ChangeSim 在线场景变化检测数据集

ChangeSim 是主要用于在线场景变化检测的数据集。通过在模拟环境中收集数据，研究人员获得多模态传感器数据和精确的 ground truth 标注，如 RGB 图像、深度图像、语义分割、变化分割、相机姿势和 3D 重建。这些模拟环境存在非目标变化，如空气浊度和光照条件变化，以及工业室内环境中的目标物体变化。

ChangeSim is a dataset primarily designed for online scene change detection. By collecting data in simulated environments, researchers obtain multimodal sensor data and precise ground truth annotations, such as RGB images, depth images, semantic segmentation, change segmentation, camera poses, and 3D reconstructions. These simulated environments feature non-object changes including air turbidity and varying lighting conditions, as well as changes to target objects within industrial indoor settings.

搜集汇总

背景与挑战

背景概述

ChangeSim是一个用于在线场景变化检测的模拟数据集，提供RGB图像、深度图像、语义分割等多种数据类型，支持端到端的模型开发。数据集包含目标和非目标变化场景，适用于复杂环境下的变化检测研究。