Subgraph Learning for Topological Geolocalization: Comparison
View Latest Version
Please note this is a comparison between Version 2 by Catherine Yang and Version 1 by BING ZHA.

One of the challenges of spatial cognition, such as self-localization and navigation, is to develop an efficient learning approach capable of mimicking human ability. One of the enduring challenges for the autonomous agent in the field of geoinformatics, computer vision, and robotics is to determine its location in the environment. The concept of location is inherently relative, and one cannot describe the location of an object without providing a reference or map. 

  • geolocalization
  • subgraph
  • map
  • graph neural network

1. Introduction

The human brain is a brilliant information processor and is exceptionally skilled at finding one’s location on a map. Such extraordinary abilities have attracted much attention from neuroscientists seeking to explore and model how the human brain performs this fundamental cognitive task. An early neuroscience study has shown that an internal map of the environment referred to as the “cognitive map” uses a graph representation to locate oneself [2][1] and navigate to a designated destination [3][2]. For instance, in vector-based navigation agents can simply find their location on a map based on the distance they traversed and corners they turned [4,5][3][4]. Understanding such a process and building computational models is crucial to offer advanced artificial intelligent capabilities to a number of applications, including path planning [6][5] and navigation [7][6].
In parallel with the exploration of biological mechanisms for localization and navigation, engineered alternative solutions have also been designed to achieve such functionality. The most commonly used system is the GPS, which was established in the 1970s for outdoor positioning using the constellation of a satellite network [8][7]. Apart from GPS, traditional relative localization typically utilizes visual or inertial information to simultaneously compute the platform’s pose and 3D environmental structure [9][8]. Despite these studies, there is still no widely accepted solution for localization in challenging conditions, due to environmental confusers, sensor drifts, multi-path problems, and high computational costs.
Unlike the GPS embedded in devices, our brain’s system accesses location and navigation information by integrating multiple signals relating internal self-motion (path integration) [10][9] and planning direct trajectories to goals (vector-based navigation) [3,11][2][10]. Recent research [11,12][10][11] has shown that the mammalian brain uses an incredibly sophisticated GPS-like localization and tracking system of its own to help recognize locations and guide them from one location to the next. One typical method used is called path integration [10][9], a mechanism of calculating location simply by integrating self-motion information, including direction and speed of movement—a task carried out without reference to external cues such as physical landmarks. Another method suggested representing space as a graph structure in which nodes denote specific places and links are represented as roads between pairs of nodes [5][4]. The resulting graph reflects the topology of the explored environment upon which localization and navigation can be directly implemented by the graph search algorithm. This preseaper rch aims at exploiting characteristics from these two methods together.
With the recent progress in deep learning, especially for graph neural networks (GNN) [13,14,15[12][13][14][15],16], researchers have shown powerful models that yield expressive embedding of non-Euclidean data and result in promising performances in a variety of tasks [7,17,18][6][16][17]. 

2. Visual Localization

A major category of work in the literature is dedicated to the use of images for localization, referred to as visual localization. These methods can be classified into photogrammetric localization [20,21,22,23][18][19][20][21] and retrieval-based localization [24,25][22][23]. The first set of approaches assumes the scene is represented by 3D sparse point clouds, which are commonly generated from structure from motion [26][24]). Then, the camera pose for a given input image is directly estimated. The training dataset consists of pairs of images and the corresponding camera poses where the camera pose is usually represented by 6-DoF position and orientation. Despite their performance, the photogrammetric pipeline for generating and storing large 3D maps is not trivial and needs a large memory footprint. Another set of methods works by matching a given image to a database of location-tagged images or location-tagged image features. From the hand-craft features such as SIFT [27][25], bag-of-visual words [28][26], Fisher Vector [29][27] and VLAD [30][28], to the learned features [31,32][29][30], all of these approaches struggle to find a good representation robust to changes in viewpoint, appearance, and scale, which is a requirement hard to fulfill in practice. Furthermore, creating an up-to-date image/feature database seems at best costly if not impossible. There is also a potential privacy issue of storing visual descriptors in the database. 

3. Probabilistic Localization

A common form of localization problem is to use sensory readings to estimate the absolute coordinates of the object on the map using Bayesian filtering [33,34,35,36,37][31][32][33][34][35]. The authors of [33][31] presented a Bayesian approach to model the posterior distribution of the position given the prior map, which is considered a classic method commonly adopted in the robotics field. However, this method requires GPS readings and endures a rigorous mathematical model. In more recent studies [34[32][33],35], the authors proposed a probabilistic self-localization method using OpenStreetMap and visual odometry where the location is determined by matching with road topology. The authors of [36,37][34][35] presented a localization approach based on stochastic trajectory matching using brute-force search. However, all of these methods require the generation and maintenance of posterior distributions, which lead to complicated inference and high computational costs. For interested readers, a more comprehensive reference about probabilistic approaches is given in [38][36].

