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

37results about How to "Avoid ambiguous situations" patented technology

Image processing method and device based on multiple frames of images

The invention provides an image processing method and device based on multiple frames of images, and the method comprises the steps: obtaining multiple frames of original images, carrying out the synthesis according to the multiple frames of original images, obtaining a high-dynamic-range image, and carrying out the artificial intelligence noise reduction of the high-dynamic-range image, so as toobtain a target noise reduction image. According to the method, noise reduction processing is carried out, the image noise and effective details of the high-dynamic-range image can be distinguished more accurately. Meanwhile, noise reduction processing is carried out after high-dynamic synthesis of a plurality of frames of original images. Therefore, both the bright light area and the dark light area in the high-dynamic-range image obtained through high-dynamic synthesis can be subjected to noise reduction, the noise reduction effectiveness is improved, image details are reserved while image noise is reduced through the target noise reduction image obtained through noise reduction, an imaging effect with better definition is obtained, and then the use experience of a user is improved.
Owner:GUANGDONG OPPO MOBILE TELECOMM CORP LTD

Intelligent medical record generation method and device, computer device and storage medium

Embodiments of the invention disclose an intelligent medical record generation method and device, a computer device and a storage medium. The intelligent medical record generation method includes thesteps: shooting a paper medical record book issued by a hospital to obtain an original medical record image; uploading and storing the original medical record image; classifying the saved original medical record image according to different hospital names; using an OCR (Optical Character Recognition) technology to identity the classified original medical record image to obtain text information inthe original medical record image; sorting the acquired text information according to the issue time of the medical record, and extracting the valid keywords in each text information, wherein the valid keywords are used to embody the main symptoms of the patient; and displaying the valid keywords in the form of statistical graphics. The intelligent medical record generation method based on image detection is convenient for the doctor to understand the past medical history of the patient, and prevents the loss of the medical record and the fuzzy description of the medical history information ofthe patient.
Owner:PING AN TECH (SHENZHEN) CO LTD

Method and terminal for controlling overlong exposure

The invention discloses a method and a terminal for controlling overlong exposure, so as to solve the problems that an overlong exposure realization mode in the prior art is fixed, and the flexibility is poor. In the embodiment of the invention, after the terminal receives a photographing instruction, the current jitter offset is determined; the terminal compares the current jitter offset with a jitter threshold, and an exposure mode is selected according to the comparison result; and the terminal carries out exposure treatment according to the selected exposure mode. By adopting the mode of the embodiment of the invention, an applicable overlong exposure mode can be determined according to the current jitter offset of the terminal, the condition of a blurred image caused by adopting an improper exposure method can be effectively avoided, and the flexibility of the overlong exposure realization mode is improved.
Owner:QINGDAO HISENSE MOBILE COMM TECH CO LTD

Image processing method, terminal and server

The invention provides an image processing method, a terminal and a server. The image processing method applied to the first terminal comprises the following steps: acquiring a first image shot by a camera; sending the first image to a server; receiving N alternative images sent by the server, wherein shooting parameters of N alternative images are matched with the shooting parameter of the firstimage, and the shooting parameters at least comprise a shooting site, shooting time and shooting angle; receiving a first input on M target images in N alternative images by the user; in response to the first input, performing image stitching on the first image and M target images, and outputting a second image, wherein M and N are positive integer, and M is not more than N. Through the technicalscheme provided by the invention, the problem that the bad picture quality is easily caused due to user jittering in the panoramic shooting of the existing terminal is solved.
Owner:VIVO MOBILE COMM HANGZHOU CO LTD

Pre-impurity-removal system and impurity removal method used before raw cotton processing

The invention relates to a pre-impurity-removal system and impurity removal method used before raw cotton processing. The pre-impurity-removal system comprises a cotton opening dust removal box for preliminary dust removal, a first treatment module for preliminary treatment and a second treatment module for final treatment, wherein the first treatment module specifically comprises a photoelectricdetection unit and first high-pressure spray guns; after the preliminary treatment is carried out by the first treatment module, the second treatment module is used for further treatment; the second treatment module comprises a plurality of groups of high-definition CCD cameras which are sequentially arranged in parallel along the conveying direction of a cotton conveying belt, and second high-pressure spray guns; and the high-definition CCD cameras detect in regions, a detection region of each group of high-definition CCD cameras is relatively independent, and the detection regions are attached to one another along the length direction of the cotton conveying belt. The pre-impurity-removal system and the impurity removal method have the effects of complete and thorough impurity removal and high impurity removal efficiency.
Owner:苏州基列德智能制造有限公司

