Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

4results about How to "Reduce memory size" patented technology

Gain calling system and method

The present invention provides a gain calling system, comprising an image processing chip and an image processing auxiliary module, wherein the image processing chip comprises a lens shading correction unit, a cache unit, an on-chip storage unit, an on-chip storage control unit and an off-chip storage control unit, and the image processing auxiliary module comprises an off-chip storage unit, wherein all block point gain values ​​are uniformly stored through the off-chip storage unit, and when the lens shading correction unit performs lens shading correction processing on an image, the off-chip storage control unit retrieves the corresponding block point gain value from the off-chip storage unit and transmits it to the on-chip storage control unit, and then the on-chip storage control unit writes the on-chip storage unit, and then the on-chip storage control unit reads the on-chip storage unit and writes the cache unit, thereby greatly reducing the memory size of the on-chip storage unit, thereby reducing the area of ​​the image processing chip. The present invention also provides a gain calling method.
Owner:SHANGHAI INTEGRATED CIRCUIT RESEARCH & DEVELOPMENT CENTER CO LTD

A method for identifying fractures in roadway surrounding rock based on semantic segmentation and joint loss function

ActiveCN117809177BExactly quantify the maximum lengthAccurately quantify areaCharacter and pattern recognitionBiological modelsPattern recognitionData set
This invention discloses a method for identifying fractures in roadway surrounding rock based on semantic segmentation and a joint loss function. The method includes constructing and labeling three types of labeled borehole fracture datasets; data augmentation and pixel binarization equalization preprocessing; pixel-level segmentation of the augmented borehole dataset; introducing a two-stage transfer learning training model; using a trained and improved Deeplabv3+ model to identify borehole fracture test sets, and evaluating the segmentation effect using MIoU and PA; batch importing the predicted fracture segmentation images of different types into ImageJ software to set pixel legend scales and obtain actual length parameters. This method reduces the model size while ensuring accurate and rapid extraction of depth feature information of annular fractures, longitudinal fractures, and fractured zones from the rock strata, and obtaining microscopic fracture quantification indicators. It achieves automated identification of borehole fractures in surrounding rock, providing a more reliable reference for evaluating roadway surrounding rock instability.
Owner:CHINA UNIV OF MINING & TECH

Display processing method and device, electronic equipment, storage medium and program product

The invention provides a display processing method and device, electronic equipment, a storage medium and a program product, and the method comprises the steps: obtaining a color value of each pixel of a to-be-processed image, the color value comprising component values of a plurality of color components; determining a target correction coefficient corresponding to the component value of each color component according to the component values of the plurality of color components and a pre-stored mapping relationship between color components and correction coefficients, the stored mapping relationship corresponding to a part of values in a value range of the color components; correcting the color value of each pixel according to a target correction coefficient corresponding to the component value of each color component; and the corrected to-be-processed image is displayed, so that all color components are corrected by storing part of the correction coefficients, the size of a memory needing to be stored is reduced, and the cost is reduced.
Owner:HEFEI MACROSILICON TECH CO LTD

Ranging methods, systems, devices and computer-readable storage media

This invention discloses a ranging method, system, device, and computer-readable storage medium. The method includes: periodically emitting laser light through a laser emitter and receiving the laser light reflected from a target object through a laser receiver; randomly selecting at least one target photon from among the photons received by the laser receiver within a laser emission cycle; storing or outputting the measurement results corresponding to the acquired target photon; and determining the ranging result of the target object based on the measurement results stored or output within multiple laser emission cycles. The number of target photons determined within a laser emission cycle is less than the total number of photons received by the laser receiver within the corresponding laser emission cycle. This invention achieves improved accuracy in long-distance ranging while alleviating circuit area constraints.
Owner:HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO LTD