Source Camera Verification from Strongly Stabilized Videos
This addresses the problem of digital forensics for law enforcement or security agencies by improving attribution in videos with strong stabilization, though it is incremental as it builds on existing photo-response non-uniformity techniques.
The paper tackles the challenge of source camera verification from strongly stabilized videos by introducing a method that accounts for spatially variant stabilization transformations and other disruptive video generation steps, achieving verification of 23-30% of such videos without significantly increasing false attribution.
Image stabilization performed during imaging and/or post-processing poses one of the most significant challenges to photo-response non-uniformity based source camera attribution from videos. When performed digitally, stabilization involves cropping, warping, and inpainting of video frames to eliminate unwanted camera motion. Hence, successful attribution requires the inversion of these transformations in a blind manner. To address this challenge, we introduce a source camera verification method for videos that takes into account the spatially variant nature of stabilization transformations and assumes a larger degree of freedom in their search. Our method identifies transformations at a sub-frame level, incorporates a number of constraints to validate their correctness, and offers computational flexibility in the search for the correct transformation. The method also adopts a holistic approach in countering disruptive effects of other video generation steps, such as video coding and downsizing, for more reliable attribution. Tests performed on one public and two custom datasets show that the proposed method is able to verify the source of 23-30% of all videos that underwent stronger stabilization, depending on computation load, without a significant impact on false attribution.