Feature Pyramid Network for Multi-Class Land Segmentation

2018/06/09 by Seferbekov, Selim S., Iglovikov, Vladimir I., Buslaev, Alexander V. +1 · 2 citations
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.1806.03510

Abstract

Semantic segmentation is in-demand in satellite imagery processing. Because of the complex environment, automatic categorization and segmentation of land cover is a challenging problem. Solving it can help to overcome many obstacles in urban planning, environmental engineering or natural landscape monitoring. In this paper, we propose an approach for automatic multi-class land segmentation based on a fully convolutional neural network of feature pyramid network (FPN) family. This network is consisted of pre-trained on ImageNet Resnet50 encoder and neatly developed decoder. Based on validation results, leaderboard score and our own experience this network shows reliable results for the DEEPGLOBE - CVPR 2018 land cover classification sub-challenge. Moreover, this network moderately uses memory that allows using GTX 1080 or 1080 TI video cards to perform whole training and makes pretty fast predictions.

Cited by

• TransLK-Net: Entangling Transformer and Large Kernel for Progressive and Collaborative Feature Encoding and Decoding in Medical Image Segmentation
• CLAIRE: A Dual Encoder Network with RIFT Loss and Phi-3 Small Language Model Based Interpretability for Cross-Modality Synthetic Aperture Radar and Optical Land Cover Segmentation

Related

• Dense Fusion Classmate Network for Land Cover Classification
• Convolutional Neural Network Segmentation for Satellite Imagery Data to Identify Landforms Using U-Net Architecture
• Land Cover Semantic Segmentation Using ResUNet
• PyramidMamba: Rethinking Pyramid Feature Fusion with Selective Space State Model for Semantic Segmentation of Remote Sensing Imagery
• LULC Segmentation of RGB Satellite Image Using FCN-8