ChangeGAN: A deep network for change detection in coarsely registered point clouds
| Autor: | Balázs Nagy, Lorant Kovacs, Csaba Benedek |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Control and Optimization
Computer science business.industry Mechanical Engineering Feature extraction Biomedical Engineering Point cloud Binary number Pattern recognition QA75 Electronic computers. Computer science / számítástechnika számítógéptudomány Convolutional neural network Computer Science Applications Convolution Human-Computer Interaction Transformation (function) Lidar Artificial Intelligence Control and Systems Engineering Computer Vision and Pattern Recognition Artificial intelligence business Change detection |
| Popis: | In this letter we introduce a novel change detection approach called ChangeGAN for coarsely registered point clouds in complex street-level urban environment. Our generative adversarial network-like (GAN) architecture compounds Siamese-style feature extraction, U-net-like use of multiscale features, and Spatial Trans-formation Network (STN) blocks for optimal transformation estimation. The input point clouds are represented by range images, which enables the use of 2D convolutional neural networks. The result is a pair of binary masks showing the change regions on each input range image, which can be backprojected to the input point clouds without loss of information. We have evaluated the proposed method on various challenging scenarios and we have shown its superiority against state-of-the-art change detection methods. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|