An Affine Motion Model for Removing Rolling Shutter Distortions

作者：Sun, Yufen; Liu, Gang^*; Sun, Yue

来源：IEEE Signal Processing Letters, 2016, 23(9): 1250-1254.

DOI：10.1109/LSP.2016.2591878

• Affine transformation
• CMOS image sensor
• neural network
• rolling shutter distortion

Rolling shutter distortions degrade the quality of videos captured by hand-held cameras. This letter proposes an affine motion model for removing rolling shutter distortions. The model represents the image motion during image capture as a sequence of affine transformations and computes the composition of these affine transformations precisely. Because an affine transformation can be represented by a neural network with one layer of linear neurons, the motion model can be represented by a multi-layer neural network of linear neurons. Thus, the backpropagation algorithm can be used to improve the efficiency of the optimization process that estimates the model parameters. The proposed model is calibration-free. It is more general than other rolling shutter motion models because it only assumes that the velocity of the image during image acquisition is piecewise constant. Experimental results demonstrate that the model is more accurate than two stateof- the-art models and that the model parameters can be estimated efficiently.

• 出版日期2016-9
• 单位武汉理工大学