4991results about How to "Avoid misjudgment" patented technology

The invention discloses a method for quickly and accurately detecting and tracking a human face based on a video sequence, which relates to the technical field of mode identification. The method comprises the following steps of: 1, extracting a video frame image from a video stream; 2, preprocessing the video frame image, namely compensating light rays, extracting skin color areas, performing morphological processing and combining the areas; 3, detecting the human face, namely representing the human face by using Harr-like characteristics and detecting the human face by using a cascaded Adaboost algorithm with an assistant decision function; 4, establishing the characteristics of the human face, namely detecting the area characteristics of the detected human face and the shape characteristics of the edge profile of the human face; 5, tracking the human face, particularly tracking the human face by using a human face area characteristic model when an intersection does not occur in a human face area, and further matching when the intersection occurs according to the shape characteristics of the edge profile of the human face; and 6, extracting the sequence of a human face image. By the technical method, the human face can be detected and tracked quickly and accurately on the basis of the video sequence.

The invention relates to an automatic generating method for a multi-lane vehicle track space-time diagram. The method comprises the steps that firstly, a camera is utilized for obtaining internal parameters and external parameters of the camera through off-line calibration, an area of interest is set according to the actual monitoring requirement, and three virtual detecting belts are set at the upstream initial position of the traffic flow; secondly, the vehicle feature points are extracted based on the three virtual detecting belts, the feature point tracking and grouping correction are carried out according to vehicle grouping, the vehicle tracks are extracted in a high-precision mode, a longitudinal space-time track diagram of passing vehicles is automatically generated for each lane, and a transverse space-time track diagram comprising all lanes is generated; finally, whether it is in the lane line correction stage or not is automatically judged, wherein if yes, the lane line position is automatically corrected based on the track clustering method. Compared with the prior art, the method improves the robustness of the target luminance change, improves the precision of vehicle detecting and track tracing, is capable of well automatically correcting the lane line on line and avoids misjudgment on the lane number to which the vehicle track point belongs.

An abnormality determining apparatus is capable of avoiding mistaken determinations due to the normal value of information obtained by an information obtaining unit differing according to the content of specific information such as the operating mode setting, and deterioration of the determination precision due to a change in the user of a detection subject. The abnormality determining apparatus comprises an information storage unit for storing normal index information serving as an index of a normal state of the detection subject, an information obtaining unit for obtaining a plurality of types of information, and an abnormality determining unit for determining the presence of an abnormality in the detection subject on the basis of the normal index information stored in the information storage unit, and the information obtained by the information obtaining unit. The information storage unit stores a plurality of normal index information having different values. The abnormality determining unit selects, at a predetermined timing, normal index information to be used to determine the presence of an abnormality in the detection subject from the plurality of normal index information.

In the voltage detecting device according to the present invention, voltage detecting lines respectively extend from a plurality of voltage input terminals, a plurality of capacitative elements are respectively interposed on coupling lines each coupling two adjacent voltage detecting lines to each other, and the voltage detecting lines are connected to a voltage detecting unit. At least all the voltage detecting lines respectively disposed on the positive electrode side of the cells are each connected to ground via one or more disconnection detection resistors. The voltage detecting unit detects a disconnection on a wire between each of a plurality of voltage detecting points of the assembled battery and a plurality of voltage input terminals based on voltage inputted from each voltage detecting line.

The invention discloses a touch screen and a display device. A plurality of self-capacitance electrodes are arranged on the same layer and independent to each other by means of the self-capacitance principle. Two or more self-capacitance electrodes arranged alternatively are connected with a frame of the touch screen through a lead and then connected with a touch detection chip through a corresponding periphery wire to perform touch position detection. When the human body touches the screen, the touch detection chip determines the touch position by judging changes of capacitance of the adjacent self-capacitance electrodes connected with different leads, and accuracy of touch sensing is achieved. By means of the mode that a plurality of self-capacitance electrodes which are not adjacent to each other are connected with one lead correspondingly, total quantity of the leads in the touch screen can be reduced effectively, the area of the touch blind region is decreased, and touch performance is ensured. In addition, due to decrease of the quantity of the leads, the quantity of the periphery wires corresponding to the leads is decreased, and design of the narrow frame of the touch screen is facilitated.

