204results about How to "Fast matching" patented technology

The invention discloses a method for recognizing a road traffic sign for an unmanned vehicle, comprising the following steps of: (1) changing the RGB (Red, Green and Blue) pixel value of an image to strengthen a traffic sign feature color region, and cutting the image by using a threshold; (2) carrying out edge detection and connection on a gray level image to reconstruct an interested region; (3) extracting a labeled graph of the interested region as a shape feature of the interested region, classifying the shape of the region by using a nearest neighbor classification method, and removing a non-traffic sign region; and (4) graying and normalizing the image of the interested region of the traffic sign, carrying out dual-tree complex wavelet transform on the image to form a feature vector of the image, reducing the dimension of the feature vector by using a two-dimension independent component analysis method, and sending the feature vector into a support vector machine of a radial basis function to judge the type of the traffic sign of the interested region. By using the method, various types of traffic signs in a running environment of the unmanned vehicle can be stably and efficiently detected and recognized.

The invention discloses a fingerprint image matching method based on fingerprint structural features and texture analysis. The method comprises the following steps: (1) processing the feature minutiae and the adjacent minutiae of a fingerprint image to generate structural feature vectors; (2) matching the structural feature vectors, considering the minutiae matching is successful if the vectors fall in a bounding box, representing and the fingerprint matching degree with the number of the successfully matched minutiae; (3) performing Gabor filtering on the incomplete fingerprint containing proper amount of information or the fingerprint image without central part, and dividing the fingerprint into several regions by circular grids to extract the texture features respectively; (4) representing the matching degree with the feature difference among the fingerprint images by taking the gray-scale standard deviation of each region as a feature code, and ; and (5) finding out the most matched fingerprint image by the structural features and the texture features of a BP neural network. The method is independent of translation and rotation of the fingerprint, has strong anti-noise performance, and can solve the problem of non-linear deformation in a certain range.

The invention discloses a method for measuring distance and image acquisition equipment. The method comprises the following steps of: respectively acquiring corresponding images of a reference object and a tested object at two different positions, and analyzing position coordinates of the reference object and the tested object as well as parameters representing the size of the reference object in a first image and a second image, wherein the different positions are in the direction where the tested object can generate a parallax error; and calculating the distance between the tested object and the image acquisition equipment through a distance algorithm according to the distance between the stored reference object and the image acquisition equipment, the position coordinates of the reference object and the parameters representing the size of the reference object. According to the method, simple operation is required, the distance of the target can be calculated at any time, the efficiency is improved, and the cost is saved.

The invention discloses a component multiple size measuring method and system based on binocular vision. The component multiple size measuring method based on binocular vision includes the steps: performing binocular camera calibration on original left and right images to obtain the binocular calibration parameters, and performing distortion correction on the left and right images after binocularcamera calibration to obtain first left and right images; performing polar correction on the first left and right images to obtain second left and right views; based on polar threshold constraints, mapping the points to be matched in the second left and right images to the corresponding grey-scale map to obtain characteristic points; based on a triangulation principle, according to the binocular calibration parameters and a parallax map, obtaining the three dimensional coordinates of the characteristic points; and according to the three dimensional coordinates, performing space curve and linefitting to obtain the target size, and taking the target size as the size of the component. The component multiple size measuring method and system based on binocular vision can solve the technical problem that a current binocular vision measuring method is difficult to match characteristic points.

The invention discloses a height measurement method and device of a highway height permitted frame for a vehicle based on binocular vision. Two wide-angle cameras and a binocular vision system are used for shooting, tracking and locating a height permitted beam target in real time, the binocular vision system is used for measuring the distance from the vehicle to the height permitted frame and therelative height of a vehicle roof in real time, early warning information is provided for drivers, driving and road traffic safety are ensured, a space geometry relation is used for calculating the height of a road frame and the distance between the vehicle and the road frame, the height measurement method and device have the advantages of being high in computing speed and less in calculation resource consumption, the real-time requirements of vehicle safety early warning are effectively met, a limit constraint binocular correction method is adopted to reduce the matching search space, two-dimensional search is reduced to one-dimensional search, the advantage of high matching speed is realized, a checkerboard calibration method is adopted, the internal parameters of the camera can be obtained effectively, and the accuracy of image depth data calculation can be ensured.

