42 results about "White line" patented technology

To provide an image recognition device and image recognition method which confirm whether a vanishing point exists at a correct position and detect an installation abnormality of an on-vehicle camera even when a white line cannot be detected during vehicle travel.SOLUTION: An image recognition device 10 comprises: an image acquisition unit 11 that acquires an image of a scene ahead of a vehicle imaged by an on-vehicle camera 5; and a vanishing point calculation unit (second vanishing point calculation unit 14) that sets a predetermined region in the image as a detection frame and calculates a vanishing point on the basis of movements of feature points within the detection frame. The vanishing point calculation unit sets the size of the detection frame on the basis of at least a traveling speed of the vehicle and a time interval for capturing the image, and calculates the vanishing point on the basis of a position of a feature point detected within the detection frame in a first image captured at a first time and a position of the feature point detected within the detection frame in a second image captured at a second time after the time interval has elapsed from the first time.SELECTED DRAWING: Figure 1

A light-emitting device (1) is attached to a support body of a mobile body (100) alongside an imaging device (2), and emits invisible light which is detected by the imaging device (2) toward the ground. In the light-emitting device (1), a position (PP) of peak illuminance in an irradiation region (IA) of the invisible light with which the ground is irradiated is present at a position away from the support body. The irradiation region (IA) includes a first region (A1) including the position (PP) of peak illuminance, and a second region (A2) surrounding the first region (A1). When irradiance with which a white line (210) drawn on the ground can be detected is defined as white line irradiance, the first region (A1) is a region irradiated with the invisible light at an irradiance equal to or higher than the white line irradiance, and the second region (A2) is a region irradiated with the invisible light at an irradiance lower than the white line irradiance.

The present invention relates to the field of inkjet printing technology, and provides an inkjet printer comprising: a paper motion control unit, an ink tank, a print head, and a control unit; the print head comprising an ignition mechanism and M inkjet channels; the M inkjet channels being arranged along the direction of paper motion, with the length of the inkjet channels being perpendicular to the direction of paper motion; the control unit instructing the print head to simultaneously ignite the nozzles of the M inkjet channels at first designated intervals, with the distance between each two adjacent inkjet channels being M×N times the unit dot pitch, for a total of N ignitions, with the distance between two adjacent ignitions of each inkjet channel along the direction of paper motion being M times the unit dot pitch, and the N ignitions constituting a group; a second designated time is paused between each group of ignitions, and multiple groups of ignitions are repeated until printing is completed; the ratio of the second designated time to the first designated time being M-1:M. This solution can effectively increase printing speed and prevent the appearance of a white line that affects printing quality.

The invention provides a general plane graph color migration method and system based on a depth diffusion model, and the method comprises the following steps: (1) carrying out the semantic segmentation of a black and white general plane line draft graph, and generating a semantic mask graph; (2) extracting global style features of the color general plane reference image and local color distribution features of different semantic regions; (3) inputting color features of the line draft image, the semantic mask image and the reference image into a depth diffusion model, restraining the structure of the generated image to be consistent with that of the line draft through a ControlNet module, and migrating the color features of the reference image to a corresponding position of the line draft according to a semantic region through a region perception attention mechanism; and (4) in the de-noising process of the diffusion model, combining the style consistency loss function and the regional color histogram matching loss to generate an image after color migration. According to the method, the color of the reference picture is migrated to the black-and-white line draft according to the semantic region, meanwhile, the line draft structure is kept complete, and the requirement for rapid personalized drawing can be met.

This invention discloses a 3D grating UV high-precision alignment printing method and printer, belonging to the field of UV printing. The method includes: S100, using a grating ruler with quartz glass as the substrate and an optical positioning accuracy of 0.1μm as the core positioning element in the UV printer; S200, placing the transparent grating image core on the printing platform, and converting the grating cylinder into a black and white line pattern recognizable by machine vision through the optical interaction between the grating ruler and the transparent grating image core; S300, activating the machine vision recognition system to capture the black and white line pattern, identifying and positioning each transparent grating cylinder; S400, the vision system detects the direction of the black and white line pattern to determine the tilt, identifies the positions of the black lines at both ends of the same cylinder, calculates the tilt angle, and automatically corrects it by the motion control system; S500, controlling the printing carriage to move along the correction path to perform UV curing and precise alignment printing of the transparent grating image core. This invention can improve the machine vision recognition accuracy of the printer equipment and achieve a high degree of matching with the grating image core.

