FE-YOLO: An Efficient Deep Learning Model Based on Feature-Enhanced YOLOv7 for Microalgae Identification and Detection
The identification and detection of microalgae are essential for the development and utilization of microalgae resources. Traditional methods for microalgae identification and detection have many limitations. Herein, a Feature-Enhanced YOLOv7 (FE-YOLO) model for microalgae cell identification and de...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Biomimetics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2313-7673/10/1/62 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588959290490880 |
|---|---|
| author | Gege Ding Yuhang Shi Zhenquan Liu Yanjuan Wang Zhixuan Yao Dan Zhou Xuexiu Zhu Yiqin Li |
| author_facet | Gege Ding Yuhang Shi Zhenquan Liu Yanjuan Wang Zhixuan Yao Dan Zhou Xuexiu Zhu Yiqin Li |
| author_sort | Gege Ding |
| collection | DOAJ |
| description | The identification and detection of microalgae are essential for the development and utilization of microalgae resources. Traditional methods for microalgae identification and detection have many limitations. Herein, a Feature-Enhanced YOLOv7 (FE-YOLO) model for microalgae cell identification and detection is proposed. Firstly, the feature extraction capability was enhanced by integrating the CAGS (Coordinate Attention Group Shuffle Convolution) attention module into the Neck section. Secondly, the SIoU (SCYLLA-IoU) algorithm was employed to replace the CIoU (Complete IoU) loss function in the original model, addressing the issues of unstable convergence. Finally, we captured and constructed a microalgae dataset containing 6300 images of seven species of microalgae, addressing the issue of a lack of microalgae cell datasets. Compared to the YOLOv7 model, the proposed method shows greatly improved average Precision, Recall, mAP@50, and mAP@95; our proposed algorithm achieved increases of 9.6%, 1.9%, 9.7%, and 6.9%, respectively. In addition, the average detection time of a single image was 0.0455 s, marking a 9.2% improvement. |
| format | Article |
| id | doaj-art-2e9bf49e9beb49ca9b5967cda60c231a |
| institution | Kabale University |
| issn | 2313-7673 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Biomimetics |
| spelling | doaj-art-2e9bf49e9beb49ca9b5967cda60c231a2025-01-24T13:24:47ZengMDPI AGBiomimetics2313-76732025-01-011016210.3390/biomimetics10010062FE-YOLO: An Efficient Deep Learning Model Based on Feature-Enhanced YOLOv7 for Microalgae Identification and DetectionGege Ding0Yuhang Shi1Zhenquan Liu2Yanjuan Wang3Zhixuan Yao4Dan Zhou5Xuexiu Zhu6Yiqin Li7China Waterborne Transport Research Institute, Beijing 100088, ChinaSchool of Railway Intelligent Engineering, Dalian Jiaotong University, Dalian 116028, ChinaSchool of Railway Intelligent Engineering, Dalian Jiaotong University, Dalian 116028, ChinaSchool of Railway Intelligent Engineering, Dalian Jiaotong University, Dalian 116028, ChinaChina Waterborne Transport Research Institute, Beijing 100088, ChinaChina Waterborne Transport Research Institute, Beijing 100088, ChinaChina Waterborne Transport Research Institute, Beijing 100088, ChinaChina Waterborne Transport Research Institute, Beijing 100088, ChinaThe identification and detection of microalgae are essential for the development and utilization of microalgae resources. Traditional methods for microalgae identification and detection have many limitations. Herein, a Feature-Enhanced YOLOv7 (FE-YOLO) model for microalgae cell identification and detection is proposed. Firstly, the feature extraction capability was enhanced by integrating the CAGS (Coordinate Attention Group Shuffle Convolution) attention module into the Neck section. Secondly, the SIoU (SCYLLA-IoU) algorithm was employed to replace the CIoU (Complete IoU) loss function in the original model, addressing the issues of unstable convergence. Finally, we captured and constructed a microalgae dataset containing 6300 images of seven species of microalgae, addressing the issue of a lack of microalgae cell datasets. Compared to the YOLOv7 model, the proposed method shows greatly improved average Precision, Recall, mAP@50, and mAP@95; our proposed algorithm achieved increases of 9.6%, 1.9%, 9.7%, and 6.9%, respectively. In addition, the average detection time of a single image was 0.0455 s, marking a 9.2% improvement.https://www.mdpi.com/2313-7673/10/1/62microalgal detectionfeature fusionobject detectiondeep learning |
| spellingShingle | Gege Ding Yuhang Shi Zhenquan Liu Yanjuan Wang Zhixuan Yao Dan Zhou Xuexiu Zhu Yiqin Li FE-YOLO: An Efficient Deep Learning Model Based on Feature-Enhanced YOLOv7 for Microalgae Identification and Detection Biomimetics microalgal detection feature fusion object detection deep learning |
| title | FE-YOLO: An Efficient Deep Learning Model Based on Feature-Enhanced YOLOv7 for Microalgae Identification and Detection |
| title_full | FE-YOLO: An Efficient Deep Learning Model Based on Feature-Enhanced YOLOv7 for Microalgae Identification and Detection |
| title_fullStr | FE-YOLO: An Efficient Deep Learning Model Based on Feature-Enhanced YOLOv7 for Microalgae Identification and Detection |
| title_full_unstemmed | FE-YOLO: An Efficient Deep Learning Model Based on Feature-Enhanced YOLOv7 for Microalgae Identification and Detection |
| title_short | FE-YOLO: An Efficient Deep Learning Model Based on Feature-Enhanced YOLOv7 for Microalgae Identification and Detection |
| title_sort | fe yolo an efficient deep learning model based on feature enhanced yolov7 for microalgae identification and detection |
| topic | microalgal detection feature fusion object detection deep learning |
| url | https://www.mdpi.com/2313-7673/10/1/62 |
| work_keys_str_mv | AT gegeding feyoloanefficientdeeplearningmodelbasedonfeatureenhancedyolov7formicroalgaeidentificationanddetection AT yuhangshi feyoloanefficientdeeplearningmodelbasedonfeatureenhancedyolov7formicroalgaeidentificationanddetection AT zhenquanliu feyoloanefficientdeeplearningmodelbasedonfeatureenhancedyolov7formicroalgaeidentificationanddetection AT yanjuanwang feyoloanefficientdeeplearningmodelbasedonfeatureenhancedyolov7formicroalgaeidentificationanddetection AT zhixuanyao feyoloanefficientdeeplearningmodelbasedonfeatureenhancedyolov7formicroalgaeidentificationanddetection AT danzhou feyoloanefficientdeeplearningmodelbasedonfeatureenhancedyolov7formicroalgaeidentificationanddetection AT xuexiuzhu feyoloanefficientdeeplearningmodelbasedonfeatureenhancedyolov7formicroalgaeidentificationanddetection AT yiqinli feyoloanefficientdeeplearningmodelbasedonfeatureenhancedyolov7formicroalgaeidentificationanddetection |