自我中心视频中的左右手分割
Left/Right Hand Segmentation in Egocentric Videos
摘要：
可穿戴摄像头允许人们从以用户为中心（第一人称视觉）的角度记录他们的日常活动。由于其有利的位置，可穿戴相机经常捕捉用户的手，并因此可能代表一个有前途的用户-机器交互工具，用于不同的应用。直观的第一人称视觉方法将手部分割作为背景-前景问题来处理，忽略了两个重要的事实：i）手部不是单个“类皮肤”移动元素，而是一对交互的协作实体，ii）近距离手部交互可能导致手到手的遮挡，并且因此创建单个类手部的段。这些事实使正确理解手部运动和相互作用变得复杂。我们的方法扩展了传统的背景-前景策略，通过包括基于角度和位置的麦克斯韦分布的手识别步骤（左-右）。通过利用时间超像素来解决手到手的遮挡。实验结果表明，除了可靠的左/右手分割，我们的方法大大改善了传统的背景前景手分割。
英文摘要：
Wearable cameras allow people to record their daily activities from a user-centered (First Person Vision) perspective. Due to their favorable location, wearable cameras frequently capture the hands of the user, and may thus represent a promising user-machine interaction tool for different applications. Existent First Person Vision methods handle hand segmentation as a background-foreground problem, ignoring two important facts: i) hands are not a single "skin-like" moving element, but a pair of interacting cooperative entities, ii) close hand interactions may lead to hand-to-hand occlusions and, as a consequence, create a single hand-like segment. These facts complicate a proper understanding of hand movements and interactions. Our approach extends traditional background-foreground strategies, by including a hand-identification step (left-right) based on a Maxwell distribution of angle and position. Hand-to-hand occlusions are addressed by exploiting temporal superpixels. The experimental results show that, in addition to a reliable left/right hand-segmentation, our approach considerably improves the traditional background-foreground hand-segmentation.
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。
