Yang Wenji, Qiu Xiaoying
Software College, Jiangxi Agricultural University, Nanchang, China.
Front Plant Sci. 2024 Aug 6;15:1395796. doi: 10.3389/fpls.2024.1395796. eCollection 2024.
As one of the most important economic crops, grapes have attracted considerable attention due to their high yield, rich nutritional value, and various health benefits. Identifying grape bunches is crucial for maintaining the quality and quantity of grapes, as well as managing pests and diseases. In recent years, the combination of automated equipment with object detection technology has been instrumental in achieving this. However, existing lightweight object detection algorithms often sacrifice detection precision for processing speed, which may pose obstacles in practical applications. Therefore, this thesis proposes a lightweight detection method named YOLOv8s-grape, which incorporates several effective improvement points, including modified efficient channel attention (MECA), slim-neck, new spatial pyramid pooling fast (NSPPF), dynamic upsampler (DySample), and intersection over union with minimum point distance (MPDIoU). In the proposed method, MECA and NSPPF enhance the feature extraction capability of the backbone, enabling it to better capture crucial information. Slim-neck reduces redundant features, lowers computational complexity, and effectively reuses shallow features to obtain more detailed information, further improving detection precision. DySample achieves excellent performance while maintaining lower computational costs, thus demonstrating high practicality and rapid detection capability. MPDIoU enhances detection precision through faster convergence and more precise regression results. Experimental results show that compared to other methods, this approach performs better in the grapevine bunch detection dataset and grapevine bunch condition detection dataset, with mean average precision (mAP50-95) increasing by 2.4% and 2.6% compared to YOLOv8s, respectively. Meanwhile, the computational complexity and parameters of the method are also reduced, with a decrease of 2.3 Giga floating-point operations per second and 1.5 million parameters. Therefore, it can be concluded that the proposed method, which integrates these improvements, achieves lightweight and high-precision detection, demonstrating its effectiveness in identifying grape bunches and assessing biophysical anomalies.
作为最重要的经济作物之一，葡萄因其高产、丰富的营养价值和多种健康益处而备受关注。识别葡萄串对于维持葡萄的质量和产量以及病虫害管理至关重要。近年来，自动化设备与目标检测技术的结合对实现这一目标起到了重要作用。然而，现有的轻量级目标检测算法往往为了处理速度而牺牲检测精度，这可能在实际应用中造成障碍。因此，本文提出了一种名为YOLOv8s-grape的轻量级检测方法，该方法包含几个有效的改进点，包括改进的高效通道注意力机制（MECA）、细颈结构、新型快速空间金字塔池化（NSPPF）、动态上采样器（DySample）以及基于最小点距离的交并比（MPDIoU）。在所提出的方法中，MECA和NSPPF增强了主干网络的特征提取能力，使其能够更好地捕捉关键信息。细颈结构减少了冗余特征，降低了计算复杂度，并有效地重用浅层特征以获得更详细的信息，进一步提高了检测精度。DySample在保持较低计算成本的同时实现了出色的性能，从而展现出高实用性和快速检测能力。MPDIoU通过更快的收敛速度和更精确的回归结果提高了检测精度。实验结果表明，与其他方法相比，该方法在葡萄串检测数据集和葡萄串状况检测数据集中表现更好，平均精度均值（mAP50-95）分别比YOLOv8s提高了2.4%和2.6%。同时，该方法的计算复杂度和参数也有所降低，每秒浮点运算次数减少了2.3G，参数减少了150万个。因此，可以得出结论，所提出的整合这些改进的方法实现了轻量级和高精度检测，证明了其在识别葡萄串和评估生物物理异常方面的有效性。
