30 results about "Sight-reading" patented technology

The invention discloses a sight tracking and fatigue early warning method, and belongs to the technical field of intelligent traffic. The method comprises the step of obtaining the information of the driver face through a mini-type camera, the step of controlling starting and stopping of a near axial infrared controllable light source and a far axis infrared controllable light source, the step of starting the near axial infrared controllable light source at the odd number frame, the step of starting the far axis infrared controllable light source at the even number frame, and the step of determining the position of the human eye pupils in a video sequence after the difference calculation according to the human eye pupil reflection characteristics. After the pupil positioning through the image difference frequency is carried out based on an infrared effect under infrared light, the sight projection position is reversely calculated according to the pupil center position and the feature recognition points of a vehicle-mounted displayer, and fine adjustment or fine calibration can be carried out according to the user individual difference in the calculation process. Compared with other control methods, the time for obtaining the eye characteristics of a driver can be effectively shortened, the interference caused by the ambient light change is avoided, and the sight information of the driver can be rapidly and accurately obtained.

The invention provides an operation pointer indication control device based on a human eye image and sight tracking. The device can be worn on the head of a human body, and human-computer interaction can be achieved by means of operation control over an operation pointer through actions of eyes. In the interaction control process of the device, interference caused by a dark visible light environment and other situations can be avoided, a displacement error generated due to jittering can be relieved and even shielded, and the human-computer interaction effect that the indication position of the operation pointer and a real scene observed by human eye sight overlap is achieved. Thus, the human-computer interaction ability of a head-worn computer terminal is enhanced, and abundant operability and powerful expandability can be achieved. Consequently, the problem that in the prior art, popularization and application of the head-worn computer terminal in the technical field of industry and commerce are limited because the human-computer interaction ability of the head-worn computer terminal is limited is effectively solved, and the operation pointer indication control device has broad application prospect in the technical field of wearable computer terminals.

The invention discloses a sight tracking and human eye area-of-interest positioning system. The system comprises image acquisition equipment, a hardware platform and display and output equipment, the image acquisition equipment comprises an infrared human eye camera and a foreground camera, the output end of the infrared human eye camera and the output end of the foreground camera are connected with the input end of the hardware platform, and the output end of the hardware platform is connected with the input end of the display and output equipment; the hardware platform comprises a storage unit and is based on an FPGA and a dicaryon ARM9 processor; the infrared human eye camera is used for shooting a human eye pupil image and transmitting the image to the hardware platform in real time; the foreground camera is used for shooting a human eye sight area image and transmitting the human eye sight area image to the hardware platform in real time. By means of the mapping relation between the pupils and a mark point of the sight tracking and human eye area-of-interest positioning system, a fixation point / a point-of-interest of the human eyes in the sight area image can be determined, and the sight tracking function is achieved.

The invention discloses a tracked vehicle gun aiming method based on line-of-sight tracking. The tracked vehicle gun aiming method based on line-of-sight tracking aims to overcome the problems of lowapplicability, low precision and unsatisfactory real-time performance in the prior art, and comprises the following steps of: 1) acquiring a human eye image, wherein after a line-of-sight tracker is correctly worn, the position of a human eye CCD camera relative to the center of two eyes is adjusted, and the human eye CCD camera faces right towards the front direction so as to ensure that the line-of-sight tracker can accurately complete acquisition of the eye image of a shooter; 2) pupil detection, wherein (1) eye image preprocessing, (2) pupil center positioning, (3) pupil tracking, (4) Pulchin facula center positioning and (5) P-CR vector obtaining are carried out; 3) fixed-point calibration; 4) line-of-sight tracking, wherein after the mapping relationship between a P-CR vector and thecoordinates of a point of sight of a scene image is obtained, eye movement parameters of a new human eye image are further obtained, and then the position of the point of sight in the scene image isestimated by means of a determined mapping relationship to complete final line-of-sight tracking; and 5) executing control instructions.

