Lossless ROI Privacy Protection of H.264/AVC Compressed Surveillance Videos
Bibliographic record
Abstract
Privacy becomes one of the major concerns of video surveillance systems, especially in cloud-based systems. Privacy protection of surveillance videos aims to protect privacy information without hampering normal video surveillance tasks. Region-of-interest (ROI) privacy protection is more practical compared with the whole video encryption approaches. However, one common drawback of virtually all current ROI privacy protection methods is that the original compressed surveillance video recorded in the camera is permanently distorted by the privacy protection process, due to the quantization in the re-encoding process. Thus, the integrity of the original compressed surveillance video captured by the camera is destroyed. This is unacceptable for some application scenarios, such as video forensics for investigations and video authentication for law enforcement. In this paper, we introduce a new paradigm for privacy protection in surveillance videos, referred to as lossless privacy region protection, which has the property that the distortion introduced by the protection of the privacy data can be completely removed from the protected videos by authorized users. We demonstrate the concept of lossless privacy region protection through a proposed scheme applied on H.264/Advanced Video Coding compressed videos.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".