Patents
Literature
Patsnap Copilot is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Patsnap Copilot

34results about How to "Increase effective resolution" patented technology

Fire intelligent detection system and control method thereof

The invention provides a fire intelligent detection system and a control method thereof. The system comprises multiple groups of flame detectors, an information processing unit, a PTZ camera and an upper computer monitoring center; each group of flame detectors is complied into a monitored region in a latticed manner, and used for collecting flame data information of different regions and transmitting the information to the information processing unit; a photoelectric self-identification device can be arranged at each flame detector; each photoelectric self-identification device is connected with the information processing unit and used for giving an alarm signal through the control of the information processing unit when the flame detector at a corresponding location collects abnormal data; the PTZ camera is connected with the information processing unit, the PTZ camera tracks the alarm signal sent out by the photoelectric self-identification device; and the image data at the photoelectric self-identification device region is collected and then sent to the information processing unit. The automatic precise sensing on the fire occurrence location can be realized, the fire alarm monitoring is more reliable, and the misinformation resistance is higher.
Owner:浙江图析威视科技有限公司

Flexible ultrasonic detecting device and use method thereof

The invention relates to a flexible ultrasonic detecting device and a use method thereof. The flexible ultrasonic detecting device comprises a row selector, a column selector, a top snakelike guide line, a bottom snakelike guide line, ultrasonic array elements, an ultrasonic array main negative electrode interface, an ultrasonic array resultant signal output port, a top flexible substrate and a bottom flexible substrate; the plurality of ultrasonic array elements are arranged on the upper surface of the top flexible substrate in an array mode; the row selector and the column selector are respectively used for controlling the on-off state of the ultrasonic array elements in each row and each column; the top snakelike guide line is arranged on the top flexible substrate, is respectively connected with the positive electrode of each ultrasonic array element and the ultrasonic array resultant signal output port, and is used for transmitting signals thereof; the bottom snakelike guide lineis arranged on the bottom flexible substrate, is respectively connected with the negative electrode of each ultrasonic array element and the ultrasonic array main negative electrode interface, and isused for connecting the negative electrode of each ultrasonic array element to the ultrasonic array main negative electrode interface; the lower surface of the top flexible substrate is engaged with the upper surface of the bottom flexible substrate. The signals collected by the flexible ultrasonic detecting device are high in accuracy.
Owner:TSINGHUA UNIV

Method for speech emotion recognition by utilizing emotion perception spectrum characteristics

The invention relates to a method for speech emotion recognition by utilizing emotion perception spectrum characteristics. Firstly, a pre-emphasis method is used to perform high-frequency enhancementon an input speech signal, and then, the signal is converted into frequency field by using fast Fourier transform to obtain a speech frequency signal; the speech frequency signal is divided into a plurality of sub-bands by using an emotion perception sub-band dividing method; emotion perception spectrum characteristic calculation is carried out on each sub-band, wherein the spectrum characteristics comprises an emotion entropy characteristic, an emotional spectrum harmonic inclination degree and an emotional spectrum harmonic flatness; global statistical characteristic calculation is carried out on the spectrum characteristics to obtain a global emotion perception spectrum characteristic vector; finally, the emotion perceptual spectrum characteristic vector is input to an SVM classifier toobtain the emotion category of the speech signal. According to the speech psychoacoustic model principle, the perceptual sub-band dividing method is used to accurately describe the emotion state information, and emotion recognition is carried out through the sub-band spectrum characteristics, and the recognition rate is improved by 10.4% compared with prior MFCC characteristics.
Owner:湖南商学院 +1

Light valve type stereo display structure

The invention discloses a light valve type stereo display structure, belonging to the field of electronic display. The light valve type stereo display structure mainly comprises a backlight unit (1), a light valve system (2), a color filtering layer (3) and a lens layer (4). A backlight system is composed of a luminous device and a control circuit and used for generating a plane light source of which the color and brightness are adjustable in certain range of a space domain and a time domain. The luminous device can be a point light source array combined with a uniform light sheet. The light valve system is used for accurately controlling the backlight passing rate of each pixel on corresponding position within corresponding time. The light valve system can be realized by a liquid crystal, electrowetting or micro-mirror array, and the light transmittance of each pixel point is controlled by an auxiliary circuit. The color filtering layer enables full spectrum to pass or selects part of the spectrum to pass. The lens layer is used for controlling the light path to form parallax error between left and right eyes and realize stereo display. The backlight system, the light valve system and the lens array coordinate to work and are used for two-dimensional or three-dimensional image or video display.
Owner:SOUTHEAST UNIV

Mobile shooting system and method

The invention discloses a mobile shooting system and method, and belongs to the technical field of electric appliances, and the system comprises a communication device which is used for transmitting shooting information planned for a shooting object to a control device, wherein the shooting information comprises an initial position and a moving path of a mobile shooting device during shooting; a control device which is used for controlling the mobile shooting device to move to an initial position and shooting according to a moving path after the mobile shooting device receives a shooting instruction triggered by the outside, and controlling a monochromatic light source arranged in the mobile shooting device to carry out stroboflash according to a preset stroboflash mode so as to expose the mobile shooting device; a mobile shooting device which is used for performing each single-channel analog gain according to a preset circular exposure mode after receiving a shooting instruction so as to collect a black-and-white image shot by a shooting object; and an image processing device which is used for carrying out picture splicing on the acquired black and white images and carrying out similarity registration on the image of each channel to obtain a true color image with all-channel alignment. According to the invention, the resolution can be improved.
Owner:SHENZHEN TECH UNIV

A Method for Speech Emotion Recognition Using Emotion Perceptual Spectrum Features

The invention relates to a method for speech emotion recognition using emotion perception spectrum features. Firstly, a pre-emphasis method is used to perform high-frequency enhancement on the input speech signal, and then the fast Fourier transform is used to convert it to a frequency to obtain a speech frequency signal; and then for the speech frequency The signal is divided into multiple sub-bands by using the emotion-aware sub-band division method; the emotional-aware spectral features are calculated for each sub-band, and the spectral features include emotional entropy features, emotional spectrum harmonic inclinations, and emotional spectrum harmonic flatness; The spectral features are calculated by global statistical features to obtain the global emotion perception spectrum feature vector; finally, the emotion perception spectrum feature vector is input to the SVM classifier to obtain the emotion category of the speech signal. According to the principle of the speech psychoacoustic model, the invention adopts the perceptual sub-band division method to accurately describe the emotional state information, and performs emotional recognition through the sub-band spectral features, and improves the recognition rate by 10.4% compared with the traditional MFCC features.
Owner:湖南商学院 +1
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products