2018 · 78 citations · 13 references
ComputingComputer ScienceComputer VisionMachine LearningMachine VisionDeep LearningImage ClassificationImage Feature EngineeringPattern RecognitionRemote Sensing Image AnalysisRepresentation LearningConvolutional Neural NetworksPost-processingPost-processing WorkflowRoad ExtractionRoad Feature DetectionSatellite Imagery AnalysisThresholds
With the recent advances of Convolutional Neural Networks (CNN) in computer vision, there have been rapid progresses in extracting roads and other features from satellite imagery for mapping and other purposes. In this paper, we propose a new method for road extraction using stacked UNets with multiple output. A hybrid loss function is used to address the problem of unbalanced classes of training data. Post-processing methods, including road map vectorization and shortest path search with hierarchical thresholds, help improve recall. The overall improvement of mean IoU compared to the vanilla VGG network is more than 20%.
13
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2016 · 222.1K citations · Full text
DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Images
İlke Demir, Krzysztof Koperski, David Lindenbaum et al. · 2018 · 1.1K citations · Full text