基于改进YOLO v7的微藻轻量级检测方法

Lightweight detection method for microalgae based on improved YOLO v7

为了解决传统的微藻检测方法依赖于复杂的设备和大量的人工操作,不仅耗时长且检测结果易受检测人员技术经验影响等问题,结合微藻显微图像特征,采用K-means++算法聚类锚框,并基于YOLO v7模型,提出一种轻量级实时检测微藻的方法YOLO v7-MA。该方法将GhostNet引入YOLO v7模型中作为主干特征提取网络,以减少网络的参数量,同时将特征融合网络中的普通卷积块替换为深度可分离卷积块,进一步降低模型的计算复杂度,并在特征融合网络中加入CBAM注意力模块,以提高网络的特征表达能力。结果表明:在14种微藻数据集上的试验显示,本研究中提出的YOLO v7-MA模型的平均精度均值为98.56%,召回率为96.88%,F1值为97.42%,参数量为22.64×10^(6),浮点运算次数(FLOPs)为38.45×10^(9);相较于YOLO v7模型,YOLO v7-MA模型平均精度均值提高了0.95%,召回率和F1值分别提高了1.15%、0.23%,参数量和FLOPs分别降低了14.63%和66.55%;相较于FasterRCNN-VGG16、FasterRCNN-Resnet50、YOLO v4、YOLO v4-Mobilenet v3、YOLO v4-VGG16、YOLO v4-Resnet50和YOLO v5s等模型,YOLO v7-MA模型的平均精度均值也均有提高,参数量均有减少。研究表明,YOLO v7-MA模型能够为微藻的识别分类提供一种轻量化的实时高效检测方法,大大降低了检测人员的工作量。

Traditional microalgae detection methods rely on a large number of manual operations with complex equipment,which are time consuming and the results easily influenced by the detectors’knowledge and experience.A lightweight real-time microalgae detection method,YOLO v7-MA,was proposed by clustering anchor frames with K-means++algorithm based on YOLO V7 model.In this method,GhostNet was introduced into YOLO v7 model as the backbone feature extraction network,which reduced the parameters of the network.At the same time,the ordinary convolution block in the feature fusion network was replaced by the deeply separable convolution block,which further decreased the computational complexity of the model,and added CBAM attention module to the feature fusion network to improve the feature expression ability of the network.The results showed that the YOLOv7-MA model had mean average precision of 98.56%,increased by 0.95%;the recall rate of 96.88%,increased by 1.15%;the F1 score of 97.42%,increased by 0.23%;the parameters quantities of 22.64×10^(6),decreased by 14.63%,and the floating-point operations number of 38.45×10^(9),decreased by 66.55%of the original compared with YOLOv7.Compared with FasterRCNN-VGG16,FasterRCNN-Resnet50,YOLOv4,YOLOv4-Mobilenet v3,YOLOv4-VGG16,YOLOv4-Resnet50,and YOLOv5s models,the mean average precision of YOLOv7-MA model was also improved,and the numbers of parameters were decreased.The findings indicate that it seems that the YOLO v7-MA model could provide a lightweight,real-time and efficient detection method for the identification and classification of microalgae,greatly reducing the workload of the detectors.