SPREAD: A Large-scale, High-fidelity Synthetic Dataset for Multiple Forest Vision Tasks (Part I)

This page only provides the ground-level image dataset. For the drone-view image dataset, please visit SPREAD: A Large-scale, High-fidelity Synthetic Dataset for Multiple Forest Vision Tasks (Part II). For the point clouds, please visit SPREAD: A Large-scale, High-fidelity Synthetic Dataset for Multiple Forest Vision Tasks (Part III). The dataset contains ground-level RGB images, depth maps, semantic segmentation labels, and instance segmentation labels collected from different scenes. Data from each scene is stored in a separate .7z file, along with a color_palette.xlsx file, which contains the RGB_id and corresponding RGB values. All files follow the naming convention: {central_tree_id}_{timestamp}, where {central_tree_id} represents the ID of the tree centered in the image, which is typically in a prominent position, and timestamp indicates the time when the data was collected. Specifically, each 7z file includes the following folders: rgb: This folder contains the RGB images (PNG) of the scenes and their metadata (TXT). The metadata describes the weather conditions and the world time when the image was captured. An example metadata entry is: Weather:Snow_Blizzard,Hour:10,Minute:56,Second:36. depth_pfm: This folder contains absolute depth information of the scenes, which can be used to reconstruct the point cloud of the scene through reprojection. semantic_segmentation: This folder contains grayscale images representing semantic segmentation labels, where 1 indicates tree trunks and 0 represents other elements. instance_segmentation: This folder stores instance segmentation labels (PNG) for each tree in the scene, along with metadata (TXT) that maps tree_id to RGB_id. The tree_id can be used to look up detailed information about each tree in obj_info_final.xlsx, while the RGB_id can be matched to the corresponding RGB values in color_palette.xlsx. This mapping allows for identifying which tree corresponds to a specific color in the segmentation image. obj_info_final.xlsx: This file contains detailed information about each tree in the scene, such as position, scale, species, and various parameters, including trunk diameter (in cm), tree height (in cm), and canopy diameter (in cm). landscape_info.txt: This file contains the ground location information within the scene, sampled every 0.5 meters. For forest datasets: birch_forest, broadleaf_forest, burned_forest, rainforest and redwood_forest, there's an additional folder called coco_annotation where we generated the COCO-format annotation files (.json) for each image. ⚠️: 7z files that begin with "!" indicate that the RGB values in the images within the instance_segmentation folder cannot be found in color_palette.xlsx. Consequently, this prevents matching the trees in the segmentation images to their corresponding tree information, which may hinder the application of the dataset to certain tasks. This issue is related to a bug in Colossium/AirSim, which has been reported in link1 and link2.本页面仅提供地面视角图像数据集。 如需获取无人机视角图像数据集，请访问《SPREAD：面向多森林视觉任务的大规模高保真合成数据集（第二部分）》。 如需获取点云数据集，请访问《SPREAD：面向多森林视觉任务的大规模高保真合成数据集（第三部分）》。 本数据集包含从不同场景采集的地面RGB图像、深度图、语义分割标签与实例分割标签。每个场景的数据均存储于独立的.7z压缩文件中，同时附带一个color_palette.xlsx文件，该文件包含RGB_id及其对应的RGB色彩值。 所有文件遵循命名格式：{central_tree_id}_{timestamp}，其中{central_tree_id}代表图像中心突出位置的目标树木ID，timestamp表示数据采集的时间戳。 具体而言，每个.7z压缩文件包含以下文件夹： rgb：该文件夹包含场景的RGB图像（PNG格式）及其元数据（TXT格式）。元数据用于描述图像拍摄时的天气状况与世界时间，示例元数据条目为：Weather:Snow_Blizzard,Hour:10,Minute:56,Second:36。 depth_pfm：该文件夹包含场景的绝对深度信息，可通过重投影操作重建场景点云。 semantic_segmentation：该文件夹包含代表语义分割标签的灰度图像，其中像素值1代表树干，0代表其他元素。 instance_segmentation：该文件夹存储场景中每棵树木的实例分割标签（PNG格式），以及用于映射tree_id与RGB_id的元数据（TXT格式）。tree_id可用于在obj_info_final.xlsx中查询每棵树木的详细信息，而RGB_id则可与color_palette.xlsx中的对应RGB色彩值匹配，以此确定分割图像中特定色彩所对应的树木。 obj_info_final.xlsx：该文件包含场景中每棵树木的详细信息，例如位置、缩放比例、物种，以及各类参数，包括树干直径（单位：厘米）、树高（单位：厘米）与冠幅直径（单位：厘米）。 landscape_info.txt：该文件包含场景内的地面位置信息，采样间隔为0.5米。 针对白桦林（birch_forest）、阔叶林（broadleaf_forest）、火烧林（burned_forest）、热带雨林（rainforest）与红杉林（redwood_forest）这几类森林数据集，还额外设有一个coco_annotation文件夹，其中为每张图像生成了COCO格式标注文件（.json格式）。 ⚠️：文件名以“!”开头的.7z压缩文件，其instance_segmentation文件夹内图像的RGB值无法在color_palette.xlsx中找到，因此无法将分割图像中的树木匹配至对应的树木信息，可能会阻碍该数据集在部分任务中的应用。该问题与Colossium/AirSim中的一个漏洞相关，相关报告已发布于link1与link2。