Frame-rate conversion detection based on convolutional neural network for learning spatiotemporal features시공간 특징 학습을 위한 합성곱 신경망 기반의 프레임율 변환 탐지

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 91
  • Download : 0
With the advance in user-friendly and powerful video editing tools, anyone can easily manipulate videos without leaving prominent visual traces. Frame-rate up-conversion, a representative temporal-domain operation, increases the motion continuity of videos with a lower frame-rate and is used by malicious counterfeiters in video tampering such as generating fake frame-rate video without improving the quality or mixing temporally spliced videos. Frame-rate conversion is based on frame interpolation schemes and subtle artifacts that remain in interpolated frames are often difficult to distinguish. Hence, detecting such forgery traces is a critical issue in video forensics. This paper proposes a frame-rate conversion detection network (FCDNet) that learns forensic features caused by frame-rate conversion in an end-to-end fashion. The proposed network uses a stack of consecutive frames as the input and effectively learns interpolation artifacts using network blocks to learn spatiotemporal features. This study is the first attempt to apply a neural network to the detection of frame-rate conversion. Moreover, it can cover the following three types of frame interpolation schemes: nearest neighbor interpolation, bilinear interpolation, and motion-compensated interpolation. In contrast to existing methods that exploit all frames to verify integrity, the proposed approach achieves a high detection speed because it observes only six frames to test its authenticity. Extensive experiments were conducted with conventional forensic methods and neural networks for video forensic tasks to validate our research. The proposed network achieved state-of-the-art performance in terms of detecting the interpolated artifacts of frame-rate conversion. The experimental results also demonstrate that our trained model is robust for an unseen dataset, unlearned frame-rate, and unlearned quality factor. Furthermore, FCDNet can precisely localize the tampered region applied to manipulation along the time-domain through temporal localization.
Advisors
Lee, Heung-Kyuresearcher이흥규researcher
Description
한국과학기술원 :전산학부,
Publisher
한국과학기술원
Issue Date
2021
Identifier
325007
Language
eng
Description

학위논문(박사) - 한국과학기술원 : 전산학부, 2021.2,[v, 67 p. :]

Keywords

Video forensics▼aFrame-rate conversion detection▼aFrame interpolation scheme▼aConvolutional neural network▼aResidual features▼aSpatiotemporal features; 비디오 포렌식▼a프레임율 변환 탐지▼a프레임 보간 기법▼a합성곱 신경망▼a잔차 특징▼a시공간 특징

URI
http://hdl.handle.net/10203/309269
Link
http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1006564&flag=dissertation
Appears in Collection
CS-Theses_Ph.D.(박사논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0