The invention discloses a cloud platform-based combined safety lock system and a control method thereof. The system comprises a cloud platform, a mobile terminal and an intelligent lock connected to cloud; an unlock APP is installed in the mobile terminal and used for receiving a locking password and transmitting it to the intelligent lock or for encrypting the unlocking password and modulating it into an acoustic signal transmitted to the intelligent lock, and the unlocking password is characteristic values of the face of an unlocking user or user information and password entered by the unlocking user; the intelligent lock comprises a control module and the following items connected with the control module: an electronic control module, a fingerprint acquirer, an IC (integrated circuit) card reader, a sound acquisition module, a Bluetooth module, a communication module, a storage and a judging module; the cloud platform comprises a comparison module, a safety level correcting module, a key management module and a storage module. The safety level herein may be adjusted in real time, the system is applicable to places with different safety level requirements or requiring frequent safety level adjustment, and the system enables real-time management for all intelligent locks connected to the cloud platform.

The invention discloses a log analysis method, which comprises: presetting keyword list, cutting the URL according to delimiter, deciding whether the URL containing word not contained in said keyword list; if no, storing the URL into URL list as well as user access condition; or else, replacing this word with uniform symbol to store in URL list as well as the word and user access condition; according to statistic condition, acquiring data. This invention can flexible add channel or page for statistic with little effect to analysis time and speed, and improves log analysis speed.

The invention discloses an information processing method and an electronic device. The information processing method is applied to the electronic device. The method includes: displaying a voice control on the display unit, wherein the voice control corresponds to a voice recognition engine; when the voice recognition engine is in a working state, acquiring first voice input used for invoking a first application; based on the voice recognition engine, acquiring a first invoking instruction for recognition of the first voice input; responding to the first invoking instruction, invoking the first application; judging whether or not the first application satisfies a first preset condition; when the first application satisfies the first preset condition, generating a first identification corresponding to the first application; relating and displaying the voice control with the first identification on the display unit.

The invention discloses a method and a device for redrawing two-dimension vector graphics. The method comprises the following steps: drawing all visual graphic primitive objects in two-dimension vector graphics in a buffer zone, buffering the visual graphic primitive objects in form of raster graphics, dividing the buffered raster graphics into at least two zones, and storing the mapping relationship between the zones and the visual graphic primitive objects in the two-dimension vector graphics in the zones; when the visual graphic primitive objects in the two-dimension vector graphics changes, determining the corresponding zones of changed graphic primitive objects before the change according to the mapping relation between the visual graphic primitive objects and the zones; determining the corresponding zones of the changed graphic primitive objects after the change according to the position and/or size of the changed graphic primitive objects; and redrawing the raster graphics of the corresponding zones of the graphic primitive objects before and after the change on a display screen. The amount of data to be processed is reduced due to local redrawing, so the redrawing of the two-dimension vector graphics is speeded up.

The invention discloses a vulnerability scanning method and server and a risk assessment system and relates to the technical field of information security. The method comprises the steps that the server receives a scanning parameter configuration file from a client side and scans a scanned target according to the scanning parameter configuration file; the server extracts keywords from a scanning result; based on a bloom filter algorithm, the server performs quick matching on the extracted keywords and vulnerability features, compressed based on the bloom filter algorithm, in a vulnerability library, and the server determines whether vulnerability exists in the scanning result according to a matching result. As the vulnerability features are compressed based on the bloom filter algorithm, the know vulnerability features can be compressed into an m-bit array, and then storage space is reduced. In addition, a Hash operation is performed on the scanned keywords based on the bloom filter algorithm, matching is performed on Hash operation results and the m-bit array of the known vulnerability features, in this way, it can be determined whether the vulnerability exists in the scanning result, and the matching speed is higher.

The invention belongs to the technical field of vision navigation and positioning, and discloses a stereo vision rapid navigation and positioning method based on double trifocal tensors. The method includes that initial movement parameters of double trifocal tensor motion constraints on a 3D-3D pose estimation method are built by using feature point image coordinates of stereo camera four images before and after moving, the parameters are optimized, and the parameter optimization accuracy is high. The method uses BRISK characteristics suggested by the CCV2011 as tracking matched characteristics, the calculation speed of the characteristics is rapid, and the positioning accuracy and the robustness are high. Stereo matching and front and back frame matching both use local descriptor U-BRISK, and the calculation speed of the descriptor is rapid. As the U-BRISK descriptor is a binary bit string, the matching speed is rapid. The stereo matching and front and back frame matching both use local descriptor U-BRISK to be matched, the robustness and the positioning accuracy are high.

The invention discloses a method and a system for tracing a homologous image through a watermark. The method comprises the steps as follows: an image characteristic value stored in a watermark of a current image is acquired; and a homologous image matched with the image characteristic value is searched in a data base according to the image characteristic value. According to the method and the system, fault tolerance matching is performed by using the accurate characteristic value of the image, if the value can be matched with data in the data base, the image can be determined to a homologous image basically, the error rate is extremely low, and the accuracy is high; and the watermark of the image can also be used for performing tracing, the complexity of occurrence and reading of the watermark is smaller than that of the similarity identification; and the length of a characteristic string is far smaller than the similarity, so that the matching speed is higher.

