MF-ShipNet: a multi-feature weighted fusion and PCA-SVM model for ship detection in remote sensing images

Due to the complex sea background and the different sizes and shapes of ships, the detection of ship targets has the problems of low detection rate, high false detection rate and high missed detection rate. To solve this problem, this paper proposes a multi-feature weighted fusion and PCA-SVM model for ship detection in remote sensing images. A weighted fusion method of Local Binary Pattern (LBP) and Histogram of Oriented Gradients (HOG) was used to extract shape and texture features simultaneously. Principal Component Analysis (PCA) was used to reduce the dimension of fused features to reduce the false detection rate caused by redundant noise interference. The feature pyramid was constructed to realize the feature fusion of different levels. In addition, a re-screening method based on color features or geometric features is proposed to further reduce the false detection rate. The accuracy and recall rate of the proposed detection algorithm in the DFH-MODIS dataset reach 97.9%and 79.8% respectively. Compared with the ship target detection algorithm based on HOG feature combined with SVM classifier, the F1-score is improved from 0.554 to 0.879. It effectively improves the detection performance of the ship target detection algorithm in optical remote sensing images, and has better effectiveness and robustness.