Xu Wenchao, Wang Yangxu, Yang Jiahao
School of Electrical and Computer Engineering, Nanfang College Guangzhou, Conghua, Guangdong, China.
Department of Network technology, Guangzhou Institute of Software Engineering, Conghua, Guangdong, China.
PeerJ Comput Sci. 2025 Jan 2;11:e2085. doi: 10.7717/peerj-cs.2085. eCollection 2025.
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.
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.
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.
随着现代农业技术的发展，草莓的自动检测、分类和收获已成为必然趋势。在这些任务中，草莓的分类是一个关键环节。然而，现有的目标检测方法存在计算需求大、资源利用率高和检测效率降低等问题。这些挑战使得在边缘设备上部署变得困难，并导致用户体验不佳。
在本研究中，我们开发了一种能够实时检测和分类草莓果实的轻量级模型，名为草莓轻量级特征分类网络（SLFCNet）。这个创新系统包含一个轻量级编码器和一个自行设计的特征提取模块，称为组合卷积拼接与顺序卷积（C3SC）。在保持模型紧凑性的同时，这种架构显著增强了其特征解码能力。为了评估模型的泛化潜力，我们使用了直接从田间收集的高分辨率草莓数据集。通过采用图像增强技术，我们对手动计数数据与基于模型推理的检测和分类结果进行了实验比较。
SLFCNet模型在mAP@0.5指标上的平均精度达到98.9%，精确率为94.7%，召回率为93.2%。值得注意的是，SLFCNet设计精简，模型大小仅为3.57MB。在经济实惠的GTX 1080 Ti GPU上，每张图像的处理时间仅为4.1毫秒。这表明该模型可以在边缘设备上平稳运行，确保实时性能。因此，它成为草莓收获自动化和管理的一种新解决方案，提供实时性能，并为草莓采摘的自动管理提出了一种新方案。
