3 results about "Correlation test" patented technology

This application relates to the field of image processing technology, and discloses a method, apparatus, and computer device for estimating the radial distortion coefficient of an image. The method performs discrete sampling within a preset range of radial distortion coefficients to generate an ordered sequence of distortion coefficients. For each coefficient in the sequence, a parameter traversal operation is performed: trial correction is performed based on the coefficient and the original image size; straight lines are detected and filtered in the corrected image; intersection points of straight lines are randomly sampled and outliers are cleaned; and statistics describing the dispersion of the intersection point distribution are calculated in the X and Y directions. After traversal, two corresponding statistical sequences are formed. A convexity trend test is performed on both sequences sequentially, and a correlation test is performed on the sequences that pass the test. The distortion coefficient corresponding to the global minimum point in the statistical sequences that pass all tests is determined as the optimal estimate. This application achieves automatic estimation without calibration or manual intervention, and has the advantages of strong robustness and wide adaptability.

The application provides a kind of based on one-dimensional simplified water quality model, predicts water quality mutation, calculates real degradation coefficient and pollutant migration speed of the whole year using the monitoring data of water quality monitoring station, analyzes the relationship between degradation coefficient and river pollutant migration speed, builds regression model, and obtains the optimal degradation coefficient, migration speed by using correlation test calculation and mean square error calculation, and brings it into one-dimensional model formula, and calculates time sliding to form final prediction data, output prediction result graph.

This application relates to a method, apparatus, and equipment for analyzing post-meter water leakage based on smart water meter flow data. The method sequentially processes the original time-series-cumulative reading sequence using a data quality assessment algorithm, Boolean matrix and Fisher exact correlation test, robust Mahalanobis distance, and exponential smoothing filtering algorithms to generate a high-quality standard time-series-flow sequence. This ensures the data input to the model is "clean" and complete, laying the foundation for subsequent leakage analysis. The constructed dynamic threshold leakage judgment module automatically adjusts the threshold according to changes in user water usage habits, avoiding the limitations of fixed threshold judgment. The constructed micro-leakage identification model effectively identifies small, persistent leaks. Overall, this approach more accurately identifies post-meter water leakage, effectively avoiding misjudgments and omissions, and improving the reliability of leakage judgment.