980 results about "Color recognition" patented technology

A method is described comprising: positioning a plurality of color-coded motion capture markers at a plurality of points on a performer's body, wherein the color-coded motion capture markers are colored with at least two or more different colors; and tracking the color-coded motion capture markers during a motion capture session using two or more color cameras and a color-coded motion capture subsystem, the color-coded motion capture subsystem identifying each individual color-coded motion capture element based on its color and/or its relationship to the other color-coded motion capture markers.

The invention discloses a method for locating a vehicle license plate in complex background. The method comprises the following steps: (1). Differentiating a gray scale mean of a fixed-size region and extracting a vehicle body image from a video; (2). preprocessing the vehicle body image such as gradation, gradient information enhancing, binarization and the like; (3). performing mathematical morphology operation on the processed vehicle body image, and performing primary screening by combining structural features of the vehicle license plate to obtain a plurality of candidate vehicle license plate regions; (4). converting the obtained candidate vehicle license plate regions into an HSV color spatial image; (5). adopting a BP neural network to perform color identification on the HSV color spatial candidate vehicle license plate image, and performing color edge detection by computing the mean color distance between two adjacent regions of a certain pixel; (6). judging edge color pair of an edge point, and eliminating the false vehicle license plate edge; and (7). performing final vehicle license plate location by the texture feature of the vehicle license plate. The method is suitable for complex background, and has higher location accuracy rate and higher robustness.

Disclosed herein are methods and apparatus for authentication of various substrates, including paper based substrates such as currency. Techniques are disclosed for use of security features to generate security codes. The security codes are deciphered with apparatus including a color recognition sub-system that provides for verification of authenticity of the substrate containing the security features.

Position detection and/or movement tracking via image capture and processing. Digital cameras perform image capture of one or more objects within a particular region (e.g., a physical gaming environment). A game module or processing module processes the images captured by the digital cameras to identify a position of and/or track movement of objects (e.g., a player, a gaming object, a game controller, etc.). Various digital image processing techniques may be employed including pattern recognition of objects, color recognition/distinction, intensity recognition/distinction, relative size comparison, etc. to identify objects and/or track their movement. The coupling between the digital cameras and the game module or processing module may be wired, wireless, or a combination thereof. If wireless, any number of different signaling means may be employed including Code Division Multiple Access (CDMA) signaling, Time Division Multiple Access (TDMA) signaling, or Frequency Division Multiple Access (FDMA) signaling.

The invention discloses a multi-unmanned aerial vehicle cooperation highway intelligent inspection system. According to the multi-unmanned aerial vehicle cooperation highway intelligent inspection system, with multi-rotor unmanned aerial vehicles adopted as carriers, omni-directional and zero-dead inspection can be performed on highways based on aerial photography technology, so that a plurality of traffic condition parameters such as vehicle speed, traffic flow and road occupancy of the highways can be obtained, and vehicles conducting traffic violations and traffic conditions of the highways can be monitored in real time; a GPS positioning and image processing integrated navigation technology is adopted to display a region of interest at an aerial photography center; a machine vision application control theory is adopted to realize autonomous flight of the unmanned aerial vehicles, manual operation is not required, and long-distance flight can be realized; the multi-rotor unmanned aerial vehicles are adopted to coordinate inspection, and transfer stations are established at ground, and therefore, unmanned aerial vehicle full-section inspection can be realized; and color recognition is adopted to realize accurate landing of the unmanned aerial vehicles; wireless power supply is adopted, which can bring great conveniences, and solar panels are utilized, and energy is environmentally friendly; and unmanned aerial vehicle transfer station protection devices are adopted to protect devices such as the unmanned aerial vehicles and wireless charging devices to the greatest extent.

The invention relates to a target object recognition and positioning method based on color images and depth images. The method is characterized by comprising the following steps that (1), a target region is confirmed by a robot by the adoption of the remote HSV color recognition, the distance between the robot and the target region is obtained according to the RGB color images and the depth images, and the robot conducts navigation and path planning and moves to the portion near the target region; (2), when the robot reaches the portion near the target region, through the SURF feature point detection, the RGB feature information of the target object is obtained, feature matching is conducted on the RGB feature information and the pre-stored RGB feature information of the target object, and if the feature of the target object accords with an existing object model, the target object is positioned; and (3), the RGB color images are collected to an imaging plane, the two-dimensional coordinates of the target object in the imaging plane are obtained, and the relative distance between the target object and a camera is obtained through the depth images, so that the three-dimensional coordinates of the target object are obtained. By the adoption of the target object recognition and positioning method, the category of the object can be judged quickly, and the three-dimensional coordinates of the object can be determined quickly.

