Heterogeneous parallel computing system and method for threshold method image segmentation, and electronic equipment

Abstract

The invention provides a heterogeneous parallel computing system and method for threshold value method image segmentation, and electronic equipment. The system comprises an image slicing function unit, a sub-image classification coarse segmentation calculation unit based on local features, a target and background boundary sub-image fine segmentation calculation unit based on an OTSU threshold value and a sub-image segmentation result splicing function unit. On the basis of processing characteristic analysis of functional units of threshold method image segmentation, a microprocessor and an FPGA (Field Programmable Gate Array) provided by a heterogeneous system-on-chip are utilized to realize design of a heterogeneous computing system for controlling intensive tasks and computing intensive tasks; a heterogeneous system-on-chip has the characteristics of flexible control capability of a microprocessor and high computing capability of an FPGA (Field Programmable Gate Array), a threshold method image segmentation heterogeneous parallel computing system is designed, and control flexibility of rearrangement of image pixel positions is kept while accelerated computing is performed on processing steps which consume long computing time in a threshold method, and overall execution efficiency of the image segmentation method is improved.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a heterogeneous parallel computing system, method and electronic equipment for image segmentation based on a threshold method. Background technique [0002] Image segmentation is one of the basic image processing links in computer vision tasks. It aims to divide a complete image into multiple sub-regions. There are large differences between different sub-regions, while the pixels in the same sub-region have similar characteristics, so as to achieve the goal. Separation of local area from background area. In image processing tasks with strong timeliness and high precision requirements such as target detection and target tracking, image segmentation is often used as an important preprocessing step to preselect the area where the target is located, reduce the amount of data, and improve the efficiency and accuracy of target detection. At present, methods such a...

AI Technical Summary

Problems solved by technology

[0005] To sum up, the threshold method image segmentation is widely used in pre-processing such as target area pre-selection due to its simple calculation process, but its processing method of traversing the image pixel by pixel is less efficient under the serial processing capability provided by the edge microprocessor. Low, there is currently a lack of high-performance parallel computing system design for such methods

Images