The widespread use of smart computer vision systems in our personal spaces has led to an increased consciousness about the privacy and security risks that these systems pose. On the one hand, we want these systems to assist in our daily lives by understanding their surroundings, but on the other hand, we want them to do so without capturing any sensitive information. Towards this direction, this paper proposes a simple, yet robust privacy-preserving encoder called BDQ for the task of privacy-preserving human action recognition that is composed of three modules: Blur, Difference, and Quantization. First, the input scene is passed to the Blur module to smoothen the edges. This is followed by the Difference module to apply a pixel-wise intensity subtraction between consecutive frames to highlight motion features and suppress obvious high-level privacy attributes. Finally, the Quantization module is applied to the motion difference frames to remove the low-level privacy attributes. The BDQ parameters are optimized in an end-to-end fashion via adversarial training such that it learns to allow action recognition attributes while inhibiting privacy attributes. Our experiments on three benchmark datasets show that the proposed encoder design can achieve state-of-the-art trade-off when compared with previous works. Furthermore, we show that the trade-off achieved is at par with the DVS sensor-based event cameras. Code available at: https://github.com/suakaw/BDQ_PrivacyAR.
翻译:我们个人空间广泛使用智能计算机视觉系统,使人们更加认识到这些系统带来的隐私和安全风险。一方面,我们希望这些系统通过了解周围环境协助我们的日常生活,但另一方面,我们希望它们这样做,而不捕捉任何敏感信息。朝这个方向看,本文件建议使用一个简单而有力的隐私保护编码器,称为BDQ,用于执行保护隐私的人类行动识别任务,由三个模块组成:Blur、差异和量化。首先,输入场被传送到Blor模块以平滑边缘。接下来是“差异”模块,以便在连续框架之间应用一条分解式的强度减法,以突出运动特征并压制明显的高层次隐私属性。最后,本文件建议对运动差异框架应用定量化模块,以消除低层次的隐私属性。BDQ参数通过对端对端前端前端的内端训练得到优化,从而在抑制隐私属性的同时学习行动识别属性。我们用三个基调的 D- 测试在三个基调的 D- 交易时,我们用 D- 测试 D- 的 Dser 展示了先前的 交易中, 显示我们所建的 Dseral- seral 显示的工程。