77 results about "Visual matching" patented technology

A system and method for automatically matching images of screens. A system and method may include automatically matching images of screens. A first screenshot of a screen may be obtained, the first screenshot including a view port exposing a portion of a panel. A second screenshot of a screen may be obtained. A digital difference image may be generated and a match between the first and second screenshots may be determined based on the digital difference image.

The invention discloses a binocular visible light camera and thermal infrared camera-based target identification method. The method comprises the steps of calibrating internal and external parametersof two cameras of a binocular visible light camera through a position relationship between an image collected by the binocular visible light camera and a pseudo-random array stereoscopic target in a world coordinate system, and obtaining a rotation and translation matrix position relationship, between world coordinate systems, of the two cameras; according to an image collected by a thermal infrared camera, calibrating internal and external parameters of the thermal infrared camera; calibrating a position relationship between the binocular visible light camera and the thermal infrared camera;performing binocular stereoscopic visual matching on the images collected by the two cameras of the binocular visible light camera by adopting a sift feature detection algorithm, and calculating a visible light binocular three-dimensional point cloud according to a matching result; performing information fusion on temperature information of the thermal infrared camera and the three-dimensional point cloud of the binocular visible light camera; and inputting an information fusion result to a trained deep neural network for performing target identification.

The invention provides an automatic spraying system based on point cloud and image matching. The automatic spraying system comprises a three-dimensional scanning module, an automatic trajectory planning module, a visual matching module and a spraying module. The three-dimensional scanning module is used for scanning a spraying object and acquiring a point cloud model according to scanned three-dimensional point cloud data; the automatic trajectory planning module is used for planning spraying trajectories in a point cloud space; the visual matching module is used for acquiring a transformational relation between a point cloud coordinate system and a spraying robot coordinate system; the spraying module is used for automatically spraying the spraying object. The automatic spraying system has the advantages that an algorithm is planned automatically according to a robot spraying path of the point cloud coordinate system, the point cloud coordinate system is correlated with the robot coordinate system according to the cloud point and image matching algorithm, and accordingly, automatic spraying of the spraying object is realized; on the basis of guaranteeing spraying efficiency, the spraying quality is improved greatly, calculation quantity for trajectory planning is reduced, and trajectory planning quality is improved.

The invention discloses a double exposure implementation method for an inhomogeneous illumination image. The double exposure implementation method for the inhomogeneous illumination image comprises the following steps: obtaining an illumination image; obtaining a reflection image; overlaying the illumination image with the reflection image to obtain the global enhancement effect; fusing the global enhancement effect with the original image; and carrying out color correction on an enhancement result to obtain a visual matching image. According to the double exposure implementation method for the inhomogeneous illumination image, which is disclosed by the invention, the smooth property of the illumination image is constrained, and the reflection image is sharpened by the visual threshold value characteristic to guarantee the detail information of the image; with an image fusion method, the luminance, the contrast ratio and the color information of an original image luminance range can be effectively kept; because the characteristic of the human eye visual perception of average background brightness is introduced in, the fused image can be used for effectively eliminating image color distortion near a shadow boundary; the color of a low-illuminance zone is restored by the color correction technology; the colors of the low-illuminance zone and the luminance range are free from obvious distortion; the continuity is good; and the visual effect is more nature.

A system for monitoring an image tagging system comprises a processor and a memory. The processor is configured to provide a user display for a type of monitoring of an image tagging system. The user display includes image tagging monitoring for: a) in the event that a computer vision match is found, a computer vision match and an associated computer vision tag and, b) in the event that no computer vision match is found, a human vision match and an associated human vision tag. A memory coupled to the processor and configured to provide the processor with instructions.

The invention discloses a scenic spot scenery moving augmented reality method based on space relationship and image analysis. The method comprises the following steps that a geographical space data model facing an object is adopted for building a scenic spot geographical database according to the scenic spot scenery moving augmented reality guide demands and the scenic spot scenery space data organization characteristics; a built-in sensor of an intelligent mobile phone is adopted for obtaining the current position coordinates and the space orientation, an image pick-up view sight model based on multiple sensors is built, and the corresponding relationship between the real scenery images and the actual geographical space is generated; key frames are extracted from video image flows shot by the intelligent mobile phone and are fast divided sequentially through binaryzation and mathematical morphology methods; the visual matching between the real scenery space and the information space is realized through a measure of combining the image analysis with the space relationship, and the scenic spot scenery is identified; and the identified scenery is subjected to tracking registration by a moving detection method. The scenic spot scenery moving augmented reality method overcomes the defects of poor precision and low image identification technology efficiency of a space relationship realization method.

