Learn to Extract Building Outline from Misaligned Annotation through Nearest Feature Selector

Abstract

For efficient building outline extraction, many algorithms, including unsupervised or supervised, have been proposed over the past decades. In recent years, due to the rapid development of the convolutional neural networks, especially fully convolutional networks, building extraction is treated as a semantic segmentation task that deals with the extremely biased positive pixels. The state-of-the-art methods, either through direct or indirect approaches, are mainly focused on better network design. The shifts and rotations, which are coarsely presented in manually created annotations, have long been ignored. Due to the limited number of positive samples, the misalignment will significantly reduce the correctness of pixel-to-pixel loss that might lead to a gradient explosion. To overcome this, we propose a nearest feature selector (NFS) to dynamically re-align the prediction and slightly misaligned annotations. The NFS can be seamlessly appended to existing loss functions and prevent misleading by the errors or misalignment of annotations. Experiments on a large scale aerial image dataset with centered buildings and corresponding building outlines indicate that the additional NFS brings higher performance when compared to existing naive loss functions. In the classic L1 loss, the addition of NFS gains increments of 8.8% of f1-score, 8.9% of kappa coefficient, and 9.8% of Jaccard index, respectively.

Learn to Optimize Panchromatic Imagery for Accurate Building Extraction

“…Owing to its tremendous representation capability, in principle, we can train a perfect DCN that can work for all conditions while there is sufficient training data. However, in most cases, there are only specified or imperfect annotations [21]. For largescale analysis (e.g., city-or country-level building extraction), robust model transfer methods are vital for enabling the model trained on limited locations or data sources to work properly in different areas or data sources.…”