蚊子种类检测数据集13166张存在增强处理yolovoccoco三种标注方式图像尺寸:512*512类别数量:17类训练集图像数量:11520; 验证集图像数量:1097 测试集图像数量:549类别名称: 每一类图像数 每一类标注数Aedes_albobictus-白纹伊蚊468,468Aedes_aegypti-埃及伊蚊2860,2860Anopheles jamesii-詹姆斯按蚊480,480Anopheles_barbirostris-须喙按蚊477,477Anopheles_culicifacies-库态按蚊484,485Anopheles_stephensi-斯氏按蚊473,473Anopheles_subpictus-浅色按蚊477,477Anopheles_vagus-迷走按蚊401,401Armigeres_subalbatus-骚扰阿蚊476,476Aedes_vittatus-白线伊蚊480,480Culex_bitaeniorhynchus-二带喙库蚊477,477Culex_quinquefasciatus-致倦库蚊949,949Culex_tritaeniorhynchus-三带喙库蚊476,476Culex_gelidus-寒库蚊470,470Mansonia indiana-印度曼蚊480,480Mansonia_uniformis-常型曼蚊474,475Culex_vishnui-韦氏库蚊2760,2763image num: 13166模型代码采用 YOLOv11n 网络训练训练轮次80 个 epoch提供全部训练 测试源代码训练精度 mAP 效果如图所示PyQt5 界面功能界面使用 PyQt5 开发提供全部源码.ui、.qrc、.py 及图标文件支持图片检测、视频检测、摄像头实时检测界面实时显示目标位置、目标总数、置信度等信息蚊子种类检测数据集一、数据集参数表项目详情数据集名称蚊子种类检测数据集图像总数量13166张含数据增强处理图像分辨率512×512标注格式YOLO、VOC、COCO 三种格式类别总数17类数据集划分训练集11520张验证集1097张测试集549张Aedes_albobictus白纹伊蚊图像数468标注数468Aedes_aegypti埃及伊蚊图像数2860标注数2860Anopheles jamesii詹姆斯按蚊图像数480标注数480Anopheles_barbirostris须喙按蚊图像数477标注数477Anopheles_culicifacies库态按蚊图像数484标注数485Anopheles_stephensi斯氏按蚊图像数473标注数473Anopheles_subpictus浅色按蚊图像数477标注数477Anopheles_vagus迷走按蚊图像数401标注数401Armigeres_subalbatus骚扰阿蚊图像数476标注数476Aedes_vittatus白线伊蚊图像数480标注数480Culex_bitaeniorhynchus二带喙库蚊图像数477标注数477Culex_quinquefasciatus致倦库蚊图像数949标注数949Culex_tritaeniorhynchus三带喙库蚊图像数476标注数476Culex_gelidus寒库蚊图像数470标注数470Mansonia indiana印度曼蚊图像数480标注数480Mansonia_uniformis常型曼蚊图像数474标注数475Culex_vishnui韦氏库蚊图像数2760标注数2763训练网络YOLOv11n训练轮次80 epoch配套文件完整数据集、三种格式标注文件、训练测试源码、训练权重、PyQt5界面全套源码.ui/.qrc/.py/图标界面功能图片检测、视频检测、摄像头实时检测实时展示目标位置、数量、置信度交易说明标价即售价24小时内发货运行环境Python、OpenCV、PyQt5、PyTorch适配系统Windows、Linux二、YOLOv11 训练测试代码1. 环境安装命令pipinstallultralytics opencv-python torch2. 数据集配置文件mosquito_17class.yamlpath:./mosquito_datasettrain:images/trainval:images/valtest:images/testnc:17names:[Aedes_albobictus,Aedes_aegypti,Anopheles_jamesii,Anopheles_barbirostris,Anopheles_culicifacies,Anopheles_stephensi,Anopheles_subpictus,Anopheles_vagus,Armigeres_subalbatus,Aedes_vittatus,Culex_bitaeniorhynchus,Culex_quinquefasciatus,Culex_tritaeniorhynchus,Culex_gelidus,Mansonia_indiana,Mansonia_uniformis,Culex_vishnui]3. 