Cyber-Physical System for Terminal Infrastructure Monitoring: A Depth-Free Registration Framework via Geometric-Model Fusion
Source abstract
Abstract
The monitoring and security of large-scale terminal infrastructures represent a critical application domain for industrial cyber-physical systems. However, real-time 3D visualization in such environments faces significant challenges from dense crowds, specular reflections, and complex architectural layouts. This paper presents a cyber-physical system for terminal infrastructure monitoring, underpinned by a novel, depth-free camera registration framework. At its core, the system establishes explicit geometric mappings across four coordinate systems (world, 3D model, camera, image), leveraging known installation parameters to eliminate dependency on depth sensors. Dynamic inconsistencies are resolved through a multi-stage layout refinement process, enabling robust operation under terminal-specific challenges. The framework maintains real-time performance at over 25 FPS when processing 16 concurrent video streams on commercial hardware. Extensive evaluations demonstrate a 44.9% reduction in registration error compared to state-of-the-art methods, validating the system’s practicality for enhancing situational awareness and security in large-scale, dynamic terminals.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Robotics and Sensor-Based Localization · Advanced Vision and Imaging · 3D Surveying and Cultural Heritage
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Communication and Information Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China
Second Research Institute of the Civil Aviation Administration of China, Chengdu 610041, China
Funding
the NNSFC and CAAC · the CAAC 430 Safety Capacity Building Project
References (53)
Show source-provided references
1. Spatial Visualization by Realistic 3D Views
2. Airport security comprehensive monitoring management system are discussed
3. Sebe, I., Hu, J., You, S., and Neumann, U. (2003, January 2–8). 3D video surveillance with Augmented Virtual Environments. Proceedings of the IWVS ’03: First ACM SIGMM International Workshop on Video Surveillance, Berkeley, CA, USA.10.1145/982452.982466 ↗
4. Zhong, Z., You, J., Yang, J., Zhou, Y., and Wu, W. (2018). Method for 3D Scene Structure Modeling and Camera Registration from Single Image. (9,942,535), US Patent.
5. Sawhney, H.S., Arpa, A., Kumar, R., Samarasekera, S., Aggarwal, M., Hsu, S., Nister, D., and Hanna, K. (2002, January 7–11). Video flashlights: Real time rendering of multiple videos for immersive model visualization. Proceedings of the ACM International Conference Proceeding Series, Honolulu, HI, USA.
6. Text2nerf: Text-driven 3d scene generation with neural radiance fields10.1109/TVCG.2024.3361502 ↗
7. Robust dual Gaussian splatting for immersive human-centric volumetric videos10.1145/3687926 ↗
8. Gao, R., Chen, K., Li, Z., Hong, L., Li, Z., and Xu, Q. (2024). Magicdrive3d: Controllable 3d generation for any-view rendering in street scenes. arXiv.
9. Jang, H., Baek, S., and Joo, K. (2023, January 1–6). Structure-from-Motion is Dead: Long Live Structure-from-Motion!. Proceedings of the ICCV, Paris, France.
10. Evaluation of metrics and a dynamic thresholding strategy for high precision single sensor scene matching applications10.1007/s11042-021-10656-y ↗
11. Distinctive image features from scale-invariant keypoints10.1023/B:VISI.0000029664.99615.94 ↗
12. Bay, H., Tuytelaars, T., and Van Gool, L. (2006, January 7–13). Surf: Speeded up robust features. Proceedings of the European Conference on Computer Vision, Graz, Austria.10.1007/11744023_32 ↗
13. Rublee, E., Rabaud, V., Konolige, K., and Bradski, G. (2011, January 6–13). ORB: An efficient alternative to SIFT or SURF. Proceedings of the 2011 International Conference on Computer Vision, Barcelona, AR, USA.10.1109/ICCV.2011.6126544 ↗
14. ORB-SLAM2: An open-source SLAM system for monocular, stereo, and RGB-D cameras10.1109/TRO.2017.2705103 ↗
15. Content-preserving warps for 3D video stabilization
16. Kumar, R., Sawhney, H.S., Hsu, S., and Samarasekera, S. (2000, January 15). Pose estimation, model refinement, and enhanced visualization using video. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Hilton Head, SC, USA.
17. Volume image registration by template matching10.1016/S0262-8856(00)00101-3 ↗
18. ElasticFusion: Real-time dense SLAM and light source estimation10.1177/0278364916669237 ↗
19. Engel, J., Schöps, T., and Cremers, D. (2014, January 6–12). LSD-SLAM: Large-scale direct monocular SLAM. Proceedings of the European Conference on Computer Vision, Zurich, Switzerland.10.1007/978-3-319-10605-2_54 ↗
20. Modersitzki, J. (2004). Numerical Methods for Image Registration, Oxford University Press.10.1093/acprof:oso/9780198528418.001.0001 ↗
21. Lim, A.X.W., Ng, L.H.X., Griffin, C., Kryer, N., and Baghernezhad, F. (2024). Reverse projection: Real-time local space texture mapping. arXiv.10.1145/3588028.3603653 ↗
22. INTERACTIVE 3D RECONSTRUCTION AND DLT CAMERA CALIBRATION: A MANUAL REGISTRATION APPROACH10.48141/2764-5959.01.v32.n38.2024_ISAAC_pgs_1_10.pdf ↗
23. He, Y., Li, G., Shao, Y., Wang, J., Chen, Y., and Liu, S. (2020, January 1–4). A point cloud compression framework via spherical projection. Proceedings of the 2020 IEEE International Conference on Visual Communications and Image Processing (VCIP), Macau, China.10.1109/VCIP49819.2020.9301809 ↗
24. Deep convolutional neural network for multi-modal image restoration and fusion10.1109/TPAMI.2020.2984244 ↗
25. Cross-modal attention for multi-modal image registration10.1016/j.media.2022.102612 ↗
26. Interpretable multi-modal image registration network based on disentangled convolutional sparse coding10.1109/TIP.2023.3240024 ↗
27. Wen, K., Xie, B., Duan, B., and Yan, Y. (2024). MambaReg: Mamba-Based Disentangled Convolutional Sparse Coding for Unsupervised Deformable Multi-Modal Image Registration. arXiv.