4. Topological Localization

There are a small number of studies closely related to ours that uses topological map and deep learning. Traditional approaches utilize topological road structures and try to match features onto the map using Chamfer distance and Hamming distance [39,40][37][38]. Chen et al. [7][6] proposed a topological approach to achieve localization and visual navigation using several different deep neural networks. However, the method aims at visual navigation problems and is only investigated in a small indoor environment. Wei et al. [41][39] proposed a sequence-to-sequence labeling method for trajectory matching using a neural machine translation network. This approach was shown to only work well on synthetic scenarios where the input trajectory was synthetically generated with a known sequence of nodes from the map. In [42][40], the author presented a variable-length sequence classification method for motion trajectory localization using a recurrent neural network, which largely inspired us to employ motion-based data to achieve localization. Zha et al. [43][41] introduced a topological map-based trajectory learning method and utilized hypotheses generation and pruning strategies to achieve consistent geolocalization of moving platforms where the problems were formulated as conditional sequence prediction. In contrast, this preseaperrch focuses on the node localization problem on a topological map based on motion trajectory and develops a subgraph embedding classification model using a graph neural network, which generalizes sequence representation to graph representation and preferably fits the graph-based map structure.

5. Vector-Based Navigation

In neuroscience, much of the literature focuses on studying the mechanisms of animals’ ability to learn maps, as well as self-localization and navigation [2,11,44][1][10][42]. These studies have shown that one typical method used in animals, such as desert ants, is path integration, which is a mechanism in which neurons calculate location by integrating self-motion. Self-motion includes direction and the speed of movement, which inspired us to utilize turning and distance information in this paper. In [5][4], the authors elaborated on a topological strategy for navigation using place cells [44,45][42][43] and metric vector navigation using grid cells [12][11], from a biological perspective.

6. GNN on Spatial Data

The idea of GNN is to generate representations of nodes, edges, or whole graphs that depend on the structure of the graph, as well as any feature information endowed by the graph. The basic GNN model can be motivated in a variety of ways, either from the perspective of a spatial domain [15,46][14][44] or a spectral domain [47,48][45][46]. Further comprehensive reviews can be found in [13,14,49][12][13][47]. In recent years, the GNN has extended its applications to geospatial data due to its powerful ability to model irregular data structures. For example, the authors of [50][48] combined the convolutional neural network and GNN to infer road attributes, which overcome the limitation of capturing the long-term spatial propagation of the features; the authors of [51][49] presented a graph neural network estimator for an estimated time of arrival (ETA), which accounts for complex spatiotemporal interactions and has been employed in production at Google Maps; and the authors of [52][50] improved the generalization ability of GNN through a sampling technique and demonstrated its performance on real-world street networks. Ref. [53][51] proposed a GNN architecture to extract road graphs from satellite images.

