Patents
Literature
Hiro is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Hiro

80results about How to "Precise compression" patented technology

Electronic map data processing method

The invention discloses a method used for mobile phone end map treatment, mainly comprising the following steps: superfluous attributes unused by a mobile phone end electronic map in original map data are deleted; the map clipping is carried out to realize the one-time selecting multi-region multi-layer clipping, and the condition that a plurality of geographic entities have the same mark in clipping results is automatically recognized and treated according to the requirements of users; the map compression is carried out, including lossless compression and loss compression, wherein, the lossless compression cannot influence the precision and the information amount of original maps, the loss compression realizes the maximum compression under the premise of losing part of the map precision, the users are supported to input compression tolerance to obtain maps which better accord with the practical application requirement; feature points on the map are automatically recognized and reserved, and the users are supported to appoint extra feature points; the loss compression adopts a strategy that common edges are compressed firstly and then the body of a polygon is compressed, therefore, the compression distortion phenomenon is avoided effectively; to the compression distortion caused by the original map data, the accuracy of the compressed data is guaranteed.
Owner:NANJING LES INFORMATION TECH

Hyperspectral image compression method based on deep learning and distributed information source coding

ActiveCN111145276APrecise compressionOvercoming the disadvantage of low compression efficiencyClimate change adaptationImage codingPattern recognitionSpectral bands
The invention provides a hyperspectral image compression method based on deep learning and distributed information source coding. The hyperspectral image compression method comprises the following steps: step 1, constructing a hyperspectral image saliency detection deep learning network model; step 2, extracting spectral segment groups and key frames of a to-be-compressed hyperspectral image; 3, extracting the spectral band group local significance characteristics of the to-be-compressed hyperspectral image; 4, obtaining a global saliency mapping graph of the spectral segment group; step 5, obtaining a region of interest of the spectral band group of the hyperspectral image to be compressed; step 6, performing distributed compression on the region of interest of the spectrum segment group;7, obtaining a compressed code of the hyperspectral image. According to the method, the defect that the scene saliency deep representation problem is difficult to solve in the prior art is overcome,and the method has the advantage of accurately compressing useful information; the method overcomes the defect of low hyperspectral image compression efficiency in the prior art, and has the advantageof quickly realizing compression.
Owner:HENAN UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products