6results about How to "Avoid aliasing" patented technology

This invention discloses a two-stage hybrid heuristic method for crack path detection in solar cells. The method includes: acquiring an electroluminescence image; generating a crack potential map (CPM) that suppresses background noise and enhances crack features using cascaded morphological processing; dividing the CPM into a coarse-grained region of interest (ROI) grid; searching for a globally optimized ROI path that satisfies spatial continuity constraints in the grid space using a first heuristic algorithm; generating a constrained pixel search space based on the regions contained in this path and after region expansion processing; and finally, searching for the optimal crack path within the constrained space using a second heuristic algorithm based on a movement cost that is non-linearly negatively correlated with the pixel potential value. This invention effectively reduces the search space and, combined with a cost function modified for crack features, achieves high-precision, topologically complete crack path extraction without the need for a high-performance GPU.

The embodiment of the invention provides a logistics information dynamic tracking method and device, equipment and a storage medium, and belongs to the technical field of logistics information processing. The method comprises the following steps: obtaining logistics information formed in a fresh food logistics process, and constructing a disturbance fragment used for representing an environmental parameter deviation process; identifying the logistics operation behavior of the fresh food in the time range corresponding to the disturbance fragment, and generating an operation behavior time window aligned with the disturbance fragment; disturbance morphological characteristics used for representing the environmental parameter change process are extracted from the disturbance fragments; and on the basis of the time coverage relationship between the disturbance fragment and the operation behavior time window, and in combination with the disturbance morphological characteristics, determining an abnormal type corresponding to the disturbance fragment, and carrying out association recording on the abnormal type and the corresponding operation behavior information to form a logistics information dynamic tracking result. According to the scheme of the invention, the operation stage positioning and type determination of the abnormal environment in the fresh food logistics process are realized, and the logistics information dynamic tracking result capable of being continuously traced is formed.

This invention discloses a wavelength calibration method for a computational spectral video imaging system, comprising: controlling a spectral lamp to output M sets of standard spectral lines within the imaging spectral range of the computational spectral video imaging system to a narrowband filter group; M being a positive integer; filtering the light beam using the narrowband filter group to obtain a single-spectral-line beam output to the computational spectral video imaging system; imaging using the computational spectral video imaging system to obtain a wavelength calibration mask image corresponding to the center wavelength of the filters; and performing wavelength calibration using the wavelength calibration mask image and the spectral calibration mask image obtained from the computational spectral video imaging system. This invention solves the wavelength calibration problem of high spatiotemporal-spectral resolution computational spectral video imaging systems.

This invention relates to a Gaussian super-resolution reconstruction method based on physically consistent sparsity and frequency awareness, comprising: performing feature extraction and saliency prediction on the spacecraft image to be processed to obtain a multi-scale deep feature tensor and a foreground saliency mask; using the foreground saliency mask to perform spatial feature modulation on the multi-scale deep feature tensor to obtain a modulated multi-scale deep feature tensor; decoding the feature vector corresponding to each spatial position of the modulated multi-scale deep feature tensor to predict the corresponding Gaussian kernel parameters; based on the foreground saliency mask, performing a physically consistent hard gating operation on the opacity of all Gaussian kernel parameters to generate a sparsified set of Gaussian kernel parameters; and based on the sparsified set of Gaussian kernel parameters, obtaining the final super-resolution result image through differentiable Gaussian sputtering. This method can obtain high-quality arbitrary-scale super-resolution reconstruction results while meeting the high-performance requirements of spaceborne edge devices.

The invention belongs to the field of wireless communication, and particularly relates to a wireless signal coding processing method and system based on multi-dimensional array modeling. The method comprises the following steps: acquiring a target signal received by an antenna array; determining an environment characteristic parameter set of a wireless channel according to the target signal, and determining a time window length and a frequency sub-band number for constructing a multi-dimensional array according to the environment characteristic parameter set; according to the time window length and a preset sampling period, time domain sampling is carried out on the target signal, a time dimension index sequence is constructed, spectral decomposition is carried out on the target signal according to the frequency sub-band number, and a frequency dimension index vector is constructed; determining a spatial dimension index vector according to the physical layout of each antenna unit in the antenna array; and taking the time dimension index sequence, the space dimension index vector and the frequency dimension index vector as dimension coordinates, and constructing a complex number field multi-dimensional array corresponding to the target signal. According to the method, signal characteristics can be more completely reserved, and the adaptability is better.

The invention relates to the technical field of pregnancy risk prediction, in particular to a pregnancy risk prediction system for early pregnancy ultrasonic examination. Comprising a data acquisition module, a preprocessing module used for preprocessing detection data to obtain a user data group, and a processing module used for determining whether the operation of the data acquisition module is qualified based on the abnormal data rate of the user data group, and determining whether the operation of the data acquisition module is abnormal when the operation of the data acquisition module is abnormal. The verification module is used for correcting the acquisition of the user data group based on the image characterization parameters; the data correction module is used for correcting the preprocessing parameters of the detection data; and the acquisition correction module is used for correcting the acquisition parameters of each ultrasonic inspection picture. According to the method, analysis is performed based on the abnormal data rate of the user data set to determine whether the operation of the data acquisition module is qualified, and when the operation of the data acquisition module is determined to be abnormal, the preprocessing parameters for the detection data are corrected, so that the accuracy and reliability of the data are improved, and then the accuracy of pregnancy risk prediction is improved.