完整训练代码fromultralyticsimportYOLOif__name____main__:# 加载YOLOv11n预训练模型modelYOLO(yolov11n.pt)# 启动训练train_resultsmodel.train(datamosquito_17class.yaml,epochs80,imgsz512,batch16,device0,workers4,projectmosquito_detection,nameyolov11n_mosquito,patience15,augmentTrue,hsv_h0.015,hsv_s0.7,hsv_v0.4,fliplr0.5,flipud0.2,mosaic1.0)# 模型验证metricsmodel.val()print(fmAP0.5:{metrics.box.map50:.3f})print(fmAP0.5-0.95:{metrics.box.map:.3f})# 单图测试推理model.predict(test_mosquito.jpg,saveTrue,conf0.25)4. 通用测试推理代码fromultralyticsimportYOLO# 加载训练好的权重modelYOLO(best.pt)# 图片推理resultsmodel.predict(test.jpg,conf0.25,saveTrue)total_num0forresinresults:forboxinres.boxes:total_num1cls_idint(box.cls[0])conffloat(box.conf[0])x1,y1,x2,y2map(int,box.xyxy[0])cls_namemodel.names[cls_id]print(f蚊虫种类{cls_name}| 置信度{conf:.2f}| 坐标{x1},{y1},{x2},{y2})print(f检测到蚊虫总数{total_num})5. PyQt5 可视化界面完整代码fromPyQt5.QtWidgetsimportQApplication,QMainWindow,QFileDialogfromPyQt5.uicimportloadUifromultralyticsimportYOLOimportcv2importsysclassMosquitoDetectUI(QMainWindow):def__init__(self):super().__init__()loadUi(mosquito_ui.ui,self)self.modelYOLO(best.pt)# 绑定功能按钮self.btn_img.clicked.connect(self.detect_image)self.btn_video.clicked.connect(self.detect_video)self.btn_camera.clicked.connect(self.detect_camera)defdetect_image(self):path,_QFileDialog.getOpenFileName()ifpath:resultsself.model(path,conf0.25)self.show_result(results)defdetect_video(self):path,_QFileDialog.getOpenFileName()ifpath:capcv2.VideoCapture(path)whilecap.isOpened():ret,framecap.read()ifnotret:breakresultsself.model(frame,conf0.25)self.show_result(results)cv2.waitKey(1)cap.release()defdetect_camera(self):capcv2.VideoCapture(0)whilecap.isOpened():ret,framecap.read()ifnotret:breakresultsself.model(frame,conf0.25)self.show_result(results)cv2.waitKey(1)cap.release()defshow_result(self,results):total0forresinresults:forboxinres.boxes:total1x1,y1,x2,y2map(int,box.xyxy[0])cls_idxint(box.cls[0])conffloat(box.conf[0])nameself.model.names[cls_idx]print(f种类{name}置信度{conf:.2f}位置{x1},{y1},{x2},{y2})print(f当前检测总数{total}\n)if__name____main__:appQApplication(sys.argv)windowMosquitoDetectUI()window.show()sys.exit(app.exec_())三、应用场景病媒生物监测疾控中心、卫健部门开展蚊虫种群普查识别不同传播类蚊虫防控登革热、疟疾等虫媒传染病。消杀作业辅助小区、公园、养殖场、疫区精准识别蚊虫种类制定针对性消杀方案。实验室昆虫分类科研院所、生物实验室自动化完成蚊虫样本种类识别提升分类效率。环境智能监测户外监测设备、智慧园区接入检测模型实时统计蚊虫种类与数量。农林卫生防护农田、林区蚊虫监测减少蚊虫对人畜侵扰保障农林作业环境安全。出入境检疫检测口岸检疫场景快速识别外来蚊虫品种防范外来物种及疫病入侵。