Underwater images collected by an Autonomous Surface Vehicle in St-Leu, Réunion - 2024-03-13

This dataset was collected by an Autonomous Surface Vehicle in St-Leu, Réunion - 2024-03-13. Underwater or aerial images collected by scientists or citizens can have a wide variety of use for science, management, or conservation. These images can be annotated and shared to train IA models which can in turn predict the objects on the images. We provide a set of tools (hardware and software) to collect marine data, predict species or habitat, and provide maps. This dataset is part of larger collection referencing numerous underwater and aerial images Seatizen Altas. Methods, tools and scientific objectives are also described in a dedicated data paper. Image acquisition This session has 21.93 GB of MP4 files, which were trimmed into 6033 frames (at 2997/1000 fps). The frames are georeferenced. 99.9% of these extracted images are useful and 0.1% are useless, according to predictions made by Jacques model. Multilabel predictions have been made on useful frames using DinoVd'eau model. GPS information: The data was processed with a PPK workflow to achieve centimeter-level GPS accuracy. Base : Files coming from rtk a GPS-fixed station or any static positioning instrument which can provide with correction frames. Device GPS : Emlid Reach M2 Quality of our data - Q1: 94.64 %, Q2: 5.34 %, Q5: 0.02 % Bathymetry The data are collected using a single-beam echosounder ETC 400. We only keep the values which have a GPS correction in Q1. We keep the points that are the waypoints. We keep the raw data where depth was estimated between 0.2 m and 10.0 m deep. The data are first referenced against the WGS84 ellipsoid. Then we apply the local geoid if available. At the end of processing, the data are projected into a homogeneous grid to create a raster and a shapefiles. The size of the grid cells is 0.111 m. The raster and shapefiles are generated by linear interpolation. The 3D reconstruction algorithm is ballpivot. Photogrammetry OpenDroneMap software was used to create an orthophoto from the raw images. Here is the list of parameters different from the default values for the orthophoto generation. For more details, you can read the log.json file or the 000_photogrammatry_report.pdf report. {'auto_boundary': True, 'cog': True, 'fast_orthophoto': True, 'feature_quality': 'ultra', 'gps_accuracy': 0.1, 'max_concurrency': 50, 'optimize_disk_space': True, 'orthophoto_resolution': 0.1, 'rolling_shutter': True, 'skip_3dmodel': True} Generic folder structure YYYYMMDD_COUNTRYCODE-optionalplace_device_session-number ├── DCIM : folder to store videos and photos depending on the media collected. ├── GPS : folder to store any positioning related file. If any kind of correction is possible on files (e.g. Post-Processed Kinematic thanks to rinex data) then the distinction between device data and base data is made. If, on the other hand, only device position data are present and the files cannot be corrected by post-processing techniques (e.g. gpx files), then the distinction between base and device is not made and the files are placed directly at the root of the GPS folder. │ ├── BASE : files coming from rtk station or any static positioning instrument. │ └── DEVICE : files coming from the device. ├── METADATA : folder with general information files about the session. ├── PROCESSED_DATA : contain all the folders needed to store the results of the data processing of the current session. │ ├── BATHY : output folder for bathymetry raw data extracted from mission logs. │ ├── FRAMES : output folder for georeferenced frames extracted from DCIM videos. │ ├── IA : destination folder for image recognition predictions. │ └── PHOTOGRAMMETRY : destination folder for reconstructed models in photogrammetry. └── SENSORS : folder to store files coming from other sources (bathymetry data from the echosounder, log file from the autopilot, mission plan etc.). Software All the raw data was processed using our worflow. All predictions were generated by our inference pipeline. You can find all the necessary scripts to download this data in this repository. Enjoy your data with SeatizenDOI!本数据集由自主水面载具（Autonomous Surface Vehicle）于2024年3月13日在留尼旺圣勒（St-Leu, Réunion）采集。 科学家与民众采集的水下及航空影像，可广泛应用于科学研究、资源管理与生态保护领域。此类影像经标注并共享后，可用于训练人工智能（AI）模型，进而实现影像内目标的自动识别与预测。本团队提供一套软硬件工具集，可用于海洋数据采集、物种/生境预测及地图生成。 本数据集隶属于涵盖大量水下与航空影像的大型数据集集合Seatizen Atlas。相关研究方法、工具集及科学目标已在专属数据论文中详述。 图像采集 本次采集任务包含21.93 GB的MP4视频文件，经剪辑后提取得到6033帧图像（帧率为2997/1000 fps）。所有提取帧均已完成地理配准。经Jacques模型预测，本次提取的影像中99.9%为有效帧，仅0.1%为无效帧。针对有效帧，已通过DinoVd'eau模型完成多标签分类预测。 GPS定位信息 本数据集采用后处理运动学（PPK）工作流进行处理，实现了厘米级的GPS定位精度。 基准站数据：来自固定GPS基准站或可提供校正帧的静态定位设备的文件。 设备GPS：采用Emlid Reach M2型号设备。 数据质量占比：Q1级94.64%，Q2级5.34%，Q5级0.02%。 水深测量 本次水深数据采用单波束测深仪ETC 400采集。仅保留Q1等级且带有GPS校正信息的测量值，保留所有航点数据点，并筛选出水深估算值介于0.2米至10.0米之间的原始数据。数据首先以WGS84椭球面为基准进行参考校准，随后若存在本地大地水准面，则应用本地大地水准面模型进行转换。处理完成后，数据被投影至统一格网中，生成栅格文件与形状文件（shapefiles），格网单元尺寸为0.111米。栅格与形状文件通过线性插值法生成，三维重建算法采用ballpivot算法。 摄影测量 本研究采用OpenDroneMap软件基于原始影像生成正射影像。以下为正射影像生成过程中与默认参数不同的配置项： {'auto_boundary': 启用自动边界, 'cog': 启用航向跟踪, 'fast_orthophoto': 启用快速正射影像模式, 'feature_quality': 'ultra'（超高特征质量）, 'gps_accuracy': 0.1（GPS定位精度）, 'max_concurrency': 50（最大并发线程数）, 'optimize_disk_space': 启用磁盘空间优化, 'orthophoto_resolution': 0.1（正射影像分辨率）, 'rolling_shutter': 启用卷帘快门校正, 'skip_3dmodel': 跳过三维模型生成} 如需了解更多细节，可查阅log.json文件或000_photogrammetry_report.pdf报告。 通用文件夹结构 本数据集采用如下命名规则：YYYYMMDD_COUNTRYCODE-可选地点_设备_会话-编号 ├── DCIM：用于存储采集得到的视频与照片文件，具体内容取决于采集的媒体类型。 ├── GPS：用于存储所有与定位相关的文件。若文件可通过后处理运动学（PPK，如基于rinex数据）进行校正，则需区分基准站数据与设备数据；若仅存在设备定位数据且无法通过后处理技术校正（如gpx文件），则无需区分基准站与设备数据，文件直接放置于GPS文件夹根目录。 │ ├── BASE：存放来自RTK基准站或静态定位设备的文件。 │ └── DEVICE：存放来自采集设备的定位文件。 ├── METADATA：用于存储本次采集任务的通用信息文件。 ├── PROCESSED_DATA：用于存储本次采集任务的数据处理结果，包含以下子文件夹： │ ├── BATHY：存储从任务日志中提取的水深测量原始数据的输出目录。 │ ├── FRAMES：存储从DCIM文件夹视频中提取的地理配准帧图像的输出目录。 │ ├── IA：存储图像识别预测结果的目标目录。 │ └── PHOTOGRAMMETRY：存储摄影测量重建模型的目标目录。 └── SENSORS：用于存储其他来源的文件（如测深仪采集的水深数据、自动驾驶仪日志文件、任务规划文件等）。 软件工具 所有原始数据均通过本团队自研工作流进行处理，所有预测结果均由本团队的推理管线生成。您可在本代码仓库中获取下载该数据集所需的全部脚本。祝您使用SeatizenDOI数据集愉快！