Continuous stamp device without repeatedly dipping red ink paste

The invention relates to the technical field of office accommodations, and discloses a continuous stamp device without repeatedly dipping red ink paste. The continuous stamp device without repeatedlydipping red ink paste comprises a stamp block, a fixing frame and a solenoid, a switch is fixedly mounted at the upper left portion of a supporting frame, a guide rod is fixedly connected to the middle of the fixing frame, an extrusion plate and a first sponge storage block are arranged at the lower end of the guide rod, a baffle is mounted below the first sponge storage block, a fine hole is formed in the baffle, the stamp block is fixedly mounted on the lower face of the baffle, according to the continuous stamp device without repeatedly dipping the red ink paste, the powered-on solenoid attracts an iron block and drives the fixing frame to move downwards, the stamp block moves a stamp downwards, the extrusion plate extrudes the first sponge storage block, stamp pigment in the first sponge storage block is extruded partly, the pigment enters the stamp block through the fine hole, the stamp block always keeps sufficient stamp pigment, the effects of continuous stamp and improving thestamp efficiency are achieved, and the device does not need to repeatedly dip the red ink paste.
Owner:广西博腾猎狗商贸有限公司

Image processing method and device, electronic equipment and computer readable storage medium

The embodiment of the invention discloses an image processing method and device, electronic equipment and a computer readable storage medium. The method comprises the following steps: performing face recognition on a first image to obtain face information of each face contained in the first image; generating a weight mask according to a portrait mask of the first image and the face information, wherein the weight mask is used for determining a face clear area corresponding to each face in the first image and a portrait fuzzy transition area corresponding to each face; acquiring a blurred image and a background blurred image corresponding to the first image; fusing the blurred image and the background blurred image according to the weight mask to obtain a second image. According to the image processing method and device, the electronic equipment and the computer readable storage medium, the problem that all portrait areas in an image are clear and no highlighted key points exist can be avoided, and the visual display effect of the image is improved.
Owner:GUANGDONG OPPO MOBILE TELECOMM CORP LTD

Image processing method, mobile terminal and computer readable storage medium

The invention relates to the communication technical field, and provides an image processing method, a mobile terminal and a computer readable storage medium; the method comprises the following steps: shooting pictures on a target so as to obtain a first image group and a second image group, wherein the first image group comprises at least one image, the second image group comprises at least one image; brightening the first image group and / or the second image group, thus obtaining a third image group; using the third image group to use images, thus obtaining the target image. The method can prevent taken image fuzzy conditions caused by the moving shooting target or a jittering camera, thus improving the image dynamic scope.
Owner:VIVO MOBILE COMM CO LTD

Unmanned aerial vehicle flight shooting quality optimization method, system, equipment and storage medium

The invention provides an unmanned aerial vehicle flight shooting quality optimization method, system, equipment and a storage medium for performing flight shooting on a to-be-shot target through an unmanned aerial vehicle flight detection system. The unmanned aerial vehicle flight detection system comprises an unmanned aerial vehicle, an airborne computer, a position sensor, a camera and a pan-tilt. The method comprises the following steps: controlling the camera through the pan-tilt, so that the camera faces to the to-be-shot target; along with the flight of the unmanned aerial vehicle, theorientation of the camera is controlled through the pan-tilt, so that the orientation of the camera is kept towards the to-be-shot target; and when the unmanned aerial vehicle flies to an image acquisition position, the camera is controlled to carry out image acquisition on the to-be-shot target. According to the method, the system, the equipment and the storage medium in the invention, relative movement generated between the unmanned aerial vehicle and the to-be-shot target is eliminated through movement of the pan-tilt, thereby avoiding the situation that the image collected by the camera isfuzzy due to the relative movement between the unmanned aerial vehicle and the to-be-shot target, and improving the quality of the image collected during flight of the unmanned aerial vehicle.
Owner:SHANGHAI CLOBOTICS TECHNOLOGY CO LTD

Road security security and protection monitoring device

The invention relates to the field of security and protection monitoring, in particular to a road security and protection monitoring device which comprises a pre-buried base, an electric power storagestructure, an installation structure, an adjusting structure, a cleaning structure and a winding structure. The electric power storage structure is installed in the pre-buried base, the gravity of vehicles and pedestrians frequently going in and out of a road junction can be converted into electric energy needed by monitoring equipment, the electric energy can be stored through the storage battery, an external power source is not needed, and the effect of saving energy can be achieved; people can be more delighted to go in and out of the road. the electric power storage structure can synchronously drive the cleaning structure to work while carrying out electric power storage work, and dust and rainwater on the mirror surface of the monitoring equipment can be scraped off through the workof the cleaning structure, so that the situation that a monitoring picture is fuzzy due to excessive accumulation of dust can be avoided. Rainwater can be scraped in rainy days, so that the monitoringdefinition of the monitoring equipment is guaranteed.
Owner:力坤科技有限公司

