Detection of Double Compression in HEVC Videos Containing B-Frames

TL;DR

This paper introduces a new method to detect if HEVC videos have been compressed twice, using machine learning and frame-level features.

Contribution

The novelty lies in detecting double compression in HEVC videos with B-frames using a Bi-LSTM model and frame-level encoding features.

Findings

A 28-dimensional feature vector was used to represent HEVC videos for double compression detection.

The proposed method achieved 80.06% detection accuracy, outperforming existing methods.

The method was tested on a dataset of 129 HEVC-encoded YUV videos with various bitrates and GOP structures.

Abstract

This study proposes a method to detect double compression in H.265/HEVC videos containing B-frames, a scenario underexplored in previous research. The method extracts frame-level encoding features—including frame type, coding unit (CU) size, quantization parameter (QP), and prediction modes—and represents each video as a 28-dimensional feature vector. A bidirectional Long Short-Term Memory (Bi-LSTM) classifier is then trained to model temporal inconsistencies introduced during recompression. To evaluate the method, we created a dataset of 129 HEVC-encoded YUV videos derived from 43 original sequences, covering various bitrate combinations and GOP structures. The proposed method achieved a detection accuracy of 80.06%, outperforming two existing baselines. These results demonstrate the practical applicability of the proposed approach in realistic double compression scenarios.

Figures