Reconstruction of Textured Meshes for Fire and Heat Source Detection

Automated fire and heat source detection is a helpful and important capability of a robotic system to assist firefighters in various search and rescue (SAR) scenarios. In this paper, we investigate thermal mapping using textured meshes from preregistered LIDAR scans and show how to detect and localize heat sources therein. Further, we propose a novel occupancy mapping approach based on a sparse permutohedral lattice with a contradiction indicator deduced from ray-tracing the mesh. We evaluate our system on three datasets recorded with a micro aerial vehicle (MAV) including heat sources in a hall and real flames at a fire brigades training site. Dynamic objects are removed from the mesh, heat sources are located and their extend estimated.

[1]  Sven Behnke,et al.  Detection and Tracking of Small Objects in Sparse 3D Laser Range Data , 2019, 2019 International Conference on Robotics and Automation (ICRA).

[2]  Erik Reinhard,et al.  Photographic tone reproduction for digital images , 2002, ACM Trans. Graph..

[3]  Girum G. Demisse,et al.  Interpreting thermal 3D models of indoor environments for energy efficiency , 2013, 2013 16th International Conference on Advanced Robotics (ICAR).

[4]  Sebastian G. Elbaum,et al.  Smokey comes of age: unmanned aerial systems for fire management , 2016 .

[5]  Peter V. Gehler,et al.  Sparse Convolutional Networks using the Permutohedral Lattice , 2015, ArXiv.

[6]  Sven Behnke,et al.  Registration of non-uniform density 3D laser scans for mapping with micro aerial vehicles , 2015 .

[7]  Andrew Adams,et al.  Fast High‐Dimensional Filtering Using the Permutohedral Lattice , 2010, Comput. Graph. Forum.

[8]  David H. Douglas,et al.  ALGORITHMS FOR THE REDUCTION OF THE NUMBER OF POINTS REQUIRED TO REPRESENT A DIGITIZED LINE OR ITS CARICATURE , 1973 .

[9]  F. Nex,et al.  UAV for 3D mapping applications: a review , 2014 .

[10]  Hideo Saito,et al.  Superimposing Thermal-Infrared Data on 3D Structure Reconstructed by RGB Visual Odometry , 2018, IEICE Trans. Inf. Syst..

[11]  Bernardo Wagner,et al.  Tempered point clouds and octomaps: A step towards true 3D temperature measurement in unknown environments , 2017, 2017 IEEE International Symposium on Safety, Security and Rescue Robotics (SSRR).

[12]  Bernardo Wagner,et al.  Fusion of radar, LiDAR and thermal information for hazard detection in low visibility environments , 2017, 2017 IEEE International Symposium on Safety, Security and Rescue Robotics (SSRR).

[13]  Sridha Sridharan,et al.  Real-Time Mobile 3D Temperature Mapping , 2015, IEEE Sensors Journal.

[14]  Matthias Nießner,et al.  State of the Art on 3D Reconstruction with RGB‐D Cameras , 2018, Comput. Graph. Forum.

[15]  Hannes Kaufmann,et al.  3D building reconstruction and thermal mapping in fire brigade operations , 2013, 2013 IEEE Virtual Reality (VR).

[16]  Alexander Ferrein,et al.  Evaluation of sensors and mapping approaches for disasters in tunnels , 2013, 2013 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR).

[17]  Florian Bugarin,et al.  Automated thermal 3D reconstruction based on a robot equipped with uncalibrated infrared stereovision cameras , 2018, Adv. Eng. Informatics.

[18]  Marco Scaioni,et al.  INTEGRATION OF INFRARED THERMOGRAPHY AND PHOTOGRAMMETRIC SURVEYING OF BUILT LANDSCAPE , 2017 .

[19]  Michael Garland,et al.  Simplifying surfaces with color and texture using quadric error metrics , 1998, IEEE Visualization.

[20]  Sven Behnke,et al.  Semi-supervised Semantic Mapping Through Label Propagation with Semantic Texture Meshes , 2019, International Journal of Computer Vision.

[21]  Michael M. Kazhdan,et al.  Screened poisson surface reconstruction , 2013, TOGS.

[22]  Mario Gianni,et al.  Rescue robots at earthquake-hit Mirandola, Italy: A field report , 2012, 2012 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR).

[23]  Andreas Nüchter,et al.  Thermal 3D Mapping of Building Façades , 2012, IAS.

[24]  Grit Thürmer,et al.  Computing Vertex Normals from Polygonal Facets , 1998, J. Graphics, GPU, & Game Tools.

[25]  Ingo Wald,et al.  Embree: a kernel framework for efficient CPU ray tracing , 2014, ACM Trans. Graph..

[26]  Václav Hlavác,et al.  Deployment of ground and aerial robots in earthquake-struck Amatrice in Italy (brief report) , 2016, 2016 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR).

[27]  Wolfram Burgard,et al.  Vision-based Autonomous Landing in Catastrophe-Struck Environments , 2018, ArXiv.

[28]  Guilherme N. DeSouza,et al.  A New 4D-RGB Mapping Technique for Field-Based High-Throughput Phenotyping , 2018, BMVC.

[29]  Dan B. Goldman,et al.  Vignette and exposure calibration and compensation , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[30]  Youngjib Ham,et al.  3D as-is building energy modeling and diagnostics: A review of the state-of-the-art , 2015, Adv. Eng. Informatics.

[31]  Hideo Saito,et al.  Registration of RGB and Thermal Point Clouds Generated by Structure From Motion , 2017, 2017 IEEE International Conference on Computer Vision Workshops (ICCVW).

[32]  Pileun Kim,et al.  Robotic sensing and object recognition from thermal-mapped point clouds , 2017, International Journal of Intelligent Robotics and Applications.

[33]  Youmin Zhang,et al.  A survey on technologies for automatic forest fire monitoring, detection, and fighting using unmanned aerial vehicles and remote sensing techniques , 2015 .