63results about How to "Avoid background distractions" patented technology

The invention discloses a video target tracking method based on CAMSHIFT and Kalman filtering. The method takes a search window as a parameter and comprises the following steps of: predicting a search window Win by a Kalman filter; calling a CAMSHIFT algorithm by taking Win as a parameter to search for the target, and returning to the window targetWin containing candidate models; calculating similarity between the targetWin and the target model; if the similarity is greater than the set threshold, finding the target and returning to the target window; otherwise, taking the target window of the previous frame and the distance predicted by the Kalman filter as a window expanding parameter instead of enlarge, and calling an adaptive iterative search algorithm. By introducing the similarity judgment and the re-positioning technology, the method effectively eliminates the background interference and improves the tracking precision.

The invention belongs to the technical field of organic photoelectric functional material, and specifically provides a preparation method of an aza BODIPY based near infrared fluorescent dye and application of the near infrared fluorescent dye to Hg<2+> detection, cell imaging and biomarker. The material is a micromolecular near infrared dye based on aza BODIPY, and near infrared absorption and emission wavelength of which are adjusted by changing Ar group. The material has a structural general formula shown as below, simple synthesis steps with mild conditions, can be used as a near infrared fluorescent material and has good application prospect in ion detection, cell imaging and biomarker.

The invention aims to provide a method for preparing surface plasma resonant imaging gold film micro-array. The method comprises the following steps: firstly self-assembling a gold size nanometer particle monolayer with the diameter of 2.5 nanometer on a glass plate modified by 3-Aminopropyltrimethoxysilane, taking the monolayer as a catalytic template; then taking a transparent film high-precision printed lattice array as a mask to carry out photo-etching to the glass plate modified by the gold nanometer particles, thereby preparing the micro-array of the gold nanometer particles; and controlling the gradual increase of the gold nanometer particle micro-array within the nanometer scale range by adopting the electroless plating technique, thereby constructing the required gold film micro-array. The size and the interval of each gold point in the micro-array can be conveniently controlled by the mask, and the thickness of the gold point is controlled by adjusting the electroless plating time.

The invention relates to a self-adaptive charge control system for electric vehicles on the basis of an SDP (SECC (supply equipment communication controller) discovery protocol) and a V2GTP-EXI (vehicle to grid communication transport protocol-efficient XML interchange) and a control method of the charge control system. The self-adaptive charge control system comprises an energy supply equipment communication controller SECC, and the SECC comprises a main controlling CPU (central processing unit), a power source module, a sampling module, a man-machine module, an in/out module, a guidance control module, and a PLC (programmable logic controller) module. The main controlling CPU is used for scheduling a charge system of an electric vehicle, processing and controlling data. The power source module is used for supplying power source for the SECC. The sampling module is used for collecting voltage and current information and uploading the same to the main controlling CPU. The man-machine module is used for interface displaying and keyboard inputting. The in/out module is used for collecting switching value and state value, uploading the same to the main controlling CPU, and executing control commands of the main controlling CPU. The guidance control module is used for monitoring state of a guidance control wire and uploading the state to the main controlling CPU. The PLC control module is used for converting network communication data between the main CPU and an EVCC (electric vehicle communication controller) into carrier data. By information interaction between the EVCC and the SECC of a plug-in electric vehicle, interaction V2G (vehicle to grid) between the electric vehicle and the power grid is realized, and self-adaptive charging of the electric vehicle is completed.

The invention discloses an image automatic segmentation method based on a PCANet depth learning model. The method comprises the following steps that (1) the images to be segmented are sequentially processed by preprocessing, super pixel clustering, the first PCANet network and the first SVM classifier to obtain the coarsely segmented images; the coarse segmented image is binary pre-segmented image. (2) the coarse segmented image obtained in the step (1) is sequentially processed by a second PCANet network and a second SVM classifier to obtain a refined segmented image, and the refined segmented image is a binary final segmented image, thereby completing automatic image segmentation. By controlling the whole data processing flow of the automatic segmentation method and the frame structure of the corresponding automatic segmentation system, the method of the invention combines the super pixel with the PCANet network to realize the automatic image segmentation, and can greatly improve thesegmentation accuracy and robustness of the molybdenum target mass.