The present invention provides an orbital invader detection method based on an orbit visual characteristic spectrum. The method comprises: cruising and capturing an image along an orbital line at a certain height, angle and speed, and by using image data, establishing a feature image library for 6 image capturing and affine changes, and constructing a orbit visual feature spectrum based on the orbit feature image library; and performing feature matching by using the orbit visual feature spectrum and a feature of a to-be-detected orbit image , and according to a matching result, determining whether an orbit invader exists in the to-be-detected orbit image. The orbital invader detection method based on an orbit visual characteristic spectrum provided by the present invention can be employed into the invader detection system based on UAV, and solves the problem that the conventional detection system has poor reliability and high costs. The method has a fast feature extraction and matching speed, and can effectively invaders in the orbit, and can be applied to the invader detection system based on UAV.

The invention discloses an intelligent safety lock for a gun. The intelligent safety lock comprises a left lock seat and a right lock seat which are locked with each other. The left lock seat and the right lock seat can be fixedly clamped at a trigger position of the gun after being locked with each other, the right lock seat comprises a lock frame and a lock seat shell, a fingerprint acquisition plate is arranged on the lock seat shell, the lock frame and the lock seat shell are fixedly integrally connected with each other, an accommodating cavity is formed inside the lock frame and the lock seat shell, and a locking mechanism, an intelligent fingerprint processing module and a motor are arranged in the accommodating cavity; the left lock seat is provided with a spring bolt which can extends into the accommodating cavity of the right lock seat and can be fittingly locked with the locking mechanism; the fingerprint acquisition plate, the intelligent fingerprint processing module and the motor are connected with one another by electric signals. The intelligent safety lock has the advantages that the safety lock can be unlocked in a fingerprint recognition mode and accordingly is high in safety performance; the intelligent safety lock can be quickly locked and unlocked, can be operated easily and conveniently and is reliable in use.

The invention relates to the field of information processing and provides a system and a method for processing nucleic acid sequencing information. The system comprises a short-segment establishing unit, a database establishing unit and a sequence matching unit. The short-segment establishing unit is used for segmenting each nucleic acid sequence segment to establish short segments, the database establishing unit is used for establishing referential sequence indexes and storing the short segments to obtain a database, and the sequence matching unit is used for respectively matching the short segments established by segmenting each nucleic acid sequence segment in the database individually. The invention further comprises a method based on the system. The technical scheme of the system and the method for processing the nucleic acid sequencing information can realize accurate and quick matching of nucleic acid sequence segments.

The invention relates to a sparse parallax obtaining method based on target edge features and gray scale similarity and belongs to the technical field of stereoscopic vision. According to the method, the image edge features are extracted by means of the Canny image edge detection method, a strong edge feature point of a target in an image is chosen as a point to be matched, feature similarity and the gray scale similarity of the image are combined, a similarity detecting method of fusion of gray scale and gray scale Census change is adopted, error matching points are eliminated by means of cross detection, and accuracy of matching is further improved. The sparse parallax obtaining method based on the target edge features and the gray scale similarity provides necessary sparse parallax information for recovery of the three-dimensional position and attitude information of an object, has the advantages of being high in accuracy, high in matching speed and stable in matching, and can effectively provides the necessary sparse parallax information for binocular vision system measurement especially active measurement of the attitude information of the object.

The invention provides a stereo matching optimization method of a binocular visual system. The method comprises a step of using the binocular visual system to gain a binocular image; a step of correcting a distortion and polar line of the binocular visual system; a step of transferring the binocular image from a colorful image into a grayscale image; a step of regarding one of the grayscale images as a basic standard and matching with another image according to pixel masterplate; a step of optimizing ZNCC factor; a step of regarding the optimized ZNCC as a similarity measure to calculate in a matched mode so as to ensure matching parallax of each pixel point; a step of producing a dense disparity map according to the matching parallax of each pixel point. The method has the advantages of reducing times of calculation greatly and reducing calculating load of computer chip greatly by optimizing a computational formula of the ZNCC factors and calculating method. The method can improve real-time performance of the stereo matching as well as reducing cost of day-to-day and military high-precision image identification.

