Estabilización Robusta de Vídeo basada en Diferencia de Nivel de Gris

Resumen — La estabilizacion de video se esta convirtiendo en una importante tecnica de post-procesado para secuencias de fotogramas (frames) adquiridas con camaras digitales, especialmente debido al uso generalizado de camaras de mano (hand-held) asi como la utilizacion de estos dispositivos como elementos de entrada en sistemas robotizados complejos, robots humanoides o vehiculos aereos no tripulados. El presente articulo propone una combinacion del metodo iterativo RANSAC (RANdom SAmple Consensus), para otorgar robustez a la estimacion del movimiento como parte del proceso de estabilizacion de video, en conjunto con una funcion coste basada en la diferencia del nivel de gris entre imagenes. Palabras Clave: Estabilizacion de Video, RANSAC, Transformacion Afin, Transformacion Proyectiva, SIFT, SURF.

[1]  Jean Ponce,et al.  Computer Vision: A Modern Approach , 2002 .

[2]  Luc Van Gool,et al.  SURF: Speeded Up Robust Features , 2006, ECCV.

[3]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[5]  Dan Schonfeld,et al.  Robust Video Stabilization Based on Particle Filter Tracking of Projected Camera Motion , 2009, IEEE Transactions on Circuits and Systems for Video Technology.

[6]  Sung-Jea Ko,et al.  Video stabilization based on motion segmentation , 2012, 2012 IEEE International Conference on Consumer Electronics (ICCE).

[7]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.

[8]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[9]  Bing-Yu Chen,et al.  Video stabilization using robust feature trajectories , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[10]  Sebastiano Battiato,et al.  SIFT Features Tracking for Video Stabilization , 2007, 14th International Conference on Image Analysis and Processing (ICIAP 2007).

[11]  Konstantinos G. Derpanis,et al.  Overview of the RANSAC Algorithm , 2005 .

[12]  Sung-Jea Ko,et al.  Robust digital image stabilization using the Kalman filter , 2009, IEEE Transactions on Consumer Electronics.

[13]  Shang-Hong Lai,et al.  A robust and efficient video stabilization algorithm , 2004, 2004 IEEE International Conference on Multimedia and Expo (ICME) (IEEE Cat. No.04TH8763).

[14]  Bernhard P. Wrobel,et al.  Multiple View Geometry in Computer Vision , 2001 .

[15]  S. Govindarajulu,et al.  A Comparison of SIFT, PCA-SIFT and SURF , 2012 .

[16]  David W. Murray,et al.  Guided Sampling and Consensus for Motion Estimation , 2002, ECCV.

[17]  Hai Zhao,et al.  Robust video stabilization based on particle filtering with weighted feature points , 2012, IEEE Transactions on Consumer Electronics.

[18]  Jie Xu,et al.  Fast feature-based video stabilization without accumulative global motion estimation , 2012, IEEE Transactions on Consumer Electronics.

[19]  Yu-Feng Hsu,et al.  Moving camera video stabilization using homography consistency , 2012, 2012 19th IEEE International Conference on Image Processing.