7248results about How to "Improve visual effects" patented technology

The invention discloses a real-time panoramic image stitching method of aerial videos shot by an unmanned plane. The method comprises the steps of: utilizing a video acquisition card to acquire images which are transmitted to a base station in real time by an unmanned plane through microwave channels, carrying out key frame selection on an image sequence, and carrying out image enhancement on key frames; in the image splicing process, firstly carrying out characteristic detection and interframe matching on image frames by adopting an SURF (speeded up robust features) detection method with good robustness; then reducing the series-multiplication accumulative errors of images in a frame-to-mosaic image transformation mode, determining images which are not adjacent in time sequence but adjacent in space on a flight path according to the GPS (global positioning system) position information of the unmanned plane, optimizing the frame-to-mosaic transformation relation, determining image overlapping areas, thereby realizing image fusion and the panoramic image construction and realizing real-time effect of carrying out flying and stitching simultaneously; and in image transformation, based on adjacent frame information in a vision field and adjacent frame information in airspace, optimizing image transformation to obtain the accurate panoramic images. The stitching method has good real-time performance, is fast and accurate and meets the requirements of application occasions in multiple fields.

A fibrous product (10, 20, 20b, 30), especially tissue paper product, non-woven products or a hybrid thereof, and preferably hygiene and cleaning product has at least one first ply (42; 62; 84; 104) with at least one embossing pattern including embossed depressions starting from a base plane of the ply; the embossed pattern being characterized by the following features: the embossing pattern has a minimum motive surface area of at least 3 cm×3 cm; the pattern includes a high number of embossed depressions which are sized and/or positioned such as to form a motive element covering the motive surface area; wherein at least some of the embossed depressions are sized and/or positioned such that minimum distances between pairs of consecutively arranged embossed depression vary. A method for producing such a fibrous product is also described.

The invention discloses a passive auto-focusing method and a device so as to solve the problem of slow focusing speed. The method provided by the invention comprises the following steps: original image data is acquired; sharpness is calculated to obtain sharpness value of the original image data; current valid focusing range is determined according to current zoom value, the position of a lens is adjusted by a large-step rough-focusing strategy if the current position of the lens is not within the current valid focusing range, and the position of the lens is adjusted by a small-step fine-focusing strategy when the current position of the lens is within the current valid focusing range; and if the current position of the lens is within the current valid focusing range, the position of the lens is adjusted by a small-step fine-focusing strategy. The large-step rough-focusing strategy is as follows: a first-step shift lens is adopted until the current position of the lens is within the current valid focusing range. The small-step fine-focusing strategy is as follows: a step shift lens with step being less than the first step is used until the calculated sharpness value is the best sharpness value.

The invention provides a compressed sensing theory-based reconstruction method of a magnetic resonance random sampled K space data image. The reconstruction method applies a contourlet conversion and iterative soft thresholding method to realize reconstruction of a magnetic resonance image. The method comprises the following steps: collecting K space data in a magnetic resonance image scanner according to a preset observation matrix phi to generate a measurement value, and keeping y; acquiring y from a coil of the magnetic resonance image scanner, and transmitting y to a computer; and finallyconstructing a same phi, constructing any orthogonal transformation psi, and recovering from y by adopting a compressed sensing theory-based magnetic resonance random sampled K space data image reconstruction method according to reconstruction. According to the method, scanning time is saved, quick imaging is realized, high-quality reliable image information is provided to medical nuclear magnetic resonance imaging detection, and solid theoretical and practical foundation is established for further development and large-scale popularization and application of the medical imaging detection technology.

The invention discloses an ReLU convolutional neutral network-based image denoising method. The method comprises the following steps of building an ReLU convolutional neutral network model, wherein the ReLU convolutional neutral network model comprises a plurality of convolutional layers and active layers after the convolutional layers, wherein the active layers are ReLU functions; selecting a training set, and setting training parameters of the ReLU convolutional neutral network model; training the ReLU convolutional neutral network model by taking a minimized loss function as a target according to the ReLU convolutional neutral network model and the training parameters of the ReLU convolutional neutral network model to form an image denoising neural network model; and inputting a to-be-processed image to the image denoising neural network model, and outputting a denoised image. According to the ReLU convolutional neutral network-based image denoising method disclosed by the invention, the learning ability of the neural network is greatly enhanced, accurate mapping from noisy images to clean images is established, and real-time denoising can be realized.

The invention discloses a background blurring method based on a depth of field, used for processing scene data collected by an electronic device, wherein the scene data comprises a scene main image. The background blurring method comprises the steps of processing the scene data to acquire image depth information of the scene main image; acquiring the most front point of the scene main image according to the image depth information; determining an area except the area adjoined with the most front point and with continuously variable depth to be a background part; acquiring background depth information of the background part; dividing the background part into at least one blurring area according to the background depth information, wherein the span of a depth range corresponding to each blurring area is positively correlated with the distance between the depth range and the most front point of the scene main image; determining a blurring degree of each blurring area, wherein the blurring degree of each blurring area is positively correlated with the corresponding depth; and blurring the background part. The invention also discloses a background blurring device based on the depth of field and the electronic device. According to the method and the devices provided by the invention, the blurring effect of the image can be more natural and closer to an optical out-of-focus effect.

Contact lenses incorporating asymmetric radial power profiles that increase the radial dioptric power from the center to the margin of the optical zone of the lenses may be utilized to prevent and/or slow myopia progression. The power profiles vary along different meridians.

A vision metric, called the sharpness metric, indicates the subjective sharpness of a patient's vision by taking into account both the wavefront aberration and the retinal response to the image. A retinal image quality function such as the point spread function is convolved by a neural quality function, and the maximum of the convolution over the retinal plane provides the sharpness metric. The sharpness metric can be used to control eye surgery or the fabrication of a lens.

A method for enhancing vision of an eye includes a laser delivery system having a laser beam for ablating corneal material from the cornea of the eye. Measurements are made to determine an optical path difference between a plane wave and a wavefront emanating from the retina of the eye for a location at a surface of the cornea. An optical correction is provided to the laser delivery system for the location based on the optical path difference and refractive indices of media through which the wavefront passes. The optical correction includes dividing the optical path difference by a difference between an index of refraction of corneal material and an index of refraction of air. The laser beam is directed to the location on the surface of the cornea and corneal material ablated at the location in response to the optical correction to cause the wavefront to approximate the shape of the plane wave at that location.

A screen display method by which to configure a screen in which media objects are moved according to navigational inputs in order to easily browse for a desired media object from among a plurality of media objects. The screen display method in a mobile terminal includes displaying media objects to be piled up at first and second positions and media objects to be arranged along a course that connects the first and second positions; and displaying the piled-up media objects at one of the first and second positions to be sequentially moved along the course toward the other of the first and second positions when an input event occurs.

The invention relates to a video auto-focusing system based on an embedded media processor. The system comprises a video collection module, an image acquisition and processing module, a focusing search module and a focusing execution module, wherein the acquisition and processing module is used to perform noise processing to the obtained original video image data and extract Y-component in the data, wherein the induction area selection algorithm based on region segmentation is adopted to extract focus area, the Tenengrad function based on Sobel gradient operator is adopted to calculate definition; the focusing search module is used to determine the moving direction of the camera lens and calculate the required step length (mov_step = step*level) of the lens; the position corresponding to the maximum definition value is used as focus position; and the focusing execution module is used to transmit control signals to a stepping motor used for driving the lens so as to adjust the position of the lens, according to the determined moving direction and step length of the lens in the focusing search module. By using the video auto-focusing system, the focusing accuracy and stability can be effectively increased, and the smoothness is improved.