32results about How to "Simple detection algorithm" patented technology

The invention relates to the technical field of traffic detection and discloses a method for detecting a fire accident on an expressway or in a tunnel based on a video detection technology. The method comprises the following steps: extracting a picture from an obtained video according to a preset frame rate; utilizing the obtained picture to establish a tunnel background model; extracting a foreground target image from the picture with a background differentiating method; dividing the picture into a background part and a foreground part, and respectively updating the background part and the foreground part in different updating rates; analyzing the foreground target of the image in a detection period, and judging whether a suspected static target exists or not according to time sequence information; and if the suspected static target exists, determining a suspected flame region in combination with the moving and static features of flames, and finally analyzing the suspected flame region of a sequentially extracted image according to flame judging rules and judging whether the fire accident exists or not. The method has the advantages of simple detection algorithm, small calculated amount, capability of shortening processing time, capability of improving detection efficiency, and capability of reducing the influence of the complicated scenic illumination condition of the tunnel on fire detection.

The invention provides a laser high-temperature liquid height measurement and control system. The system comprises a laser transmitter used for transmitting laser beams, a laser receiver used for receiving laser beams, a driving unit used for driving the laser transmitter and the laser receiver to rotate synchronously, a controller used for analyzing electric signals, calculating the liquid level height and change rate of high-temperature liquid according to a formula, and sending out warning information, and a liquid level control pump used for regulating the level of high-temperature liquid in a high-temperature container. Laser beams resistant to high temperature and interference are used as a measurement light source, the liquid level height and liquid level height change rate of high-temperature liquid can be measured in real time in a high-temperature environment, and the level of high-temperature liquid is regulated in real time. The invention further provides a laser high-temperature liquid height measurement and control method. The method comprises the steps of signal zero setting, liquid level measurement, liquid level regulation and the like and overcomes the defects of existing detection methods that adopted algorithms are complicated and detection precision is low.

The invention discloses a parallel single-phase H-bridge cascade type active electric power filter control device and a method thereof. A DC voltage equalization control unit detects the DC side voltage of the H-bridge power unit of a cascade type active electric power filter, outputs the phase correction of a reference voltage signal to an output compensation current control unit, and outputs an active current to a reference compensation current calculating unit; the reference compensation current calculating unit detects a bus current, performs sinusoidal signal integration and bandpass filtering processing on the bus current, and calculates a reference compensation current according to instantaneous power and the active current; and the output compensation current control unit, according to the phase corrections of the reference compensation current and the reference voltage signal, obtains the reference voltage signal of the H-bridge power unit and obtains the driving signal of the power unit. By using the device and method provided by the invention, system resonance can be effectively inhibited, reference compensation current calculating exerts no influence of time delay and attenuation on fundamental wave signals, harmonic wave components and DC biases can be well inhibited, besides, the calculating is simple, the precision is high, the implementation is easy, and the versatility is high.

The invention discloses a fault tolerant proportional coordinated control method for a multi-motor servo drive system under a coupling control structure. A fault detector of a motor servo control system is used for detecting the faults of motors and electric drive modules of the motors in real time, based on the coupling control structure of the multi-motor system, a logic switching module of a motor coordinated compensator mixed with fault detection information is designed, and the working mode of the coordinated compensator is improved. When the motor control system fails, the output path ofthe coordinated compensator is cut off, so that the multi-motor system is transformed from the coupling control structure to a master-slave control structure. In the master-slave control structure, amain motor is a fault motor, a slave motor is a normal motor, which ensures that the proportion relationship of the output of each motor in the multi-motor servo drive system remains unchanged so asto achieve a fault tolerance function; when the fault motor returns to normal, the output path of the coordinated compensator of the motor is connected by a fault logic decision-making module, the whole system is restored to the original coupling control structure, and the proportional relationship between the output of each motor remains unchanged.

The invention discloses a negative voltage detecting device and detecting method. A gating circuit, an RC (resistance-capacitance) circuit, a timer and a processor are arranged; to-be-detected negative voltage and the RC circuit are connected firstly through the gating circuit, a capacitor in the RC circuit is charged through the to-be-detected negative voltage, positive-polarity reference voltage is switched to and is connected with the RC circuit after charging of the capacitor ends, the capacitor is controlled to discharge, a timer is started for timing, and discharge time T2 of the capacitor is recorded; and a negative voltage value can be calculated according to a amplitude value of the reference voltage, charge time T1 of the capacitor by the reference voltage and the discharge time T2. A voltage value of the negative voltage is quantified to a time value and is reversely detruded by means of the corresponding quantified time value of the known reference voltage, the detecting algorithm is simple, the detection accuracy of the voltage value is high, a hardware circuit required to be established is simple, the cost is low, and power consumption is low.

