TUB-IRML at MediaEval 2014 Visual Privacy Task: Privacy Filtering through Blurring and Color Remapping
نویسندگان
چکیده
This paper describes the participation of the TUB-IRML group to the MediaEval 2014 Visual Privacy task. We present a method for privacy protection of individuals in surveillance videos. In order to achieve this, our method obscures both shape and appearance of identity-related regions through blurring and color remapping. The intelligibility is preserved by displaying edges and anomalous events are hinted at by special colors. The experimental results obtained on surveillance videos show that our method considerably outperforms other participating teams in terms of privacy score. However, the drawback is that the results in terms of intelligibility are below average.
منابع مشابه
TUB-IRML at MediaEval 2014 Violent Scenes Detection Task: Violence Modeling through Feature Space Partitioning
This paper describes the participation of the TUB-IRML group to the MediaEval 2014 Violent Scenes Detection (VSD) affect task. We employ lowand mid-level audio-visual features fused at the decision level. We perform feature space partitioning of training samples through k -means clustering and train a different model for each cluster. These models are then used to predict the violence level of ...
متن کاملOverview of the MediaEval 2014 Visual Privacy Task
This paper presents an overview of the Visual Privacy Task (VPT) of MediaEval 2014, its objectives, related dataset, and evaluation approaches. Participants in this task were required to implement a privacy filter or a combination of filters to protect various personal information regions in video sequences as provided. The challenge was to achieve an adequate balance between the degree of priv...
متن کاملUNIZA @ Mediaeval 2014 Visual Privacy Task: Object Transparency Approach
This paper describes our approach for the Visual Privacy Task (VPT) of the MediaEval 2014. Video privacy filtering based on privacy-sensitive-object transparency is proposed. The background (hidden behind the object) is estimated by median filtering 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 rat...
متن کاملTUB @ MediaEval 2014 Visual Privacy Task: Reversible Scrambling on Foreground Masks
This paper describes our participation in the Visual Privacy Task of MediaEval 2014, which aims to obscure human occurrence in image sequences. As a result the recorded person should be unrecognisable, but if needed the obscured areas can be recovered. We use an approach which models the background and pseudo-randomly scrambles pixels within disjunct foreground areas. This technique is reversib...
متن کاملMediaEval 2014 Visual Privacy Task: De-identification and Re-identification of Subjects in CCTV
We present in this paper a method for de-identification of persons in a CCTV environment which uses different levels of filtering depending on the privacy sensitivity of the region of interest. The proposed method tries to tackle the problem of re-identifying (de-filtering) a person which has committed a crime. Validation of the method shows low results in privacy as a result of the identity of...
متن کامل