Explore MATLAB source code curated for "检测" with clean implementations, documentation, and examples.
Detection and tracking of moving vehicles through threshold segmentation, implementing image segmentation in video sequences by adjusting grayscale threshold values and labeling the resulting objects.
Utilizing beamlet's superior straight-line detection capabilities for bridge identification in images achieves 80% accuracy through multi-scale line segment analysis and geometric feature extraction.
Simulation of weak signal detection using stochastic resonance principles, including source code implementation of the fourth-order Runge-Kutta algorithm for solving the Langevin equation.
Algorithm for detecting parabolas using Hough Transform with implementation details. Demonstrates how to apply standard Hough Transform to detect parabolic curves from binary (black and white) images, including parameter space mapping and mathematical foundations.
Digital watermark embedding algorithm, featuring multi-resolution watermark embedding and extraction techniques, blind watermark embedding and detection algorithms, along with implementations for calculating Peak Signal-to-Noise Ratio (PSNR) and Normalized Cross-Correlation Coefficient (NCC) for quality assessment.
This video demonstrates motion object detection using background subtraction in static scenes, with the image converted to binary format.
Implementation of circle detection through Hough Transform methodology. This function employs Standard Hough Transform to identify circular patterns in binary images. Based on the Hough Transform principle for circles, each pixel in image space corresponds to a circular surface in Hough parameter space and vice versa. The upper-left corner serves as the coordinate system origin. The implementation involves accumulator array management and peak detection algorithms for optimal circle identification.
Implementation of signal singularity detection leveraging MATLAB's wavelet toolbox with wavelet transform algorithms and modulus maxima analysis
Implementation of dynamic object recognition, tracking, and detection in videos using MATLAB with computer vision and machine learning algorithms
MATLAB implementation of Principal Component Analysis (PCA) for TE data detection, featuring SPE statistic computation along with SPE and T-squared control limit calculations using built-in statistical functions and matrix operations.