The invention relates to a high-precision maximum power point tracing method, which is an MPPT algorithm combining variable step-size optimization and a disturbance observation method based on power prediction, i.e. a variable step-size disturbance observation method based on the power prediction. The high-precision maximum power point tracing method can overcome the defects of the conventional disturbance observation method, the variable step-size disturbance observation method, and the like, solve the problems of failure judgment, local maximum power, and the like and quickly and precisely trace a maximum power point.

The invention relates to the technical field of touching, in particular to a capacitive touching structure, an embedded touch screen, a display device and a scanning method of the display device. The number of wires in the self-capacitance touching structure is decreased, and the probability of occurrence of the problems that the narrow frame design is not facilitated and a touch blind area is large is decreased to a certain degree. The capacitive touching structure comprises a plurality of self-capacitance electrodes which are arranged on the same layer, area electrodes, first wires, second wires and touch detection chips, wherein the self-capacitance electrodes are located in at least two areas contained by the surface of a film where the self-capacitance electrodes are located respectively; the area electrodes are located in the areas respectively, and the area electrodes and the self-capacitance electrodes are located on the same layer; the first wires are connected with the self-capacitance electrodes, and each first wire is connected with at least two self-capacitance electrodes which are located in different areas respectively; the second wires are connected with the area electrodes, and the area electrodes located in the areas are electrically connected with the different second wires; the touch detection chips are connected with the first wires and the second wires.

The invention provides an inter-class variance MODIS forest fire point detection method, which comprises the following steps: pretreating original data required from an MODIS satellite receiving station, acquiring brightness temperature or reflectivity of each channel, and excluding illegal data; identifying image elements of cloud and water; identifying a smog mask; extracting potential fire points from excluded image elements of the cloud, the water and the illegal data; calculating inter-class variance yield of each potential fire point and effective background image elements in a background window; verifying fire points according to the threshold value of the inter-class variance and the smog mask; and outputting an MODIS image containing the fire points. By adopting lower threshold value, the potential fire points comprise true fire points as well as comprise certain false fire points of which the underlying surfaces have higher temperature so as to avoid omission; the threshold value of the inter-class variance is adopted to judge and remove the false fire points so as to prevent from being misjudged; moreover, information of the underlying surfaces around the fire points is considered fully, so that the method can adapt to different areas and seasons.

The invention relates to a fault detection device and method for detecting an initial fault of a motor. The fault detection device comprises a voltage collection apparatus, a current collection apparatus, a signal collection system and a fault analyzing and processing system, wherein the voltage collection apparatus is used for collecting voltage signals of the motor; and the current collection apparatus is used for collecting current signals of the motor. The fault detection device is characterized in that the voltage collection apparatus and the current collection apparatus are connected with the signal collection system; the signal collection system processes collected voltage signals and current signals and then transmits to the fault analyzing and processing system; and the fault analyzing and processing system calculates, analyzes and processes data transmitted by the signal collection system so as to obtain the state information of the asynchronous motor. The fault detection method is used for measuring the voltage and the current of the motor and obtaining the fault indexes of turn-to-turn short-circuit faults, rotor broken faults and bearing faults according to a measuring result. The invention provides a foundation for analyzing the initial fault of the asynchronous motor and offers a proposal for the maintenance of the motor.

The invention relates to a checking method and a device of automobile deviation, wherein the method is mainly an image identification and processing procedure, wherein the image identification and processing procedure comprises the following steps: an image acquisition step which comprises utilizing an image pick-up device to extract image picture data, and a lane line identification step which comprises analyzing image picture data, distinguishing a lane line position, utilizing a quadratic curve to fit an equation, connecting a segmental lane line, and making a lane line predicating model, wherein the lane line predicating module which is got through utilizing the above steps is used to check automobile deviation, and is supplied for warning. The checking method of automobile deviation mainly comprises an image pick-up device which is used to extract road image information, a calculating platform which is used to analyze the road image information extracted by the image pick-up unit, and judges the corresponding relationship of a current automobile and a road, and a signal outlet unit which utilizes light, visual variation or sound to reach the behavior of warning. The invention can give off warning to prompt a driver to pay attention and reach the behavior of warning when an automobile does not normally run.

