可還原的分級式隱私保護視訊監視系統

Abstract

現在因為科技的發達，大量數位攝影機遍佈在公共場所以利調查犯罪行為。但另一方面，大量的攝影機對一般人會有隱私被侵犯的疑慮。在本論文中，我們提出了一個可保護隱私的視訊監視系統，並且可以依照使用者的權力給予適當的保護程度。 首先，我們分割出影片中具有隱私的區域(Privacy-sensitive Region)，針對此區域我們使用數個虛擬隨機排列(Pseudo-randomly Permutation)函式使之越來越模糊。在使用者端我們使用一個身份驗證系統來確認使用者的身份，使用者輸入密鑰本系統即可針對此密鑰還原對應的隱私保護步驟，權力越高者能夠看到越清楚的影片。實驗結果顯示，使用者權力由低到高所看到的隱私保護程度是逐漸的由雜亂到非常清楚。並且此方法可以應用在現有的視訊壓縮標準上且對壓縮效率不會有太大影響。

In recent years, video surveillance system has been widely equipped for crime investigation and deterrence in an attempt to reduce the occurrence of crime events. But the widespread cameras may invade the privacy of innocent persons. In this thesis, we provide a scalable and recoverable video privacy protection system. First, privacy-sensitive regions are segmented. Then, three permutation functions are employed for scalable and recoverable video privacy protection. Users with different authorization levels will get different authentication keys. Thus, users with the lowest authorization level can only watch the video with the privacy-sensitive region scrambled dramatically and users with the highest authorization level can investigate the original video. Furthermore, the proposed video privacy protection system can be embedded in current video standard codecs with the compression rate being reduced slightly.