491results about How to "Resolve distortion" patented technology

The invention provides an automatic synthesis method for a facial image. A user inputs two facial source images, a target image and semantic information of an area to be edited; a model matching module utilizes an active appearance model to automatically search an image and provide facial shape information and facial texture information of the facial image; then, the shapes of the two facial images are aligned by using the characteristics of the model, and the shapes of the source images in the edited area are aligned to a corresponding area in the target image by virtue of the deformation of a sheet sample band; a characteristic synthesis module is used for characteristic synthesis for the shape information and the texture information of the aligned source images and the target image, so as to generate a synthetic image automatically; an occlusion processing module is used for occlusion processing the synthetic image, and the occlusion areas of the source images are divided, matched and seamlessly integrated into the target image. Compared with the traditional facial synthesis, the invention integrates the characteristic areas of the two images and solves the problem of image distortion caused by partial face occlusion in the target image.

The invention belongs to the field of visual sensors, laser radars, embedded unmanned aerial vehicles and provides a visual sensor laser radar fused unmanned aerial vehicle positioning and mapping device and method in order to solve the problems of autonomous positioning and environment map establishment of an unmanned aerial vehicle in a GPS denial environment and achieve autonomous flight and obstacle avoidance of the unmanned aerial vehicle in an unknown environment. The invention comprises a binocular camera, a laser radar, an IMU inertial measurement unit, an embedded airborne processor and an unmanned aerial vehicle platform. The binocular camera collects visual information of the surrounding environment; the laser radar is mainly used for measuring three-dimensional position information of the surrounding environment of the unmanned aerial vehicle; the IMU inertial measurement unit is used for measuring acceleration and angular velocity information of the unmanned aerial vehicleat high frequency; the embedded airborne processor is used for algorithm operation, and operates an autonomous positioning and mapping algorithm by processing data acquired by the camera, the radar and the IMU, so as to obtain the pose of the unmanned aerial vehicle and establish an environment map. The invention is mainly applied to unmanned aerial vehicle design and manufacturing occasions.

The invention provides a method and a device used for video enhancement. The method comprises the steps as follows: a nonlinear tensioning curve mapping table is arranged; for each frame of image, the histogram balance mapping table of the frame of image is calculated according to the brightness data; subsequently, the mapping value of at least each brightness value of a brightness value set of the pixel point of the frame of image in the nonlinear tensioning curve mapping table and the histogram balance mapping table is weighted and averaged; furthermore, a brightness mapping table is used for recording the corresponding relationship between each brightness value and the mapping value after weighted-average; subsequently, according to the brightness mapping table, the brightness value of the pixel point of the frame of image is updated as the mapping value after weighted average corresponding to the brightness value. The device of the invention comprises a brightness enhancement module which further comprises a nonlinear curve tensioning table memory unit, a histogram balance mapping table calculation unit, a brightness mapping table calculation unit and an image brightness enhancement mapping unit. The method and the device of the invention can improve the visible effect of the video images under the condition of low illumination and normal illumination.

The invention belongs to the technical field of computers, relates to a personalized recommendation technology finished by a computer and discloses three recommendation methods based on the neighborhood. The method includes that attributes of users are analyzed through modeling of interests and hobbies of the users, then similar user groups are found for target users, and objects which the users may be interested in are recommended for the users. During object recommendation, the method considers observed behavior data such as scoring and purchasing information, and also considers missed scoring information, namely hidden feedback information. Meanwhile, the method fully uses similarity of the interests and the hobbies of the users in social networks to model the interests of the users, considers effects of hidden feedback on results and effectively improves the recommendation precision.

The invention discloses an image processing method, device and terminal. According to the scheme, when an image is processed, the overexposure region, provided with the target color, in the image is judged according to color components of pixels in the image, then, the color components of the pixels in the overexposure region are corrected according to a preset correction model, and through correction, the spectral characteristic of the overexposure region can be changed, the color of the image can be restored to a certain degree, and the problem of image distortion is solved.