Monitoring device for municipal engineering

The invention discloses a monitoring device for municipal engineering, relates to the technical field of municipal engineering devices, and mainly aims at solving the problems that the monitoring angle of an existing monitoring device for municipal engineering is inconvenient to adjust, and a monitoring picture becomes fuzzy due to the fact that the existing monitoring device for municipal engineering is easily influenced by dust. The monitoring device for municipal engineering comprises an installation plate, a motor is fixedly installed on the lower side of the installation plate, the outputend of the motor is fixedly connected with a rotating shaft, the rotating shaft movably penetrates through the installation plate and extends to the position above the installation plate, and the end, located above the installation plate, of the rotating shaft is fixedly connected with a fixing plate. A fixing rod and an electric telescopic rod are fixedly installed on the upper surface of the fixing plate, and a first hinge block is fixedly hinged to the upper end of the fixing rod. The electric telescopic rod is fixedly hinged to a second hinge block through a telescopic rod, and the same mounting box is fixedly mounted on the upper sides of the second hinge block and the first hinge block.
Owner:邹永洋

Color and depth information combined adaptive depth image restoration method

InactiveCN110827209AReduce repair errorsImplement Adaptive Repair RepairImage enhancementImage analysisPattern recognitionImage restoration
The invention discloses a color and depth information combined adaptive depth image restoration method. The method comprises the steps of obtaining a to-be-restored depth image and a color original image before depth processing of the to-be-restored depth image; then, according to the mask of the to-be-restored depth map, obtaining cavity and noise point coordinates of the to-be-restored depth mapso as to confirm cavity and noise point coordinate information of the depth map, and carrying out image noise point restoration on noise points in the to-be-restored depth map by adopting a bilateralfiltering method; for holes in the to-be-repaired depth map, obtaining the to-be-repaired depth map; obtaining pixel points of which the pixel values cover the same positions in the depth map to be restored, wherein the pixel points are the same as the pixel points in the depth map to be restored in the color original image; the method achieves the restoration of the hole and noise information through employing a double-selection processing method, effectively solves a problem that a single filter cannot process a large-area hole in a depth image, reduces the restoration error of the depth image, achieves the reasonable restoration of the depth image of a scene, and achieves a very good effect and performance.
Owner:XI AN JIAOTONG UNIV

CT image blind denoising method based on multiple scales and attention mechanism

The invention discloses a CT (Computed Tomography) image blind denoising method based on multiple scales and an attention mechanism. The method specifically comprises the following steps of 1, performing feature fusion; step 2, weight distribution; step 3, de-noising processing is carried out; step 4, comparing and screening; the invention relates to the technical field of image processing. According to the CT image blind denoising method based on the multiple scales and the attention mechanism, the attention mechanism is used for weight redistribution, feature maps with more sufficient key detail feature expression are output, assistance is provided for noise level authentication, effective collection of feature maps of different levels of noise is achieved through sampling processing of the different levels of noise, and the accuracy of denoising of the CT image blind denoising method based on the multiple scales and the attention mechanism is improved. When the CT image to be denoised is denoised, the noise of the corresponding level can be accurately and effectively retrieved, then the denoising model matched with the noise can be selected, the definition of the denoised CT image is ensured, the training burden of the image feature set is effectively reduced in cooperation with the setting of the residual network, and a good guarantee is provided for the denoising robustness of the CT image.
Owner:NANJING UNIV OF TECH

Photograph method, device and electronic equipment

The embodiment of the invention relates a photograph method, device and electronic equipment, belonging to technical field of image. The method comprises the steps of detecting luminance of the surrounding environment of the camera when the image sensor collects images; controlling the image sensor to adopt overlapping mode to collect images when the luminance is smaller than the preset threshold value. The overlapping mode is used for improving sensitivity of the image. When the illumination intensity is low, the shorter exposure time and smaller gain can be used to take images with normal illumination, which avoids that the photos are unclear due to too loud image noise caused by long-time exposure and amplification of gain.
Owner:LETV HLDG BEIJING CO LTD +1

Section determining method and device for road construction

The invention provides a section determining method and device for road construction. The method comprises the steps of obtaining a road plane graph, and extracting a center line of a target road from the road plane graph; dividing a center line into a plurality of unit line segments according to stake numbers marked on the center line; each unit line segment being a part, between two connected stake numbers, in the center line; generating a unit range frame based on each unit line segment; each unit range frame being used for representing a road construction range corresponding to the corresponding unit line segment; adjusting the unit range frames, so that overlapping and gaps do not exist between every two adjacent unit range frames, and the unit range frames cover corresponding areas of the target road; and determining the section of the target road according to all the adjusted unit range frames.
Owner:GLODON CO LTD