The invention discloses an earphone and a method for detecting an earphone wearing state. The earphone comprises a controller, a reference sensor, a state judging sensor and a memorizer memorized with production line testing capacitance values of the reference sensor and the state judging sensor, wherein the reference sensor and the state judging sensor are connected with the controller. The reference sensor and the state judging sensor are capacitance-type sensors, and the reference sensor is arranged at the position in the earphone isolated from the outside environment. When the earphone is started up, the controller confirms influencing parameters of the environment to capacitance values of the capacitance-type sensors according to a detected capacitance value of the reference sensor and a production line testing capacitance value of the reference sensor and judges the earphone wearing state according to the influencing parameters of the environment to capacitance values of the capacitance-type sensors, a detected capacitance value of the state judging sensor and a detected production line testing capacitance value of the state judging sensor. By means of the scheme, the erroneous judgment problem of the earphone wearing state of the capacitance-type sensors can be effectively solved.

The invention discloses an automatic test system for a digital integrated circuit. The automatic test system is composed of a tested chip, a test interface board, an integration module, a test module, a control module, a display module and an upper computer. The control module is connected with the upper computer. The test module is connected with the control module. A base pin of the tested chip is connected with the test interface board which is connected with the test module. The integration module is connected with the test module and the upper computer. The display module is connected with the control module and displays a waveform after final comparison by the aid of upper computer software, so that the automatic test for functions and performance of the chip is completed. The automatic test system is low in cost, easy to implement under laboratory conditions, easy and convenient to operate, high in development rate and capable of meeting the test requirements of small-batch products. According to the system, through an automatic test, the problem that operation is complex due to the fact that the number of test items is large in a manual test is solved, the test efficiency is enhanced, a misjudgment caused by artificial factors in the manual test is avoided, and therefore test quality is improved.

The invention relates to the testing field, which discloses a method and a device of surface detection of defect, the method includes the following steps: acquiring an original surface image; calculating gradient values of every pixel point of the original image along multiple directions respectively, taking a maximum value therein as a new gray value of the pixel point, obtaining a gradient image; if the gray value of the gray value pixel point is greater than the threshold value, then the gray value is evaluated as: the first gray value, otherwise is evaluated as: the second gray value, obtaining a binary image; refining the binary image, obtaining a single wired binary image, wherein, the single wired defective edge is included; converting the single wired defective edge into a close looped defective edge; in the original image, comparing the gray values between the pixel point in the close looped defective edge and the pixel point nearby the outside, if less than, the defect of the close loop is judged as surface defect. Using the technical scheme can achieve the automatic detection of defects in the tested object, which improves the testing efficiency.

The invention discloses a pedestrian detection method. Multiple times of convolution and pooling are performed on an input image through the pedestrian detection method based on a convolutional neuralnetwork; the features of the original image are extracted so as to obtain the corresponding feature graph of the original image; the corresponding feature graph after zooming of the original image isapproximately calculated through the image feature pyramid rules; a candidate window is generated through a region proposal network RPN; a candidate proposal window is further selected and summarizedaccording to the pedestrian size distribution in the candidate window; the corresponding weight of different scales of pedestrian targets on different scales of images is trained by using the training data having the tag; and the classifier network is trained. The summarized candidate window is solved, and the confidence obtained through the classifier and the set threshold are compared and finalpedestrian detection judgment is performed. Heavy calculation amount of obtaining the feature graph through image zooming calculation can be avoided by application of the image feature pyramid, and detection is performed on different feature graphs by using the weighing mode of different weights so that misjudgment and leak detection caused by single feature graph detection can be effectively avoided.

