ISPRS International Journal of Geo-Information, Volume 11, Issue 10
2022 October - 38 articles
Cover Story: Deep learning has been investigated for the pattern recognition of complex road junctions to provide support for many applications. The existing methods usually generate raster images from vector junctions with a predefined sampling area coverage, which makes it difficult to ensure the integrity and clarity of junctions of different sizes. This study proposes a stacking ensemble learning method to address this issue. The ensemble learning strategy aims to obtain a finer result by combining the outputs of two or more CNN-based base-classifiers, which are constructed to classify the junction patterns by collecting images with different sampling area coverages. This method improved the classification accuracy for junction patterns compared to existing CNN-based classifiers that were trained using raster images of junctions with a fixed area coverage. View this paper - Issues are regarded as officially published after their release is announced to the table of contents alert mailing list .
- You may sign up for email alerts to receive table of contents of newly released issues.
- PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Reader to open them.