References

  1. Tolman, E.C. Cognitive maps in rats and men. Psychol. Rev. 1948, 55, 189.
  2. Erdem, U.M.; Hasselmo, M. A goal-directed spatial navigation model using forward trajectory planning based on grid cells. Eur. J. Neurosci. 2012, 35, 916–931.
  3. Banino, A.; Barry, C.; Uria, B.; Blundell, C.; Lillicrap, T.; Mirowski, P.; Pritzel, A.; Chadwick, M.J.; Degris, T.; Modayil, J.; et al. Vector-based navigation using grid-like representations in artificial agents. Nature 2018, 557, 429–433.
  4. Edvardsen, V.; Bicanski, A.; Burgess, N. Navigating with grid and place cells in cluttered environments. Hippocampus 2020, 30, 220–232.
  5. Dolgov, D.; Thrun, S.; Montemerlo, M.; Diebel, J. Path planning for autonomous vehicles in unknown semi-structured environments. Int. J. Robot. Res. 2010, 29, 485–501.
  6. Chen, K.; de Vicente, J.P.; Sepulveda, G.; Xia, F.; Soto, A.; Vázquez, M.; Savarese, S. A Behavioral Approach to Visual Navigation with Graph Localization Networks. In Proceedings of the Robotics: Science and Systems, Breisgau, Germany, 22–26 June 2019.
  7. Reid, T.G.; Chan, B.; Goel, A.; Gunning, K.; Manning, B.; Martin, J.; Neish, A.; Perkins, A.; Tarantino, P. Satellite navigation for the age of autonomy. In Proceedings of the 2020 IEEE/ION Position, Location and Navigation Symposium (PLANS), Portland, ON, USA, 20–23 April 2020; pp. 342–352.
  8. Cadena, C.; Carlone, L.; Carrillo, H.; Latif, Y.; Scaramuzza, D.; Neira, J.; Reid, I.; Leonard, J.J. Past, present, and future of simultaneous localization and mapping: Toward the robust-perception age. IEEE Trans. Robot. 2016, 32, 1309–1332.
  9. McNaughton, B.L.; Battaglia, F.P.; Jensen, O.; Moser, E.I.; Moser, M.B. Path integration and the neural basis of the ‘cognitive map’. Nat. Rev. Neurosci. 2006, 7, 663–678.
  10. Bush, D.; Barry, C.; Manson, D.; Burgess, N. Using grid cells for navigation. Neuron 2015, 87, 507–520.
  11. Hafting, T.; Fyhn, M.; Molden, S.; Moser, M.B.; Moser, E.I. Microstructure of a spatial map in the entorhinal cortex. Nature 2005, 436, 801–806.
  12. Bronstein, M.M.; Bruna, J.; LeCun, Y.; Szlam, A.; Vandergheynst, P. Geometric deep learning: Going beyond euclidean data. IEEE Signal Process. Mag. 2017, 34, 18–42.
  13. Battaglia, P.W.; Hamrick, J.B.; Bapst, V.; Sanchez-Gonzalez, A.; Zambaldi, V.; Malinowski, M.; Tacchetti, A.; Raposo, D.; Santoro, A.; Faulkner, R.; et al. Relational inductive biases, deep learning, and graph networks. arXiv 2018, arXiv:1806.01261.
  14. Hamilton, W.; Ying, Z.; Leskovec, J. Inductive representation learning on large graphs. In Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA, 4–9 December 2017; pp. 1024–1034.
  15. Xu, K.; Hu, W.; Leskovec, J.; Jegelka, S. How powerful are graph neural networks? arXiv 2018, arXiv:1810.00826.
  16. Sarlin, P.E.; DeTone, D.; Malisiewicz, T.; Rabinovich, A. Superglue: Learning feature matching with graph neural networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA, 13–19 June 2020; pp. 4938–4947.
  17. Shi, W.; Rajkumar, R. Point-gnn: Graph neural network for 3d object detection in a point cloud. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA, 13–19 June 2020; pp. 1711–1719.
  18. Kendall, A.; Cipolla, R. Geometric loss functions for camera pose regression with deep learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 21–26 July 2017; pp. 5974–5983.
  19. Sattler, T.; Leibe, B.; Kobbelt, L. Fast image-based localization using direct 2d-to-3d matching. In Proceedings of the 2011 International Conference on Computer Vision, Barcelona, Spain, 6–13 November 2011; pp. 667–674.
  20. Sattler, T.; Zhou, Q.; Pollefeys, M.; Leal-Taixe, L. Understanding the limitations of cnn-based absolute camera pose regression. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA, 15–20 June 2019; pp. 3302–3312.
  21. Weyand, T.; Kostrikov, I.; Philbin, J. Planet-photo geolocation with convolutional neural networks. In Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands, 11–14 October 2016; pp. 37–55.
  22. Hays, J.; Efros, A.A. IM2GPS: Estimating geographic information from a single image. In Proceedings of the 2008 IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, Alaska, 23–28 June 2008; pp. 1–8.
  23. Walch, F.; Hazirbas, C.; Leal-Taixe, L.; Sattler, T.; Hilsenbeck, S.; Cremers, D. Image-based localization using lstms for structured feature correlation. In Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy, 22–29 October 2017; pp. 627–637.
  24. Schonberger, J.L.; Frahm, J.M. Structure-from-motion revisited. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 27–30 June 2016; pp. 4104–4113.
  25. Lowe, D.G. Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 2004, 60, 91–110.
  26. Philbin, J.; Chum, O.; Isard, M.; Sivic, J.; Zisserman, A. Object retrieval with large vocabularies and fast spatial matching. In Proceedings of the 2007 IEEE Conference on Computer Vision and Pattern Recognition, Minneapolis, MI, USA, 18–23 June 2007; pp. 1–8.