The invention discloses an automatic geometric correction and orthorectification method for multispectral remote sensing satellite images of a mountainous area. The method comprises the following steps of: selection and splicing of reference images; automatic selection of object points with same names; screening of the object points with same names, and geometric correction and orthorectification for correcting the images; precision evaluation; and output of the images. The multispectral remote sensing satellite images of the mountainous area, such as images of China domestic environment and disaster monitoring small satellite (with the model HJ-1A/B), have the characteristic of serious geometric distortion, but the automatic geometric correction and orthorectification method can be used for performing the orthorectification on the multispectral remote sensing satellite images of the mountainous area in mass and generating residual error reports of the coherent images by adopting a concept of the object points with same names to implement the geometric correction and orthorectification. The automatic geometric correction and orthorectification method has the advantages of high efficiency and precision, is very efficient when being used for processing the multispectral remote sensing satellite images with mass data of the mountainous area, can remarkably save manpower and material resources needed by the conventional remote sensing image processing process, and particularly is beneficial to the processing of the images of the China domestic environment and disaster monitoring small satellite.

The invention combines a wavelet lifting process and a difference process and provides an integratable fast algorithm for denoising electrocardiosignal and identifying QRS waves. The invention provides a method for denoising a weighted threshold value and solves the problem of signal distortion after denoising by using a global threshold value. The invention proposes to realize the lifting transformation of an electrocardiosignal by using a DB4 first-order derivative, avoid a wavelet lifting and re-decomposing process of the denoised signal and speed up the identification of QRS waves by combining the difference process in a DB4 wavelet lifting transformation process; meanwhile, an improved self-adaptive threshold updating method is adopted to improve the accuracy of QRS wave identification. In the invention, both the wavelet lifting process and a difference process, which are adopted, have the characteristics of high computing speed, low memory space occupation and capacity of realizing integer operation; therefore, the integrated application of the algorithm can be realized easily on the conventional hardware platform and can be realized easily in applications of computers and large processors.

An ultrasound gray-scale imaging system and method. The system comprises a probe (1); a transmission circuit (2) for exciting the probe (1) to transmit non-focused ultrasound beams to fluid; a receiving circuit (4) and a beam-forming module (5) for receiving echoes of the non-focused ultrasound beams and obtaining non-focused ultrasound echo signals; a signal processing module (6) for obtaining fluid display data after performing signal detection and enhancement process on the multi-group of non-focused ultrasound echo signals; an image processing module (7) for performing data conversion on the fluid display data and obtaining a B mode ultrasound image sequence; and a display (8) for displaying the B mode ultrasound image sequence to present the visual effect of fluid dynamic flow. A plurality of scanning lines even the whole image can be obtained for one time by utilization of non-focused wave or plane wave emission, time resolution of the ultrasound image can be largely improved, and the distortion problem when high-speed blood flow is displayed by traditional gray-scale blood flow imaging is solved.

The present invention relates to the digital image processing technology, especially to a water level identification method based on binary coding character staff gauge and image processing. The water level identification method based on the binary coding character staff gauge and the image processing comprises: extracting the binary coding character staff gauge image key pixel, performing binary coding character staff gauge tilt correction through adoption of the Radon conversion algorithm; determining the left, the right, the upper and the lower edges of the binary coding character staff gauge; extracting the binary coding character staff gauge scale line; performing the location and the segment of the binary coding character representing the staff gauge measuring range; performing the binary coding character staff gauge measuring range identification through combination of the Hopfield nerve network and the template matching; and realizing the resolving of the water level value through adoption of the mathematical relationship of the binary coding character staff gauge scale line and the binary coding character staff gauge measuring range. The water level identification method based on the binary coding character staff gauge and the image processing is safe, efficient and small in investment.

The invention discloses a narrow-band imaging endoscope device which comprises a light source structure, an endoscope structure, an image processing module, a synchronous irradiating assembly and a spectrum light splitting assembly. The light source structure irradiates at least one beam of illuminating light provided with regulated wavelength frequency bands on detected tissue. The endoscope structure photographs an image of the detected tissue irradiated by the illuminating light provided with the regulated wavelength frequency bands. The image processing module processes the image photographed by the endoscope structure. The synchronous irradiating assembly irradiates the illuminating light emitted by the light source structure on the surface of the detected tissue synchronously. The spectrum light splitting assembly splits the light reflected back by the detected tissue and then inputs the light into the image processing module. The narrow-band imaging endoscope device effectively solves the problem that due to motion of the detected tissue, a narrow-band image is distorted, the structure of the endoscope device is simplified, the reliability of the endoscope device is improved, and consumed energy is reduced.

