There is provided a video signal noise elimination method for performing noise correction by digital processing. The video signal noise elimination method includes using, as an output video signal, a mixed video signal obtained by mixing an input video signal and a low-pass video signal at a predetermined mixing ratio corresponding to a contour signal. The method further includes subtracting an off-set, which grows larger as the low-pass video signal becomes greater, from the contour signal. The method further includes controlling the predetermined mixing ratio so that a ratio of the low-pass video signal contained in the mixed video signal increases in a portion where the contour signal is small and so that the ratio of the low-pass video signal contained in the mixed video signal decreases in a portion where the contour signal is large.

There is provided a video signal noise elimination method for performing noise correction by digital processing. The video signal noise elimination method includes using, as an output video signal, a mixed video signal obtained by mixing an input video signal and a low-pass video signal at a predetermined mixing ratio corresponding to a contour signal. The method further includes subtracting an off-set, which grows larger as the low-pass video signal becomes greater, from the contour signal. The method further includes controlling the predetermined mixing ratio so that a ratio of the low-pass video signal contained in the mixed video signal increases in a portion where the contour signal is small and so that the ratio of the low-pass video signal contained in the mixed video signal decreases in a portion where the contour signal is large.

A signal receiving end of a digital television includes: an analog-to-digital converter (ADC), converting an input signal from an analog format to a digital format, the input signal including a target signal and an interference signal; a digital gain control circuit, coupled to the ADC, adjusting an amplitude of the target signal according to a gain; a detecting module, coupled to the digital gain control circuit, detecting a variance in the gain to generate a detection value; and a control circuit, coupled to the digital gain control circuit, determining a gain setting parameter according to the detection value. Wherein, the digital gain control circuit further updates the gain according to the gain setting parameter.

A signal receiving end of a digital television includes: an analog-to-digital converter (ADC), converting an input signal from an analog format to a digital format, the input signal including a target signal and an interference signal; a digital gain control circuit, coupled to the ADC, adjusting an amplitude of the target signal according to a gain; a detecting module, coupled to the digital gain control circuit, detecting a variance in the gain to generate a detection value; and a control circuit, coupled to the digital gain control circuit, determining a gain setting parameter according to the detection value. Wherein, the digital gain control circuit further updates the gain according to the gain setting parameter.

A 70,000-gate device and method which provide substantially real-time TV video images that are similar to pre-degradation original images by: setting luminance distribution of a degraded image and an estimated luminance distribution of initial values of a reconstructed image for one frame of TV video images; using a first PSF luminance distribution in a first-time iterative calculation, said first PSF luminance distribution having been specified in accordance with the degree of degradation of the degraded image; using a second PSF luminance distribution in a second-time iterative calculation; and while setting a reconstructed image estimated luminance distribution from the first-time iterative calculation as a second-time estimated luminance distribution of the initial values of the reconstructed image, performing the second-time iterative calculation in an image reconstructioner which determines, in the luminance distribution of the degraded image, the most likely estimated luminance distribution of the reconstructed image based on the Bayse probability theorem.

A 70,000-gate device and method which provide substantially real-time TV video images that are similar to pre-degradation original images by: setting luminance distribution of a degraded image and an estimated luminance distribution of initial values of a reconstructed image for one frame of TV video images; using a first PSF luminance distribution in a first-time iterative calculation, said first PSF luminance distribution having been specified in accordance with the degree of degradation of the degraded image; using a second PSF luminance distribution in a second-time iterative calculation; and while setting a reconstructed image estimated luminance distribution from the first-time iterative calculation as a second-time estimated luminance distribution of the initial values of the reconstructed image, performing the second-time iterative calculation in an image reconstructioner which determines, in the luminance distribution of the degraded image, the most likely estimated luminance distribution of the reconstructed image based on the Bayse probability theorem.

A computer-implemented method and system are provided for video-based anomaly detection. The method includes forming, by a processor, a Deep High-Order Convolutional Neural Network (DHOCNN)-based model having a one-class Support Vector Machine (SVM) as a loss layer of the DHOCNN-based model. An objective of the SVM is configured to perform the video-based anomaly detection. The method further includes generating, by the processor, one or more predictions of an impending anomaly based on the high-order deep learning based model applied to an input image. The method also includes initiating, by the processor, an action to a hardware device to mitigate expected harm to at least one item selected from the group consisting of the hardware device, another hardware device related to the hardware device, and a person related to the hardware device.

A computer-implemented method and system are provided for video-based anomaly detection. The method includes forming, by a processor, a Deep High-Order Convolutional Neural Network (DHOCNN)-based model having a one-class Support Vector Machine (SVM) as a loss layer of the DHOCNN-based model. An objective of the SVM is configured to perform the video-based anomaly detection. The method further includes generating, by the processor, one or more predictions of an impending anomaly based on the high-order deep learning based model applied to an input image. The method also includes initiating, by the processor, an action to a hardware device to mitigate expected harm to at least one item selected from the group consisting of the hardware device, another hardware device related to the hardware device, and a person related to the hardware device.

Embodiments relate to the field of image processing technologies, and in particular, to an image processing method and apparatus. In embodiments, when an image is being photographed, an exposure time that is required is first determined, and if the required exposure time is longer than a preset exposure time, the preset exposure time is used to photograph N second images, that is, and a final image is obtained by processing the N second images.

The present invention aims to provide an image processing device which enables reconstruction of a sharp high resolution image similar to the original of the unknown input image.

An image processing device according to one of the exemplary aspects of the present invention includes: inferring means for selecting, for each of local unknown patches including a target unknown patch, candidate patches from a plurality of input patches based on similarity to the local unknown patch, the local unknown patches being images generated from a part of an unknown image, the plurality of input patches being images generated from a plurality of input images, a subject ID (Identifier) being correlated with the input patches that are generated from a input image to which the subject ID is assigned in the plurality of input image; first score calculation means for calculating a score representing nearness of a candidate patch in the candidate patches to a local unknown patch in the local unknown patches; and patch replacement means for calculating a score summation for the subject ID by summing up scores of the candidate patches being correlated with a same subject ID in the candidate patches of the local unknown patches, and selecting, as a selected patch being used for reconstruction of a reconstruction image, a candidate patch that is correlated with the subject ID for which the score summation is highest from the candidate patches selected for the target unknown patch.