The invention discloses a particle filter target tracking method based on multi-feature fusion. The method comprises the following steps: acquiring a video image and performing filtering processing; calibrating a tracking target in the initial frame by using a rectangular frame, and calculating an edge histogram, a texture histogram and a depth histogram of the target template; updating a particlestate by adopting a second-order autoregression model, and obtaining a feature histogram of each particle; calculating the similarity of the two templates, obtaining a single feature discrimination degree according to the position mean value, the standard deviation and the overall position mean value of the particles under the single feature, and adaptively adjusting the fusion weight; determining the particle weight at the current moment in combination with the observation model of multi-feature fusion and the particle weight at the previous moment; sorting the particle weights, counting thenumber of particles with small weights, comparing the number of particles with small weights with a threshold value, correcting the size of a window, and determining the state of a tracking target. According to the method, the edge, texture and depth characteristics are combined, so that the target can be tracked more accurately and continuously.

The invention provides a clothes color recognition method based on semantic segmentation, and the method comprises the steps: collecting a certain number of portrait pictures with different parametersin different scenes, and marking the collected portrait pictures; carrying out random parameter transformation processing on the marked portrait picture to generate an initial sample set; creating aclothing region extraction model based on a JPPNet network, and extracting a local picture of each clothing region contained in each portrait picture; carrying out background transformation and colorclassification labeling on the extracted local picture; performing size unification and random parameter transformation processing on the marked local pictures to generate a training sample set; and creating a clothing color recognition model based on the classifier, and importing the training sample set into the clothing color recognition model to train the clothing color recognition model. According to the method, higher recognition success rate and recognition accuracy can be achieved, and particularly, the improvement amplitude of the recognition success rate and the recognition accuracy is higher under the complex conditions that only a half figure exists in a picture, and shielding exists in the picture.

The invention relates to a fetal cell capturing module, an application method thereof, a micro-fluidic chip for fetal cell capturing and an application method of the micro-fluidic chip for fetal cellcapturing. The fetal cell capturing module comprises a cell capturing carrier and a distinguishing molecule for specific capturing of cells, and the distinguishing molecule is connected to the surfaceof the carrier through an organic coupler containing disulfide bonds. The surface of the micro-fluidic chip for fetal cell capturing is modified with the distinguishing molecule used for specific capturing of the fetal cells by means of the organic coupler containing disulfide bonds, and after the distinguishing molecule captures the cells, chemical chopping is performed on the disulfide bonds inthe organic coupler to realize the release of the cells. The capturing module, the application method thereof, the micro-fluidic chip and the application method of the micro-fluidic chip can realizefetal cell capturing of whole blood without being pretreated, the capturing rate is high, the cell loss is low, the cells are simple in release operation and accurate in action, so that the fetal cells can be efficiently and harmlessly released, and complete genomes can be analyzed.

The invention discloses a method for counting archenteric flora of aquatic animals and a special primer thereof. The special primer provided by the invention is a primer pair consisting of nucleotide shown in a sequence 1 of a sequence table and nucleotide shown in a sequence 2 of the sequence table. The special primer can be applied to preparation of kit counting the archenteric flora of the aquatic animals or used for carrying out counting of the archenteric flora of the aquatic animals. The special primer and the method can avoid background interference, can make accurate quantification on the number of total flora in a complex micro-ecological environment, and has the characteristics of high sensitivity, stronger specificity and reliability, multiple reaction realization, high automation degree, non pollution, real time, accuracy and the like.

The invention discloses a vehicle behavior recognition method, particularly relates to a method for extracting matching difference image features to recognize vehicle behaviors, and belongs to the technical field of intelligent traffic. According to the vehicle behavior recognition method, differential treatment is performed on a pretreated image, the horizontal edge of the differential image is extracted to generate vehicle feature descriptors, and the motion trail of a vehicle is determined through two adjacent vehicle feature descriptors successfully matched; afterwards, vehicle behaviors are analyzed according to the motion trail of the vehicle. The method has an excellent inhibiting effect on all types of interference in a complex scene. Meanwhile, the amount of calculation is small, and reliability is high. Besides, the problem of background interference in motion target detection and the problem that the amount of calculation for feature extraction in a single image is large are effectively avoided.

