Abstract
In this paper, we propose a novel, efficient and fast method to extract the walkable area from high-resolution aerial images for the purpose of computer-aided evacuation simulation for major public events. Compared to previous work, where authors only extracted roads and streets or solely focused on indoor scenarios, we present an approach to fully segment the walkable area of large outdoor environments. We address this challenge by modeling human movements in the terrain with a sophisticated seeded region growing algorithm (SRG), which utilizes digital surface models, true-orthophotos and inclination maps computed from aerial images. Further, we propose a novel annotation and scoring scheme especially developed for assessing the quality of the extracted evacuation maps. Finally, we present an extensive quantitative and qualitative evaluation, where we show the feasibility of our approach by evaluating different combinations of SRG methods and parameter settings on several real-world scenarios.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Helbing, D., Mukerji, P.: Crowd disasters as systemic failures: analysis of the love parade disaster. EPJ Data Sci. 1, 1–40 (2012)
Krausz, B., Bauckhage, C.: Loveparade 2010: automatic video analysis of a crowd disaster. Comput. Vis. Image Underst. 116, 307–319 (2012)
Hsu, E.B., Burkle, F.M.: Cambodian bon om touk stampede highlights preventable tragedy. Prehospital Disaster Med. 27, 481–482 (2012)
Taubenböck, H., Post, J., Kiefl, R., Roth, A., Ismail, F.A., Strunz, G., Dech, S.: Risk and vulnerability assessment to tsunami hazard using very high resolution satellite data: the case study of padang, indonesia. EARSeL eProceeding 8, 53–63 (2009)
Lämmel, G., Grether, D., Nagel, K.: The representation and implementation of time-dependent inundation in large-scale microscopic evacuation simulations. Transp. Res. Part C Emerg. Technol. 18, 84–98 (2010)
Schenk, F., Rüther, M., Bischof, H.: Automated segmentation of the walkable area from aerial images for evacuation simulation. In: Proceedings of the 2nd International Conference on Geographical Information Systems Theory, Applications and Management, pp. 125–135 (2016)
Galea, E.R.: Simulating evacuation and circulation in planes, trains, buildings and ships using the exodus software. In: Pedestrian and Evacuation Dynamics, pp. 203–225. Springer (2002)
Klüpfel, H.: The simulation of crowds at very large events. In: Schadschneider A., Pöschel, T., Kühne, R., Schreckenberg, M., Wolf, D.E. (eds) Traffic and Granular Flow 2005. Springer, Heidelberg (2007)
Tsai, J., Fridman, N., Bowring, E., Brown, M., Epstein, S., Kaminka, G., Marsella, S., Ogden, A., Rika, I., Sheel, A., et al.: Escapes: evacuation simulation with children, authorities, parents, emotions, and social comparison. In: AAMAS, pp. 457–464 (2011)
Schneider, V., Könnecke, R.: Simulating evacuation processes with aseri. In: Pedestrian and Evacuation Dynamics, pp. 301–313 (2001)
Johnson, C.W.: Olympic venues. Safety Sci. 46(2008), 302–322 (2012)
Shi, C., Zhong, M., Nong, X., He, L., Shi, J., Feng, G.: Modeling and safety strategy of passenger evacuation in a metro station in China. Safety Sci. 50, 1319–1332 (2012)
Tang, F., Ren, A.: GIS-based 3d evacuation simulation for indoor fire. Build. Environ. 49, 193–202 (2012)
Mas, E., Adriano, B., Koshimura, S.: An integrated simulation of tsunami hazard and human evacuation in la punta, peru. J. Disaster Res. 8, 285–295 (2013)
Koch, D.B., Payne, P.W.: An incident management preparedness and coordination toolkit. In: Global Humanitarian Technology Conference (GHTC), pp. 31–35. IEEE (2012)
Dal Poz, A.P., Gallis, R.A., da Silva, J.F., Martins, É.F.: Object-space road extraction in rural areas using stereoscopic aerial images. IEEE Geosci. Remote Sens. Lett. 9, 654–658 (2012)
Hu, J., Razdan, A., Femiani, J.C., Cui, M., Wonka, P.: Road network extraction and intersection detection from aerial images by tracking road footprints. IEEE Trans. Geosci. Remote Sens. 45, 4144–4157 (2007)
Lin, Y., Saripalli, S.: Road detection and tracking from aerial desert imagery. J. Intell. Robot. Syst. 65, 345–359 (2012)
Zhou, H., Kong, H., Wei, L., Creighton, D., Nahavandi, S.: Efficient road detection and tracking for unmanned aerial vehicle. IEEE Trans. Intell. Transp. Syst. 16, 297–309 (2015)
Cheriyadat, A.M.: Unsupervised feature learning for aerial scene classification. IEEE Trans. Geosci. Remote Sens. 52, 439–451 (2014)