Equal-angle division angle determination method for orthodontic arch wire bending sequence planning

The invention relates to the technical field of orthodontic arch wire bending, in particular to an equal-angle division angle determination method for orthodontic arch wire bending sequence planning.When equal-angle division is used to plan the bending sequence for an orthodontic arch wire, based on an orthodontic arch wire curve forming control point information set and a robot motion information set of forming control points, an upper limit value of the bending point density of an equal-angle region and an upper limit value of a bending point angular distance ratio sum of the equal-angle region are set in combination with the orthodontic arch wire bending characteristic of a robot; the equal-angle division angle determination method for orthodontic arch wire bending sequence planning isestablished; a division angle is changed according to the bending point density and the bending point angular distance ratio sum of the equal-angle region in the equal-angle division process; and finally the division angle is determined and output. Through quantitative constraint on the bending point density and the bending difficulty of the divided region, the rationality of division angle determination is ensured, and the planning efficiency is improved.
Owner:HARBIN UNIV OF SCI & TECH

Image magnification method based on edge extraction

The invention discloses an image magnification method based on edge extraction. The image magnification method based on the edge extraction includes the following steps: carrying out pretreatment of Gaussian filter and noise reduction on an image needing to be magnified, constructing a pixel grid by using each pixel point as a vertex of the grid in the image after the pretreatment and looking up intersection points of the pixel grid and an edge needing to be determined; optimizing numbers and positions of the intersection points which are found; connecting optimized intersection points to form a coherent edge; looking up and marking pixel points with pixel values affected by the edge at two sides of the edge; subdividing the pixel grid evenly according to the multiple to which the image needs to be magnified; carrying out calculus of interpolation according to the information of the edge and the pixel points with the marks to obtain corresponding pixel points of each subdivided grid to achieve the magnification of the image. The image magnification method based on the edge extraction is capable of extracting complete and accurate edge information of an image, enabling a magnified image to keep original gradient change, high in efficiency and strong in expandability.
Owner:ZHEJIANG UNIV

Engineering vehicle centralized monitoring device

The invention discloses an engineering vehicle centralized monitoring device which comprises a vehicle body, a first limiting cavity is fixedly connected with the top of the vehicle body, a vehicle frame is rotatably connected with the top of the first limiting cavity through a rotating bearing, a second limiting cavity is fixedly connected with the top of the first limiting cavity, the interior of the second limiting cavity is slidably connected with a sliding block through a sliding groove, the interior of the first limiting cavity is rotatably connected with a plurality of threaded sleeves,and the interiors of the threaded sleeves are in threaded connection with threaded air rods. According to the invention, a third monitoring probe is mounted on the inner side wall, close to a secondmonitoring probe, of the vehicle frame, so that the condition in the vehicle frame can be observed, whether goods in the vehicle frame fall off due to jolt or not can be found in time in the transportation process of the engineering vehicle, the goods in the vehicle frame are monitored in a centralized manner, and when the vehicle unloads, whether goods in the vehicle frame are unloaded or not canbe observed, and whether the goods in the vehicle frame are completely unloaded or not can be observed.
Owner:SHANGQIU INST OF TECH

Light filtering structure, camera module and electronic equipment

PendingCN113820849AAvoid ambiguous situationsAvoid the situation that it is impossible to get a clear image based on the visible light of the human eyeTelevision system detailsColor television detailsFirst lightEngineering
The invention discloses a light filtering structure, a camera module and electronic equipment. The light filtering structure comprises a light filtering container which comprises a light passing area; the light filtering structure further comprises a first light filtering assembly, a first light filtering medium is stored in the first light filtering assembly, and the first light filtering assembly is communicated with the light filtering container; the light filtering structure further comprises a second light filtering assembly, a second light filtering medium is stored in the second light filtering assembly, and the second light filtering assembly is communicated with the light filtering container; the first light filtering medium and the second light filtering medium are respectively used for filtering light of different wave bands; the light filtering structure has a first state and a second state; under the condition of the first state, the first light filtering medium is located in a light passing area; under the condition of the second state, the second light filtering medium is located in the light passing area.
Owner:VIVO MOBILE COMM CO LTD

