4results about How to "High engineering value" patented technology

The invention provides a method and system for counting the attendance number of students in daily teaching, and relates to the field of image processing, and the method comprises the steps: collecting continuous multi-frame images of a multimedia classroom based on camera equipment equipped in the multimedia classroom; for each frame of image of the multimedia classroom, obtaining corresponding illumination sensing information, performing adaptive illumination normalization processing, generating an image after brightness processing, generating an improved image through a resolution adjustment model, identifying target human bodies and feature vectors through a target detection model, and allocating a unique identifier for each target human body; for each target human body, identifying an effective target human body based on the feature vector of the target human body in the continuous multi-frame image of the multimedia classroom; and generating a student attendance counting result based on the effective unique identifier of the target human body, so that the method has the advantages of counting the attendance condition of the students based on the camera equipment equipped in the existing multimedia classroom and reducing the education management cost.

A radar image difference recognition method based on scattering center modeling and deep learning is proposed. This method utilizes a Gaussian scattering center model to parametrically model the target scattering source, extracting features such as position, amplitude, width, and direction. An automatic thresholding method based on mutual information is employed for image registration. Optimal rigid body transformation parameters are obtained through cross-threshold search and derivative-free optimization, effectively eliminating geometric errors caused by imaging offset. A difference map is generated using a logarithmic ratio operator, and high-confidence pseudo-label samples are obtained through hierarchical fuzzy C-means clustering. Simultaneously, virtual sample generation technology is combined to expand the training set. Finally, a wavelet-constrained convolutional neural network is constructed, incorporating dual-tree complex wavelet transform to enhance direction sensitivity, achieving accurate classification and diagnosis of scattering source changes. This invention significantly improves radar image registration accuracy, change detection robustness, and model generalization ability, making it suitable for applications such as stealth target performance evaluation, radar image detection, and target recognition.

The present application relates to single point load dynamic distribution technical field, specifically, it is a kind of inner rotating tower pontoon type single point load dynamic distribution design method.It includes the following steps: S1, in SESAM software HydroD module, according to the FPSO hull lines, establish wet surface model, according to the FPSO loading information, establish quality model, based on wet surface model and quality model, water dynamic analysis is obtained FPSO overall motion response operator RAO;S2, in Orcaflex software, according to the wind flow coefficient of FPSO, mooring cable parameter, mooring arrangement and key control working condition, establish mooring model, simultaneously, motion response operator RAO is imported, carry out full coupling mooring time domain analysis and obtain dynamic data.The present application design fully considers the releasable characteristics of inner rotating tower pontoon and ship body, carries out systematic stress analysis to multiple coupling structures, the force on mooring connecting piece is decomposed along transmission path and dynamic balance equation is established, and SESAM and Orcaflex two software are used to carry out water dynamic analysis and mooring time domain analysis respectively.

This application provides a distributed control device and method for hot-plugging multiple active bridge transformer submodules, comprising: a resistor divider circuit electrically connected to a high-frequency AC bus, used to convert the high-frequency AC bus voltage into a 0-5V divided voltage signal; a voltage comparator electrically connected to the output of the resistor divider circuit, comparing the divided voltage signal with a set reference potential and outputting high and low level digital signals; a DSP controller electrically connected to the voltage comparator, which sets a phase qualification flag when the phase difference between the local counter and the zero-phase reference t0 is less than a phase threshold; and a transformer submodule electrically connected to the DSP controller, which controls an AC relay to close to connect to the high-frequency AC bus when it receives the phase qualification flag from the DSP controller. This invention addresses the problems of related technologies that often employ centralized control, over-reliance on a central controller, and limitations in computing power and flexibility, especially as the number of modules increases.