The invention discloses a sight line tracking method combining bidirectional LSTM and Itacker. The method comprises the following steps of 1) data preprocessing, 1.1) enabling a face reference point to be at an image center at a fixed distance from a camera; 1.2) converting the human face into an image plane in a specific camera space through the transformation matrix; 2) performing sight line estimation by using a bidirectional LSTM network structure and combining time sequence information; 2.1) respectively inputting the face, the left eye and the right eye into one branch of the network, and finally extracting a combined feature from each branch and mapping the combined feature to a screen to obtain a final three-dimensional sight line direction; 2.2) filtering out required discarding information by each LSTM cell under the forgetting door, integrating effective information at the input door, acquiring a required hidden layer at the output door, and finally mapping the forward unitand the backward unit of the last frame through the full connection layer to obtain a sight vector to complete sight tracking. According to the method, the estimation precision under 3D sight line tracking is improved, and the influence of other interference factors is reduced.

The invention discloses a method, an apparatus, a device and a computer-readable storage medium for realizing eyeball three-dimensional line-of-sight tracking, which comprises the following steps: inputting a face image to be detected into a preset head posture detection network to obtain a head posture in the face image; Inputting the face image into a preset eye movement detection network to obtain the eye movement of the face image; The head posture and the eye movement are input to a pre-constructed three-dimensional line-of-sight vector detection network to obtain a three-dimensional line-of-sight direction vector of the eye in the face image. The method, the device, the device and the computer-readable storage medium provided by the invention can extract the three-dimensional line-of-sight direction vector of the eyeball of the photographed person from the two-dimensional face image, and have a wide range of application scenes.

The present invention provides a line-of-sight tracing-based mouse control device. The device comprises a region positioning unit for positioning a field of vision and a center point of the vision, a line-of-sight tracing unit for dynamically tracing motion of a line of sight relative to a reference position, a converting unit for converting the motion of the line of sight relative to the reference position into mouse motion in the field of vision, and a control unit for controlling a mouse to respond to an operation of a position where the mouse is. According to the device, the line of sight of a user can be traced by using an image pickup device like a low-cost common camera, a variable of the line of sight of the user relative to the reference position is obtained with reference to eye motion of the user according to a positioning identification result, a relative position of the mouse in the field of vision is dynamically adjusted, and a traditional mouse operation method is changed. The device has a simple structure, the operation method can be used by multiple crowds of people, a convenient human-computer interaction manner is provided for disabled users, and better user experience is achieved.

The invention discloses a resident identification card loss report, lost property finding and loss report canceling method. The method comprises the following steps of receiving a loss report application form filled by a declarant, and according to input loss report person information, searching loss report person accreditation information in a database; if the loss report person accreditation information is found, displaying the loss report person accreditation information, and determining whether a sight reading photo in the accreditation information accords with a scene declarant and whether a certificate number and a name in the accreditation information accord with a certificate number and a name which are about to be reported; verifying fingerprint information: if a resident identification card which is about to be reported contains the fingerprint information, according to a finger position indicated in the accreditation information, collecting a fingerprint corresponding to any one finger position of a proposer in the field and verifying whether the fingerprints are consistent; shooting a photo of the scene and taking the photo as loss report declaration service processing trace leaving information; registering loss report information; and according to the inquired resident identification card effective accreditation information, confirming a certificate which is about to be reported by the declarant and marking the confirmed certificate as a loss report state.

The invention discloses an automatic real-time tracking method for a construction progress of a house building. The method comprises the steps that tracking points are arranged on a tower crane; height readings of different angle tracking points and a target building (a target) are obtained by rotating the tower crane, stored, screened, averaged and sent to scale units; data of the scale units is calculated; the height (target height) from the target to the tower crane is stored; angle scale values are read; target height values are screened and averaged when the stored data size reaches a preset value or the setting time is elapsed from storing the first data; the average target height value, the angle scale values, horizontal positions of the tracking points, and the like are transmitted to a server; the server screens and averages the all-day target height of each scale unit; and the average all-day target height, the angle scale values and data quality information are stored in a database. The screening is reliability screening; a corresponding system mainly comprises a range sensor, an angle measurement element, a processor, an AD (Analog to Digital) converter, a wireless communication module and the server; the range sensor is connected with the processor by the AD converter; and the angle measurement element outputs a signal to the processor.

