TreeFormer: A Semi-Supervised Transformer-Based Framework for Tree Counting From a Single High-Resolution Image

Automatic tree density estimation and counting using single aerial and satellite images is a challenging task in photogrammetry and remote sensing, yet has an important role in forest management. In this article, we propose the first semi-supervised transformer-based framework for tree counting which reduces the expensive tree annotations for remote sensing images. Our method, termed as TreeFormer, first develops a pyramid tree representation module based on transformer blocks to extract multiscale features during the encoding stage. Contextual attention-based feature fusion (CAFF) and tree density regressor (TDR) modules are further designed to utilize the robust features from the encoder to estimate tree density maps in the decoder. Moreover, we propose a pyramid learning strategy that includes local tree density consistency and local tree count ranking losses to utilize unlabeled images in the training process. Finally, the tree counter token (TCT) is introduced to regulate the network by computing the global tree counts for both labeled and unlabeled images. Our model was evaluated on two benchmark tree counting datasets, Jiangsu and Yosemite, as well as a new dataset, KCL-London, created by ourselves. Our TreeFormer outperforms the state-of-the-art semi-supervised methods under the same setting and exceeds the fully-supervised methods using the same number of labeled images. The codes and datasets are available at
https://github.com/HAAClassic/TreeFormer
.