作者:黄英来，李大明，吕鑫，杨柳松
Authors:HUANG Ying-lai,LI Da-ming,LU Xin,YANG Liu-song摘要:摘要:为探索对袋料栽培香菇的机械式采摘，提出一种基于改进YOLOv4的识别算法。主要改进方法为：在PANet（Path Aggregation Network）结构中，增加一条具有残差注意力机制的特征图路径，提高对小目标的识别精度，并用深度可分离卷积结构替换PANet网络中卷积层，降低了参数量。使用Focal loss损失函数改进原置信度损失函数。在数据预处理方面，采用gamma变换方法对数据进行增强扩充。在训练过程中利用迁移学习的思想，对主干网络载入VOC数据集的预训练权重。相比原YOLOv4算法，mAP值增加了4.82个百分点，达到94.39%,算法参数量降为原来的58.13%，算法更加高效和轻量化，为机械采摘提供视觉算法支持。
Abstract:Abstract:In order to explore the picking of Lentinus edodes which are cultivated in bags, a recognition algorithm based on improved YOLOv4 is proposed.The main improvement measures are: in the structure of PANet (Path Aggregation Network), we add a feature map path with residual attention mechanism to improve the recognition accuracy of small targets, and replace the convolution layer in PANet network with deep separable convolution structure to reduce the amount of parameters.Focal loss is selected to improve the original confidence loss function.In the aspect of data preprocessing, gamma transform method is used to enhance and expand the data.In the training process, the idea of transfer learning is used to load the pre training weight of VOC data set on the backbone network.Compared with the original YOLOv4 algorithm, the mAP value is increased by 4.82 percentage points to 94.39%, and the amount of algorithm parameters is reduced by 58.13%.The algorithm is more efficient and lightweight, providing visual algorithm support for mechanical picking.

PDF全文下载地址:

可免费Download/下载PDF全文