A simultaneous bi-lateral blood pressure system with position indicator has a dual input blood pressure monitor that allows a left and right blood pressure cuff to be plugged and to obtain left and right readings simultaneously. A position indicator attaches to a comfortable adjustable collar that attaches to a patient's neck and is retractably positioned to indicate the position of the reading to be taken. The blood pressure monitor displays systolic and diastolic readings as well as pulse. If there is a significant difference between the left and right readings, then further tests are ordered. The position indicator is marked with measurement lines to allow the user to record the position where the reading is being taken. This establishes a repeatable baseline where further readings are taken from the same position.

The present invention relates to an HRV ((Heart Rate Variability) feature range estimation method for pressure description. The method comprises the following steps of: the step 1, employing a game named rhythm sight reading trainer to induce a subject to generate pressure, collecting subject's electrocardiograph signals, and estimating a subject's pressure state tag at this time; the step 2, extracting HRV time domain and frequency domain features from the collected electrocardiograph signals, and constructing a feature set; the step 3, constructing trees by employing the feature set obtainedin the step 2 according to an improved C4.5 decision tree algorithm, and selecting appropriate tree models according to a parameter control strategy; and the step 4, combining the selected trees intoa new tree, and extracting one value range of each HRV feature from the new tree. Individual differences is inclusive in the HRV feature value ranges extracted from the decision tree, so that the HRVfeature range estimation method for pressure description has universal significance; and moreover, the HRV feature range estimation method for pressure description can analyze whether a person is ina high-pressure state or not according to any one electrocardiographic wave of the person so as to give people a high-pressure early warning.

A system of associating sheet music notation with keyboard keys of a keyboard instrument and sight reading comprises a rectilinear colored strip adapted to be disposed upon the keyboard instrument. The colored strip includes first and second sets of markings corresponding to first and second octaves of the keyboard. Each of the sets includes wide markings corresponding to white keys of the keyboard and narrow markings corresponding to black keys thereof. Each of the wide markings of the first set is color-coded with a first color and each of the wide markings of the second set is color-coded with a second color different from the second color. The system further comprises a musical notation including musical notes color-coded with the same colors the first and second sets of markings on the colored rectilinear strip.

A color measurement instrument that is capable of both spot reading and strip reading. The instrument includes a handheld unit and a docking unit. When removed from the docking unit, the handheld unit is used for spot reading. When docked in the docking unit, the handheld unit and the docking unit are used together for strip reading. The handheld unit includes a self-storing target that is deployed for spot reading and stored for strip reading. The handheld unit also includes a self-storing calibration plaque that is deployed for calibration and stored otherwise. When docked, the handheld unit teeters on the docking unit between a normally closed position and a manually selectable open position to accommodate a variety of sample thicknesses.

The invention provides a sight training chart which comprises first sight mark sets and second sight mark sets. The first sight mark sets are annularly distributed and are provided with a first center, and the second sight mark sets are annularly distributed and are provided with a second center, wherein the first center coincides with the second center. The radian of the first sight mark sets is larger than or equal to 90 degrees but smaller than or equal to 270 degrees, and the radian of the second sight mark sets is larger than or equal to 90 degrees but smaller than or equal to 270 degrees. The sight training chart is provided with a center, in the process of sight training and the process of sight detecting, focusing of the optic nerve can be automatically excited, the sight training effect on people who suffer from the amblyopia, the polarization sight and the astigmatism is better, and the measured sight is more accurate.

A method for emulating prerecorded images may comprise acquiring at least one organ timing signal reading representing an activity state of an organ with at least one organ timing signal detector, acquiring a plurality of images with a medical imaging system, associating each of the plurality of images with an organ timing signal reading, removing any of the organ timing signal readings and associated images that are not representative of a normal organ configuration, and outputting a sequence of the representative images for a display.

The invention provides an apparatus and method for notating music for a harmonica. The apparatus incorporates a vertical staff in which vertical lines or tracks represent individual notes, the length of which represents duration of the note, and the horizontal location represents the physical location of the corresponding hole in a harmonica. The invention provides a rapid means of learning to play a harmonica and, for experienced players, provides a means for sight reading a new piece of music. The invention further provides ways of representing the dynamics of both pitch and loudness and a convenient way to manually transcribe musical selection for archival purposes.