The invention relates to a method for splicing maskless digital projection lithography pattern. The method comprises the steps of S1 segmenting a pattern to be etched to obtain multiple segmented frames of sub-pattern, wherein each frame of sub-pattern is of same size; S2 setting a template size which is the same with the size of each frame of sub-pattern; S3 multiplying each segmented frame of sub-pattern by the template to obtain a boundary splicing region of the sub-pattern, and employing a gray modulation template to modulate the gray value of the boundary splicing region to obtain the modulated sub-pattern; S4 carrying out exposure on the modulated sub-pattern frame-by-frame with digital micromirror display to realize the splicing of the reproduction transfer of the modulated sub-pattern which is displayed by the digital micromirror to a substrate. The method provided by the invention can fairly solve the splicing problem which exists when a pattern with a large area is etched, thus the etching quality of the digital projection lithography pattern is improved.

The invention discloses a method for excavating a weak surrounding rock tunnel under water-rich high-ground-stress conditions. The method includes the following steps that firstly, advanced small pipe grouting and pre-supporting are carried out in advance before tunnel excavation; secondly, excavation is carried out according to a three-step seven-excavation-surface method; thirdly, C35 reinforced concrete is adopted in the secondary lining process, wherein the C35 reinforced concrete is 65cm in inverted arch thickness and 55cm in arch wall thickness and comprises phi22@20cm annular main ribs, phi14@20cm longitudinal steel ribs and phi8 stirrups. The method can effectively avoid the steel frame torsion and cracking phenomenon, thereby guaranteeing normal tunnel construction, accelerating construction and improving construction safety and engineering quality.

The invention discloses a filtering method for intra-frame and inter-frame prediction. For pixel values obtained after prediction, whether to filter prediction blocks or not is adaptively selected through RDO (Rate distortion optimization) decision; filters are established based on a generalized Gaussian distribution function; different filters are employed for the prediction blocks of different sizes; the prediction blocks of various sizes are trained to obtain filter parameters. At a coding end, RDO is carried out on each coding unit; intra-frame prediction or inter-frame prediction is carried out on each coding unit; the prediction blocks are filtered through utilization of the filtering method provided by the invention; and whether to employ prediction block filtering or not is determined through RDO decision. At a decoding end, for different prediction block sizes, different filtering coefficients are set; and decoding is carried out according to marks. The distortion problem of the prediction blocks is solved. The prediction precision is improved. The coding efficiency of intra-frame and inter-frame prediction blocks is improved.

The electronic throttle gate includes valve plate, shaft, casing and gas channel, and the valve plate is fixed to the shaft capable of rotating inside the gas channel. One stepped motor drives the shaft of the electronic throttle gate to rotate, and one rotation position indicator includes at least one triggering signal generator or one rotation position blocking mechanism. The present invention has raised throttle gate shaft position controlling precision, long service life, low cost, open-looped control of shaft position and less control time of the electric control unit.

The embodiment of the invention provides a shooting method and a mobile terminal. The method comprises the following steps: receiving a sliding input on the preset control in a shooting preview interface by a user; controlling a camera to perform rotary shooting in response to the sliding input; acquiring N frame images collected by the camera in the rotary shooting process; performing image processing on N frame images to output panoramic, wherein the first frame image is one frame image collected by the camera at a sliding start location of the sliding input; the N-th frame image is one frame image collected by the camera at a sliding ending location of the sliding input; the panoramic data comprises the image or a video, and N is integer greater than one. Through the shooting method provided by the embodiment of the invention, the problem that the torsion, the warping, the distortion and the morphing are existent in the panoramic image since the mobile terminal handheld by the useris easy to jitter in the movement in the existing panoramic image shooting process can be solved.

