PP-LinkNet: Improving Semantic Segmentation of High Resolution Satellite Imagery with Multi-stage Training

• URL: http://arxiv.org/abs/2010.06932v1
• Date: Wed, 14 Oct 2020 10:23:48 GMT
• Title: PP-LinkNet: Improving Semantic Segmentation of High Resolution Satellite Imagery with Multi-stage Training
• Authors: An Tran, Ali Zonoozi, Jagannadan Varadarajan, Hannes Kruppa
• Abstract summary: Road network and building footprint extraction is essential for many applications such as updating maps, traffic regulations, city planning, ride-hailing, disaster response textitetc.
• Score: 4.694536172504848
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Road network and building footprint extraction is essential for many applications such as updating maps, traffic regulations, city planning, ride-hailing, disaster response \textit{etc}. Mapping road networks is currently both expensive and labor-intensive. Recently, improvements in image segmentation through the application of deep neural networks has shown promising results in extracting road segments from large scale, high resolution satellite imagery. However, significant challenges remain due to lack of enough labeled training data needed to build models for industry grade applications. In this paper, we propose a two-stage transfer learning technique to improve robustness of semantic segmentation for satellite images that leverages noisy pseudo ground truth masks obtained automatically (without human labor) from crowd-sourced OpenStreetMap (OSM) data. We further propose Pyramid Pooling-LinkNet (PP-LinkNet), an improved deep neural network for segmentation that uses focal loss, poly learning rate, and context module. We demonstrate the strengths of our approach through evaluations done on three popular datasets over two tasks, namely, road extraction and building foot-print detection. Specifically, we obtain 78.19\% meanIoU on SpaceNet building footprint dataset, 67.03\% and 77.11\% on the road topology metric on SpaceNet and DeepGlobe road extraction dataset, respectively.

Related papers

• DeepTriNet: A Tri-Level Attention Based DeepLabv3+ Architecture for Semantic Segmentation of Satellite Images [0.0]
  This research proposes a tri-level attention-based DeepLabv3+ architecture (DeepTriNet) for semantic segmentation of satellite images. The proposed hybrid method combines squeeze-and-excitation networks (SENets) and tri-level attention units (TAUs) with the vanilla DeepLabv3+ architecture. The proposed DeepTriNet performs better than many conventional techniques with an accuracy of 98% and 77%, IoU 80% and 58%, precision 88% and 68%, and recall of 79% and 55% on the 4-class Land-Cover.ai dataset and the 15-class GID-2 dataset respectively.
  arXiv  Detail & Related papers  (2023-09-05T18:35:34Z)
• PaRK-Detect: Towards Efficient Multi-Task Satellite Imagery Road Extraction via Patch-Wise Keypoints Detection [12.145321599949236]
  We propose a new scheme for multi-task satellite imagery road extraction, Patch-wise Road Keypoints Detection (PaRK-Detect) Our framework predicts the position of patch-wise road keypoints and the adjacent relationships between them to construct road graphs in a single pass. We evaluate our approach against the existing state-of-the-art methods on DeepGlobe, Massachusetts Roads, and RoadTracer datasets and achieve competitive or better results.
  arXiv  Detail & Related papers  (2023-02-26T08:26:26Z)
• MultiScale Probability Map guided Index Pooling with Attention-based learning for Road and Building Segmentation [18.838213902873616]
  We propose a novel attention-aware segmentation framework, Multi-Scale Supervised Dilated Multiple-Path Attention Network (MSSDMPA-Net) MSSDMPA-Net is equipped with two new modules Dynamic Attention Map Guided Index Pooling (DAMIP) and Dynamic Attention Map Guided Spatial and Channel Attention (DAMSCA) to precisely extract the building footprints and road maps from remotely sensed images.
  arXiv  Detail & Related papers  (2023-02-18T19:57:25Z)
• GraphCSPN: Geometry-Aware Depth Completion via Dynamic GCNs [49.55919802779889]
  We propose a Graph Convolution based Spatial Propagation Network (GraphCSPN) as a general approach for depth completion. In this work, we leverage convolution neural networks as well as graph neural networks in a complementary way for geometric representation learning. Our method achieves the state-of-the-art performance, especially when compared in the case of using only a few propagation steps.
  arXiv  Detail & Related papers  (2022-10-19T17:56:03Z)
• Aerial Images Meet Crowdsourced Trajectories: A New Approach to Robust Road Extraction [110.61383502442598]
  We introduce a novel neural network framework termed Cross-Modal Message Propagation Network (CMMPNet) CMMPNet is composed of two deep Auto-Encoders for modality-specific representation learning and a tailor-designed Dual Enhancement Module for cross-modal representation refinement. Experiments on three real-world benchmarks demonstrate the effectiveness of our CMMPNet for robust road extraction.
  arXiv  Detail & Related papers  (2021-11-30T04:30:10Z)
• SPIN Road Mapper: Extracting Roads from Aerial Images via Spatial and Interaction Space Graph Reasoning for Autonomous Driving [64.10636296274168]
  Road extraction is an essential step in building autonomous navigation systems. Using just convolution neural networks (ConvNets) for this problem is not effective as it is inefficient at capturing distant dependencies between road segments in the image. We propose a Spatial and Interaction Space Graph Reasoning (SPIN) module which when plugged into a ConvNet performs reasoning over graphs constructed on spatial and interaction spaces projected from the feature maps.
  arXiv  Detail & Related papers  (2021-09-16T03:52:17Z)
• DeepSatData: Building large scale datasets of satellite images for training machine learning models [77.17638664503215]
  This report presents design considerations for automatically generating satellite imagery datasets for training machine learning models. We discuss issues faced from the point of view of deep neural network training and evaluation.
  arXiv  Detail & Related papers  (2021-04-28T15:13:12Z)
• Boundary-Aware Segmentation Network for Mobile and Web Applications [60.815545591314915]
  Boundary-Aware Network (BASNet) is integrated with a predict-refine architecture and a hybrid loss for highly accurate image segmentation. BASNet runs at over 70 fps on a single GPU which benefits many potential real applications. Based on BASNet, we further developed two (close to) commercial applications: AR COPY & PASTE, in which BASNet is augmented reality for "COPY" and "PASTING" real-world objects, and OBJECT CUT, which is a web-based tool for automatic object background removal.
  arXiv  Detail & Related papers  (2021-01-12T19:20:26Z)
• Scribble-based Weakly Supervised Deep Learning for Road Surface Extraction from Remote Sensing Images [7.1577508803778045]
  We propose a scribble-based weakly supervised road surface extraction method named ScRoadExtractor. To propagate semantic information from sparse scribbles to unlabeled pixels, we introduce a road label propagation algorithm. The proposal masks generated from the road label propagation algorithm are utilized to train a dual-branch encoder-decoder network.
  arXiv  Detail & Related papers  (2020-10-25T12:40:30Z)
• DiResNet: Direction-aware Residual Network for Road Extraction in VHR Remote Sensing Images [12.081877372552606]
  We present a direction-aware residual network (DiResNet) that includes three main contributions. The proposed method has advantages in both overall accuracy and F1-score.
  arXiv  Detail & Related papers  (2020-05-14T19:33:21Z)
• Real-Time High-Performance Semantic Image Segmentation of Urban Street Scenes [98.65457534223539]
  We propose a real-time high-performance DCNN-based method for robust semantic segmentation of urban street scenes. The proposed method achieves the accuracy of 73.6% and 68.0% mean Intersection over Union (mIoU) with the inference speed of 51.0 fps and 39.3 fps.
  arXiv  Detail & Related papers  (2020-03-11T08:45:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.