Litcius/Paper detail

Crop Classification of Multitemporal PolSAR Based on 3-D Attention Module With ViT

Qiang Yin, Zhiyuan Lin, Wei Hu, Carlos López-Martínez, Jun Ni, Fan Zhang

2023IEEE Geoscience and Remote Sensing Letters26 citationsDOIOpen Access PDF

Abstract

Multi-temporal polarimertic SAR is considered to be very effective in crop classification and cultivated land detection, which has received much attention from researchers. Currently, for most multi-temporal polarimetric SAR data classification methods, the simultaneous temporal-polarimetric-spatial feature extraction capability has not been exploited sufficiently. Also, the diversity of different time and different polarimetric features has not been taken into account sufficiently. In this paper, we propose a classification model that combines a dual-stream network as a temporal-polarimetric-spatial feature extraction module with Vision Transformer(ViT) called Temporal-Polarimetric-Spatial Transformer(TSPT) to address the above problems. Secondly, a 3 dimension(3D) convolutional attention module that enables the network to weight the temporal dimension, polarimetric feature dimension and spatial dimension is developed, according to their importance. Experimental results on both UAVSAR and RADARSAT-2 datasets show that the proposed method outperforms ResNet.

Topics & Concepts

Computer sciencePolarimetryFeature extractionPattern recognition (psychology)Dimension (graph theory)Artificial intelligenceContextual image classificationRemote sensingGeographyMathematicsImage (mathematics)OpticsPure mathematicsScatteringPhysicsSynthetic Aperture Radar (SAR) Applications and TechniquesAdvanced SAR Imaging TechniquesSoil Moisture and Remote Sensing