SLFCNet: an ultra-lightweight and efficient strawberry feature classification network
Background As modern agricultural technology advances, the automated detection, classification, and harvesting of strawberries have become an inevitable trend. Among these tasks, the classification of strawberries stands as a pivotal juncture. Nevertheless, existing object detection methods struggle...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2025-01-01
|
| Series: | PeerJ Computer Science |
| Subjects: | |
| Online Access: | https://peerj.com/articles/cs-2085.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841560285763076096 |
|---|---|
| author | Wenchao Xu Yangxu Wang Jiahao Yang |
| author_facet | Wenchao Xu Yangxu Wang Jiahao Yang |
| author_sort | Wenchao Xu |
| collection | DOAJ |
| description | Background As modern agricultural technology advances, the automated detection, classification, and harvesting of strawberries have become an inevitable trend. Among these tasks, the classification of strawberries stands as a pivotal juncture. Nevertheless, existing object detection methods struggle with substantial computational demands, high resource utilization, and reduced detection efficiency. These challenges make deployment on edge devices difficult and lead to suboptimal user experiences. Methods In this study, we have developed a lightweight model capable of real-time detection and classification of strawberry fruit, named the Strawberry Lightweight Feature Classify Network (SLFCNet). This innovative system incorporates a lightweight encoder and a self-designed feature extraction module called the Combined Convolutional Concatenation and Sequential Convolutional (C3SC). While maintaining model compactness, this architecture significantly enhances its feature decoding capabilities. To evaluate the model’s generalization potential, we utilized a high-resolution strawberry dataset collected directly from the fields. By employing image augmentation techniques, we conducted experimental comparisons between manually counted data and the model’s inference-based detection and classification results. Results The SLFCNet model achieves an average precision of 98.9% in the mAP@0.5 metric, with a precision rate of 94.7% and a recall rate of 93.2%. Notably, SLFCNet features a streamlined design, resulting in a compact model size of only 3.57 MB. On an economical GTX 1080 Ti GPU, the processing time per image is a mere 4.1 ms. This indicates that the model can smoothly run on edge devices, ensuring real-time performance. Thus, it emerges as a novel solution for the automation and management of strawberry harvesting, providing real-time performance and presenting a new solution for the automatic management of strawberry picking. |
| format | Article |
| id | doaj-art-95ad0b0dc85e4485829cf0bd8efa209b |
| institution | Kabale University |
| issn | 2376-5992 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ Computer Science |
| spelling | doaj-art-95ad0b0dc85e4485829cf0bd8efa209b2025-01-04T15:05:11ZengPeerJ Inc.PeerJ Computer Science2376-59922025-01-0111e208510.7717/peerj-cs.2085SLFCNet: an ultra-lightweight and efficient strawberry feature classification networkWenchao Xu0Yangxu Wang1Jiahao Yang2School of Electrical and Computer Engineering, Nanfang College Guangzhou, Conghua, Guangdong, ChinaDepartment of Network technology, Guangzhou Institute of Software Engineering, Conghua, Guangdong, ChinaCollege of Robotics, Guangdong Polytechnic of Science and Technology, Zhuhai, Guangdong, ChinaBackground As modern agricultural technology advances, the automated detection, classification, and harvesting of strawberries have become an inevitable trend. Among these tasks, the classification of strawberries stands as a pivotal juncture. Nevertheless, existing object detection methods struggle with substantial computational demands, high resource utilization, and reduced detection efficiency. These challenges make deployment on edge devices difficult and lead to suboptimal user experiences. Methods In this study, we have developed a lightweight model capable of real-time detection and classification of strawberry fruit, named the Strawberry Lightweight Feature Classify Network (SLFCNet). This innovative system incorporates a lightweight encoder and a self-designed feature extraction module called the Combined Convolutional Concatenation and Sequential Convolutional (C3SC). While maintaining model compactness, this architecture significantly enhances its feature decoding capabilities. To evaluate the model’s generalization potential, we utilized a high-resolution strawberry dataset collected directly from the fields. By employing image augmentation techniques, we conducted experimental comparisons between manually counted data and the model’s inference-based detection and classification results. Results The SLFCNet model achieves an average precision of 98.9% in the mAP@0.5 metric, with a precision rate of 94.7% and a recall rate of 93.2%. Notably, SLFCNet features a streamlined design, resulting in a compact model size of only 3.57 MB. On an economical GTX 1080 Ti GPU, the processing time per image is a mere 4.1 ms. This indicates that the model can smoothly run on edge devices, ensuring real-time performance. Thus, it emerges as a novel solution for the automation and management of strawberry harvesting, providing real-time performance and presenting a new solution for the automatic management of strawberry picking.https://peerj.com/articles/cs-2085.pdfStrawberryLightweightDetection and classificationReal-time recognitionAutomated management |
| spellingShingle | Wenchao Xu Yangxu Wang Jiahao Yang SLFCNet: an ultra-lightweight and efficient strawberry feature classification network PeerJ Computer Science Strawberry Lightweight Detection and classification Real-time recognition Automated management |
| title | SLFCNet: an ultra-lightweight and efficient strawberry feature classification network |
| title_full | SLFCNet: an ultra-lightweight and efficient strawberry feature classification network |
| title_fullStr | SLFCNet: an ultra-lightweight and efficient strawberry feature classification network |
| title_full_unstemmed | SLFCNet: an ultra-lightweight and efficient strawberry feature classification network |
| title_short | SLFCNet: an ultra-lightweight and efficient strawberry feature classification network |
| title_sort | slfcnet an ultra lightweight and efficient strawberry feature classification network |
| topic | Strawberry Lightweight Detection and classification Real-time recognition Automated management |
| url | https://peerj.com/articles/cs-2085.pdf |
| work_keys_str_mv | AT wenchaoxu slfcnetanultralightweightandefficientstrawberryfeatureclassificationnetwork AT yangxuwang slfcnetanultralightweightandefficientstrawberryfeatureclassificationnetwork AT jiahaoyang slfcnetanultralightweightandefficientstrawberryfeatureclassificationnetwork |