Even if the distance between the imaging unit and the road surface changes due to changes in the weight of the moving object or changes in the air pressure of the wheels, calibration will be performed in accordance with these changes. [Solution] Based on the image captured by the imaging unit 210 regarding the stop line, which is a road surface feature having a known length along the direction of travel of the moving body MV, the movement amount detection unit 321A detects the amount of pixel movement. The identification unit 322A identifies the white line region in the captured image. Then, the calibration unit 323A, based on the amount of pixel movement and the identification result of the white line region in the captured image, as well as the known length of the stop line along the direction of travel of the moving body MV, determines that the moving body MV is traveling in a straight line at a constant speed on a flat road surface, and calibrates the distance on the road surface corresponding to one pixel, which is related to the distance between the imaging unit 210 and the road surface.

The surrounding object or the lane is detected from the monitoring result of the surrounding situation monitoring device, and the host vehicle image depicting the host vehicle or the surrounding vehicle image depicting the surrounding vehicle is displayed, and the white line of the detected lane is displayed. At this time, when the current position is not on the expressway or the arterial road, the control to not display the white line of the lane is performed. Alternatively, in a case where the current position is a non-public road excluding the parking lot, the white line of the lane is not displayed.

To provide a lane marking construction vehicle capable of forming lane markings on road surfaces with sufficient accuracy while responding to speeding-up of lane marking construction.SOLUTION: In a lane marking construction vehicle according to the present invention, a control part 21 constituting a control device 17 executes processing for extracting existing lane markings by using camera images captured by a forward cameras 15 and a downward camera 16 to adjust a paint injecting position based on lane marking extraction results, and processing for instructing injection start / stop timing to a coating device 11, a bead spraying device 13, and a release agent spraying device 14. In the processing for extracting the existing lane markings, an AI image generation model is used to generate an AI image that extracts only a white line portion of the lane markings from a composite image that includes unnecessary information other than the lane markings, and based on the AI image, unnecessary information other than the lane markings is deleted from the composite image that includes unnecessary information other than the lane markings.SELECTED DRAWING: Figure 2

The invention relates to the technical field of arena robots, in particular to an arena robot environment sensing method based on multi-sensor time sequence fusion, and mainly solves the technical problems of low sensing precision, poor robustness and unreasonable scheduling of the arena robot environment sensing method. The method is based on an arena robot carrying a visual sensor, an IMU sensor, an ultrasonic sensor and an infrared reflection type sensor and is iteratively updated according to a preset sensing period. In each sensing period, the method executes the following steps: S1, generating a synchronous observation sequence; s2, forming a feature sequence; s3, calculating a credibility index; s4, constructing a dynamic attention network, and outputting a fusion weight vector and a scheduling instruction set; s5, calculating a white line boundary risk degree; s6, performing coverage correction through a security policy layer; s7, carrying out multi-sensor time sequence fusion; and S8, feeding back a result and updating a historical time sequence window.

The application discloses a method for detecting a red water line of a bill, comprising the following steps: acquiring a target detection image of a target detection area of a target bill to be detected, acquiring a first quantity of red pixel points and a second quantity of black pixel points in the target detection image, and calculating a first ratio of a sum of the first quantity and the second quantity to a total quantity of pixels of the target detection image; determining whether the first ratio is less than a preset first threshold value, and if not, acquiring a binary image of the target detection image; acquiring a first number of white line penetrations of at least one column in the binary image, and calculating a first average value of the first number; determining whether the first average value is less than a preset second threshold value, and if not, acquiring a projection histogram of a horizontal direction projection of the binary image; determining whether the projection histogram meets a preset image requirement, and if the projection histogram meets the preset image requirement, determining that the target detection area has a red water line. The application further discloses a system for detecting a red water line of a bill, a detection device and a storage medium.

The present application relates to the field of intelligent image processing and computer vision, and particularly relates to a badminton match video line violation intelligent visual detection method, comprising: constructing a badminton match image dataset containing foot contour and field key point annotation; designing and training a DFSNet foot segmentation network, which introduces an attention mechanism in the decoder part to realize accurate segmentation of left and right foot contours; training a key point detection model based on the annotated key points, and generating a bottom line, a service line and a center line binary mask that conforms to the actual white line in the image through secondary refinement; finally, performing pixel-level overlap detection on the foot contour output by the DFSNet and the refined field line mask, and if there are overlapping pixels, it is determined that the foot has violated the line. The present application takes foot contour analysis as the core, combines deep learning feature extraction with geometric prior optimization, realizes automatic and accurate detection of badminton line violation, and can be widely applied to sports event auxiliary judgment and sports analysis.