The invention provides an apparatus and method for notating music for a harmonica. The apparatus incorporates a vertical staff in which vertical lines or tracks represent individual notes, the length of which represents duration of the note, and the horizontal location represents the physical location of the corresponding hole in a harmonica. The invention provides a rapid means of learning to play a harmonica and, for experienced players, provides a means for sight reading a new piece of music. The invention further provides ways of representing the dynamics of both pitch and loudness and a convenient way to manually transcribe musical selection for archival purposes.

The invention relates to a remote-control toy capable of realizing 3D visual presentation in a non-line-of-sight range. The remote-control toy is characterized in that the toy comprises a double-camera module, a power supply module, a moving control center and a CPU (Central Processing Unit); a mobile phone comprises a communication module and a mobile phone APP (Application); the power supply module is connected with the moving control center, the double-camera module and the CPU; the power supply is provided for the moving control center, the double-camera module and the CPU through the power supply module; the CPU is connected with the moving control center and the double-camera module; the CPU is connected with the mobile phone APP through the communication module for realizing data communication; a 3D image capture algorithm is installed in the double-camera module; and a 3D presentation algorithm is installed in the mobile phone APP. The remote-control toy has the beneficial effects and advantages that the visual effect presentation of the intelligent toy on ambient environment is changed; the real and vivid effects are achieved; the visual impact feeling is strong; and higher playability is realized, and the like.

The invention discloses a method for fast reading a cross electrical parameter graph. The method comprises the following steps of reading a bitmap graph to be analyzed in an operating system, inputting the X-axis coordinate range X of the graph, the Y-axis coordinate range Y of the graph and the curve number Z in the graph, transforming the graph in a matrix mode, removing transverse and vertical grid lines, arranging the graph, determining the function relationship between x0 of the X axis and y0 of the Y axis within the certain X-axis coordinate range and the Y-axis coordinate range according to a matrix value of the obtained arrangement graph, wherein the function relationship meets a formula that y0 is equal to f(x0), and using the function relationship in calculation in actual work. The method can carry out quantitative analysis on the electrical parameter graph with a high speed and an accurate rate, the determined function relationship brings convenience to use and calculation, and effective data can be provided for normal proceeding of follow-up design development work.

The invention discloses a novel watt-hour meter which is convenient for reading at night, and relates to the technical field of power system metering equipment. Including the watt-hour meter body, a ring-shaped LED light is provided around the reading of the watt-hour meter on the lens of the watt-hour meter, and a mirror cover hinged with one side of the watt-hour meter is also provided on the surface where the lens is located. The mirror cover is opened and closed by means of a motor at one end of the rotating shaft, and the motor and the LED lamp are controlled by a control unit located at one side of the watt-hour meter. The mirror cover on the watt-hour meter can ensure that the lens surface is clean and not damaged. The mirror cover is automatically opened and closed to make the operation more convenient. The LED light on the lens can illuminate the reading at night, which is convenient for the staff to read.

The invention discloses a method and system for quickly reading empty files by an upper file system. The method includes attaching an empty file processing system to a Fuse kernel component; the empty file processing system performs emptying on files in the upper file system Discriminate, find and mark the empty page of the file, and add an empty mark to the empty page; in the process of reading the file, for the empty page with the empty mark, the empty file processing system stops the upper file system from reading it. By pre-marking empty pages, the present invention solves the problem of serious performance loss when fuse reads empty files, which leads to excessive pressure in system memory copying and process switching, and enhances its support for empty files. In the case of file holes, It can return quickly without complicated scheduling to the upper file system, which improves the performance of reading certain files with a large number of holes.

The invention discloses a toy capable of being presented in an AR (Augmented Reality) way within a non-line-of-sight range. The toy capable of being presented in the AR way within the non-line-of-sight range comprises a toy and a mobile phone, and is characterized in that the toy comprises a camera module, a power supply module, a motion control center and a CPU (Central Processing Unit); the mobile phone comprises a communication module and a mobile phone APP; the camera module, the CPU and the mobile phone APP are connected with an intelligent cloud background through the communication module respectively; and the intelligent cloud background is used for providing auxiliary AR information. According to the toy capable of being presented in the AR way within the non-line-of-sight range provided by the invention, visual capture of the surrounding environment is performed through the camera module and an algorithm, captured content is returned to the mobile phone APP, the environment and objects are identified through the intelligent cloud background, and relevant information is extracted from the identified objects and returned to the mobile phone APP, so that extra auxiliary AR information is presented to an operator.

