TreeFormer: a Semi-Supervised Transformer-based Framework for Tree Counting from a Single High Resolution Image
This work addresses the challenge of automatic tree density estimation for forest management, offering a semi-supervised approach that reduces annotation costs, though it is incremental as it builds on existing transformer and semi-supervised techniques.
The authors tackled the problem of tree counting from single high-resolution aerial and satellite images by proposing TreeFormer, a semi-supervised transformer-based framework that reduces the need for expensive annotations. The result showed that TreeFormer outperformed state-of-the-art semi-supervised methods and exceeded fully-supervised methods using the same number of labeled images on benchmark datasets.
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 paper, we propose the first semisupervised 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 multi-scale features during the encoding stage. Contextual attention-based feature fusion and tree density regressor 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 into the training process. Finally, the tree counter token 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.