Moving Object Segmentation (MOS), a crucial task in computer vision, has numerous applications such as surveillance, autonomous driving, and video analytics. Existing datasets for moving object segmentation mainly focus on RGB or Lidar videos, but lack additional event information that can enhance the understanding of dynamic scenes. To address this limitation, we propose a novel dataset, called DSEC-MOS. Our dataset includes frames captured by RGB cameras embedded on moving vehicules and incorporates event data, which provide high temporal resolution and low-latency information about changes in the scenes. To generate accurate segmentation mask annotations for moving objects, we apply the recently emerged large model SAM - Segment Anything Model - with moving object bounding boxes from DSEC-MOD serving as prompts and calibrated RGB frames, then further revise the results. Our DSEC-MOS dataset contains in total 16 sequences (13314 images). To the best of our knowledge, DSEC-MOS is also the first moving object segmentation dataset that includes event camera in autonomous driving. Project Page: https://github.com/ZZY-Zhou/DSEC-MOS.

翻译：运动物体分割（Moving Object Segmentation，MOS）是计算机视觉中的一项关键任务，广泛应用于监控、自动驾驶和视频分析等领域。现有的运动物体分割数据集主要聚焦于RGB或激光雷达视频，但缺乏能够增强动态场景理解的额外事件信息。为解决这一局限性，我们提出一种名为DSEC-MOS的新型数据集。该数据集包含由搭载于移动车辆上的RGB相机捕获的帧，并融入了事件数据，这些数据提供了关于场景变化的高时间分辨率和低延迟信息。为生成精确的运动物体分割掩码标注，我们应用近期兴起的大型模型SAM（Segment Anything Model），以DSEC-MOD中的运动物体边界框作为提示，结合校准后的RGB帧，并进一步修正结果。我们的DSEC-MOS数据集总计包含16个序列（13314张图像）。据我们所知，DSEC-MOS也是首个在自动驾驶中纳入事件相机的运动物体分割数据集。项目主页：https://github.com/ZZY-Zhou/DSEC-MOS。