Multi-scale ship enterprise scene recognition and extraction method combined with spatial distance constraint

Abstract

The invention provides a multi-scale ship enterprise scene recognition and extraction method combined with spatial distance constraint. The method comprises the following steps: obtaining the nationwide ship enterprise distribution condition and structural features, and making a high-resolution ship enterprise remote sensing data set; utilizing the remote sensing data set to train a ship enterprise remote sensing image recognition model based on the global scale and the local scale; performing multi-model and multi-scale detection on the to-be-predicted remote sensing image by adopting a shipenterprise remote sensing image recognition model; based on a multi-scale detection result, extracting a spatial distance between the ship enterprise objects of the remote sensing image to be predicted; and performing scene category comprehensive evaluation on the to-be-predicted remote sensing image in combination with global and local multi-scale detection results, a local object label combination mode and an object space distance constraint condition. The ship enterprise complex scene extraction method has the beneficial effects that ship enterprise complex scene extraction is effectively carried out, theoretical support can be provided for ship industry development and coastal environment monitoring in China, and a macroscopic decision basis can be further provided for government capacity adjustment and industrial layout for overseas ship enterprise extraction.

Description

technical field [0001] The invention relates to the technical field of remote sensing, in particular to a multi-scale ship enterprise scene recognition and extraction method combined with space distance constraints. Background technique [0002] In the development of the national economy, the shipbuilding industry provides equipment support for marine resource development, shipping transportation, and national defense construction in the marine field. It plays an important role in many fields and has been valued by countries all over the world, especially coastal areas and countries. While enjoying the economic dividends brought by the rapid development of the shipbuilding industry, the ensuing ecological and environmental pollution of water areas is becoming increasingly serious. Therefore, clarifying the distribution of shipbuilding enterprises can provide assistance for government departments to regulate production capacity and monitor the ecological environment, assist t...

AI Technical Summary

Problems solved by technology

Although the development of remote sensing technology and computer technology has promoted the application of deep learning in the field of remote sensing, the types and quantities of remote sensing training sample sets have also increased, but the current data sets are mostly common land cover types such as schools, buildings, and rivers. Related sample sets of complex artificial shorelines of shipbuilding enterprises

[0008] To sum up, the use of remote sensing images to automatically analyze the scene of shipbuilding enterprises has the following problems: (1) the scenes of shipbuilding enterprises are complex; (2) the remote sensing images are large, and the proportion of shipbuilding enterprises is small; (3) there is a lack of artificial coastline distribution data sets of shipbuilding enterprises

The above problems lead to low recognition effect and poor accuracy of using remote sensing images to automatically analyze shipbuilding scenes

Images