Efficient and accurate monitoring of green tide is of great significance to marine disaster prevention and marine environment protection. A method was proposed in this article for the automatic extraction of green tide from Chinese Gaofen-3 satellite SAR images, which is based on feature selection and deep learning. Since SAR images contain rich polarization information, we first extract the high-dimensional features from GF-3 SAR images. Secondly, a novel feature selection method for SAR images is designed by using the Bhattacharyya distance and the Separability index, which can select the optimal features subset with a strong ability for recognizing green tide and without correlation between features from the high-dimensional features of SAR. Then, to alleviate the model training burden and improve the prediction efficiency, a lightweight semantic segmentation network, Mobile-SegNet, is designed based on MobileNets and SegNet. Finally, the selected optimal features and their labels are sent to Mobile-SegNet for training and obtaining the automatic recognition model of green tide, and the automatic extraction of green tide is achieved through model prediction. To verify the effectiveness of the proposed method, GF-3 SAR images taken in 2020 that covered the Yellow Sea are collected and used in green tide extraction experiments. The results show that the proposed method is available for an effective reduction of the feature dimension required for green tide extraction, and the improvement of the accuracy and efficiency of detection. The overall accuracy, F1-score, MIoU, and kappa coefficient of the proposed method reached 99.52%, 95.76%, 92.19%, and 0.92, respectively.