The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLII-2/W13
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-2/W13, 13–20, 2019
https://doi.org/10.5194/isprs-archives-XLII-2-W13-13-2019
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-2/W13, 13–20, 2019
https://doi.org/10.5194/isprs-archives-XLII-2-W13-13-2019

  04 Jun 2019

04 Jun 2019

FULLY CONVOLUTIONAL NETWORKS FOR STREET FURNITURE IDENTIFICATION IN PANORAMA IMAGES

Y. Ao1, J. Wang2, M. Zhou3, R. C. Lindenbergh2, and M. Y. Yang1 Y. Ao et al.
  • 1Dept. of Earth Observation Science, Faculty ITC, University of Twente, The Netherlands
  • 2Dept. of Geoscience and Remote Sensing, Delft University of Technology, The Netherlands
  • 3Academy of Opto-Electronics, Chinese Academy of Sciences, China

Keywords: Panoramic Images, Semantic Segmentation, Street Furniture, Object Identification, Fully Convolutional Networks

Abstract. Panoramic images are widely used in many scenes, especially in virtual reality and street view capture. However, they are new for street furniture identification which is usually based on mobile laser scanning point cloud data or conventional 2D images. This study proposes to perform semantic segmentation on panoramic images and transformed images to separate light poles and traffic signs from background implemented by pre-trained Fully Convolutional Networks (FCN). FCN is the most important model for deep learning applied on semantic segmentation for its end to end training process and pixel-wise prediction. In this study, we use FCN-8s model that pre-trained on cityscape dataset and finetune it by our own data. The results show that in both pre-trained model and fine-tuning, transformed images have better prediction results than panoramic images.