Multi-scale classification method and device and computer readable storage medium
A classification method and multi-scale technology, applied in computer parts, calculations, instruments, etc., can solve the problems of limited accuracy and robustness of analysis results, and cannot achieve robust solutions of segmentation algorithms, so as to improve accuracy and robustness. sexual effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
no. 1 example
[0030] In order to solve the problem of multi-scale object-based image analysis in related technologies, it is necessary to set scale parameters before image segmentation, and the scale parameters are determined based on low-level image features or human experience, resulting in relatively low accuracy and robustness of the analysis results. Limited technical issues, this embodiment proposes a multi-scale classification method, such as figure 1 Shown is a schematic flow chart of the multi-scale classification method provided in this embodiment. The multi-scale classification method proposed in this embodiment includes the following steps:
[0031] Step 101. Initially divide the input remote sensing image into multiple superpixel blocks, and merge the adjacent superpixel blocks in the multiple superpixel blocks step by step to build a tree-like hierarchical structure; the cost of merging adjacent superpixel blocks is Scale flag for merged nodes.
[0032] Specifically, the remo...
no. 2 example
[0052] In order to solve the problem of multi-scale object-based image analysis in related technologies, it is necessary to set scale parameters before image segmentation, and the scale parameters are determined based on low-level image features or human experience, resulting in relatively low accuracy and robustness of the analysis results. Limited technical issues, this embodiment shows a multi-scale classification device, please refer to Figure 5 , the multi-scale classification device of this embodiment includes:
[0053] Segmentation module 501, for initializing and dividing the input remote sensing image into a plurality of superpixel blocks, and merging adjacent superpixel blocks in the plurality of superpixel blocks step by step to construct a tree-like hierarchical structure; adjacent superpixel blocks The merge cost is the scale mark of the merged node;
[0054] A generation module 502, configured to generate segmentation result maps under different scale parameter...
no. 3 example
[0069] This embodiment provides an electronic device, see Figure 6 As shown, it includes a processor 601, a memory 602, and a communication bus 603, wherein: the communication bus 603 is used to realize connection and communication between the processor 601 and the memory 602; the processor 601 is used to execute one or more programs stored in the memory 602 A computer program to implement at least one step in the multi-scale classification method in the first embodiment above.
[0070] The present embodiment also provides a computer-readable storage medium, which includes information implemented in any method or technology for storing information, such as computer-readable instructions, data structures, computer program modules, or other data. volatile or nonvolatile, removable or non-removable media. Computer-readable storage media include but are not limited to RAM (Random Access Memory, random access memory), ROM (Read-Only Memory, read-only memory), EEPROM (Electrically...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More