智慧灾害识别-山体滑坡与落石灾害检测数据集山体滑坡与落石灾害检测数据集含7900张无人机航拍及地面实拍图像总计17888个精准标注框。覆盖山地地形与道路周边场景聚焦地质灾害对基础设施影响的视觉识别。共2个标签类别landslide滑坡共7765个标注分布于7066张图像中rockfall落石共10123个标注分布于2251张图像中。YOLO格式即拿即用已划分训练验证测试集解压即可对接训练流程。适合地质灾害监测、道路巡检、遥感图像分析等科研与项目场景。山体滑坡与落石灾害检测数据集数据集信息表项目详情数据集名称山体滑坡与落石灾害检测数据集图像总数量7900张无人机航拍地面实拍总标注框数量17888个标注格式YOLO格式已划分训练/验证/测试集类别数量2类采集场景山地地形、道路周边地质灾害基础设施影响识别类别标注统计landslide(滑坡)7066张图像7765个标注rockfall(落石)2251张图像10123个标注适用场景地质灾害监测、道路巡检、遥感图像分析、科研项目训练关键词山体滑坡落石地质灾害无人机航拍道路灾害巡检遥感目标检测灾害应急YOLO数据集数据集yaml配置 rockslide.yamlnc:2names:0:landslide1:rockfalltrain:./datasets/rock_slide/images/trainval:./datasets/rock_slide/images/valtest:./datasets/rock_slide/images/testYOLOv11简易训练代码 train_rock_slide.pyfromultralyticsimportYOLOif__name____main__:#加载预训练权重modelYOLO(yolo11n.pt)train_resmodel.train(datarockslide.yaml,epochs70,imgsz640,batch8,device0,workers2,patience10,conf0.25,iou0.45,projectgeological_disaster,namelandslide_rockfall_exp)#模型评估metricmodel.val()print(fmAP50:{metric.box.map50}, mAP50‑95:{metric.box.map})#推理测试model.predict(source./test_imgs,saveTrue,conf0.3)PyQt5简易推理GUI代码 rock_slide_gui.pyimportsysimportcv2fromPyQt5.QtWidgetsimport*fromPyQt5.QtGuiimport*fromPyQt5.QtCoreimport*fromultralyticsimportYOLOclassGeoDisasterWindow(QMainWindow):def__init__(self):super().__init__()self.setWindowTitle(山体滑坡落石灾害检测系统)self.resize(1100,750)self.modelYOLO(./weights/best.pt)self.img_labelQLabel()self.img_label.setFixedSize(600,550)self.btn_imgQPushButton(打开图片检测)self.btn_img.clicked.connect(self.open_img)self.tableQTableWidget()self.table.setColumnCount(4)self.table.setHorizontalHeaderLabels([序号,目标类别,置信度,坐标框])left_layoutQVBoxLayout()left_layout.addWidget(self.img_label)left_layout.addWidget(self.table)right_layoutQVBoxLayout()right_layout.addWidget(self.btn_img)main_layoutQHBoxLayout()main_layout.addLayout(left_layout)main_layout.addLayout(right_layout)wQWidget()w.setLayout(main_layout)self.setCentralWidget(w)defopen_img(self):file_path,_QFileDialog.getOpenFileName(self,选择灾害图片,,*.jpg *.jpeg *.png)ifnotfile_path:returnresultself.model.predict(sourcefile_path,conf0.3,saveFalse)[0]imgcv2.imread(file_path)imgcv2.cvtColor(img,cv2.COLOR_BGR2RGB)self.table.setRowCount(0)foridx,boxinenumerate(result.boxes):cls_nameresult.names[int(box.cls)]conffloat(box.conf)x1,y1,x2,y2map(int,box.xyxy[0])cv2.rectangle(img,(x1,y1),(x2,y2),(255,0,0),2)cv2.putText(img,f{cls_name}:{conf:.2f},(x1,y1-6),cv2.FONT_HERSHEY_SIMPLEX,0.5,(255,0,0),1)rowself.table.rowCount()self.table.insertRow(row)self.table.setItem(row,0,QTableWidgetItem(str(idx1)))self.table.setItem(row,1,QTableWidgetItem(cls_name))self.table.setItem(row,2,QTableWidgetItem(f{conf:.2f}))self.table.setItem(row,3,QTableWidgetItem(f[{x1},{y1},{x2},{y2}]))qimageQImage(img.data,img.shape[1],img.shape[0],QImage.Format_RGB888)self.img_label.setPixmap(QPixmap.fromImage(qimage).scaled(self.img_label.size(),Qt.KeepAspectRatio))if__name____main__:appQApplication(sys.argv)winGeoDisasterWindow()win.show()sys.exit(app.exec_())环境安装pipinstallultralytics opencv-python pyqt5备选数据集标题中文无人机航拍山体滑坡落石地质灾害YOLO检测数据集山地道路周边滑坡‑落石灾害目标检测数据集7900张面向道路地质巡检滑坡落石灾害视觉检测数据集