Central processing unit (CPU) and ground power unit (GPU)-based remote-sensing image multi-scale heterogeneous parallel segmentation method

Abstract

The invention provides a high-efficiency image segmentation method aiming at remote-sensing image multi-scale segmentation. The method comprises the following steps: reading original remote-sensing image information to be segmented, setting segmentation parameters and formulating an optimized segmentation strategy in a CPU segmentation start control stage; segmenting by adopting a two-layer parallel computing architecture, wherein a first layer is used for solving limitation of a storage space and guaranteeing load balancing between the CPU and GPU based on a coarse-grained parallel architecture between image blocks, and a second layer is used for guaranteeing load balancing inside the CPU and GPU based on fine-grained parallel architecture of pixels; and finally, carrying out a CPU result saving stage. The method has the advantages that the segmentation speed is high, the segmentation precision is high, setting of multiple segmentation parameters is supported, segmentation of ultra-large remote-sensing images is supported, export of multiple segmentation results is supported, and the like.

Description

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine

Login to view more

AI Technical Summary

Benefits of technology

This patented technology allows for effective image processing by efficiently dividing high resolution remotely detected imagery into smaller segments that can be processed separately or together with data from more computationally expensive equipment such as cameras. By utilizing both hardware accelerators (CPUs) and graphics processors (GPU), these methods allow for faster and better performance at different levels of computational complexity while also supporting various parameters setting options like zoom level adjustment, depth values, etc., making it suitable for use across diverse types of devices.

Problems solved by technology

This patented technical problem addressed in this patents relates to improving the accuracy and performance of image analysis techniques used on remotely detected objects (R). Current methods have limitations such as slow data transfer rates or low computational speeds due to their use of multiple processors that require more memory space compared with traditional computer systems. Therefore it becomes necessary to develop faster methodologies for analyzing these high-resolution imagery without sacrificing accuracy.

Images