Neural radiation field trusted twin modeling method based on evidence fusion and storage medium

By introducing deep learning of evidence and normal inverse gamma distribution in neural radiation field models, combined with loss weighting and adaptive resampling methods, the problem of difficulty in quantifying sample size missing and uncertainty in surface defect detection of industrial components is solved, and efficient and reliable three-dimensional reconstruction and defect detection are achieved.

CN119648923AActive Publication Date: 2025-03-18NANJING UNIV OF POSTS & TELECOMM
4 Cites 6 Cited by

Patent Information

Application Number
CN202510148862.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-02-11
Publication Date
2025-03-18
Estimated Expiration
2045-02-11

AI Technical Summary

Technical Problem

In the detection of surface defects of industrial components based on computer vision, the problem of missing sample size and difficulty in quantifying sample uncertainty.

Method used

A trusted twin modeling method of neural radiation field based on evidence fusion is adopted to construct a neural radiation field model through evidence deep learning, combining the uncertainty of normal inverse gamma distribution to model the uncertainty of spatial points, and using loss weighting and adaptive resampling methods of data uncertainty to improve the stability and robustness of the model in areas with high uncertainty.

Benefits of technology

It effectively solves the problem of missing sample size and difficulty in quantifying uncertainty, improves the credibility and robustness of surface defect detection of industrial components, reduces calculation overhead, and improves the quality of reconstruction.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a neural radiation field trusted twin modeling method based on evidence fusion and a storage medium. The method comprises the following steps: acquiring multi-view image data; constructing a neural radiation field model based on evidence deep learning, and modeling the volume density, color and uncertainty of spatial points through normal inverse gamma distribution; training the model by adopting a weighted loss function with data uncertainty; in the training process, the sampling density of a high-uncertainty region is increased through a self-adaptive resampling strategy, and the rendering quality is improved; applying the trained model to a defect sample test data set; and generating a three-dimensional reconstruction image and an uncertainty quantization graph through the model, performing credibility evaluation on the defect area, and generating a final detection result in combination with a rendered image and the uncertainty quantization graph. According to the method, a fusion method of evidence deep learning and a neural radiation field is introduced, so that high-precision and high-reliability sample supplement work of product surface defect detection is realized, and the reliability and robustness can be improved.
Need to check novelty before this filing date? Find Prior Art