ABSTRACT Climate change and human activities have led to a decline in wetland vegetation and sharp reduction of wetland area, which has caused considerable damage to the hydrological cycle and ecological functions of many wetlands. Flooded vegetation (FV) is an important wetland landscape, and strengthening the research on methods of the extracting FV using remote sensing or aerial photos plays an important role in monitoring changes to wetlands. This paper used optical satellite and synthetic aperture radar satellite images as data sources, construct a set of feature variable sets suitable for FV extraction; in addition, a deep learning method based on the semantic segmentation model DeepLabv3+, FV-DLV3+, is proposed for FV extraction. The method adopts the lightweight MobileNetV2 model as the backbone feature extraction network, introduces the SegFormer network to make up for the feature information loss caused by MobileNetV2, and further captures more effective features and suppresses the interference of the background through an attention mechanism to enhance the ability to extract feature boundaries, thereby improving the accuracy of FV extraction. Taking the wetland of Poyang Lake as the experimental area, Landsat 8 and Sentinel-1A satellite data were selected as the data sources to produce a deep learning dataset, and U-Net, DeepLabv3+, Swin-Unet, Swin Transformer, and CVTNet were selected for comparison when conducting model training and validating experiments. The results show that FV-DLV3+ has an excellent effect on FV extraction of the Poyang Lake wetland, which effectively reduces the computational complexity of the process while improving extraction accuracy; the mean intersection over union of this paper’s method was higher than the five above-mentioned methods, which was 12.93% and 5.85% higher than that of DeepLabv3+ and CVTNet, respectively.