Eureka-AI is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Eureka AI

2003 results about "Single image" patented technology

System and method for improved searching on the internet or similar networks and especially improved MetaNews and/or improved automatically generated newspapers

Google has recently made available at an automated “newspaper”, which searches continuously about 4,500 news sources, and lets users view automatically generated headlines in a few general areas or lets users search for news by keywords. The automatic determination of which news items or news stories are most important is done by 3 main criteria: In how many sources the news item appeared, how important are the news sources in which it appeared, and how close it is to the top in each of these news sources. However, many problems still remain, such as for example: a. The choice of a single main news source and a single image for each item seems arbitrary to the user and limits the user. b. If the user clicks on the “related items” link for that item the user always gets a linear list of typically hundreds or even more than a thousand links to related news items, sorted either by relevance or by time, however, the new list is now without any images and without any clustering, so that many times news stories that are about the same event or even identical, may appear at different positions in the list of related links, and various other news items may appear between them and are typically also dispersed in various places. This makes it vary hard for the user to take advantage efficiently of the list of related items. The present invention solves the above problem by creating recursive clustering, so that preferably at any level in the tree the user can preferably either choose a specific news item from the cluster or from the shown sub-clusters or continue in the tree. Another improvement is that searching the Meta News by keywords can generate an automatic newspaper in a way similar to the original automatically generated newspaper. Many additional improvements to the concept of automated newspapers and/or news MetaSearch are also shown. Other improvements are suggested for improved shareware MetaSearch, improved Web pages search, and other types of searches.

Vehicle surroundings monitoring apparatus and traveling control system incorporating the apparatus

A vehicle surroundings monitoring apparatus comprises image solid object detecting means for detecting image solid objects based on image information outputted from a CCD camera, millimeter wave solid object detecting means for detecting millimeter wave solid objects based on signals outputted from a millimeter wave radar, fusion solid object establishing means for establishing fusion solid objects composed of single image solid objects, single millimeter wave solid objects and a combination of the image solid objects and the millimeter wave solid objects by fusing the image solid objects and the millimeter wave solid objects, first reliability judging means for judging a degree of reliability of the fusion solid objects based on a detecting situation of the respective fusion solid objects by the image solid object detecting means, second reliability judging means for judging a degree of reliability of the fusion solid objects based on a detecting situation of the respective fusion solid objects by the millimeter wave solid object detecting means and preceding vehicle selecting means for selecting a preceding vehicle from the fusion solid objects when it is judged that the fusion solid objects have a specified level of reliability according to either of the first reliability judging means and the second reliability judging means.

Single image super-resolution reconstruction method based on conditional generative adversarial network

The invention discloses a single image super-resolution reconstruction method based on a conditional generative adversarial network. A judgment condition, namely an original real image, is added intoa judger network of the generative adversarial network. A deep residual error learning module is added into a generator network to realize learning of high-frequency information and alleviate the problem of gradient disappearance. The single low-resolution image is input to be reconstructed into a pre-trained conditional generative adversarial network, and super-resolution reconstruction is performed to obtain a reconstructed high-resolution image; learning steps of the conditional generative adversarial network model include: learning a model of the conditional adversarial network; inputtingthe high-resolution training set and the low-resolution training set into a conditional generative adversarial network model, using pre-trained model parameters as initialization parameters of the training, judging the convergence condition of the whole network through a loss function, obtaining a finally trained conditional generative adversarial network model when the loss function is converged,and storing the model parameters.

Method And Apparatus For Generating 3D Images

The present invention is directed to an apparatus and method for displaying 3D images. The apparatus comprises: a) a screen with angular dependent diffusion characteristics for direction selectively forwarding light; b) a screen illuminating system, the screen illuminating system comprising multiple modules for generating multiple light beams incident on points of the screen, the modules being arranged so that each point of the screen is illuminated by multiple modules, and the incident light beams generated by one module are projected into multiple different directions from the module towards multiple different points of the screen, and further the different incident light beams generated by one module are forwarded towards different emitting directions from the screen, means for coding each incident light beam with the image information of a single image point in the module, where the 3D image perceived by an observer being generated by multiple modules; c) a control system to control the modules; and d) means for imparting an exit divergence to the exiting light beams being transmitted through or reflected from the screen, the measure of the exit divergence substantially corresponding to the angle between neighbouring emitting directions associated with the optically neighbouring modules, go as to provide a substantially continuous motion parallax in the 3D image perceived by an observer. The apparatus according to the invention comprises imaging means for generating the incident light beams with a convergent section converging substantially towards a point of the screen, where a convergence of the incident light beams is substantially equal to the exit divergence of the light beams exiting the screen. The modules can be video projectors, LED projectors, the optical engines of these, or the like, arranged periodically shifted, preferably in the horizontal direction and the diffuser screen is realised as a holographic screen, arrays of diffractive or refractive elements, retroreflective surfaces, or any combination thereof, for imparting a larger divergence to the exit light beams along at least one, preferably in the vertical direction, while in the other direction the angle of divergence provided by the screen is smaller than the angle between the neighbouring emitting directions associated with the optically neighbouring modules. The invention is also directed to a method implemented by the apparatus according to the invention.
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