Data processing method, system and device based on window operation

Abstract

The invention discloses a data processing method based on window operation. The method comprises the steps of obtaining and caching set height parameter H and width parameter W of a window; configuring a size of the window according to the cached parameters; reading data input frames; updating and caching the height parameter H and width parameter W of the window to be new parameters H ' and W ', if the obtained height parameter H and width parameter W of the window are changed in a process of reading the data input frames; and reconfiguring the size of the window according to the updated parameters. The invention also provides a data processing system and device based on window operation, and a memory. According to the data processing method, the size of the domain window can be configured dynamically, and therefore, the number and the locations of pixels of comparison participation images can be configured flexibly. The method has the advantages of high flexibility, high timeliness and high resource reusability.

Description

technical field [0001] The present invention relates to data processing technology, in particular to a data processing method, system and device based on window operation. Background technique [0002] Automatic detection of edges in images is an important link in the field of machine vision research. Non-maximum value suppression is an important step in edge detection. In the popular sense, it refers to finding the local maximum value of pixels. In order to improve the speed of system image processing and meet the real-time requirements of the system, field-programmable gate array FPGA (Field-ProgrammableGate Array) is often used for image preprocessing. Specifically, the non-maximum suppression is implemented on the FPGA, and the sliding window is used for pipeline processing, thereby greatly improving the calculation efficiency of the non-maximum suppression. [0003] However, when non-maximum suppression is currently implemented on the FPGA, the sliding window is usual...

AI Technical Summary

Problems solved by technology

[0003] However, when non-maximum suppression is currently implemented on the FPGA, the sliding window is usually of a fixed size, but when multiple modules need to do non-maximum suppression, and the size of the neighborhood for non-maximum suppression is different, or When the same module needs to adjust the neighborhood size according to its content when implementing non-maximum suppression, such a design is very inflexible and the resource reusability is not high

Images