A system and method for color transfer are provided. The method includes retrieving a concept color palette from computer memory corresponding to a concept selected by a user. The concept color palette includes a first set of colors, which may be statistically representative of colors of a set of predefined color palettes which have been associated with the concept. The method further includes computing an image color palette for an input image. The image color palette includes a second set of colors that are representative of pixels of the input image. Colors of the image color palette are mapped to colors of the concept color palette to identify, for colors of the image color palette, a corresponding color in the concept color palette. A transformation is computed based on the mapping. For pixels of the input image, modified color values are computed, based on the computed transformation, to generate a modified image.

The invention discloses an automatic vehicle body color recognition method of an intelligent vehicle monitoring system. The method comprises the following steps: firstly detecting a feature region on the behalf of a vehicle body color according to the position of a plate number and the textural features of the vehicle body; then, carrying out color space conversion and vector space quantization synthesis on pixels of the vehicle body feature region, and extracting normalization features of an obscure histogram Bin from the quantized vector space; carrying feature dimension reduction on the acquired high-dimension features by adopting an LDA (Linear Discriminant Analysis) method; carrying out various subspace analysis on the vehicle body color, then carrying out vehicle body color recognition of the subspaces by utilizing the recognition parameters of an offline training classifier, and adopting a multi-feature template matching or SVM (Space Vector Modulation) method; and finally, correcting color with easy intersection and low reliability according to the initial recognition reliability and color priori knowledge, so as to obtain the final vehicle body recognition result. The automatic vehicle body color recognition method is applicable to conditions of daylight, night and sunshine and is fast in recognition speed and high in recognition accuracy.

The invention discloses a method for positioning a characteristic region representing a dark and light color and a color of a vehicle body, which comprises the steps of: determining a vehicle region according to a reference region of a vehicle in an acquired vehicle image; constructing an energy distribution function according to texture characteristics and structural characteristics of the vehicle region; and positioning the characteristic region used for representing the dark and light color and the color of the vehicle body by taking a point with maximum energy in the energy distribution function as a central point. The invention also provides a method for identifying the dark and light color of the vehicle body and a method for identifying the color of the vehicle body. The application of the method can reduce computation amount, quicken computation speed, and improve identification accuracy rate.

The invention discloses a multi-task deep convolutional neural network-based vehicle color identification system. The system comprises a high-definition camera mounted above lanes on a road, a trafficcloud server and a vehicle color visual detection subsystem; the vehicle color visual detection subsystem comprises a vehicle locating detection module, a license plate locating detection module, a license plate background color identification module, a color difference calculation module, a vehicle color correction module and a vehicle color identification module; the vehicle locating detectionmodule, the license plate locating detection module and the vehicle color identification module share a same Faster R-CNN deep convolutional neural network; by adopting the deep convolutional neural network, vehicles on the road are quickly segmented; license plates on the road are quickly segmented by further adopting the deep convolutional neural network through using vehicle images; and space position information of the vehicles and the license plates in a road image is given. The multi-task deep convolutional neural network-based vehicle color identification system provided by the invention is relatively high in detection precision and relatively high in robustness.

Pretreated aluminum and aluminum alloys and the process and composition for pretreating said aluminum and its alloys to provide a coating with color recognition for identification purposes and to improved the corrosion-resistance, electrical conductivity, and adhesion properties which comprises pretreating said aluminum and its alloys with an effective amount of an acidic aqueous solution having a pH ranging from about 2.5 to 5.5 comprising water soluble trivalent chromium compounds, alkali metal hexafluorozirconates, divalent zinc compounds, alkali metal fluoro-compounds, and effective amounts of water soluble thickeners, surfactants or wetting agents.