The invention relates to a detection device and a detection method for a heavy metal migration amount of a nano filter tip, and belongs to the technical field of physical and chemical inspection of tobacco accessories. The device comprises an air inlet, air heating chambers, a ten-way valve, a filter tip holder, a smoke trapper and a smoke sucking machine; the ten-way valve comprises a plurality of rotatable air connection ports, a fixed air connection port and a numerical control turntable; the number of the rotatable air connection ports is same as the number of the air heating chambers; each rotatable air connection port is connected with one end of one air heating chamber. The other end of each air heating chamber is connected with the air inlet; the numerical control turntable is usedto control connection of each rotatable air connection port and the fixed air connection port; and the fixed air connection port, the filter tip holder, the smoke trapper and the smoke sucking machine are connected sequentially. The detection device has the advantages of simple structure, convenient operation and reducing of the influence of complex smoke, and can be used as a new analytical technique and method for heavy metal migration amount of the nano-filter tip.

The invention discloses a portable Raman spectroscopy method for detecting pesticide residues in instant tea powder, and belongs to the technical field of food monitoring and the like. The method comprises the steps of firstly generating gold nanoparticles by in situ chemical reduction on a mesoporous silica film formed at the air-water interface, constructing a gold nano surface-enhanced Raman substrate (AuMSF) that can be used as a label-free SERS substrate to enhance the Raman signal after electrostatic adsorption with pesticide molecules with mesoporous structure, secondly establishing quantitative models of different pesticides by a chemometrics method using the Raman spectrum collected by portable Raman spectroscopy, and applying the quantitative models to the pesticide residue detection of fermented black tea. The method has the advantages of simple operation, high detection speed, high precision and good stability, and can realize on-line detection of pesticide residues in thefermented black tea.

The invention provides a vehicle lower bottom edge positioning method based on horizontal edge information accumulation, and the method comprises the following steps: obtaining a rectangular frame containing a vehicle in an image frame of a video; calculating a horizontal edge strength response function of each rectangular frame and a scaling parameter and a translation parameter corresponding toeach rectangular frame; for each rectangular frame in the current image, creating or updating a horizontal edge information accumulation function; And for each rectangular frame in the current image,calculating a target lower bottom edge position according to the horizontal edge information accumulation function of the rectangular frame. The single-frame horizontal edge information is subjected to multi-frame accumulation by calculating the image zooming parameters and the translation parameters, the background edge information is continuously weakened in the accumulation process along with the movement of the vehicle, and the vehicle edge information is continuously enhanced in the accumulation process, so that the background interference is effectively overcome, and finally the accuratevehicle lower bottom edge position is obtained. Compared with an existing bottom edge positioning method based on vehicle bottom shadow characteristics, complex background interference can be effectively overcome.

The invention discloses a zero-background multi-fragment gene efficient assembling method. The method includes the following steps that a puc57-CATP carrier is established; plasmid in which CATP genefragments are cloned is established; a target gene is selected, the target gene is divided into small fragments according to the length of the gene for gene synthesis, second-class enzyme loci are added to the two ends of the gene, and the gene is connected to a cloning carrier; the small fragments comprise the established CATP gene fragments and are assembled through a Golden gate cloning reaction, T7DNA polymerase is used as ligase, an assembled product converts escherichia coli, and an LB panel with ampicillin and chloromycetin resistance is coated with the assembled product for screening.Under the condition that the carrier plasmid does not need to be treated in advance, by means of special carrier and fragment design, multiple gene fragments are efficiently assembled simultaneously at a time. The T7DNA ligase with higher fidelity is used, and the probability of correct assembly of the fragments is increased.

