Abstract：The surface temperature field model effectively reflects the temperature distribution on the surface of the object. Since the image information collected from one single viewpoint cannot cover the entire object, it is difficult to reconstruct the temperature field of the entire object surface. Additionally, in the temperature field model, the presence of non-target objects can affect temperature model analysis. A method for reconstructing the objects surface temperature field based on a multi-view thermal image sequence was proposed. Firstly, a semantic segmentation algorithm was employed to extract the contours of the target object from visible light images, and then the fusion of the single view temperature point cloud of the target object was achieved by combining depth data with temperature information from the thermal image. Subsequently, the method of multi-view image data and multi-view temperature point cloud stitching was adopted, and the initial stitching of the temperature point cloud was carried out using the poses of cameras from various viewpoints, the multi-view LM-ICP algorithm was applied to optimize the registration of the global temperature point cloud. Experimental results show that the method effectively reconstructs the object surface temperature field model, and has small size error(2.61mm) and temperature errors(0.56℃).
AIGER D, MITRA N J, COHEN-OR D. 4-points congruent sets for robust pairwise surface registration ［R］.ACM SIGGRAPH 2008 papers. 2008.
CAO Y P, XU B B, HE Z W, et al. Research progress of infrared thermal imaging signal processing technology ［J］. Journal of Vibration,Measurement & Diagnosis, 2018, 38(2): 219-227.
［4］
DLESK A, VACH K, PAVELKA K. Photogrammetric co-processing of thermal infrared images and RGB images ［J］. Sensors, 2022, 22(4): 1655-1676.
［6］
MA Y, WANG Y, MEI X, et al. Visible/Infrared Combined 3D Reconstruction Scheme Based on Nonrigid Registration of Multi-Modality Images With Mixed Features ［J］. IEEE Access, 2019, 7: 19199-19211.
XU S Y, ZHU J H, TIAN Z Q, et al. Stepwise refinement method for multi-view point cloud registration ［J］. Acta Automatica Sinica, 2019, 45(8): 1486-1494.
YANG Y L, XU C. Fusion and reconstruction method of three-dimensional temperature field on human body surface ［J］.Infrared Technology, 2022,44(1):33-40.
［11］
PANTOJA-ROSERO B G, ACHANTA R, KOZINSKI M, et al. Generating LOD3 building models from structure-from-motion and semantic segmentation ［J］. Automation in Construction, 2022, 141: 104430-104445.
CHEN B Y, SUN S Y, YE G L, et al. 3D reconstruction method of monocular infrared video based on visual odometry ［J］. Laser and Infrared, 2017, 47(10): 1271-1275.
［13］
Intel. Intel RealSense Product Family D400 Series datasheet ［EB/OL］.［2023-08-04］.https://dev.intelrealsense.com/docs/intel-realsense-d400-series-product-family-datasheet.
［25］
HAARBACH A. Multiview ICP［EB/OL］.http: //www. adrian-haarbach. de/mv-lm-icp/docs/mv-lm-icp. pdf.
［27］
KAZHDAN M, BOLITHO M, HOPPE H. Poisson surface reconstruction ［C］// Proceedings of the fourth Eurographics Symposium on Geometry Processing. 2006.
ZHANG Y H, XU B R, ZHU J J, et al. Reconstruction of 3D temperature model based on fusion of visible light and thermal image ［J］. Acta Metrology Sinica, 2022, 43(2): 256-263.
ZHANG Z Y. Flexible camera calibration by viewing a plane from unknown orientations［C］//Proceedings of the Seventh IEEE International Conference on Computer Vision. Kerkyra, Greece, 1999.
［19］
CHEN L C, ZHU Y, PAPANDREOU G, et al. Encoder-decoder with atrous separable convolution for semantic image segmentation ［C］// Proceedings of the European conference on computer vision (ECCV). 2018.
LIU Y W, BI Y W, ZHANG L J, et al. Research on multi-view point cloud registration based on depth sensor ［J］. Laser Journal,2024,45(3):161-167.
［22］
MELLADO N, AIGER D, MITRA N J. Super 4PCS Fast Global Pointcloud Registration via Smart Indexing ［J］. Computer Graphics Forum, 2014, 33(5): 205-215.
LU T D, YUAN Z C, ZHENG K. Super 4PCS point cloud registration method combined with scale-invariant features ［J］. Remote Sensing Information, 2019, 34(5): 15-20.
HAN W, LIU Y, DU L, et al. Effect of emissivity on microscopic infrared temperature measurement results of semiconductor devices ［J］. Acta Metrologica Sinica, 2021, 42(1): 35-40.
［9］
LI H, WANG S, BAI Z, et al. Research on 3D Reconstruction of Binocular Vision Based on Thermal Infrared ［J］. Sensors, Multidisciplinary Digital Publishing Institute, 2023, 23(17):7372-7378.
［17］
QI C R, SU H, MO K, et al. Pointnet: Deep learning on point sets for 3d classification and segmentation ［C］//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017.
［24］
BESL P J, MCKAY N D. A method for registration of 3-D shapes ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1992, 14(2): 239-256.
DONG Z W, HOU D X, YE S L. Testing method for thermal conductivity of soft-pack lithium batteries based on thermal imaging ［J］. Acta Metrologica Sinica, 2021, 42(12): 1597-1603.
2024, Vol. 45 
