A Visual Perception-Based Tunable Framework and Evaluation Benchmark for H.265/HEVC ROI Encryption

TL;DR

This work tackles privacy protection in video by addressing the inflexibility of ROI-based encryption and the lack of standardized evaluation. It introduces a visual perception-based ROI recognition module coupled with a three-level tunable ROI encryption scheme for H.265/HEVC, enabling flexible security-performance trade-offs. A unified ROI encryption evaluation benchmark is proposed, featuring standardized datasets, baselines, and metrics (IoU-based fineness, subjective and objective perturbation analyses, and a comprehensive objective indicator set). Experimental results show that finer tile granularity and the advanced/enhanced encryption levels achieve superior perturbation and security metrics, with the basic level offering zero bitrate increase, illustrating practical applicability for real-time privacy-preserving video processing. The benchmark and framework collectively provide a rigorous, reproducible platform to compare ROI SE methods and guide future improvements in privacy-aware video coding.

Abstract

ROI selective encryption, as an efficient privacy protection technique, encrypts only the key regions in the video, thereby ensuring security while minimizing the impact on coding efficiency. However, existing ROI-based video encryption methods suffer from insufficient flexibility and lack of a unified evaluation system. To address these issues, we propose a visual perception-based tunable framework and evaluation benchmark for H.265/HEVC ROI encryption. Our scheme introduces three key contributions: 1) A ROI region recognition module based on visual perception network is proposed to accurately identify the ROI region in videos. 2) A three-level tunable encryption strategy is implemented while balancing security and real-time performance. 3) A unified ROI encryption evaluation benchmark is developed to provide a standardized quantitative platform for subsequent research. This triple strategy provides new solution and significant unified performance evaluation methods for ROI selective encryption field. Experimental results indicate that the proposed benchmark can comprehensively measure the performance of the ROI selective encryption. Compared to existing ROI encryption algorithms, our proposed enhanced and advanced level encryption exhibit superior performance in multiple performance metrics. In general, the proposed framework effectively meets the privacy protection requirements in H.265/HEVC and provides a reliable solution for secure and efficient processing of sensitive video content.

Figures (10)

• Figure 1: Comparison between fixed encryption strategy and proposed three-level encryption strategy
• Figure 2: The architecture of visual perception network
• Figure 3: The framework of the proposed encryption strategy
• Figure 4: Detection results before and after training
• Figure 5: Some examples of proposed strategy in Akiyo sequence