The invention provides a laser processing visual matching method and system and a medium. The laser processing visual matching method comprises a device fixing step, wherein a calibration plate is fixed on a flange of an industrial robot, and a camera is fixedly placed at a first preset position of an external space of the industrial robot; a coordinate system construction step, wherein a base coordinate system Base, a flange coordinate system Flange, a calibration plate coordinate system Tool and a camera coordinate system Cam of the industrial robot are constructed; and a matrix acquisitionstep, wherein a closed kinematic chain equation between the four coordinate systems is established, and a homogeneous transformation matrix of the calibration plate coordinate system and the flange coordinate system is obtained. Shortcomings in the prior art are overcome, the vision-based matching method with simple operation and high precision is provided, and guarantees are provided for high-precision and high-stability operation for follow-up laser processing.

The invention discloses a method for reproducing colors from a display to a projector by utilizing human eyes, which is a new technical method for a color management system, and belongs to the filed of color science and technology. The technical method that the traditional color management system is required to be measured by an instrument is changed, and a method of direct human eye visual matching of 6 to 9 pieces of colors of the display and the projector is adopted; and according to known white points and gamma values respectively set in the display and the projector, and a defaulted display characteristic linear matrix, a projector color characteristic linear matrix is calculated. Through the known and acquired characteristic parameter matrixes of the display and the projector, the display color of the display is converted to the projection color of the projector so as to realize the reproduction of the color from the display to the projector. The method has the advantages of simpleness and convenience, and low cost, and can be applied to common users with not high requirement on color reproduction accuracy.

The invention relates to the technical field of intelligent agriculture devices, in particular to a pesticide spraying robot system and a control method. The pesticide spraying robot system comprises a central control device, an image collecting device, a spraying device and a moving device, wherein the central control device, the image collecting device and the spraying device are arranged on the moving device; the moving device comprises a visual navigation device used for acquiring navigation track images according to marks set by a user; the central control device is used for determining a navigation path according to the navigation track images and controlling the moving device to move along the navigation path or stop crop image collecting along the navigation path; the central control device is also used for conducting visual matching on the crop images, accurately positioning positions needing pesticide spraying on crops, acquiring the spacial position information of the positions to be sprayed and controlling the spraying device to spray pesticide to the positions to be sprayed. The system can replace people to finish heavy spraying tasks, the cost for crop pesticide spraying is reduced, and popularization of modern intelligent agriculture devices is promoted.

The visual matching of two images is facilitated. An inspection tablet image and a genuine tablet image are each scanned by a local filter, correlation values between partial images and the local filter are calculated for every position of the local filter, and luminance images are generated using the calculated correlation values as luminance values. Multiple feature points where the luminance values are equal to or greater than a predetermined threshold value are determined in the luminance images and, based upon the multiple feature points, a registration parameter for eliminating relative offset between first and second images is calculated. The first luminance image and the second luminance image are brought into positional registration using the registration parameter calculated.

The invention is applicable to the field of intelligent terminal and image processing, and provides an image collection jitter removing method based on stereoscopic visual matching; the method comprises the following steps: using a FAST characteristic point to detect characteristic interest points of extracted forward and backward frames of images; using a scheme based on the ORB descriptor to match the FAST characteristic interest points of the forward and backward frames of images; using the normalization eight-point method based on the matched characteristic points to solve a transfer matrix F of the rotary motion of an image camera between the forward and backward frames; using the transfer matrix F to correct the deviation caused by the jitter, so as to obtain a corrected image. The provided method has the advantages of preventing jitter of multiple frames of images, and fast in calculating speed.

The invention provides a mobile phone indoor positioning and navigation method including the following steps: S1, fast three-dimensional reconstruction: obtaining depth information of a user surrounding scene through a mobile phone depth camera, and modeling a three-dimensional model of the surrounding scene with combination of the collected image of the mobile phone camera; S2, computer vision: collecting surrounding scene images by using a mobile phone RGB camera, and then carrying out spatial positioning by a computer vision matching algorithm; and S3, path planning and motion tracking: obtaining a user motion state by a mobile phone motion sensor, at the same time, obtaining the features of the surrounding scene by a mobile phone motion tracking sensor in real time, mapping the features to a two-dimensional path plane planning graph to correct a path, and positioning and navigating the user spatial position and motion direction in real time. The method has the beneficial effects ofrealization of mobile phone indoor positioning and navigation, low cost, short time period, fewer interference factors and small precision fluctuation range.

