基于改进YOLOv7的无人机航拍视频西瓜计数方法  

Improved YOLOv7 method for counting watermelons in UAV aerial videos

作　　者：殷慧军 王宝丽 景运革 李菊霞[1] 王鹏岭 权高翔 孙婷婷 YIN Huijun;WANG Baoli;JING Yunge;LI Juxia;WANG Pengling;QUAN Gaoxiang;SUN Tingting(College of Information Science and Engineering,Shanxi Agricultural University,Taigu 030800,China;College of Mathematics and Information Technology,Yuncheng University,Yuncheng 044000,China)

机构地区：[1]山西农业大学信息科学与工程学院,太谷030800 [2]运城学院数学与信息技术学院,运城044000

出　　处：《农业工程学报》2024年第19期124-134,共11页Transactions of the Chinese Society of Agricultural Engineering

基　　金：国家自然科学基金项目(61703363,62272284);山西省重点实验室开放课题基金项目(CICIP2022002)。

摘　　要：为解决自然环境下西瓜分布不均且遮挡严重导致的人工计数困难问题,该研究提出一种YOLOv7-GCSF模型与Deep SORT算法相融合的无人机视频西瓜自动计数方法。采用Ghost Conv及C2f模块轻量化YOLOv7模型,以减少模型冗余信息;引入Sim AM注意力机制,构建MP-Sim AM模块,用于提高模型特征提取能力;替换CIo U为Focal EIo U损失函数,以增加模型收敛性能;在Deep SORT中提出一种掩模撞线机制,用于提高计数精度。结果表明,YOLOv7-GCSF目标检测模型精确率(P)、均值平均精度(m AP_(0.5))分别达到94.2%、98.2%,相比YOLOv7模型分别提高2.3、0.3个百分点,在模型轻量化方面,较YOLOv7模型浮点运算数下降77.5G,模型参数量、模型大小分别下降0.57M和18.88MB;与传统Tracktor和SORT算法相比,改进的Deep SORT算法跟踪准确率分别提高5.0和13.7个百分点;三白瓜及宁夏硒砂瓜计数结果决定系数为0.93、平均计数精度为96.3%、平均绝对误差为0.77。该方法可有效统计西瓜园西瓜数量,为西瓜产量预测提供一种行之有效的技术途径。To address the difficulties in manual counting for the uneven distribution and severe occlusion of watermelons in natural environments,this study utilizes drones and smartphones to collect videos and images,combined with manual annotation to establish a dataset for Sanbai melons and Ningxia selenium sand melons.A watermelon video automatic counting method based on the YOLOv7-GCSF model and an improved DeepSORT algorithm is proposed.The lightweight YOLOv7 model with GhostConv is enhanced with GBS modules,G-ELAN modules,and G-SPPCSPC modules to increase the model’s detection speed.Some ELAN modules are replaced with the C2f module from YOLOv8 to reduce redundant information.The SimAM attention mechanism is introduced into the MP module of the feature fusion layer to construct the MP-SimAM module,which is used to enhance the model's feature extraction capability.The CIoU loss function is replaced with the faster-converging,lower-loss Focal EIoU loss function to increase the model's convergence speed.In video tracking and counting,a mask collision line mechanism is proposed for more accurate counting of Sanbai melons and Ningxia selenium sand melons.The results show that in terms of object detection:the four improvements to the YOLOv7-GCSF model have all enhanced the model’s performance to some extent.Specifically,compared to the YOLOv7 model,the construction of the MP-SimAM module increased accuracy by 1.5 percentage points,indicating a greater focus on Sanbai melons and Ningxia selenium sand melons.The addition of GhostConv reduced the model size by 28.1MB,demonstrating that the construction of GBS,G-ELAN,and G-SPPCSPC modules effectively reduced the model size and improved detection speed.The incorporation of the C2f module reduced the model's floating-point operations(FLOPs)by 77.5 billion,indicating that the model has eliminated most of the redundant information.The addition of the Focal EIoU loss function significantly increased the model’s convergence speed,indicating further enhancement of the model's l

关 键 词：无人机 西瓜 YOLOv7 DeepSORT 目标追踪计数 产量预测 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术] S24[自动化与计算机技术—计算机科学与技术]