This invention relates to the field of computer hardware interface technology and discloses a magnetic positioning anti-misinsertion computer interface detection module. This magnetic positioning anti-misinsertion computer interface detection module includes a cylindrical plug and a cylindrical recessed socket. The cylindrical plug has a circular copper contact piece embedded in its surface, a locking groove on its outer side, and a white line on its outer side. A first magnet is embedded in the surface of the cylindrical plug. An elastic contact is located inside the cylindrical recessed socket. A baffle is located inside the cylindrical recessed socket, and a second magnet is embedded in its surface. A limit groove is formed on the outer side of the baffle. A locking assembly is located on the sidewall of the cylindrical recessed socket, and an infrared reflective sensor is embedded in the inner wall of the cylindrical recessed socket. This device has advantages such as automatic magnetic positioning, an active anti-misinsertion mechanism, stable connection, and safe locking, solving the problems of high directional requirements for traditional interfaces and easy damage caused by misinsertion.

By utilizing lane markings such as white lines, the system accurately estimates the vehicle's position in the direction of travel. [Solution] The self-position estimation device is mounted on a moving object and acquires the predicted position of the moving object. The self-position estimation device calculates the difference between the predicted position of the endpoint of the lane line obtained based on the endpoint information of the lane line obtained from map information and the measured position of the endpoint of the lane line measured by a measuring unit mounted on the moving object scanning light in a predetermined direction, and estimates the self-position of the moving object by correcting the predicted position with a value obtained by multiplying the difference value by a coefficient. The self-position estimation device then corrects the coefficient based on the interval of the scanning position of the measuring unit at the position where the endpoint of the lane line was detected.

The invention relates to a defective spray hole self-adaptive compensation method, computer equipment and a storage medium. Visual defects caused by defective spray holes are dynamically repaired, distribution and size of peripheral ink droplets are adjusted under the condition that the jitter direction of printing points generated after halftone processing is followed as much as possible, and blank / wrong ink dots are prevented from affecting image quality. The method comprises the following steps: dynamically calculating the position and compensation amount of a compensation printing point from three dimensions of point, line and surface based on the printing direction of a defect spraying hole point in a graph after the original halftone processing and the continuity and concentration change of the defect spraying hole point in the vertical direction and the horizontal direction according to the randomness and isotropy of dot distribution after the original halftone processing; the phenomenon that the uniformity and smoothness of the image are affected by fixed position and random position compensation in a traditional method is avoided, and'white lines' appearing in a high-concentration area or'black lines' appearing in a low-concentration area and structural defects under local out-of-control concentration in the traditional method are avoided.

An apparatus and method for road detection and polarization imaging belong to the technical field of polarization imaging and detection. The present invention provides a vehicle-mounted high-definition polarization camera imaging system. By adding polarization elements and combining corresponding optical imaging elements, image acquisition is performed on the road surface in front of the vehicle during driving. Through the mutual cooperation among modules such as a monochromatic brightness information processing unit, a polarization ratio information processing unit, a white line detection unit, a road surface edge detection unit, a road surface shape estimation unit, a lane line search area determination unit, a lane line candidate point detection unit, and a lane line detection unit, etc., the polarization image of the road is detected, and brightness information is obtained to make the white line have a higher brightness level. Accurately identifying the white road lines on the road and guiding the vehicle's progress with the white road lines as a reference can make the recognition accuracy of the vehicle's driving road higher in rainy and snowy weather, and better play the role of vehicle-assisted safe driving.

The invention relates to an electronic equipment shell forming process, in particular to the technical field of communication equipment, and the electronic equipment shell forming process comprises the steps of machining, surface treatment and insulator glue injection forming which are carried out in sequence; the insulator glue injection molding comprises the steps of surface activation, mold cavity construction, glue injection, curing and demolding; and the glue injection process comprises glue injection molding of an antenna dividing strip on the back side of the shell and glue injection molding of a decoration strip on the front side of the shell. According to the electronic equipment shell forming process provided by the invention, by adopting the glue injection process, glue injection forming of the antenna isolation strip and the decoration strip on the electronic equipment shell is realized, the bonding force of the antenna isolation strip and the decoration strip with the base material is improved, and the defects of easy cracking, acid spitting and white line generation in the subsequent anode process are avoided; and meanwhile, the antenna isolation strip and the decoration strip obtained by the glue injection molding process have good high and low temperature impact resistance and high temperature and high humidity resistance.

