitoring through scalable biodiversity assessment and empowers precision agriculture applications via actionable insights into soil health and faunal activity, underpinning sustainable land management practices. |
| format | Article |
| id | doaj-art-c61a61ad31e64b0b8c8ab8d757cb02ab |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-c61a61ad31e64b0b8c8ab8d757cb02ab2025-08-20T03:43:11ZengNature PortfolioScientific Reports2045-23222025-08-0115111610.1038/s41598-025-12058-8DMM-YOLO: A high efficiency soil fauna detection model based on an adaptive dynamic shuffle mechanismJiehui Ke0Renbo Luo1Guoliang Xu2Yuna Tan3Zhifeng Wu4Liufeng Xiao5School of Geographical Sciences and Remote Sensing, Guangzhou UniversitySchool of Geographical Sciences and Remote Sensing, Guangzhou UniversitySchool of Geographical Sciences and Remote Sensing, Guangzhou UniversitySchool of Geographical Sciences and Remote Sensing, Guangzhou UniversitySchool of Geographical Sciences and Remote Sensing, Guangzhou UniversitySchool of Geographical Sciences and Remote Sensing, Guangzhou UniversityAbstract Soil fauna play a critical role in maintaining ecosystem functions and assessing environmental health, making accurate and efficient detection essential. Therefore, this paper proposes an improved algorithm based on You Only Look Once (YOLO) v9, which enhances feature capture capability while reducing parameters by 33.6%. First, a dynamic local shuffle module (DLSConv) is proposed, which utilizes convolutions and adaptive shuffling, effectively enhancing information interaction and feature richness. Additionally, different efficient modules with multi-branch fusion structures, integrating DLSConv, are adopted for the Backbone and Neck to enhance feature extraction and fusion, while optimizing the feature maps fed into the detection head, thereby improving the network’s ability to extract features and detect targets. Ablation experiments demonstrate that the model achieves a 2.3% improvement in F-score and 1.8% increase in mean average precision (mAP)@50. On the soil fauna dataset, it attains 94.3% in mAP@75, significantly outperforming the baseline in challenging scenarios. These results highlight the model’s efficiency and reliability for soil fauna detection on resource-constrained devices. And this capability can significantly enhance ecological monitoring through scalable biodiversity assessment and empowers precision agriculture applications via actionable insights into soil health and faunal activity, underpinning sustainable land management practices.https://doi.org/10.1038/s41598-025-12058-8YOLOv9Deep learningSoil faunaObject detectionEcological monitoring |
| spellingShingle | Jiehui Ke Renbo Luo Guoliang Xu Yuna Tan Zhifeng Wu Liufeng Xiao DMM-YOLO: A high efficiency soil fauna detection model based on an adaptive dynamic shuffle mechanism Scientific Reports YOLOv9 Deep learning Soil fauna Object detection Ecological monitoring |
| title | DMM-YOLO: A high efficiency soil fauna detection model based on an adaptive dynamic shuffle mechanism |
| title_full | DMM-YOLO: A high efficiency soil fauna detection model based on an adaptive dynamic shuffle mechanism |
| title_fullStr | DMM-YOLO: A high efficiency soil fauna detection model based on an adaptive dynamic shuffle mechanism |
| title_full_unstemmed | DMM-YOLO: A high efficiency soil fauna detection model based on an adaptive dynamic shuffle mechanism |
| title_short | DMM-YOLO: A high efficiency soil fauna detection model based on an adaptive dynamic shuffle mechanism |
| title_sort | dmm yolo a high efficiency soil fauna detection model based on an adaptive dynamic shuffle mechanism |
| topic | YOLOv9 Deep learning Soil fauna Object detection Ecological monitoring |
| url | https://doi.org/10.1038/s41598-025-12058-8 |
| work_keys_str_mv | AT jiehuike dmmyoloahighefficiencysoilfaunadetectionmodelbasedonanadaptivedynamicshufflemechanism AT renboluo dmmyoloahighefficiencysoilfaunadetectionmodelbasedonanadaptivedynamicshufflemechanism AT guoliangxu dmmyoloahighefficiencysoilfaunadetectionmodelbasedonanadaptivedynamicshufflemechanism AT yunatan dmmyoloahighefficiencysoilfaunadetectionmodelbasedonanadaptivedynamicshufflemechanism AT zhifengwu dmmyoloahighefficiencysoilfaunadetectionmodelbasedonanadaptivedynamicshufflemechanism AT liufengxiao dmmyoloahighefficiencysoilfaunadetectionmodelbasedonanadaptivedynamicshufflemechanism |