28. Target-oriented deep learning-based image registration with individualized test-time adaptation10.1002/mp.16477 ↗
29. Detail-preserving image warping by enforcing smooth image sampling10.1016/j.neunet.2024.106426 ↗
30. Lee, D.C., Hebert, M., and Kanade, T. (2009, January 20–25). Geometric reasoning for single image structure recovery. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA.10.1109/CVPRW.2009.5206872 ↗
31. Nedovic, V., Smeulders, A.W., Redert, A., and Geusebroek, J.M. (2007, January 14–21). Depth information by stage classification. Proceedings of the 2007 IEEE 11th International Conference on Computer Vision, Rio de Janeiro, Brazil.10.1109/ICCV.2007.4409056 ↗
32. 3D indoor reconstruction using Kinect sensor with locality constraint10.1504/IJMIC.2023.128766 ↗
33. Highly dynamic visual SLAM dense map construction based on indoor environments10.1109/ACCESS.2024.3374523 ↗
34. A Rigid Image Registration by Combined Local Features and Genetic Algorithms10.2478/acss-2023-0025 ↗
35. RA-MMIR: Multi-modal image registration by robust adaptive variation attention gauge field10.1016/j.inffus.2023.102215 ↗
36. Improving RGB-D SLAM accuracy in dynamic environments based on semantic and geometric constraints10.1016/j.measurement.2023.113084 ↗
37. RTAB-Map as an open-source LIDAR and visual simultaneous localization and mapping library for large-scale and long-term online operation10.1002/rob.21831 ↗
38. DS-SLAM: A semantic visual SLAM towards dynamic environments
39. Shi, Y., Li, R., Shi, Y., and Liang, S. (2024). A Robust and Lightweight Loop Closure Detection Approach for Challenging Environments. Drones, 8.10.3390/drones8070322 ↗
40. Zhang, R., and Zhang, X. (2023). Geometric constraint-based and improved yolov5 semantic slam for dynamic scenes. ISPRS Int. J. Geo-Inf., 12.10.3390/ijgi12060211 ↗
41. Lee, C.Y., Badrinarayanan, V., Malisiewicz, T., and Rabinovich, A. (2017, January 22–29). Roomnet: End-to-end room layout estimation. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.521 ↗
42. Hsiao, C.W., Sun, C., Sun, M., and Chen, H.T. (2019). Flat2layout: Flat representation for estimating layout of general room types. arXiv.
43. Yang, C.W., Yang, Y.H., and Lin, Y.Y. (2022, January 23–27). AtlantaNet: Inferring room layouts from a single image in atlanta world. Proceedings of the European Conference on Computer Vision, Tel Aviv, Israel.
44. Gao, K., Ji, H., Wu, J., Lin, D., and Dai, Q. (2022, January 23–27). RoomFormer: Room-cross-view-transformer for 3D room layout reconstruction. Proceedings of the European Conference on Computer Vision, Tel Aviv, Israel.
45. Bhat, S.F., Alhashim, I., and Wonka, P. (2021, January 20–25). Adabins: Depth estimation using adaptive bins. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.
46. Liu, C., Kim, K., Gu, J., Furukawa, Y., and Kautz, J. (2019, January 15–20). Planercnn: 3D plane detection and reconstruction from a single image. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00458 ↗
47. Kneip, L., Siegwart, R., and Pollefeys, M. (2012, January 7–13). Finding the exact rotation between two images independently of the translation. Proceedings of the European Conference on Computer Vision, Florence, Italy.10.1007/978-3-642-33783-3_50 ↗
48. Zhang, Z., and Scaramuzza, D. (2018, January 1–5). A tutorial on quantitative trajectory evaluation for visual(-inertial) odometry. Proceedings of the 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Madrid, Spain.10.1109/IROS.2018.8593941 ↗
49. DCL-depth: Monocular depth estimation network based on iam and depth consistency loss10.1007/s11042-024-18877-7 ↗
50. Lambert, J., Liu, Z., Sener, O., Hays, J., and Koltun, V. (2020, January 13–19). MSeg: A composite dataset for multi-domain semantic segmentation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR42600.2020.00295 ↗
51. Stekovic, S., Hampali, S., Rad, M., Sarkar, S.D., Fraundorfer, F., and Lepetit, V. (2020, January 23–28). General 3D room layout from a single view by render-and-compare. Proceedings of the European Conference on Computer Vision, Glasgow, UK.10.1007/978-3-030-58517-4_12 ↗
52. A comprehensive automated 3D approach for building extraction, reconstruction, and regularization from airborne laser scanning point clouds10.3390/s8117323 ↗
53. 3D building model reconstruction from multi-view aerial imagery and LIDAR data10.14358/PERS.77.2.125 ↗