Abstract:
The effective detection of safflower in the field is crucial for implementing automated visual navigation and harvesting systems. Due to the small physical size of safflower clusters, their dense spatial distribution, and the complexity of field scenes, current target detection technologies face several challenges in safflower detection, such as insufficient accuracy and high computational demands. Therefore, this paper introduces an improved safflower target detection model based on YOLOv5, termed Safflower-YOLO (SF-YOLO). This model employs Ghost_conv to replace traditional convolution blocks in the backbone network, significantly enhancing computational efficiency. Furthermore, the CBAM attention mechanism is integrated into the backbone network, and a combined L C I O U + N W D loss function is introduced to allow for more precise feature extraction, enhanced adaptive fusion capabilities, and accelerated loss convergence. Anchor boxes, updated through K-means clustering, are used to replace the original anchors, enabling the model to better adapt to the multi-scale information of safflowers in the field. Data augmentation techniques such as Gaussian blur, noise addition, sharpening, and channel shuffling are applied to the dataset to maintain robustness against variations in lighting, noise, and visual angles. Experimental results demonstrate that SF-YOLO surpasses the original YOLOv5s model, with reductions in GFlops and Params from 15.8 to 13.2 G and 7.013 to 5.34 M, respectively, representing decreases of 16.6% and 23.9%. Concurrently, SF-YOLO\'s mAP0.5 increases by 1.3%, reaching 95.3%. This work enhances the accuracy of safflower detection in complex agricultural environments, providing a reference for subsequent autonomous visual navigation and automated non-destructive harvesting technologies in safflower operations.
摘要:
在野外对红花的有效检测对于实现自动视觉导航和采集系统至关重要。由于红花簇的物理尺寸小,它们密集的空间分布,以及现场场景的复杂性,当前的目标检测技术在红花检测中面临着一些挑战,如精度不足和计算要求高。因此,介绍了一种改进的基于YOLOv5的红花目标检测模型——红花-YOLO(SF-YOLO)。该模型采用Ghost_conv代替骨干网络中的传统卷积块,显著提高计算效率。此外,将CBAM注意力机制集成到骨干网中,并引入了组合的LCIOUNWD损失函数,以允许更精确的特征提取,增强的自适应融合能力,加速损耗收敛。锚箱,通过K均值聚类更新,用来替换原来的锚,使模型能够更好地适应田间红花的多尺度信息。数据增强技术,如高斯模糊,噪声添加,锐化,和通道混洗被应用于数据集,以保持对光照变化的鲁棒性,噪音,和视觉角度。实验结果表明,SF-YOLO超越了原有的YOLOv5s模型,GFlops和Params从15.8G减少到13.2G,从7.013减少到5.34M,分别,分别下降16.6%和23.9%。同时,SF-YOLO的mAP0.5增加1.3%,达到95.3%。这项工作提高了红花在复杂农业环境中检测的准确性,为后续红花作业中的自主视觉导航和自动化无损采收技术提供参考。