IEEE Transactions on Geoscience and Remote Sensing· 2016Q1
Convolutional Neural Networks for Large-Scale Remote-Sensing Image Classification
- 1,110citations
- Q1SCImago
- 2016year
Short summary
A novel end-to-end framework uses fully convolutional neural networks (CNNs) to directly generate pixelwise classification maps from satellite imagery, incorporating a multiscale neuron module for improved recognition and localization.
AI-generated from the title and abstract; the full text is not read.
Key points
- Proposes an end-to-end framework for direct pixelwise classification map generation from satellite images using CNNs.
- Introduces a two-step training approach: initialization with large, possibly inaccurate data, followed by refinement on small, accurate data.
- Designs a multiscale neuron module to overcome the tradeoff between recognition and precise localization.
- Demonstrates that the networks utilize large amounts of context for fine-grained classification maps.
AI-generated from the title and abstract; the full text is not read.
Abstract
We propose an end-to-end framework for the dense, pixelwise classification of satellite imagery with convolutional neural networks (CNNs). In our framework, CNNs are directly trained to produce classification maps out of the input images. We first devise a fully convolutional architecture and demonstrate its relevance to the dense classification problem. We then address the issue of imperfect training data through a two-step training approach: CNNs are first initialized by using a large amount of possibly inaccurate reference data, and then refined on a small amount of accurately labeled data. To complete our framework, we design a multiscale neuron module that alleviates the common tradeoff between recognition and precise localization. A series of experiments show that our networks consider a large amount of context to provide fine-grained classification maps.
The authors' abstract, as published at the source. IEEE Transactions on Geoscience and Remote Sensing, 2016 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Media Technology
Media TechnologyEngineering