The invention discloses a method for detecting gene chip hybridization results through total internal reflection, which comprises the following steps of constructing a gene chip detector, and dividing a camera obscura (1) of the gene chip detector into a light source camera obscura (3) and an imaging camera obscura (16) by using a quartz glass plate (2); adding an equal refractive index solution (9) with the same refractive index as the quartz glass on the quartz glass plate (2); placing a quartz glass substrate of the gene chip on an equal refractive index solution (9); adjusting the position and an angle of the plane parallel light source generator (6) so that the emitted plane parallel light forms total internal reflection; the total internal reflection evanescent wave (11) exciting a fluorescent substance on a probe (12) of the gene chip to emit marking fluorescence (13); and the labeled fluorescence (13) being captured by a high-resolution camera (15), and finally a detection result being obtained. According to the method, background interference in the fluorescence imaging process is avoided, and the signal-to-noise ratio and detection sensitivity of a gene chip hybridization result are improved.

The invention relates to a method for detecting enzymatic activity concentration through combined use of subject and object probes and a nanopore technique. The invention firstly provides a molecule combination for detecting the enzymatic activity concentration. The molecule combination comprises DNA-peptide molecules and cucurbituril, wherein the DNA-peptide molecules consist of double-stranded DNA molecules and peptide molecules, the carboxyl terminals of the peptide molecules are in covalent connection to 5' terminals or 3' terminals of the double-stranded DNA molecules, and after the DNA-peptide molecules are subjected to action by enzymes to be detected, the exposure state of amino terminal aromatic amino acids is changed. After the enzymes to be detected excise a part of peptide chains through an enzymatic reaction, exposed (or lost) aromatic amino acids can (cannot) generate subject and object action with the cucurbituril, and the DNA subject and object probes can (cannot) be formed. When penetrating through nanopores, the DNA subject and object probes can produce characteristic current signals, and through detecting the current signals, high-sensitivity high-specificity detection of the enzymatic activity concentration can be realized.

The invention provides an exosome particle size analysis device and method based on deep learning, and belongs to the technical field of exosome detection and recognition equipment. The exosome particle size analysis method comprises the steps that: an excitation module shapes laser to form an excitation light sheet which is emitted into a to-be-detected exosome sample; the detection module transmits the exciting light sheet through the exosome sample to be detected to form exosome lateral scattered light; the acquisition module is used for acquiring a video of exosome Brownian motion; then the analysis module is combined with the video and utilizes a deep learning algorithm to position the exosome particles, so that the motion trail of the exosome particles is obtained and the particle size of the particles is calculated. According to the method, background interference and stray light influence are avoided, and the signal-to-noise ratio is relatively high; the cost is low, the cross contamination problem and sample waste are avoided, excessive and overestimation of the particle size cannot be caused, and large-size magnetic beads do not need to be marked, so that marking steps and cost are simplified; therefore, the particle positioning precision is improved, continuous parameter adjustment is not needed, the influence of subjective factors is reduced, and the robustness and applicability of the result are ensured.

The invention discloses an antibody detection method for combining a three-chain DNA molecular beacon with a nanopore technology for combination. The method comprises the steps that the three-chain DNA molecular beacon used for detecting an antibody is designed and synthesized, when the antibody is combined with the three-chain DNA molecular beacon, the molecular beacon structure is destroyed, anda probe is released; an antibody-antibody capture DAN molecular complex cannot penetrate through a nanopore due to too large volume, the probe passes through the nanopore and can generate a characteristic current signal, the signal specificity is extremely high, molecular recognition can be accurately achieved, and the background interference problem is avoided. In addition, the unique thermodynamics and kinetic properties of the molecular beacon are combined with the nanopore single molecular technique, and high sensitivity detection on the variable antibody is achieved. In addition, the method has the advantages that implementation is easy, reagent consumption is extremely low, and large-scale equipment is not needed.

The application discloses an ultrasonic imaging method and device. The method comprises the steps: gathering magnetic particles into a target region by using an external magnetic field; activating the magnetic particles in the target region by using an external alternating magnetic field so as to enable the magnetic particles to generate an ultrasonic signal; detecting the ultrasonic signal of the target region; and generating an ultrasonic image of the target region by using the ultrasonic signal. According to the technical scheme, the magnetic particles in the target region are activated by utilizing the external alternating magnetic field so as to enable the magnetic particles to generate the ultrasonic signal, thereby implementing high-signal-to-noise-ratio real-time tracing on the magnetic particles in deep tissues through ultrasonic imaging.