Impacts of Image Obfuscation on Fine-grained Activity Recognition in Egocentric Video.
Impacts of Image Obfuscation on Fine-grained Activity Recognition in Egocentric Video.
复制标题
图像混淆对自我中心视频中细粒度活动识别的影响。
DOI：
10.1109/percomworkshops53856.2022.9767447
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Alshurafa,Nabil
中科院分区：
文献类型：
--
作者：
Shahi,Soroush;Alharbi,Rawan;Gao,Yang;Sen,Sougata;Katsaggelos,AggelosK;Hester,Josiah;Alshurafa,Nabil
近年来，由于RGB图像提供的丰富信息，从以自我为中心的视觉中自动检测和验证细粒度的人类活动得到了越来越多的关注。然而，辨别需要多少丰富的信息来可靠地检测感兴趣的活动并不容易。图像中的手和物体的定位已被证明有助于区分与手相关的细粒度活动。本文描述了一种基于手对象的掩模混淆方法（HOBM）的设计，并评估其对细粒度人体活动的自动识别效果。HOBM屏蔽除手和手中物体以外的所有像素，提高了对个人用户信息（PUI）的保护。我们使用一个具有86个类标签的公共自我中心活动数据集测试了一个经过模糊处理和未经模糊处理训练的深度学习模型，并实现了几乎相似的分类准确率（模糊处理降低了2%）。我们的研究结果表明，它是可以保护PUI在较小的图像效用成本（损失的准确性）。
Automated detection and validation of fine-grained human activities from egocentric vision has gained increased attention in recent years due to the rich information afforded by RGB images. However, it is not easy to discern how much rich information is necessary to detect the activity of interest reliably. Localization of hands and objects in the image has proven helpful to distinguishing between hand-related fine-grained activities. This paper describes the design of a hand-object-based mask obfuscation method (HOBM) and assesses its effect on automated recognition of fine-grained human activities. HOBM masks all pixels other than the hand and object in-hand, improving the protection of personal user information (PUI). We test a deep learning model trained with and without obfuscation using a public egocentric activity dataset with 86 class labels and achieve almost similar classification accuracies (2% decrease with obfuscation). Our findings show that it is possible to protect PUI at smaller image utility costs (loss of accuracy).