To provide an other vehicle meandering detection device that improves the accuracy of detecting meandering of vehicles.SOLUTION: A CPU 2 detects meandering of other vehicles 200 based on the behavior of the other vehicles 200 captured in a camera image. The CPU 2 detects meandering of an own vehicle 100 based on the positions of white lines 300R and 300L on a traffic lane where the own vehicle 100 captured in the camera image travels, or based on lateral G-values detected by a G-sensor 24. When detecting meandering of the own vehicle, the CPU 2 stops detecting meandering of the other vehicles.SELECTED DRAWING: Figure 2

The application discloses a method for detecting chicken breast with wood and white line symbiotic muscle defects by hyperspectral imaging, and comprises the following steps: acquiring wood meat samples and white line meat samples with different grade gradients; acquiring hyperspectral images of the samples; extracting image texture features; preprocessing spectral data; selecting characteristic wavelengths for the spectrum; measuring the physicochemical quality of the samples; taking the image texture features and the spectral data under the selected characteristic wavelengths as inputs, and taking quality index values as outputs, to establish a CNN model; collecting hyperspectral images of chicken breast with wood and white line symbiotic muscle defects, inputting the image texture features and the spectral information of each pixel point in the multispectral image under the characteristic wavelength points into the optimized CNN model, obtaining comprehensive quality index values of each pixel point, respectively assigning colors to each pixel point, and forming a classified visual image; and the model detection and the visual image can accurately analyze and represent the symbiotic state of the white line and the wood tissue.

And a display device that detects surrounding objects and lanes on the basis of the monitoring result of the surrounding situation monitoring device, displays a host vehicle image that simulates the host vehicle, and a surrounding vehicle image that simulates the surrounding vehicle, and displays white lines of the detected lanes. At this time, when the current position is other than the expressway or the trunk road, control is performed so that the white line of the lane is not displayed. Alternatively, when the current position is an off-road other than the parking lot, the white line of the lane is not displayed.

The light distribution control method controls the vehicle lamp capable of irradiating the front of the vehicle according to the information of the light distribution pattern (P1) formed by the vehicle lamp. The method controls the driving of the vehicle lamp so as to irradiate a region farther than a region (R1) in which a white line is detected on the basis of image information obtained by capturing an image of the front of the vehicle.

The present application relates to the field of intelligent image processing and computer vision, and particularly relates to a badminton match video line violation intelligent visual detection method, comprising: constructing a badminton match image dataset containing foot contour and field key point annotation; designing and training a DFSNet foot segmentation network, which introduces an attention mechanism in the decoder part to realize accurate segmentation of left and right foot contours; training a key point detection model based on the annotated key points, and generating a bottom line, a service line and a center line binary mask that conforms to the actual white line in the image through secondary refinement; finally, performing pixel-level overlap detection on the foot contour output by the DFSNet and the refined field line mask, and if there are overlapping pixels, it is determined that the foot has violated the line. The present application takes foot contour analysis as the core, combines deep learning feature extraction with geometric prior optimization, realizes automatic and accurate detection of badminton line violation, and can be widely applied to sports event auxiliary judgment and sports analysis.

The invention is applicable to the technical field of computer graphic processing, and provides a method for rendering a three-dimensional model wireframe structure in real time based on UV mapping and line chartlet, which comprises the following steps: S1, a modeling stage: screening and marking key side lines of a model in three-dimensional modeling software, executing UV expansion, newly building an independent UV channel to store side line information, and reserving an original UV channel for conventional chartlet; s2, a baking stage: constructing a black background base map in three-dimensional modeling software, exporting a black and white line map containing side lines based on the independent UV channel, and optionally optimizing the line map through image processing software; s3, a coloring stage: creating a shader containing wireframe parameters and a related material in real-time rendering software, loading the line chartlet, then adjusting wireframe attributes in real time, introducing anti-aliasing processing, and endowing the material to the model to complete rendering; according to the invention, the compatibility and the performance are obviously improved, the degree of freedom and the efficiency of adjustment are greatly optimized, and the quality and the visual effect of the wireframe are obviously improved.