  27. Perronnin, F.; Liu, Y.; Sánchez, J.; Poirier, H. Large-scale image retrieval with compressed fisher vectors. In Proceedings of the 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Francisco, CA, USA, 13–18 June 2010; pp. 3384–3391.
  28. Jégou, H.; Douze, M.; Schmid, C.; Pérez, P. Aggregating local descriptors into a compact image representation. In Proceedings of the 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Francisco, CA, USA, 13–18 June 2010; pp. 3304–3311.
  29. Arandjelovic, R.; Gronat, P.; Torii, A.; Pajdla, T.; Sivic, J. NetVLAD: CNN architecture for weakly supervised place recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 27–30 June 2016; pp. 5297–5307.
  30. Lin, T.Y.; Cui, Y.; Belongie, S.; Hays, J. Learning deep representations for ground-to-aerial geolocalization. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA, 7–12 June 2015; pp. 5007–5015.
  31. Oh, S.M.; Tariq, S.; Walker, B.N.; Dellaert, F. Map-based priors for localization. In Proceedings of the 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No. 04CH37566), Sendai, Japan, 28 September–2 October 2004; Volume 3, pp. 2179–2184.
  32. Brubaker, M.A.; Geiger, A.; Urtasun, R. Map-based probabilistic visual self-localization. IEEE Trans. Pattern Anal. Mach. Intell. 2015, 38, 652–665.
  33. Floros, G.; Van Der Zander, B.; Leibe, B. Openstreetslam: Global vehicle localization using openstreetmaps. In Proceedings of the 2013 IEEE International Conference on Robotics and Automation, Karlsruhe, Germany, 6–10 May 2013; pp. 1054–1059.
  34. Gupta, A.; Chang, H.; Yilmaz, A. Gps-denied geo-localisation using visual odometry. In Proceedings of the ISPRS Annual Photogrammetry, Remote Sensing Spatial Information Science, Prague, Czech Republic, 12–19 July 2016; pp. 263–270.
  35. Gupta, A.; Yilmaz, A. Ubiquitous real-time geo-spatial localization. In Proceedings of the Eighth ACM SIGSPATIAL International Workshop on Indoor Spatial Awareness, Burlingame, CA, USA, 31 October 2016; pp. 1–10.
  36. Thrun, S. Probabilistic robotics. Commun. ACM 2002, 45, 52–57.
  37. Costea, D.; Leordeanu, M. Aerial image geolocalization from recognition and matching of roads and intersections. arXiv 2016, arXiv:1605.08323.
  38. Panphattarasap, P.; Calway, A. Automated map reading: Image based localisation in 2-D maps using binary semantic descriptors. In Proceedings of the 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Madrid, Spain, 1–5 October 2018; pp. 6341–6348.
  39. Wei, J.; Koroglu, M.T.; Zha, B.; Yilmaz, A. Pedestrian localization on topological maps with neural machine translation network. In Proceedings of the 2019 IEEE Sensors, Montreal, QC, Canada, 27–30 October 2019; pp. 1–4.
  40. Zha, B.; Koroglu, M.T.; Yilmaz, A. Trajectory Mining for Localization Using Recurrent Neural Network. In Proceedings of the 2019 International Conference on Computational Science and Computational Intelligence (CSCI), Las Vegas, NV, USA, 5–7 December 2019; pp. 1329–1332.
  41. Zha, B.; Yilmaz, A. Learning maps for object localization using visual-inertial odometry. ISPRS Ann. Photogramm. Remote Sens. Spat. Inf. Sci. 2020, 1, 343–350.
  42. O’Keefe, J. Place units in the hippocampus of the freely moving rat. Exp. Neurol. 1976, 51, 78–109.
  43. O’Keefe, J.; Dostrovsky, J. The hippocampus as a spatial map: Preliminary evidence from unit activity in the freely-moving rat. Brain Res. 1971, 34, 171–175.
  44. Fey, M.; Lenssen, J.E.; Weichert, F.; Müller, H. Splinecnn: Fast geometric deep learning with continuous b-spline kernels. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 18–23 June 2018; pp. 869–877.
  45. Henaff, M.; Bruna, J.; LeCun, Y. Deep convolutional networks on graph-structured data. arXiv 2015, arXiv:1506.05163.
  46. Kipf, T.N.; Welling, M. Semi-supervised classification with graph convolutional networks. arXiv 2016, arXiv:1609.02907.
  47. Wu, Z.; Pan, S.; Chen, F.; Long, G.; Zhang, C.; Philip, S.Y. A comprehensive survey on graph neural networks. IEEE Trans. Neural Netw. Learn. Syst. 2020, 32, 4–24.
  48. He, S.; Bastani, F.; Jagwani, S.; Park, E.; Abbar, S.; Alizadeh, M.; Balakrishnan, H.; Chawla, S.; Madden, S.; Sadeghi, M.A. RoadTagger: Robust road attribute inference with graph neural networks. In Proceedings of the AAAI Conference on Artificial Intelligence, New York, NY, USA, 7–12 February 2020; Volume 34, pp. 10965–10972.
  49. Derrow-Pinion, A.; She, J.; Wong, D.; Lange, O.; Hester, T.; Perez, L.; Nunkesser, M.; Lee, S.; Guo, X.; Wiltshire, B.; et al. ETA Prediction with Graph Neural Networks in Google Maps. arXiv 2021, arXiv:2108.11482.
  50. Iddianozie, C.; McArdle, G. Improved Graph Neural Networks for Spatial Networks Using Structure-Aware Sampling. ISPRS Int. J. Geo-Inf. 2020, 9, 674.
  51. Bahl, G.; Bahri, M.; Lafarge, F. Road extraction from overhead images with graph neural networks. arXiv 2021, arXiv:2112.05215.
More
© Text is available under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/)
Video Production Service
Feedback