The invention discloses a hard disk part detection device and a hard disk part detection method, which can realize detection of different types of defects of a hard disk part, improve the product yield level, and solve the problem that some defects can only be displayed in an image at a specific lighting angle. Therefore, an electric control rotary workpiece table, an electric control light sourcelifting table and a matched image analysis algorithm are specially designed, the detection automation level is improved, and missing detection is avoided; the workpiece table is controlled through software coordination to achieve rotation of a given angle value, and an angle image is collected; And registering of the images with different rotation angles is achieved by using the rotation angle value, a gravity center algorithm and an image correlation matching algorithm. Some defects can only be displayed in the images at a specific lighting angle, so that the registered images have difference in defect positions, and the gray value difference is extracted to realize defect detection.

The invention relates to a personnel access detection method, device and equipment based on a monitoring video. The method comprises the following steps: extracting video images frame by frame from areal-time monitoring video of a commodity; sequentially carrying out foreground detection on a preset detection area in each frame of video image, and calculating to obtain a foreground pixel proportion; if the foreground pixel proportion is greater than a preset first threshold, counting the number of frames of a high foreground image in a first preset number of frames of continuous images; if the frame number of the high-foreground image is greater than a preset second threshold, judging whether a foreground pixel proportion of at least a second preset number of frames of continuous images in the high-foreground image is continuously increased or not; and if so, determining that a person enters a preset detection area. According to the invention, the personnel entry condition in the specific commodity sales area is detected in a foreground detection mode, so that the attention degree of the commodities in the area in the market can be reflected, and the method is simple in detectionalgorithm, small in calculation amount, robust in technology and good in detection effect.

The invention discloses an applicator head. The applicator head is releasably connectable to an outer housing of an apparatus for treating human skin includes a body having a housing connector end having a releasable connecting feature configured to connect to the outer housing and a skin engaging end having an opening therethrough for delivering a skin treatment composition through an opening in the applicator head onto human skin. A pair of skin engagement members is arranged and configured to flatten a surface of the skin.

The invention belongs to the field of electric power system and relates to a polyphase circuit general harmonic detection method based on instantaneous symmetrical component transformation. The polyphase circuit general harmonic detection method basically includes the general harmonic voltage detection algorithm and the general harmonic current detection algorithm. The general harmonic voltage detection algorithm includes the voltage instantaneous symmetrical component transformation algorithm, the voltage sine algebraic transformation algorithm, the voltage average filtering algorithm, the voltage initial phase algorithm, the voltage reconstruction algorithm and the general harmonic voltage computational algorithm. The general harmonic current detection algorithm includes the current instantaneous symmetrical component transformation algorithm, the current cosine algebraic transformation algorithm, the current average filtering algorithm, the current initial phase algorithm, the voltage-current phase difference algorithm, the current reconstruction algorithm and the general harmonic current computational algorithm. The poly circuit general harmonic detection method is simple in phase locking, strong in real-time effect, high in accuracy, simple in algorithm, easy to implement, economic, wide in application range and the like.

The invention discloses a ground plane identification method and device. The method comprises the following steps: preprocessing left and right eye original images of a current period to obtain a first dense disparity map; obtaining a current period pose parameter; affine transformation is carried out on a to-be-rotated image and the first dense disparity map according to the current pose parameter to obtain a rotated image and a second dense disparity map, wherein the to-be-rotated image is a preset left-eye original image or a preset right-eye original image; and identifying the rotated image and the second dense disparity map image to obtain a ground plane area. The method is high in applicability, can accurately recognize the ground plane under the condition that the vehicle body vibrates, simplifies a detection algorithm based on the disparity map on the basis, further improves the detection speed, and can be widely applied to a ground unmanned platform or an automatic driving auxiliary system and the like.