Huth, J., Kuenzer, C., Wehrmann, T., Gebhardt, S., Tuan, V.Q., Dech, S.: Land cover and land use classification with twopac: towards automated processing for pixel-and object-based image classification. Remote Sens. 4, 2530–2553 (2012)
Han, J., Zhang, D., Cheng, G., Guo, L., Ren, J.: Object detection in optical remote sensing images based on weakly supervised learning and high-level feature learning. Trans. Geosci. Remote Sens. 53, 3325–3337 (2015)
Adams, R., Bischof, L.: Seeded region growing. IEEE Trans. Pattern Anal. Mach. Intell. 16, 641–647 (1994)
Irschara, A., Rumpler, M., Meixner, P., Pock, T., Bischof, H.: Efficient and globally optimal multi view dense matching for aerial images. ISPRS Ann. Photogrammetry Remote Sens. Spatial Inf. Sci. 1, 227–232 (2012)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60, 91–110 (2004)
Fischler, M.A., Bolles, R.C.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM 24, 381–395 (1981)
Triggs, B., McLauchlan, P.F., Hartley, R.I., Fitzgibbon, A.W.: Bundle adjustment — a modern synthesis. In: Triggs, B., Zisserman, A., Szeliski, R. (eds.) IWVA 1999. LNCS, vol. 1883, pp. 298–372. Springer, Heidelberg (2000). doi:10.1007/3-540-44480-7_21
Rumpler, M., Wendel, A., Bischof, H.: Probabilistic range image integration for DSM and true-orthophoto generation. In: Kämäräinen, J.-K., Koskela, M. (eds.) SCIA 2013. LNCS, vol. 7944, pp. 533–544. Springer, Heidelberg (2013). doi:10.1007/978-3-642-38886-6_50
Collins, R.T.: A space-sweep approach to true multi-image matching. In: Computer Vision and Pattern Recognition, pp. 358–363. IEEE (1996)
Holz, D., Holzer, S., Rusu, R.B., Behnke, S.: Real-time plane segmentation using RGB-D cameras. In: Röfer, T., Mayer, N.M., Savage, J., Saranlı, U. (eds.) RoboCup 2011. LNCS, vol. 7416, pp. 306–317. Springer, Heidelberg (2012). doi:10.1007/978-3-642-32060-6_26
Rudin, L., Osher, S., Fatemi, E.: Nonlinear total variation based noise removal algorithms. Physica D Nonlinear Phenom. 60, 259–268 (1992)
Chambolle, A., Pock, T.: A first-order primal-dual algorithm for convex problems with applications to imaging. J. Math. Imag. Vis. 40, 120–145 (2011)
Dice, L.R.: Measures of the amount of ecologic association between species. Ecology 26, 297–302 (1945)
Jaccard, P.: Nouvelles recherches sur la distribution florale (1908)
Acknowledgements
This work was financed by the KIRAS program (no 840858, AIRPLAN) under supervision of the Austrian Research Promotion Agency (FFG) and in cooperation with the Austrian Ministry for Traffic, Innovation and Technology (BMVIT).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
A Appendix
A Appendix
In the Appendix, we show a typical evacuation simulation scenario where our generated digital map can be used. We use the map of the Marienhof (Munich, Germany) generated in Experiment A and utilize the software tool PedGo [8]. The package comprises three different programs:
-
PedEd - Used for editing the map, placing persons and marking the exits
-
PedGo - The simulation program, where various scenarios can be simulated
-
PedView - A 3D visualization of the previously calculated simulations
The first step is always loading the map into the editor PedEd and placing the exits (see Fig. 10, left). They are usually at the end of the streets leading away from the central area. After that, persons (or agents) can be put onto the map and corrections to the map can be made. The whole process usually takes less than three minutes. The next step is starting the simulation tool (PedGo) and loading the project. To get an estimate of the average evacuation time, multiple simulations should be performed (see Fig. 10, right). With PedView we can then view simulation files generated with PedGo in full 3D (see Fig. 11).
With PedEd the extracted CAD model can be edited and then various simulations can be performed with PedGo.
PedView can present the simulations calculated with PedGo in 3D.
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Schenk, F., Rüther, M., Bischof, H. (2017). Automated Walkable Area Segmentation from Aerial Images for Evacuation Simulation. In: Grueau, C., Laurini, R., Rocha, J. (eds) Geographical Information Systems Theory, Applications and Management. GISTAM 2016. Communications in Computer and Information Science, vol 741. Springer, Cham. https://doi.org/10.1007/978-3-319-62618-5_6
Download citation
DOI: https://doi.org/10.1007/978-3-319-62618-5_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-62617-8
Online ISBN: 978-3-319-62618-5
eBook Packages: Computer ScienceComputer Science (R0)