基于YOLO-LGC的油茶果计数及空间定位分布

Counting and Spatial Distribution of Camellia oleifera Fruits Based on YOLO-LGC

摘要:

深度学习技术在农业视觉任务中应用广泛，确定采摘参数是油茶机械化采摘的首要任务，而基于深度学习的果实自动检测与目标计数对于精准设定这些参数至关重要。然而，果园复杂环境中遮挡、光照变化等因素，直接影响检测方法的效率与准确性。本研究基于YOLO 11n提出一种高效轻量级模型YOLO-LGC，旨在提升在复杂果园环境下目标检测精度和空间定位能力。在主干网络中引入LGC（LNN Ghost Dynamic Convolution）模块，通过自适应内核选择优化特征提取，提升复杂环境下检测精度；采用可编程梯度信息（Programmable Gradient Information，PGI）机制，动态调节梯度传播，解决遮挡和光照变化导致的特征冲突；融合动态上采样模块（Dynamic UpSample），在PGI引导下增强特征保留能力，提高空间定位精度。本研究结合轴对齐边界框（AABB）和惯性测量单元（IMU）以及卡尔曼滤波将油茶果实在高度0~1.5m、1.5~1.8m、1.8m以上空间分布进行可视化，通过分析果实空间关系提供更准确的果实位置信息。试验结果表明，与YOLO 11n相比，YOLO-LGC检测精确率从82.0%提升至83.0%，召回率从76.4%提升至78.0%，mAP@0.5从85.1%提升至87.6%，检测速度从229.8f/s提升至299.7f/s，浮点运算量小幅提升至6.7×109，在保持高推理速度优势的同时增强检测性能，优于现有主流检测方法，空间分布误差率小于5%，能够满足实际检测需求，该研究结果可为油茶果机械化采摘参数匹配提供依据。

Abstract:

Deep learning methods are widely applied in agricultural vision tasks. Determining harvesting parameters is a primary task for the mechanized harvesting of Camellia oleifera fruits, and automated fruit detection and object counting based on deep learning are crucial for accurately setting these parameters. However, factors such as occlusion and illumination variations in complex orchard environments directly affect the efficiency and accuracy of detection methods. An efficient, lightweight model named YOLO-LGC was proposed based on YOLO 11n, aiming to enhance target detection accuracy and spatial localization capability in complex orchard environments. Firstly, the LNN ghost dynamic convolution (LGC) module was introduced into the backbone network to optimize feature extraction through adaptive kernel selection, thereby improving detection accuracy in complex environments. Secondly, the programmable gradient information (PGI) mechanism was adopted to dynamically adjust gradient propagation, addressing feature conflicts caused by occlusion and illumination changes. Finally, the Dynamic UpSample module was integrated, guided by PGI, to enhance feature retention and improve spatial localization accuracy. Combined axis-aligned bounding boxes (AABB), an inertial measurement unit (IMU), and Kalman filtering to visualize the spatial distribution of Camellia oleifera fruits at heights of 0~1.5m, 1.5~1.8m, and above 1.8m. By analyzing the spatial relationships of the fruits, more accurate positional information was provided. Experimental results showed that compared with YOLO 11n, YOLO-LGC improved detection precision from 82.0% to 83.0%, recall from 76.4% to 78.0%, mAP@0.5 from 85.1% to 87.6%, and FPS from 229.8f/s to 299.7f/s, with computational complexity slightly increased to 6.7×109. While maintaining the advantage of high inference speed, YOLO-LGC enhances detection performance, outperforming existing mainstream detection methods. The spatial distribution error rate was less than 5%, meeting practical detection requirements. The findings can provide a basis for matching mechanized harvesting parameters for Camellia oleifera fruits.