ChangeGAN: A Deep Network for Change Detection in Coarsely Registered Point Clouds
Open Access
- 18 August 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 6 (4) , 8277-8284
Abstract
In this paper we introduce a novel change detection approach called ChangeGAN for coarsely registered} point clouds in complex street-level urban environment. Our generative adversarial network (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.Keywords
This publication has 20 references indexed in Scilit:
- Change detection of built-up land: A framework of combining pixel-based detection and object-based recognitionISPRS Journal of Photogrammetry and Remote Sensing, 2016
- Street-side vehicle detection, classification and change detection using mobile laser scanning dataISPRS Journal of Photogrammetry and Remote Sensing, 2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Street environment change detection from mobile laser scanning point cloudsISPRS Journal of Photogrammetry and Remote Sensing, 2015
- 3D people surveillance on range data sequences of a rotating LidarPattern Recognition Letters, 2014
- 3D change detection at street level using mobile laser scanning point clouds and terrestrial imagesISPRS Journal of Photogrammetry and Remote Sensing, 2014
- Vision meets robotics: The KITTI datasetThe International Journal of Robotics Research, 2013
- Building Development Monitoring in Multitemporal Remotely Sensed Image Pairs with Stochastic Birth-Death DynamicsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2011
- SIGNATURE VERIFICATION USING A “SIAMESE” TIME DELAY NEURAL NETWORKInternational Journal of Pattern Recognition and Artificial Intelligence, 1993
- Basic principles of ROC analysisSeminars in Nuclear Medicine, 1978