Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

GPU based building footprint identification utilising self-attention multiresolution analysis

GPU based building footprint identification utilising self-attention multiresolution analysis Techniques for the semantic segmentation of remotely sensed imageries for building footprint identification have been widely studied and several supervised and unsupervised techniques have been proposed. The ability to perform online mapping and accurate segmentation on a large scale by taking into account the multifariousness inherent in aerial images has important implications. In this paper we propose a new method for building footprint identification using multiresolution analysis-based self-attention technique. The scheme is promising to be robust in the face of variability inherent in remotely sensed images by virtue of the capability to extract features at multiple scales and focusing on areas containing meaningful information. We demonstrate the robustness of the proposed method by comparing it against several state-of-the-art techniques using aerial imagery with varying spatial resolution and building clutter and it achieves better accuracy around 95% even under widely disparate image characteristics. We also evaluate the ability for online mapping on an embedded graphic processing unit (GPU) and compare it against different compute engines and it is found that the proposed method on GPU outperforms the other methods in terms of accuracy and processing time. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png All Earth Taylor & Francis

GPU based building footprint identification utilising self-attention multiresolution analysis

Ansari, Rizwan Ahmed; Ramachandran, Akshat; Thomas, Winnie
All Earth , Volume 35 (1): 10 – Dec 31, 2023
Download PDF
10 pages

GPU based building footprint identification utilising self-attention multiresolution analysis

Abstract

Techniques for the semantic segmentation of remotely sensed imageries for building footprint identification have been widely studied and several supervised and unsupervised techniques have been proposed. The ability to perform online mapping and accurate segmentation on a large scale by taking into account the multifariousness inherent in aerial images has important implications. In this paper we propose a new method for building footprint identification using multiresolution analysis-based...
Loading next page...
 
/lp/taylor-francis/gpu-based-building-footprint-identification-utilising-self-attention-u3Fvk9rYwG
Publisher
Taylor & Francis
Copyright
© 2023 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.
eISSN
2766-9645
DOI
10.1080/27669645.2023.2202961
Publisher site
See Article on Publisher Site

Abstract

Techniques for the semantic segmentation of remotely sensed imageries for building footprint identification have been widely studied and several supervised and unsupervised techniques have been proposed. The ability to perform online mapping and accurate segmentation on a large scale by taking into account the multifariousness inherent in aerial images has important implications. In this paper we propose a new method for building footprint identification using multiresolution analysis-based self-attention technique. The scheme is promising to be robust in the face of variability inherent in remotely sensed images by virtue of the capability to extract features at multiple scales and focusing on areas containing meaningful information. We demonstrate the robustness of the proposed method by comparing it against several state-of-the-art techniques using aerial imagery with varying spatial resolution and building clutter and it achieves better accuracy around 95% even under widely disparate image characteristics. We also evaluate the ability for online mapping on an embedded graphic processing unit (GPU) and compare it against different compute engines and it is found that the proposed method on GPU outperforms the other methods in terms of accuracy and processing time.

Journal

All Earth – Taylor & Francis

Published: Dec 31, 2023

Keywords: Urban analysis; building identification; multiresolution analysis; self-attenuation; graphic processing unit

References

  • Aerial LaneNet: Lane-marking semantic segmentation in aerial imagery using waveletenhanced cost-sensitive symmetric fully convolutional neural networks
  • Self-attention-based deep feature fusion for remote sensing scene classification
  • ASF-Net: Adaptive screening feature network for building footprint extraction from remote-sensing images
  • SG-NN: Sparse generative neural networks for self-supervised scene completion of RGB-D scans
  • Dual attention network for scene segmentation
  • Open cities AI challenge dataset”, version 1.0
  • Fully convolutional networks for multisource building extraction from an open aerial and satellite imagery data set
  • Deep residual learning for image recognition
  • Deep learning-based building footprint extraction with missing annotations
  • UNetFormer: A UNet-like transformer for efficient semantic segmentation of remote sensing urban scene imagery
  • MACU-Net for semantic segmentation of fine-resolution remotely sensed images
  • Attention residual U-Net for building segmentation in aerial images
  • Focal loss for dense object detection
  • SCAttNet: Semantic segmentation network with spatial and channel attention mechanism for high-resolution remote sensing images
  • RoadNet: Learning to comprehensively analyze road networks in complex urban scenes from high-resolution remotely sensed images
  • Fully convolutional networks for semantic segmentation
  • Dual-resolution U-Net: Building extraction from aerial images
  • Class-guided swin transformer for semantic segmentation of remote sensing imagery
  • U-Net: Convolutional net- works for biomedical image segmentation
  • An unsupervised framework to extract the diverse building from the satellite images using Grab-cut method
  • Learning local feature descriptors using convex optimisation
  • Building extraction with vision transformer
  • Automatic building rooftop extraction from aerial images via hierarchical RGB-D priors
  • A lightweight model of VGG-16 for remote sensing image classification
  • MarkCapsNet: Road marking extraction from aerial images using self-attention-guided capsule network
  • Self-enhanced SVM extraction of building objects from high resolution satellite images
  • Road extraction by deep residual U-Net