Digital Video Stabilization: Algorithms and Evaluation

• Marcos Roberto e Souza UNICAMP
• Helio Pedrini UNICAMP

DOI: https://doi.org/10.5753/ctd.2019.6338

Resumo

Several devices have allowed the acquisition and editing ofvideos in various circumstances, such as digital cameras, smartphones and other mobile devices. However, the use ofcameras under adverse conditions usually results in non-precise motion and occurrence of shaking, which may compromise the stability of the obtained videos. To overcome such problem, digital stabiliza- tion aims to correct camera motion oscillations that occur in the acquisition process, particularly when the cameras are mobile and handled in adverse con- ditions, through software techniques, without the use of specific hardware, to enhance visual quality either with the intention of enhancing human percep- tion or improving final applications, such as detection and tracking of objects. This is important in order to avoid hardware cost and indispensable for videos already recorded. This work proposed three methods to perform digital video stabilization and two other techniques to evaluate video stabilization quality. 1.

Palavras-chave: Processamento de imagens, Otimização matemática, Vídeos digitais, Sistemas multimídia, Estimativa de parâmetros.

Referências

Grundmann, M., Kwatra, V., and Essa, I. (2011). Auto-Directed Video Stabilization with Robust L1 Optimal Camera Paths. In IEEE Conference on Computer Vision and Pattern Recognition, pages 225–232. IEEE.

Liu, S., Yuan, L., Tan, P., and Sun, J. (2013). Bundled Camera Paths for Video Stabiliza- tion. ACMTransactions on Graphics, 32(4):78.

Souza, M. R. (2018). Digital Video Stabilization: Algorithms and Evaluation. Master’s thesis, Institute of Computing, University of Campinas.

Souza, M. R., da Fonseca, L. F. R., and Pedrini, H. (2018). Improvement of Global Mo- tion Estimation in Two-Dimensional Digital Video Stabilisation Methods. IET Image Processing, 12(12):2204–2211.

Souza, M. R. and Pedrini, H. (2017). Motion Energy Image for Evaluation of Video Stabilization. The Visual Computer, pages 1–13.

Souza, M. R. and Pedrini, H. (2018a). Combination of Local Feature Detection Methods for Digital Video Stabilization. Signal, Image andVideo Processing, 12(8):1513–1521.

Souza, M. R. and Pedrini, H. (2018b). Digital Video Stabilization Based on Adaptive Camera Trajectory Smoothing. EURASIP Journal on Image and Video Processing, 2018(1):37.

Souza, M. R. and Pedrini, H. (2018c). Visual Rhythms for Qualitative Evaluation ofVideo Stabilization. EURASIP Journal on Image and Video Processing. (submitted).