The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Publications Copernicus
Download
Citation
Articles | Volume XLIV-2/W1-2021
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIV-2/W1-2021, 149–154, 2021
https://doi.org/10.5194/isprs-archives-XLIV-2-W1-2021-149-2021
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIV-2/W1-2021, 149–154, 2021
https://doi.org/10.5194/isprs-archives-XLIV-2-W1-2021-149-2021

  15 Apr 2021

15 Apr 2021

A NOVEL APPROACH FOR PART BASED OBJECT MATCHING USING DISTANCE METRIC LEARNING WITH GRAPH CONVOLUTIONAL NETWORKS

V. Kozlov and A. Maysuradze V. Kozlov and A. Maysuradze
  • Lomonosov Moscow State University, Moscow, Russia

Keywords: Object tracking, Part based representation, Delaunay triangulation, Graph matching, Siamese network, Graph convolutional network, Distance metric learning

Abstract. Part-based object representation and part matching problem often appear in various areas of data analysis. A special case of particular interest is when parts are not fully separated, but in relations with each other. The natural way to model such objects are graphs, and part matching problem becomes graph matching problem. Over the years, many methods to solve graph matching problems have been proposed, but it remains relevant due to its complexity. We propose a novel approach to solving graph matching problem based on learning distance metric on graph vertices. We empirically demonstrate that our method outperforms traditional methods based on solving quadratic assignment problem. We also provide an theoretical estimation of computational complexity of proposed method.