The invention discloses a double-axis geomagnetic stall detecting method and a double-axis geomagnetic stall detecting device. The method comprises the following steps: reading the current geomagnetic flux density data in two directions in real time, wherein one direction refers to a direction that a vehicle enters a garage, and the other direction is perpendicular to the ground downwards; acquiring the fluctuating value of a data sequence corresponding to each direction based on the geomagnetic flux density data which are read in the two directions in real time, wherein the data sequence consists of multiple geomagnetic flux density data; judging whether a vehicle is parked in a stall according to the fluctuating value of the data sequence corresponding to each direction and preset judgment threshold values. The method disclosed by the invention has the advantages of easiness in technical realization, low cost and high detection accuracy.

The embodiment of the invention provides an anomaly detection method and device. The method comprises following steps of obtaining the history data sequence and the recent trend data sequence of performance parameters of a to-be-detected device; according to the history data sequence, calculating to obtain a first dynamic threshold range of an observing value at a current detection point; according to the recent trend data sequence, calculating to obtain a second dynamic threshold range of the observing value at the current detection point; then determining the dynamic threshold range of the current detection point according to the first dynamic threshold range, the second dynamic threshold range and a dynamic threshold selection strategy; and finally, judging whether the observing value of the current detection point belongs to the dynamic threshold range of the current detection point. According to the method, the dynamic threshold range of the current detection point can be determined through combination of the history data sequence and the recent trend data sequence of the performance parameters; different dynamic threshold selection strategies can be set according to different performance parameters; and the performance parameter anomalies of the to-be-detected device are prevented from misjudgment, underreporting and false alarm.

The invention discloses a method for automatically positioning webpage Trojan mount point in a Trojan linked webpage and belongs to the field of computer security. The method comprises the following steps of: a) determining the Trojan linking webpage; b) acquiring a style sheet in the Trojan linked webpage, and performing script analysis on the scripts therein according to a step c); c) acquiringthe scripts in the Trojan linked webpage, outputting the positions of malicious scripts in a father webpage, wherein the malicious characteristics comprise: calling the objects of known bugs, containing malicious codes, opening malicious webpages, redirecting to the malicious webpages, and adding malicious webpages; and d) acquiring an embedded webpage in the Trojan linked webpage, comparing whether the website domain name is the same as the Trojan linked webpage for the embedded webpage determined to be subjected to Trojan linkage, if so, performing recursive analysis, otherwise, outputting the position of an embedded label in the father webpage. The method can be applied to the computer security, and comprises rapidly positioning the mount position of the webpage Trojan in the webpage to assist the website management personnel to rapidly remove the malicious contents contained in the webpage.

The invention relates to a printing deviation measuring method, a printing method and a printing device for a solar cell plate. The deviation measuring method comprises the following steps of: A. measuring the actual position P1' of the solar cell plate at a waiting station after plate feeding, and calculating the position deviation delta P1 of the solar cell plate according to a preset position P1 of the solar cell plate; B. measuring the actual position M' of one station of a rotating work table at the waiting station and the actual position N' of the rotating work table after the rotating work table rotates to a printing station, and calculating the position deviation delta M and delta N of the station respectively on the waiting station and the printing station by combining the actual positions M' and N' with the preset position M of the waiting station and the preset position N of the printing station; and C. calculating the integrated position deviation delta P of the solar cell plate according to the position deviations delta P1, delta M and delta N in the step A and the step B. The invention regulates the position of a printing screen of the printing device according to the integrated position deviation delta P so that the positions of the printing screen and the solar cell plate are sufficiently coincided, thereby outstandingly enhancing the accuracy of final printing.

There is provided an electric charging system in which an electric charger and an electric vehicle are connected by a charging cable. The electric charger calculates a voltage drop amount in the charging cable on the basis of a supplied current at the electric charger side and an electric resistance of the charging cable. The electric charger also compares a determination voltage with a supplied voltage at the electric charger side and determines that a battery has been charged to a fully charged state when the supplied voltage reaches the determination voltage. The determination voltage used for such full charge determination is updated by adding the voltage drop amount to a basic determination voltage that is set in advance.