The 3D Point Cloud Registration Algorithm Based on Harris-DLFS
DOI: 10.23977/acss.2023.070614 | Downloads: 34 | Views: 439
Author(s)
Zongwei Huang 1, Juan Zhu 1, Chang Xiao 1, Zeyuan Liu 1, Zijian Cong 2
Affiliation(s)
1 School of Mechanical and Electrical Engineering, Changchun University of Technology, Changchun, China
2 School of Electrical Information, Changchun Guanghua University, Changchun, China
Corresponding Author
Juan ZhuABSTRACT
Three-dimensional model reconstruction is a pivotal technology in the realm of computer vision. Point cloud registration serves as its integral step, which decisively impacts the efficiency and precision of the entire reconstruction process. However, existing point cloud registration algorithms often face issues. These include prolonged processing time, inadequate accuracy, and poor robustness. To address these problems, this paper proposes a novel point cloud registration algorithm based on corner detection (Harris) and partition-based local feature statistics (DLFS). The main steps are as follows: Firstly, the Harris corner detection algorithm is employed. This step is crucial for extracting key points and enhancing the efficiency of the registration process. Secondly, the DLFS method is used to describe the features of each key point, generating feature vectors. Subsequently, matching point pairs are filtered based on rigid distance constraints, and an coarse registration is performed using the Random Sample Consensus (RANSAC) algorithm. Finally, the Iterative Closest Point (ICP) algorithm is applied for fine registration. Experimental results demonstrated the effectiveness of this method. It significantly improved registration accuracy, robustness, and computational efficiency. Therefore, it holds substantial value for practical point cloud registration applications.
KEYWORDS
3D point cloud; keypoints; feature description; feature matching; pairwise alignmentCITE THIS PAPER
Zongwei Huang, Juan Zhu, Chang Xiao, Zeyuan Liu, Zijian Cong, The 3D Point Cloud Registration Algorithm Based on Harris-DLFS. Advances in Computer, Signals and Systems (2023) Vol. 7: 110-117. DOI: http://dx.doi.org/10.23977/acss.2023.070614.
REFERENCES
[1] Gu L. P., Sun S. Y., Liu X. H., & Li X. (2021). Research on 3D multi-target tracking algorithm based on laser point cloud coordinate system. Laser and Infrared, 51(10), 1307-1313.
[2] Xue S., Lü N. F., Shen Y. Y., Liu Z. Y., & Guo J. B. (2019). Recognition method for mechanical parts based on laser 3D point cloud. Infrared and Laser Engineering, 48(4), 169-176.
[3] Ma X. L., Xue H. R., & Zhou Y. Q. (2023). Point cloud registration method for sheep body based on feature matching. Journal of China Agricultural University, 28(4), 129-138.
[4] Yang P. C., Yang C., Meng J., Xiao Y., & Cui J. B. (2023). Point cloud boundary registration method for cultural relics based on normal vectors and planar index features. Chinese Optics, 16(3), 654-662.
[5] Zhu J. H., Zhu L., Li Z. Y., Li C., & Cui J. R. (2016). Automatic multi-view registration of unordered range scans without feature extraction. Neurocomputing, 171, 1444-1453.
[6] Yang J. Q., Xiao Y., & Cao Z. G. (2019). Aligning 2. 5D Scene Fragments With Distinctive Local Geometric Features and Voting-Based Correspondences. IEEE Transactions on Circuits and Systems for Video Technology, 29(3), 714-729.
[7] Gojcic Z., Zhou C., Wegner J. D., & Wieser A. (2019). The Perfect Match: 3D Point Cloud Matching With Smoothed Densities. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 5540-5549.
[8] Zeng A., Song S., Nießner M., Fisher M., Xiao J., & Funkhouser T. (2017). 3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 199-208.
[9] Yang Z. P., Pan J. Z., Luo L. J., Zhou X. W., & Huang Q. X. (2018). Extreme Relative Pose Estimation for RGB-D Scans via Scene Completion. 2019 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 4531-4540.