The invention provides an image correcting method for a projection terminal and the projection terminal. The image correcting method comprises the steps that the horizontal deflection angle of the projection terminal is acquired, and a to-be-projected image of the projection terminal is rotated and corrected according to the horizontal deflection angle and the projection optical axis of the projection terminal. According to the image correcting method for the projection terminal and the projection terminal, the horizontal deflection angle of the projection terminal is acquired, the to-be-projected image is rotated according to the horizontal deflection angle, and therefore the problem that the projection picture is distorted when the projection terminal is rotated with the projection optical axis as the center is solved; meanwhile, due to the fact that only to-be-projected image rotating is referred in the correcting process, a complex graph correction algorithm is not needed to carry out correction, cost is low, the correcting speed is high, the power consumption and the produced heat are low, and the using experience of a user of a portable terminal is greatly improved.

The invention discloses a video enhancing method based on video frame self-adaption. The method comprises video frame self-adaption parameter adjustment and video frame enhancing processing. The invention also discloses a video enhancing system. The system comprises a parameter adjusting module and an enhancing processing module. According to the video frame self-adaptive video enhancing method based on an airspace point algorithm and the video enhancing system built based on the method, through starting from a performance and a video continuous frame enhancement flexibility, the performance is ensured; moreover, adjusting parameters are selected according to the video contents self-adaptively; the problem of video frame distortion resulting from excessively improving too dark images or excessively reducing too bright images by directly using conventional methods such as histogram equal saturability enhancing is solved; the enhancing of the processed video under various environments such as indoor, outdoor, low illumination and high illumination environments, is more flexible; and compared with the original video, the processed video is more clear in detail and more abundant in contrast and saturability and has better eye watching feelings.

The invention relates to a continuous casting billet surface defect binocular scanning and deep learning fusion recognition method and a continuous casting billet surface defect binocular scanning anddeep learning fusion recognition system. The method comprises the following steps: extracting a three-dimensional morphology image of the surface of a continuous casting billet by adopting binocularlaser scanning imaging; positioning a region of interest ROI according to the depth information; generating defect recognition candidate boxes. The real defect discrimination and the type recognitionare carried out on the defect area in the candidate box by adopting a full-connection neural network. For real defects, the semantic segmentation is carried out by adopting a full convolutional neuralnetwork. The three-dimensional quantitative morphological information of the defects can be accurately identified by fusing binocular laser three-dimensional scanning imaging and deep convolutional neural network target recognition and semantic segmentation methods. The method belongs to the field of continuous casting billet quality detection and control in ferrous metallurgy.

The invention discloses an Android system based screen capture method and a terminal. The method comprises: receiving an input instruction, wherein the input instruction is used for requesting screen capture for a terminal installed with an Android system; obtaining version information and storage path information of the terminal, and comparing the version information with a preset version; if the version is higher than the preset version, further judging whether the terminal has a screen capture (Screencap) storage path or not; if the terminal has the Screencap storage path, reading screen data of the terminal according to the Screencap storage path; and compressing the obtained screen data to generate a screenshot corresponding to the screen data. According to the method provided by an embodiment, the version information and the storage path information of the terminal are analyzed, so that the data is ensured to be preferentially read from Screencap and the generated screenshot is ensured not to be distorted; and the screen data is compressed, so that the efficiency of the whole screen capture process is improved.

The invention belongs to the technical field of plastic processing, and particularly relates to a double-open type hollow profile frame stretch bending forming method. By successfully using a whole filler filling method for the first time, the deformation of a profile cross section is controlled, and the problem of filler falling is solved; the problems of profile twisting deforming and opening shrinkage caused by intermediate heat treatment are solved through an improved technological process. The stretching bending forming method has the main advantages that a frame is stretched and bent along a die, so that the distortion and twisting of the cross section are prevented, the tensile rigidity of components can be improved, the resilience is low, the residual stress is lower, the forming quality is higher, components with large relative bending radiuses can be controlled, the hand finish amount is small, and the production rate is high. A product processed and formed by using the method is formed and qualified for delivery, the assembly requirement is guaranteed, and a technology foundation is established for other subsequent products using profile stretching bending frames of the structure.