The invention discloses a visual identification and grabbing method of mechanical arms. The method includes the following steps of (1) image collecting, wherein workpiece images are collected through a dual-camera system formed by two CCD visual sensors, and the images are converted into digital formats and transmitted into a computer memory, (2) image processing, wherein a processer conducts color recognition, image enhancement, edge sharpening and noise reduction on the images, conducts measurement on the length and area of workpieces, and finds out the coordinate position of the central point of the workpieces in the images, (3) coordinate transferring, wherein the coordinates of the CCD visual sensors are calibrated with the coordinates of the mechanical arms, so that the coordinate system of the CCD visual sensor can coincide with that of the mechanical arms, the coordinate position of the central point of the workpieces in the images is transmitted to a controller of the mechanical arms, and the mechanical arms are controlled by the controller to grab the workpieces. By means of the visual identification and grabbing method of the mechanical arms, the mechanical arms are made to more accurately grab the workpieces in the fast-paced production process, in other words, under the dual-camera system, even though the positions of the workpieces are slightly deviated, the mechanical arms can accurately grab the workpieces as well.

The invention relates to a device and a method for discriminating the color of a touch pen of a touch device. The method mainly comprises the following steps of: determining the imaging position of the touch pen in an image shot by the color discrimination camera through an image subtraction method or by computing the position of the touch pen on a touch screen; selecting a sampling area by taking the position as a center; respectively solving the average values of R, G, B values of pixel points in the sampling area, and converting a result to an HSV (Hue Saturation Value) color space for adjustment; and converting the adjusted H, S V values back to RGB (Red-Green-Blue) formats, and outputting the RGB color values as ultimately determined colors to a display screen for display. The invention can more accurately discriminate the color of the touch pen of the touch device, effectively improves the condition that the display color is slant dark and has easy operation.

The invention relates to a vehicle color recognition method based on area discrimination. The detected complete vehicle image is used as input, a deep learning algorithm framework is adopted, and the color type of a vehicle under recognition is outputted through processing of various steps of vehicle color area discrimination, vehicle color feature extraction and vehicle color judgment, wherein vehicle color area discrimination refers that a main clue area, an auxiliary recognition area and an unrelated area of color recognition in the complete vehicle image are discriminated according to the color information quantity, and the vehicle color features are respectively extracted through accurate detection of the areas so as to realize accurate recognition of the vehicle color. The complete vehicle image is divided into the main clue area, the auxiliary recognition area and the unrelated area of color recognition, the unrelated area is eliminated in the recognition process, and the vehicle color is recognized through combination of the features of the main clue area and the auxiliary recognition area so that the accuracy of vehicle color recognition under a complex monitoring scene can be enhanced.

The invention provides a color discrimination method which comprises the steps: acquiring and analyzing the image data of a distinguished target, acquiring red, green and blue (RGB) parameter(s) of one or more pixel(s), acquiring color mark(s) of one or more pixel(s) according to the corresponding relationship between the preset RGB parameters and the color marks and the RGB parameter(s) of one or more pixel(s), and outputting the color information according to the color mark(s). The invention also provides a color discrimination device. The color discrimination method and device can be used for realizing color discrimination.

The invention discloses a deep learning based vehicle color identifying method and device. The method includes that vehicle pictures are input as test samples and training samples for pre-treatment; training a convolution neural network by using the training samples and extracting deep layer color characteristics; using a deep layer color characteristic training classifier to identify vehicle colors of the test samples. By adopting the method and device provided by the invention, vehicle color identifying accuracy is improved, structural parameters are simplified and overfitting is eliminated.

The invention discloses a multi-index high-speed dynamic detection and material dividing method and device of an annular sliding bearing. According to the method, multiple indexes of the outer surface size and the inner surface coating defects of the sliding bearing are dynamically detected through machine vision, material division is carried out on workpieces according to the detection result through the color recognition technology of machine vision, and the method has the advantages of being high in detection efficiency, accurate in recognition, high in automation degree and the like. The device comprises a roller, a conveying belt, a high-definition camera, a digital control spraying device, an electric switch, a computer system and the like, wherein the high-definition camera is used for carrying out multi-index dynamic detection on the sliding bearing rotating in a fixed-axis mode, whether defects exist is recognized and material division is carried out through the high-definition camera and a limiting switch, the detecting speed is as high as 120-180 per second, the recognition accuracy is as high as 100 percent, automatic production is fully realized, and the detection cost is largely reduced.

