This paper describes our approach for the Visual Privacy Task (VPT) of the MediaEval 2014. Video privacy ltering based on privacy-sensitive-object transparency is proposed. The background (hidden behind the object) is estimated by median ltering over time sequence of pixel values. We focus only on the areas labeled as high privacy sensitive (i.e. face). Low and medium privacy areas were rather untouched to keep the most of information about person activities. Despite of simplicity of the proposed method it gives promising performance. The performance is at or slightly above the average among the VPT participants.
The problem of privacy protection in video surveillance
is again concerned in this year's MediaEval Visual Privacy
Task (VPT) [
The disadvantage of covering privacy information is the fact that the person's activities detection of which is crucial for surveillance purposes, are often also hidden or altered. The aim of this research activity is development of the visual ltering method that keeps as much information as possible about person's activities in video while keeping the person's privacy intact.
We propose the ltering that yields to transparency of the privacy sensitive objects. The background (hidden behind the object) estimation is based on computing median over time-sequence of pixel values for each pixel. We have focused only on the areas labeled as high privacy sensitive (i.e. face). Low and medium privacy areas were rather untouched to keep the most of information about person activities. This method is aimed to minimize discomfort of watching ltered video. Thus we utilized only the face position labels from the provided XML metadata. 2.
One of the requirements for the privacy ltering is object
segmentation. In this task, two kinds of segmentations were
at disposal. The rst one, automatic segmentation as
described in [
We examined a simple and straightforward method based
on the ltering that replaces high privacy sensitive pixel
areas by background pixels as depicted in Figure 1. The key
part of the proposed algorithm is proper estimation of the
whole background scene, with the aim to uncover the
background parts that are of high privacy (e.g. face). However
in some scenes, the background can be partially invisible
as depicted in Figure 2. The procedure of the background
estimation is as follows. Time sequence of RGB values of
each pixel is transformed into a time sequence of grayscale
values because of sorting purpose. Then median over each
time sequence is computed. In addition , the foreground
objects, detected by automatic segmentation [
The video sequences were evaluated to ful ll the UI-REF
privacy protection requirements. Overall results of the crowd
evaluation for submitted entries were quali ed in terms of
the following criteria [
The Privacy Protection Level { an average level of privacy protection across all clips.
Level of Intelligibility { the amount of useful information is retined after ltering.
The Appropriateness { aesthetic perceptual appeal to human viewers.
The evaluation scenario is composed the following three streams: Stream 1 For the crowdsourcing evaluation, about 290 workers answered several privacy, intelligibility, and pleasantness related questions for 6 pre-selected videos from the test videos submitted by participants.
Stream 2 A focus group comprising 65 participants (15 females), from Thales, France took part in this evaluation. The majority of the participants were sta from the R&D departments, while the rest were from Management, Security, and other departments.
Stream 3 A focus group comprising 59 participants (22 females), from sectors including R&D, data protection, law enforcement, from around the world took part in this study.
The evaluation results of the proposed lter performance were obtained in the 3 streams according to the VPT 2014 evaluation scenario. The reported results of the test among the VPT 2014 participants, which were evaluated in terms of the de ned criteria, are presented as median score over ten teams. This median serves as a baseline to compare our obtained results. The performance of the proposed approach compared to median results is depicted in Figure 3. Despite of simplicity of the proposed method it gives surprisingly promising performance. The obtained score is at, or slightly above the average in terms of all the three criteria.
The challenging problem is detection and estimation of the partially invisible background as shown in Figure 2. In 70,00% 60,00% 50,00% 40,00% 30,00% 20,00% 10,00% 0,00% intel igibilityscore privacyscore pleasantnessscore UNIZA1
Median1
UNIZA2
Median2
UNIZA3
Median3 our future work, we will focus to automatic detection of face position and use more precise ltering tight around person face contours as well as use of more sophisticated translucency techniques. 6.