Patents
Literature
7results about How to "Improve blur" patented technology
Efficacy Topic
Property
Owner
Technical Advancement
Application Domain
Technology Topic
Technology Field Word
Patent Country/Region
Patent Type
Patent Status
Application Year
Inventor
Image pickup apparatus
Owner:ZHEJIANG UNIVIEW TECH CO LTD
Uncertainty perception single-image super-resolution network model based on self-convolution attention
ActiveCN119444573AEnhance expressive abilityFully mine multi-scale featuresGeometric image transformationCharacter and pattern recognitionFeature extractionImage resolution
The invention discloses an uncertainty perception single-image super-resolution network model based on self-convolution attention. The model comprises a shallow feature extraction module SFE, a deep feature extraction module DFE and an image reconstruction module IR. The shallow feature extraction module SFE performs shallow feature extraction on an input low-resolution image through a convolutional layer to generate an initial feature F0: the deep feature extraction module DFE comprises a plurality of residual attention groups RAG, and each residual attention group RAG is composed of a plurality of cross-resolution mixed attention blocks CRHAB; the deep feature extraction module DFE is used for extracting a deep feature FDF from the initial feature F0, and the image reconstruction module IR is used for up-sampling the deep feature FDF and combining the deep feature FDF with the initial feature F0 to generate a final super-resolution output image ISRS.
Owner:TIANJIN UNIV
A highly efficient auto focus method and system
The application discloses a high-efficiency automatic focusing method and system, and relates to the field of automatic focusing. The method is applied to an off-axis automatic focusing device comprising a ranging module and an imaging module, and comprises the following steps: detecting height values of multiple measuring points by using the ranging module, and screening fixed-interval focusing points; based on a first height difference between adjacent focusing points, adjusting the height of an objective lens focal point in the imaging module at a constant speed, so that the height of the objective lens focal point is consistent with the horizontal plane position of the focusing point; when the horizontal plane position of the objective lens focal point coincides with that of any correction point, determining a corresponding blur kernel matrix according to a second height difference between the objective lens focal point and the correction point; and based on the blur kernel matrix, performing deblurring processing on an image generated by an image sensor to obtain a measured object image. Based on the above processing, the image blurring problem caused by poor real-time focusing performance is improved, and the detection rate of the automatic focusing device is improved.
Owner:HEFEI I TEK OPTOELECTRONICS CO LTD
A portable photographic studio
The application discloses a portable photography studio and belongs to the technical field of photography studios. The portable photography studio comprises a frame assembly, a cloth assembly, a lighting device assembly and an adjusting mechanism. The application is novel in design and ingenious in device. Three lighting lamp groups respectively emit light rays from the top at an angle of 120 degrees, from the side at an angle of 90 degrees and from the bottom at an angle of 60 degrees. After diffuse reflection in the inner layer of the cloth, the light rays form a spherical uniform light field. The lighting lamp groups light from the surroundings of a shooting subject, so that the lighting on the shooting subject is more uniform. Three-dimensional light distribution is realized. The illumination difference in each direction is controlled within + / - 15%. The overall storage volume is less than or equal to 0.08 m3. The unfolding time is less than 3 minutes. Through the cooperative work of the multiple lamp groups, the shadow transition of the photographed object is natural. The actual measurement shows that the blur degree of the shadow edge is improved by 40%. The technical contradiction that the existing portable photography equipment cannot simultaneously realize multi-directional uniform light distribution, rapid construction and compact storage is solved. The practicality of the device is greatly improved.
Owner:CHINA PICTURE SERVICE CO LTD
Image compression reconstruction method and system based on latent space discretization and parameter decoupling
The application belongs to the technical field of image compression and transmission, and particularly relates to an image compression and reconstruction method and system based on hidden space discretization and parameter decoupling, which comprises a preprocessing module, an encoder, a light-weight code stream serialization storage module and a decoder; through construction of an asymmetric coding and decoding architecture of hidden vector structured discretization on the encoder side, physical decoupling of coding and decoding parameters, serialization of light-weight code streams, independent deployment of a pre-trained decoder and industrial feature adaptive entropy coding, high compression ratio, low transmission delay and edge lightweight deployment of industrial image compression and reconstruction are achieved.
Owner:QINGDAO UNIV OF TECH
Photographing method and device and electronic equipment
PendingCN119421046AImprove blurgood effectTelevision system detailsColor television detailsComputer graphics (images)Radiology
The invention discloses a photographing method and device and electronic equipment, and belongs to the technical field of electronic equipment. The method comprises the following steps: receiving a first input of a user under the condition of displaying a preview image; in response to the first input, the preview image is imaged to obtain a first image, and the first image comprises a first object and M second objects; video clips within a first time period after the first input is received are collected, N frames of second images are obtained, and both M and N are positive integers; extracting a first pixel position set of M second objects in the first image and background pixels at positions corresponding to the M second objects in the first image in the N frames of second images; and performing pixel filling on the first pixel position set by using background pixels at positions corresponding to the M second objects in the first image in the N frames of second images to obtain a target image.
Owner:VIVO MOBILE COMM CO LTD
Unmanned aerial vehicle target direction finding method and device based on multi-band sparse array
PendingCN122652455AImprove blurImprove the problem of limited lateral spaceMulti bandUncrewed vehicle
The application provides a UAV target direction finding method and device based on a multi-band sparse array, comprising: collecting signals of a target through a non-uniform sparse antenna array arranged on the side of a UAV, and sampling the signals to obtain multi-band radio frequency data; obtaining the attitude angle of the UAV at each sampling time, and correcting the multi-band radio frequency data based on the attitude angle; constructing a virtual differential common array based on the corrected multi-band radio frequency data, and performing virtual aperture fusion on the virtual differential common array to obtain a non-hole virtual differential common array; constructing a multi-band joint observation model based on the non-hole virtual differential common array, obtaining a virtual observation vector, and performing weighted sparse reconstruction on the virtual observation vector to obtain the direction finding result of the target. The application improves the problem of limited space on the side of the UAV, and improves the target resolution accuracy.
Owner:江苏金睛智控科技有限公司