Information regarding newly added construction land can be extracted from high-resolution remote sensing images. The retrieval accuracy of land cover changes across the country has improved, and the illegal use of land is actively monitored. To address the imbalance between positive and negative training samples in extracting information regarding newly added construction land, a method for identifying newly added construction land by weakening the weight of negative samples was proposed. A focal loss function was used to weaken the negative samples’ weights and improve the overfitting U-net. Since the two parameters of the focal loss function are not independent of each other, they need to be selected at the same time. Therefore, this paper developed a formula for selecting the balance factor α based on a large number of experimental results. First, the GF-2 image was combined with the historical land change survey data and monitoring vector results to construct a dataset, and then the training dataset was input into a fully convolutional neural network (CNN) integrated with feature fusion and a focal loss function. Finally, the accuracy of the trained network model was verified. To demonstrate the applicability of the method of determining the parameters of the focal loss function, the validation set was divided into four subsets for accuracy verification. The experimental results showed that the F1-score of newly added construction land information extracted by this method reached 0.913, which is 0.078 and 0.033 higher than those of the U-net and the improved U-net. The parameters obtained by the method proposed in this study achieved the best results on the four verification sets, which shows that the method for extracting newly added construction land information and that for selecting parameters have strong applicability.

No abstract