The invention relates to a method for measuring longitudinal distances of sight of human eyes. The method includes particular steps of 1, creating an eccentric photographic measuring device comprising a camera, an infrared light source, an infrared filter lens, a telescope, a human face support, an infrared cut-off filter and the like; 2, detecting pupil boundaries, acquiring pupil regions by means of processing by the aid of run algorithms and acquiring boundaries by means of equation fitting; 3, computing the internal brightness distribution of pupils, and computing ratios of certain longitudinal lengths of the pupil regions to the lengths of integral longitudinal axes; 4, measuring longitudinal distances, acquiring the longitudinal distances of the sight by the aid of pre-measurement calibration parameters and current brightness distribution conditions of the pupils by means of computing. Average values of gray values of the integral pupil regions are used as threshold values, and the certain longitudinal lengths of the pupil regions are larger than the threshold values. The method has the advantages that information of the longitudinal distances can be obtained during sight tracking, accordingly, the sight can be truly three-dimensionally tracked, and the method further can be used for improving the precision of the traditional two-dimensional sight tracking systems; the method is low in computational complexity, and quick measuring and real-time tracking effects can be realized.

The invention discloses a free-space head-wearing eye-tracking system. The free-space head-wearing eye-tracking system comprises a head-wearing video collection device, a unit for evaluating the binocular optic axis through stereoscopic vision and a binocular vision and fixation point evaluation unit; the head-wearing video collection device collects four ways of near-infrared eye video and one way of scene video simultaneously, and the four ways of the near-infrared eye video comprise two ways of the near-infrared eye video of the left eye of a wearer who wears the head-wearing video collection device and two ways of the near-infrared eye video of the right eye of the wearer who wears the head-wearing video collection device; coordinates of pupils of both eyes and cornea center are evaluated directly through a stereoscopic vision method, and a binocular optic axis straight line equation is calculated; a binocular visual axis straight line equation is evaluated according to an eyeball Kappa angle and the binocular optic axis straight line equation, a fixation point coordinate is calculated, the position of a fixation point in the scene video is mapped and marked, and the Kappa angle is a fixed included angle between the optic axis and the visual axis of each eyeball.

The invention relates to a sighting method of a sighting telescope at different initial velocities. The sighting telescope is placed on a crossbow or a gun barrel, an object which is a certain distance away from the sighting telescope is selected to serve as a sighting object, and an image of the object is arranged on a reticle of the sighting telescope through the sighting telescope and is located at the position, at a sighting position matched with the object in distance, on the reticle; and the certain initial velocities are set, a multiple adjusting twist ring is adjusted to adjust the image of the object on the reticle until the image of the object on the reticle can right guarantee the shooting accuracy, and then sighting is completed. The sighting method has the beneficial effects that the manners that the multiple adjusting twist ring is adopted and the sighting point of the reticle is used in a matched manner to achieve sighting are adopted to adapt to the different initial velocities, the relatively-accurate sighting effect is achieved through the multiple adjusting twist ring, the method is unique, and operation is easy.

The purpose of my invention / method is to create good keyboard sight reading musicians. By marking skips between notes according to the method set forth in my detailed description and then playing them on the keyboard, the musician is able to develop good sight reading skills. The difference between my method and others is that my method uses letter names of notes only to find the beginning location of a piece of music and this is done through the use of a note / keyboard chart. All other reading is done by use of spacing and direction through recognition of skips on the staff. It is essential to the success of my method that letter names NOT be used because they interfere with the spatial and directional understanding of notes needed to sight read well. My method is useful at all levels because it is structured, concrete, and cumulative.

The purpose of my invention / method is to create good keyboard sight reading musicians. By marking skips between notes according to the method set forth in my detailed description and then playing them on the keyboard, the musician is able to develop good sight reading skills. The difference between my method and others is that my method uses letter names of notes only to find the beginning location of a piece of music and this is done through the use of a note / keyboard chart. All other reading is done by use of spacing and direction through recognition of skips on the staff. It is essential to the success of my method that letter names NOT be used because they interfere with the spatial and directional understanding of notes needed to sight read well. My method is useful at all levels because it is structured, concrete, and cumulative.