The invention discloses a robust stereoscopic vision inertial pre-integration SLAM (Simultaneous Localization and Mapping) method and belongs to the technical field of visual navigation, wherein inertial sensor measurement value is used for carrying out pre-integration forecasting carrier navigation information, the information is fused with data of a stereoscopic vision sensor to judge the imagematching quality, the pre-integration information is fused to output different results according to a judgement result, the constructed map can be multiplexed, and accumulated errors are eliminated. According to the method in the invention, the problem of visual SLAM matching errors and failure in a bad environment can be effectively solved, the high-robustness and high-precision carrier navigation information is obtained, a precise map can be constructed for multiplexing, and a good popularization prospect is achieved.

The invention relates to a design method of an AR-HUD interface for enhancing driving feeling, which belongs to the field of virtual reality and comprises the following steps: acquiring image information of a driving environment through a camera; finishing camera parameters are adjusted, and camera calibration; preprocessing the image; performing virtual imaging, calibrating parameters related to the AR-HUD system, so that virtual and real registration of an object is realized, and matching, alignment and prompting of a navigation virtual mark and a road real target are realized; designing an AR-HUD interface, building a virtual driving scene in a game engine, connecting entity vehicle equipment through a related port, then building a virtual test platform in combination with a head-mounted VR display system, and selecting an optimal AR-HUD display system. According to the invention, the defects of long real vehicle test period, high cost, high risk and the like are effectively avoided, and meanwhile, the defects in the aspects of interface design architecture, visual matching of a user and the like in the prior art are overcome.

The invention relates to a binary neural network stereo vision matching method based on an FPGA. The method comprises the following steps of 1, obtaining periodic input streams of pixels in a binocular matching grayscale image, 2, acquiring an image block from the pixel, 3, inputting the image blocks in the step 2 into a binary neural network with preset weights and parameters to obtain binary feature vectors, 4, performing cost calculation on the feature vector within the maximum search parallax to obtain a matching cost, 5, inputting the cost into semi-global cost aggregation for cost aggregation to obtain aggregated cost, 6, selecting the position with the minimum cost from the aggregated cost as parallax, and 7, carrying out consistency detection and parallax refinement calculation onthe selected parallax to obtain a parallax graph, and outputting parallax values of the pixels one by one according to a period. By means of the binarization method, computing and storage resources ofthe network can be effectively reduced, and therefore the high-precision stereo matching network can be deployed into the FPGA.

A print quality control method, comprises the steps of: providing a visual referring target on the printing substrate, setting a specific halftone of black “K”; creating a neutral grey tone i.e. NGT; placing tightly both MGT and NGT next to each other across the printing surface; and comparing both printed tones result. By adopting the grey balance theory and visual matching technique, the resultant can provide accurate ink balance information for the production personnel to immediate execute the correction on the imbalance inking condition during production.

The presently-disclosed solution provides an innovative system and method to protect a computer user from a phishing attack. Computer vision is effectively applied to match identifiable key information in suspect content against a database of identifiable key information of legitimate content. In one embodiment, the presently-disclosed solution converts suspect content to a digital image format and searches a database of logos and/or banners to identify a matching logo/banner image. Once the matching logo/banner image is found, the legitimate domain(s) associated with the matching logo/banner image is (are) determined. In addition, the presently-disclosed solution extracts all the URLs (universal resource links) directly from the textual data of the suspect content and further extracts the suspect domain(s) from those URLs. The suspect domain(s) is (are) then compared against the legitimate domain(s) to detect whether the suspect content is phishing content or not. Other embodiments and features are also disclosed.

The invention relates to the technical field of unmanned aerial vehicles, and particularly discloses a method of realizing real-time visual tracking on a target based on an image color and texture analysis. The method comprises a step of extraction and analysis of image features in which proper visual features are extracted according to the texture and the color of the image, significant features of the target in a scene are analyzed and extracted, and reference is provided for design of a tracking algorithm, a step of design of the target tracking algorithm in which the reasonable target tracking algorithm is designed according to a visual feature analysis result, the target tracking algorithm adopts a color tracking algorithm or a texture tracking algorithm and application conditions of the tracking algorithm are brought forward, and a step of target matching and recovering in which the proper target features are used for visual matching to judge the accuracy of the tracking result. When target occlusion or image loss happens, the target can be recovered through full image search. A visual tracking method is designed for a specific application situation, and high-reliability tracking on the target is thus realized.

Various embodiments provide methods and systems for users and business owners to share content and/or links to visual elements of a place at a physical location, and, in response to a user device pointing at a tagged place, causing the content and/or links to the visual elements of the place to be presented on the user device. In some embodiments, content and links are tied to specific objects at a place based at least in part upon one of Global Positioning System (GPS) locations, Inertial Measurement Unit (IMU) orientations, compass data, or one or more visual matching algorithms. Once the content and links are attached to the specific objects of the place, they can be discovered by a user with a portable device pointing at the specific objects in the real world.