The inner port areas of different ports in remote sensing images present different shapes. This paper proposes a port target recognition method based on the inner port area. First, the sea area is segmented using histograms and morphological operators; then the polygon approximation method is used to extract feature points on the coastline, and the inner port area is determined according to the closure degree of the feature points. The false alarm is reduced by detecting straight lines and corner point structures; then the main direction of the shape of the inner port area is calculated; finally, the features are extracted and similarity is measured. Experiments show that the method detects port targets accurately, and the extracted features have good invariance, which meets the requirements of recognition.
You Might Like
Recommended ContentMore
Open source project More
Popular Components
Searched by Users
Just Take a LookMore
Trending Downloads
Trending ArticlesMore