Intelligent Hybrid Model of Recognition of Plankton Populations in Marine Systems Based on Satellite Images

This paper proposes a hybrid LBP+PSPNet model for improving the accuracy of plankton population segmentation in Earth observation RGB satellite imagery, particularly in conditions of low contrast between biogenic aggregations and the marine background. The model combines local texture feature extraction (LBP) with global contextual analysis based on pyramid scene parsing network (PSPNet). LBP enhances the detail of textural characteristics of plankton aggregations, which are often masked by cloud cover or surface wave action. PSPNet provides multiscale image analysis, enabling precise segmentation of both large plankton aggregations and weakly expressed aggregations in coastal zones. Experiments showed that LBP integration increases the IoU metric by 5.14% compared to the baseline PSPNet architecture. The proposed model achieves an F1-score of 86.27% when tested on complex scenarios, demonstrating robustness to Gaussian noise and salt-and-pepper distortions. The results confirm the effectiveness of combining classical texture analysis methods with deep learning for aquatic ecosystem environmental monitoring tasks.