Image data processing method and apparatus, and electronic device

Abstract

The invention provides an image data processing method and apparatus, and an electronic device. The method comprises the steps of determining a search center point and a maximum search estimation radius of a target image, and setting at least two levels of search radiuses with different values in a maximum search estimation radius range; by taking the search center point as a center, searching for a first pixel point meeting a first matching requirement in a first search radius range selected from the search radiuses with the different values; when the first pixel point is searched out, searching for a second pixel point meeting a second matching requirement in a preset region range taking the first pixel point as a center; and when the second pixel point is searched out, taking a second pixel as a matching position point, obtained by matching, of the target image. By utilizing the image data processing method and apparatus, and the electronic device, the position point needed by the target image can be quickly matched while the matching accuracy is guaranteed, the matching calculation frequency is greatly reduced, the processing load is reduced, the matching speed is increased, and the usage experience of users is improved.

Description

technical field [0001] The present application relates to the field of video image data processing, in particular to an image data processing method, device and electronic equipment. Background technique [0002] With the rapid development of the smart phone market, users often need to track and locate the target in the collected video when using mobile terminals to take pictures, selfies, and videos, such as face tracking when taking selfies. In this way, the shooting target in the video can be automatically tracked and locked along with the movement of the terminal or the target, which can provide users with convenience and better use effect. [0003] In the tracking scene of a video target, image block matching is one of the main processing methods currently used in the prior art. A video is usually composed of multiple video frames arranged in time sequence. After obtaining the tracked target image block of the current frame, it can be used as a reference image block fo...

AI Technical Summary

Problems solved by technology

However, this strategy of traversing and searching the target area often leads to a large amount of calculation, especially if the tracking target moves a lot during the tracking process, in order to ensure the accuracy of matching, the search radius is often increased by a large increase, that is, increasing A large (range_max) value will obviously lead to a sharp increase in the number of image block matches, an increase in the amount of data processing, and a decrease in matching speed

At the same time, for terminal processing equipment, such a large number of calculations will increase the processing load, which will cause the risk of heating and freezing of the terminal, and reduce the user experience of APP or terminal equipment.

[0004] In the prior art, the image block processing method of video object tracking has many matching times, and the amount of data calculation is large, which increases the processing load, leads to low processing efficiency, and even often causes problems such as heating and freezing of terminal equipment, reducing user usage. to experience

Images