[10] Guo Y. L., Bennamoun M., Sohel F., Lu M., Wan J., & Kwok N. M. (2016). A Comprehensive Performance Evaluation of 3D Local Feature Descriptors. International Journal of Computer Vision, 116(1), 66-89.
[11] Tao H. J., & Da F. P. (2013). Automatic Registration Algorithm for the Point Clouds Based on the Normal Vector. Chinese Journal of Lasers, 40(8), 0809001.
[12] Zhang L., Xiao J., Cheng X. L., & Wang Y. (2023). Three-dimensional point cloud registration based on matching of multiple types of geometric primitives. Journal of University of Chinese Academy of Sciences, 40(2), 258-267.
[13] Liu L., Xiong F. G., Yin Y. H., Guo R., Xue H. X., & Han X. (2023). Point cloud registration driven by multi-feature extraction and matching matrix. Computer Engineering and Design, 44(5), 1419-1426.
[14] Lu J., Peng Z. T., & Xia G. H. (2015). Point cloud multi-normal neighborhood feature registration algorithm. Optoelectronics Laser, 26(4), 780-787.
[15] Fu Y., Chen, P., Guo G. S., & Liu X. Y. (2022). Application of point cloud registration method based on 4PCS and SICP in rail wear calculation. Journal of Electronic Measurement and Instrumentation, 36(12), 210-218.
[16] Zeng W., Yang T., & Yu Y. (2022). Super-4PCS point cloud registration method combining improved FPFH. Modern Radar, 1-8.
[17] Aiger D., Mitra N. J., & Cohen-Or D. (2008). 4-points congruent sets for robust pairwise surface registration. Acm Transactions on Graphics, 27(3), 1-10.
[18] Zhao B., & Xi J. T. (2020). Efficient and accurate 3D modeling based on a novel local feature descriptor. Information Sciences, 512, 295-314.
Downloads: | 15635 |
---|---|
Visits: | 269833 |
Sponsors, Associates, and Links
-
Power Systems Computation
-
Internet of Things (IoT) and Engineering Applications
-
Computing, Performance and Communication Systems
-
Journal of Artificial Intelligence Practice
-
Journal of Network Computing and Applications
-
Journal of Web Systems and Applications
-
Journal of Electrotechnology, Electrical Engineering and Management
-
Journal of Wireless Sensors and Sensor Networks
-
Journal of Image Processing Theory and Applications
-
Mobile Computing and Networking
-
Vehicle Power and Propulsion
-
Frontiers in Computer Vision and Pattern Recognition
-
Knowledge Discovery and Data Mining Letters
-
Big Data Analysis and Cloud Computing
-
Electrical Insulation and Dielectrics
-
Crypto and Information Security
-
Journal of Neural Information Processing
-
Collaborative and Social Computing
-
International Journal of Network and Communication Technology
-
File and Storage Technologies
-
Frontiers in Genetic and Evolutionary Computation
-
Optical Network Design and Modeling
-
Journal of Virtual Reality and Artificial Intelligence
-
Natural Language Processing and Speech Recognition
-
Journal of High-Voltage
-
Programming Languages and Operating Systems
-
Visual Communications and Image Processing
-
Journal of Systems Analysis and Integration
-
Knowledge Representation and Automated Reasoning
-
Review of Information Display Techniques
-
Data and Knowledge Engineering
-
Journal of Database Systems
-
Journal of Cluster and Grid Computing
-
Cloud and Service-Oriented Computing
-
Journal of Networking, Architecture and Storage
-
Journal of Software Engineering and Metrics
-
Visualization Techniques
-
Journal of Parallel and Distributed Processing
-
Journal of Modeling, Analysis and Simulation
-
Journal of Privacy, Trust and Security
-
Journal of Cognitive Informatics and Cognitive Computing
-
Lecture Notes on Wireless Networks and Communications
-
International Journal of Computer and Communications Security
-
Journal of Multimedia Techniques
-
Automation and Machine Learning
-
Computational Linguistics Letters
-
Journal of Computer Architecture and Design
-
Journal of Ubiquitous and Future Networks