BusyHands：面向装配任务语义分割的手工具交互数据库
BusyHands: A Hand-Tool Interaction Database for Assembly Tasks Semantic Segmentation
摘要：
视觉分割最近取得了巨大的进步，为各种场景类型提供了现成的解决方案，包括人手和其他身体部位。然而，在执行复杂任务（例如手动装配）时，仍然严重缺乏人手的分割。从工具、工件、背景和其他身体部位分割手是非常困难的，因为自遮挡和复杂的手握和姿势。在本文中，我们介绍了BusyHands，这是一个大型的开放数据集，包含了执行13种不同的基于工具的装配任务的手的像素级注释图像，这些任务来自真实世界的捕获和虚拟世界的渲染。我们的第一个同类数据集中包含了7906个样本，其中包括从Kinect V2相机和Blender获得的RGB和深度图像。我们评估了几个国家的最先进的语义分割方法对我们的数据集作为一个建议的性能基准。
英文摘要：
Visual segmentation has seen tremendous advancement recently with ready solutions for a wide variety of scene types, including human hands and other body parts. However, focus on segmentation of human hands while performing complex tasks, such as manual assembly, is still severely lacking. Segmenting hands from tools, work pieces, background and other body parts is extremely difficult because of self-occlusions and intricate hand grips and poses. In this paper we introduce BusyHands, a large open dataset of pixel-level annotated images of hands performing 13 different tool-based assembly tasks, from both real-world captures and virtual-world renderings. A total of 7906 samples are included in our first-in-kind dataset, with both RGB and depth images as obtained from a Kinect V2 camera and Blender. We evaluate several state-of-the-art semantic segmentation methods on our dataset as a proposed performance benchmark.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
