Motion parameter estimation method based on gray integral projection cross-correlation function characteristics

Abstract

The invention provides a motion parameter estimation method based on gray integral projection cross-correlation function characteristics. A horizontal moving motion model is adopted, and the method comprises the following steps that a target image is divided into N*N rectangular partitioning blocks with the equal size, gray integral projection is performed on each partitioning block, the variance of gray integral projection of each partitioning block is determined, R areas with the large variance can be selected as alternative areas, the cross-correlation operation is performed on gray integral projection of the alternative areas in two continuous frames of the target image, second derivatives of a cross-correlation function extreme point are calculated, weighted summation is performed on the variance of gray integral projection and the second derivatives of the cross-correlation function extreme point, good and poor factors of the alternative areas are obtained, the good and poor factors are arranged in a sort descending mode, the Q areas arranged in front are selected as the good-quality areas, local motion parameter estimation is performed on the obtained good-quality areas respectively, horizontal moving motion parameters in the direction of an axis X axis or an axis Y are obtained, and weighted summation is performed on the local motion parameters of the good-quality areas to obtain global motion parameters. According to the method, global motion parameters of an image with the low contrast ratio and the high resolution ratio can be effectively estimated.

Description

technical field [0001] The invention belongs to the technical field of image analysis, in particular to a motion parameter estimation method based on gray integral projection cross-correlation function features. Background technique [0002] The digital image stabilization system is based on digital image processing technology, which detects the image shake vector and performs real-time compensation. It does not need to rely on special equipment such as gyroscopes or prisms. The detection accuracy and compensation accuracy are only related to the algorithm implementation, so the settings are flexible and can handle a wide range Jitter can be directly applied to the back end of the popular video surveillance system, and is compatible with existing systems, so it has been widely studied and applied. A digital image stabilization system generally includes two processing units: a motion estimation unit and a motion compensation unit. The motion estimation unit acquires the glob...

AI Technical Summary

Problems solved by technology

[0003] Most of the video images in the application field of sea area security monitoring have the characteristics of low contrast and high resolution, and the wind-induced vibration causes serious image jitter

When the feature tracking method (FTA) is used to estimate the global motion parameters of the de-shaking operation, it is found that the gray level of low-contrast and high-resolution images does not change sharply, and the features such as corner points are very inconspicuous. The search threshold of corner points is very small, and often search failed

When using the block matching method (BMA), which is insensitive to the small neighborhood features of the image, it is necessary to set a matching block with a suitable size and position in advance, which is difficult to meet in the application of sea area security monitoring, while the traditional gray scale integral projection method ( IIPA) does not require excessive human intervention, but the real-time and accuracy of direct application cannot meet the application requirements

Images