The invention discloses a device for detecting cone-shaped object pose and sorting cone-shaped objects automatically and a sorting method. The device for detecting cone-shaped object pose and sortingthe cone-shaped objects automatically comprises a motion control module, a conveying module, an image collecting module, an information processing module and an automatic sorting module. The motion control module is in signal connection with the conveying module. The conveying module is connected with the image collecting module and the automatic sorting module respectively. The information processing module is in signal connection with the image collecting module and the automatic sorting module respectively. The device and method are applicable to industrial online rapid cone-shaped object pose detection and sorting scenes; the cone-shaped objects are conveyed by using a conveying belt with baffles; a camera is triggered to take photos by a photoelectric sensor through the baffles, and the purpose of stable triggering is achieved; besides, a color-variable background plate of a specific material is used; detecting algorithm is simplified, and detecting efficiency and accuracy are improved; and through constructing of the simple-structure cone-shaped object detecting device capable of rapid detection of information such as direction and color and sorting device and through image processing technology, feature detection of relevant cone-shaped objects is conducted.

The invention relates to a commodity touch information clustering method, device and equipment based on a surveillance video. The method comprises the following steps of: extracting video images frameby frame from a real-time surveillance video of a commodity; generating a differential gradient image and a binary feature image of a detection area based on a current video image and a preset background image; taking the differential gradient image as a detection image if the number of pixel points of which the pixel values are not zero in the binary feature image is greater than a preset threshold value; counting the touched times of different commodities through an information clustering method based on the detection image; and displaying the touched times in the real-time surveillance video. According to the method, the number of touched times of the commodities in the specific area is recognized in an information clustering mode, so that the attention degree of the commodities in thearea in the market can be reflected, and the method is simple in detection algorithm, small in calculated amount, robust in technology and good in detection effect.

The invention mainly describes a driver monitoring method which mainly comprises the steps of acquiring point cloud data of a monitored area, filtering the point cloud data, acquiring human face point cloud data, performing curve fitting on the face point cloud data, acquiring curve fitting data, extracting and estimating smooth point cloud data, and acquiring a normal direction of the smooth point cloud data. According to the obtained information, the face depth of the driver can be accurately sensed, the attention of the driver can be more accurately judged, the vehicle can be controlled in time through the auxiliary system, and corresponding warning information can be sent out in time.

The invention relates to the field of human body sitting posture detection, in particular to an intelligent detection system and method for a healthy sitting posture. The intelligent detection system a pressure acquisition module, an image acquisition module, an electroencephalogram monitoring module and a control module, wherein the pressure acquisition module is used for acquiring the sitting pressure data of a user; the image acquisition module is used for acquiring user image data; the electroencephalogram monitoring module is used for acquiring the electroencephalogram data of a user; and the control module is used for processing the data acquired by the pressure acquisition module, the image acquisition module and the electroencephalogram monitoring module. The invention aims to provide the intelligent detection system for the healthy sitting posture, sitting posture detection can be carried out from multiple dimensions, accuracy of human body sitting posture recognition is improved, and meanwhile, a detection algorithm is relatively simple, and practicability is high. The mental state of the human body is monitored and timely reminded, so that the user keeps a good sitting posture, the eyesight is protected, and a possibility of human body injury is reduced. When a detection result shows that the sitting posture of the user is normal, the concentration degree state of the user is monitored so as to be beneficial for improving the concentration degree, the learning efficiency and the academic records of students.

The invention discloses a modular multi-level converter fault diagnosis method based on a Luenberger observer in the technical field of multi-level power electronic converters. The fault diagnosis method comprises the following steps: step 1, acquiring required data; 2, obtaining a mathematical relationship of the change of the capacitor voltage uc of the sub-module; 3, calculating a predicted state estimated value ucp (k) of the capacitor voltage of the sub-module at the moment k and an optimal estimated value ucc (k) of the capacitor voltage of the sub-module at the moment k; and 4, judging whether the sub-module has a fault or not. According to the fault diagnosis method, fault detection and positioning can be realized at the same time, and the open-circuit fault and the short-circuit fault of the sub-module can be diagnosed more accurately and timely; the detection algorithm is simple and small in calculation amount, is not influenced by the uncertainty of system parameters, has high robustness, does not need to make any change on a hardware circuit, is easy to understand and implement, does not need to introduce circulating current into the system, and does not change the output characteristics of the system.