The invention discloses a color identifying method which includes the following steps: characteristic zones of an object to be identified in an image are defined; colors of pixel points in the characteristic zones are identified; the colors of the pixel points are calculated to acquire characteristic vectors of zone color identification and then colors of characteristic zones used for representing the color of the object to be identified are identified. The adoption of the invention can reduce calculated amount and accelerate calculation speed and enhance identification accuracy.

The invention discloses a color identifier, which comprises a color detector that measures color info in such a way that a light source emits detection light to the object and a sensor receives the reflected light; a data processing unit for collecting, saving data, comparing and identifying colors, and judging relative events; and an output unit for outputting the results of color identification. The invention additionally discloses a color identifying way corresponding to the color identifier: the object (e.g. a writing pen) is placed on the color identifier, when the object is taken up, the color of the object is automatically identified and the color info is fed back to an up-level unit. The invention can be applied on an electron white board. When using an electron white board to write, the color of the writing pen will be identified automatically, so that the writer can use the electron white board easily as using an ordinary blackboard or whiteboard, and can write characters in any color of the writing pen. The invention can also be used in other application needing color identification.

The invention discloses a method for inducing dying of clothes in a washing machine. Clothes color data are collected by a color recognition sensor, are transmitted to a controller, and are compared with preset color data by the controller, if clothes easy to dye other clothes are in a washing barrel, a running washing program is paused, and an alarm is started; and if the clothes easy to dye other clothes are not in the washing barrel, the washing machine washes the clothes. The method can alarm and remind users when detecting the clothes easy to dye other clothes, so that dying risks during washing can be avoided.

An intelligent cerebrospinal fluid drainage control and recognition warning system mainly comprises a microcomputer system (1), a flow control device (2), an infrared drop number sensor (3), a color recognition sensor (4), a pressure sensor (5), a communication module (6), a human-computer interaction interface (7) and a radio frequency recognition device (13). The intelligent cerebrospinal fluid drainage control and recognition warning system can independently set the discharge speed, the drainage amount per unit time, the drainage time interval and the drainage pressure of cerebrospinal fluid according to individual differences of patients or clinical needs so as to achieve fixed-speed discharge, quantitative discharge, timed discharge and personalized-pressure discharge of the cerebrospinal fluid; meanwhile, in the drainage process, the color recognition sensor (4) can make timely prewarning when the cerebrospinal fluid has a hemoglobin reaction.

A color detector is prepared as fixing light source and sensor on shell, shining detection light of three basic color as red and green as well as blue on object to be detected by light source, using sensor to receive reflection lights generated separately by object to be detected as per three basic colors and generating electric signal corresponding to color of object to be detected according to light parameter of said reflection light. The color identification device and relevant color identifying method are also disclosed.

The invention provides a safety helmet positioning and color recognition method and system based on deep learning, and the method comprises the steps: collecting image information, obtaining a movingobject image in the image information, and enabling the moving object image to serve as a region of interest; inputting the region of interest into a pre-established convolutional neural network model, and performing multi-target parallel detection on the image information according to a preset target classification; obtaining a parallel detection result, wherein the detection result at least comprises human head position information and safety helmet position information; judging whether a person wearing the safety helmet in the collected image information is judged according to the paralleldetection result, and when it is judged that the person does not wear the safety helmet, giving out alarm information; according to the invention, a designated area can be continuously and effectivelymonitored, safety accidents caused by the fact that personnel do not wear the safety helmet are prevented, manual intelligent analysis and processing are replaced, alarm signals are sent out in realtime, and the problems of high universality, low stability and low accuracy of security video monitoring are solved.

Barcode scanning and digitizing technology incorporated in the tip of a white cane for the blind, which houses barcode reader, sonar, color sensory and audio production mechanisms. Apparatus detects and announces via audio or vibratory output, obstacles, drop-offs, colors or suitable informational barcode sites placed with a plurality of locations or environments for assisting blind or visually impaired users to navigate. In one embodiment, the apparatus combines the white cane with a barcode scanner and decoder with laser depth finding capacity in the cane tip, an sonar technology within the cane housing; and a separate hand-held unit having color and standard UPC barcode scanners, both the cane and the hand-held unit being connected to the audio output device by a hard-wire or wireless connection. The audio production unit can be pocket or purse carried and emits verbal information via respective barcodes suitable for either component or announces color when the respective scanner is used; hand-held color/barcode scanner or cane can be used separately or simultaneously.