A Framework for Land Use Scenes Classification Based on Landscape Photos
Open Access
- 1 October 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 13 (19391404) , 6124-6141
Abstract
Space-Earth Integrated Stereoscopic Mapping promotes the progress of earth observation technologies. The method which combined remote sensing images with zenith perspectives and ground-level landscape photos with slanted viewing angles improves the efficiency and accuracy of land surveys. Recently, numerous efforts have been devoted to combining deep learning and remote sensing images for the classification of land use scenes. However, improvement of classification accuracy has been limited because of the lack of sectional representation. Landscape photos can describe the cross-sections in detail. For this reason, this study constructed a Land-use Semantic Photo Dataset (LSPD) and proposed a Land-use Classification Framework for Photos (LUCFP) based on Inception-v4. LSPD was constructed through semantic planning, scene segmentation, supervised iteration transfer learning and augmentation of photos. LSPD has 1.4 million photos collected from seven geographic regions of China, and covers 13 land-use categories and 44 semantic categories. LUCFP adapts scene segmentation based on depth of field, multi-semantic block labeling, and weighting of semantic joint spatial ranges to determine the land use category. To validate LUCFP, nine semantic samples (9 3 2000 photos) were chosen from LSPD, obtaining an overall accuracy of 97.64%. The best photo cropping method was masking, which crops the boundary of the scene labeled by the photo, leading to an accuracy of 90.32%. The optimal pixel size that balances speed and accuracy is 675 675, with speed reaching 30 photos per second with an average accuracy of 93.80%. LUCFP has been successfully applied to the automatic verification of land surveys in China.Keywords
Funding Information
- China Institute of Land Surveying and Planning (2019114017)
This publication has 34 references indexed in Scilit:
- A Linear Dirichlet Mixture Model for decomposing scenes: Application to analyzing urban functional zoningsRemote Sensing of Environment, 2015
- Accurate Urban Area Detection in Remote Sensing ImagesIEEE Geoscience and Remote Sensing Letters, 2015
- Mapping of Agricultural Crops from Single High-Resolution Multispectral Images—Data-Driven Smoothing vs. Parcel-Based SmoothingRemote Sensing, 2015
- A Comparative Study of Bag-of-Words and Bag-of-Topics Models of EO Image PatchesIEEE Geoscience and Remote Sensing Letters, 2015
- Effective and Efficient Midlevel Visual Elements-Oriented Land-Use Classification Using VHR Remote Sensing ImagesIEEE Transactions on Geoscience and Remote Sensing, 2015
- Active Batch Selection via Convex Relaxations with Guaranteed Solution BoundsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- A New Method to Remove Noise in Magnetic Resonance and Ultrasound ImagesJournal of Scientific Research, 2010
- An algorithm for data-driven bandwidth selectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2003
- A post-processing technique to remove background noise from echo integration dataICES Journal of Marine Science, 1996
- The estimation of the gradient of a density function, with applications in pattern recognitionIEEE Transactions on Information Theory, 1975