7 shed

📦 Segmentation Dataset This repository contains a dataset labeled with Roboflow in YOLOv8 segmentation format, designed for detecting and segmenting different types of terrain surfaces and obstacle negotiability. 📄 Format -Export format: YOLOv8 Segmentation-Number of classes: 10-Number of picture: 340-Annotation source: Roboflow-Annotation type: Masks for segmentation tasks 🏷️ Available Classes | ID | Label | Description |----|-------------|--------------------------------------------|| 0 | `concrete` | Hard surface, pavement or concrete | 1 | `dirtroad` | Dirt road or path | 2 | `grass` | Grass or grassy terrain | 3 | `gravel` | Gravel surface or loose rocky path | 4 | `NS` | Not traversable (Non-Surmountable) | 5 | `S50` | 50% Surmountable slope | 6 | `S75` | 75% Surmountable slope | 7 | `S100` | Fully Surmountable (100%) | 8 | `wood` | Wooden surface These classes are meant to support the training of terrain perception models, especially for legged robots operating in unstructured environments. 📁 Dataset Structure dataset/├── train/ # Training images and labels├── valid/ # Validation images and labels├── test/ # Test images and labels├── data.yaml├── README.dataset.txt └── README.roboflow.txt📦 分割数据集 本仓库包含一个采用Roboflow标注、YOLOv8分割格式的数据集，旨在实现各类地表类型与障碍物通行性的检测与分割任务。 📄 数据格式 - 导出格式：YOLOv8 分割格式 - 类别总数：10类 - 图像总量：340张 - 标注来源：Roboflow - 标注类型：分割任务专用掩码 🏷️ 可用类别 | 编号 | 类别名称 | 类别描述 | |----|-------------|--------------------------------------------| | 0 | `concrete` | 硬质铺装路面或混凝土表面 | | 1 | `dirtroad` | 泥土路或人行小径 | | 2 | `grass` | 草本植被覆盖的草地或地形 | | 3 | `gravel` | 碎石路面或松散岩石小径 | | 4 | `NS` | 无法翻越（不可通行） | | 5 | `S50` | 可翻越坡度为50%的地形 | | 6 | `S75` | 可翻越坡度为75%的地形 | | 7 | `S100` | 100%可翻越的完全可通行地形 | | 8 | `wood` | 木质表面 | 上述类别可用于支撑地形感知模型的训练工作，尤其适配非结构化环境中运行的腿式机器人。 📁 数据集组织结构 dataset/ ├── train/ # 训练集图像与标注文件 ├── valid/ # 验证集图像与标注文件 ├── test/ # 测试集图像与标注文件 ├── data.yaml ├── README.dataset.txt └── README.roboflow.txt