Road monitoring system for multi-vehicle complex road section

InactiveCN112275680AEasy to cleanAffect the monitoring effectCleaning using toolsGlass coverMonitoring system
The invention relates to the technical field of road monitoring devices, and discloses a road monitoring system for a multi-vehicle complex road section. The road monitoring system comprises a fixed bottom plate, a stable stand column is fixedly connected to the upper surface of the fixed bottom plate, and fixing rods are fixedly connected to the four corners of the upper surface of the fixed bottom plate. A fixed transverse plate is fixedly connected to the top of the left side face of the stable stand column, a fixed rotary disc is arranged on the lower surface of the fixed transverse plate,and a cleaning scraper is fixedly connected to the left side of the outer surface of the fixed rotary disc. According to the road monitoring system for the multi-vehicle complex road section, a firstbevel gear, a third bevel gear and a second bevel gear are driven by a driving motor to clean a scraper and oppositely rotate cameras, so that the surfaces of the cameras are cleaned more effectively, a better cleaning effect on the surfaces of the cameras is achieved, the monitoring effect of the cameras is effectively prevented from being influenced by dust coverage, the use convenience is further improved, and the surface of glass cover can be better cleaned.
Owner:衡阳佳鑫信息技术有限公司

Focusing method and device, terminal and storage medium

ActiveCN114755789AAvoid movement out of sync problemsAvoid blurry imagesTelevision system detailsPrintersOphthalmologyImaging quality
The invention relates to a focusing method and device, a terminal and a storage medium, and the method comprises the steps: determining the first target stroke information of a lens in a first direction based on a focusing instruction, and enabling the first direction to be the optical axis direction of the lens; according to the first target travel information, second target travel information of the lens in a second direction is determined, and the second direction is a direction perpendicular to the first direction; according to the first target stroke information and the second target stroke information, the lens is driven to move, the movement comprises sub-movement in the first direction and sub-movement in the second direction, and when the sub-movement of the lens in the first direction is driven to stop, the lens reaches a target focusing position matched with the focusing instruction. According to the method, during focusing, when the sub-motion of the lens in the optical axis direction stops, the optical center of the lens is still located on the optical axis, that is, the lens directly reaches the target focusing position matched with the focusing instruction, the situation of image blurring is avoided, the imaging quality is better guaranteed, and the use experience is improved.
Owner:BEIJING XIAOMI MOBILE SOFTWARE CO LTD

Postposition digit-drop question number type answer sheet and application method thereof

InactiveCN108909288ASave writing timeImprove answering speedWriting aidsInformatizationBlind persons
The invention relates to a postposition digit-drop question number type answer sheet and an application method of the postposition digit-drop question number type answer sheet. Each row of the answersheet comprises a question number and options. The postposition digit-drop question number type answer sheet is characterized in that each option comprises three portions, the first portion is a capital English mark symbol, the second portion is basic symbols of English letters including A, B, C and D, and the third portion is a digit-drop number or variant of the corresponding question number. Interms of each question number with two or more digits, the corresponding third portion is the digit-drop number or variant of the question number, and the question number is only a single digit. Whena student answers a question, the third portion, namely the digit-drop letter, of the chosen answer option is pressed to be flat, the first portion and the second portion are kept unchanged, and marking of the question is accomplished. If the answer needs to be corrected, the first portion and the second portion of the original option are pressed to be flat, the original option is invalid, and the student chooses the options again. When correction is conducted repeatedly, the operation can be done in the same manner. The postposition digit-drop question number type answer sheet and the application method of the postposition digit-drop question number type answer sheet are used for allowing blind persons to equally share informationization development achievements.
Owner:BEIJING UNION UNIVERSITY

A centralized monitoring device for engineering vehicles

The invention discloses a centralized monitoring device for engineering vehicles, which comprises a vehicle body, the top of the vehicle body is fixedly connected with a first limiting cavity, and the top of the first limiting cavity is rotatably connected with a vehicle frame through a rotating bearing. The top of the first limiting cavity is fixedly connected with a second limiting cavity, the inside of the second limiting cavity is slidably connected with a slider through a chute, and the inside of the first limiting cavity is rotatably connected with a plurality of threads A sleeve, the inner thread of the threaded sleeve is connected with a threaded air rod. In the present invention, by installing the third monitoring probe on the inner wall of the vehicle frame close to the second monitoring probe, the situation inside the vehicle frame can be observed, and during the transportation of the engineering vehicle, it can be found in time whether the goods inside the vehicle frame are bumpy or not. When falling, the goods inside the car frame are centrally monitored. When the vehicle is unloading, it can be observed whether the goods inside the car frame have been unloaded, and whether the goods inside the car frame are unloaded cleanly.
Owner:SHANGQIU INST OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products