The present invention provides a method and system for automatically coloring a mandala pattern. The method includes the following steps: obtaining a pattern to be colored, performing binarization processing on the pattern to be colored to obtain a black-and-white line drawing; extracting each closed region in the black-and-white line drawing and constructing a minimum bounding rectangle for each closed region; classifying the closed regions into multiple categories through a first classification based on the length and width of the minimum bounding rectangle of the closed region; obtaining the positions of all closed regions of the same category in the pattern to be colored and performing unified coloring. This solution constructs a minimum bounding rectangle for each closed region and classifies the closed regions based on specified rules. Staff can directly obtain the positions of closed regions of the same category and can uniformly color all closed regions of a category. This solution no longer requires manual determination of which small structures belong to the same shape, improving the coloring efficiency of the mandala pattern.

To realize a movement support device capable of restricting a center line arranged on a road from being erroneously determined as a braille block.SOLUTION: A movement support device 1 includes: a target detection section 40a for detecting a target in an image 21 based on information obtained from image data of the image 21 photographed by the photographing section 20; a block candidate determination section 40c for determining whether the target corresponding to a braille block candidate TC exists; a crosswalk determination section 40b for determining whether the target corresponding to a crosswalk 24 exists; an inclination calculation section 40d for calculating an inclination ΔT of the braille block candidate TC and an inclination ΔL of a white line WL on the crosswalk 24; and a braille block extraction section 40e for extracting a real braille block T. The braille block extraction section 40e does not extract the braille block candidate TC as the real braille block T when a difference between the inclination ΔT of the braille block candidate TC and the inclination of ΔL of the white line WL is less than a predetermined value.SELECTED DRAWING: Figure 2

To improve white line detection performance.SOLUTION: An image processing device 10 includes a controller 12 for detecting a white line in a detection area which is set in an image photographed by a camera 21 arranged in a vehicle. The controller 12 detects that the vehicle is moving laterally based on information related to the vehicle. The controller 12 enlarges the detection area in the opposite direction of a horizontal movement direction when it is detected that the vehicle is moving laterally.SELECTED DRAWING: Figure 5

The present invention provides an anti-counterfeiting identification method for a wrinkle anti-counterfeiting label with a fingerprint-like structure, which comprises the following steps: converting an RGB image of an optical image of the wrinkle anti-counterfeiting label into a grayscale image; setting a certain threshold to convert the grayscale image into a black-and-white binary image; refining the black and white lines in the binary image to obtain a required refined image; finding and marking the breakpoints and bifurcation points of the wrinkle pattern in the refined image using code statements, and counting the number of the breakpoints and bifurcation points; finding a breakpoint within r pixels, setting the size according to actual needs, and having no other breakpoints and bifurcation points within the radius length, recording the number of characteristic points, and counting the distances between each characteristic point; and performing anti-counterfeiting identification: using the number of breakpoints and bifurcation points of the wrinkle pattern on the anti-counterfeiting label to effectively and accurately determine the authenticity of the product. The anti-counterfeiting identification method for the wrinkle anti-counterfeiting label with a fingerprint-like structure provided by the present invention is simple and easy to implement, has a high accuracy rate, and can be practically applied in the field of anti-counterfeiting.

Lane dividing line detection correcting device with: a maximum curvature estimation circuit (12) for estimating a maximum curvature of a road, along which a vehicle is traveling, based on vehicle sensor information; and a curvature correction circuit (13) for correcting a curvature of a lane dividing line, which has been input to the curvature correction circuit based on the maximum curvature; where the lane dividing line is represented by a white line.

The product related to this design is an image that appears when a timer application is launched, which rings a metal bell at the set time. The timer time can be set by rotating the semi-transparent circular slider located on the metal bell in the center of the image in a circular motion, and the timer can be started or stopped by tapping the metal bell in the center of the image. Pressing the gear button depicted with a white line in the upper left opens the settings screen, and the title of the background sound that plays when the timer is running is displayed in the lower left.

The present invention provides a light-emitting device that can suppress the occurrence of halation in the image generated by the imaging device, even when a white line on the ground is detected using a light-emitting device in a vehicle monitoring system. [Solution] The light-emitting device 1 is mounted on the support of the mobile body 100 alongside the imaging device 2, and emits invisible light detected by the imaging device 2 toward the ground, wherein the position of the peak illuminance in the illumination area IA of the invisible light irradiated toward the ground is P P It is located away from the support, and the irradiation area IA is at the peak illuminance position P P The region includes a first region A1 containing the white line 210, and a second region A2 surrounding the first region A1. If the irradiance required to detect the white line 210 drawn on the ground is defined as the white line irradiance, then the first region A1 is a region irradiated with invisible light at an irradiance equal to or greater than the white line irradiance, and the second region A2 is a region irradiated with invisible light at an irradiance lower than the white line irradiance.