The invention discloses a rapid scene matching method based on an SAR (Synthetic Aperture Radar) image. The rapid scene matching method mainly solves the problem of long matching time and low matching precision in the prior art. The method comprises the following steps of: (1) denoising a real-time SAR image, carrying out two-level wavelet decomposition respectively on a denoised real-time image and a reference SAR image; (2) carrying out edge characteristic extraction on a two-level decomposition image and an original image; (3) carrying out secondary rough matching on the second-level decomposition image after the characteristic extraction to obtain secondary rough matching points; (4) returning to a first-level decomposition image, carrying out primary rough matching in a neighboring region of the secondary rough matching points to obtain primary rough matching points; and (5) returning to the original image, calculating an Hausdorff distance in the neighboring region of the primary rough matching points for fine matching to obtain a final matching position. The method can obviously increase a high matching speed while keeping high matching precision and a lower matching error and can be used for precision guidance of a guided missile.

The invention discloses a real-time stereo image generating system, and belongs to the technical field of image processing. The real-time stereo image generating system comprises a multi-view generating module, a caching module and a stereo image synthesizing module. The multi-view generating module is composed of N parallel depth-image-based rendering processing units, and used for generating N virtual view images according to original image and disparity map information. The data of the generated virtual view images is stored into N dual-port dual-cache units of the caching module. The stereo image synthesizing module reads the data of the virtual view images from the caching module, synthesizes the N virtual view images into a stereo image which is applied to a lenticular grating auto-stereoscopic display for displaying. According to the real-time stereo image generating system, the characteristic that FPGA supports parallel and pipeline processing is used, thus the generation speed of the stereo image is improved, and the real-time processing performance of the system is improved.

The invention relates to an automatic TV advertisement movie clip detection method based on multi-mode features. The method includes the steps that a, TV video data are divided into camera lens units; b, an index is made for audio frequency fingerprint features extracted in the step a; c, similar parts of other positions in a video are searched for in the index; d, video matching sections obtained through audio frequency comparison in the step c are in a candidate status; e, matching is refined by searching for boundary points of the matching; f, results generated by multiple video section matching pairs in the step e are subjected to postprocessing, and fragments repeated in time and content are excluded; g, feature recognition is further used for judging whether result video sections in the step f are advertisement movie clips or not; h, after the judgment in the step g is finished, the result is output finally. The automatic TV advertisement movie clip detection method based on the multi-mode features has the advantages that the automatic advertisement movie clip sections are efficiently, accurately and automatically found, the advertisement movie clip sections are automatically found in an unsupervised mode, and the redundant results are excluded through the postprocessing.

The invention provides a radio-frequency antenna impedance self-adaption matching device and method with the quantum algorithm applied. The radio-frequency antenna impedance self-adaption matching device with the quantum algorithm applied comprises a sensor measuring unit, a control unit and a matching unit, wherein the sensor measuring unit is electrically connected with the control unit, the control unit is electrically connected with the matching unit, the matching unit is electrically connected with the sensor measuring unit, and the matching unit is externally connected with an antenna. The invention further provides a self-adaption matching method of the radio-frequency antenna impedance self-adaption matching device with the quantum algorithm applied. Through the radio-frequency antenna impedance self-adaption matching device and method with the quantum algorithm applied, according to the quantum technology, a radio-frequency antenna impedance matching mathematical model is established. The radio-frequency antenna impedance self-adaption matching device and method with the quantum algorithm applied has the advantages of being high in matching speed, high in precision, good in effect, and applicable to real-time matching.

The invention discloses a multi-string matching method for compression flow. A core component of the method is a compression flow string matching engine which is built by using a string to be matched, and scans and matches compression flow byte content to output a matching result; the engine comprises a decoding module, a matching module, a string matching automatic machine module and a state recording module for recording state, namely data needed by a processing process. According to the technical scheme of the method provided by the invention, a relatively high multi-string matching throughput rate is achieved for the compression flow, and the method is convenient to use and has relatively good expansibility.

The invention discloses a logistics information interaction method which comprises steps as follows: goods owners send goods source information to a logistics management center through operating terminals and send first transportation requests simultaneously to be processed by a CPU (central processing unit); vehicle owners send vehicle source information to the logistics management center through intelligent mobile terminals and mobile wireless networks to be processed by the CPU; the CPU matches the goods source information with the vehicle source information and feed back the goods source information and the vehicle source information to the goods owners and the vehicle owners respectively. The convenient and effective logistics information interaction method can be provided for the goods owners and the vehicle owners to the greatest extent, the matching speed is high, costs of the goods owners and the vehicle owners are saved, the method has the advantage of high intelligence and automation degree, more chances are provided for the service of the logistics industry, and the service efficiency and the service speed of the logistics industry are greatly increased.

The invention relates to a manifold learning-based pulmonary nodule case matching auxiliary detection system and a working method thereof. The method comprises the steps that firstly, a case needing to be judged is marked and input a t-SNE computing framework of a text together with a formed case library, a two-dimensional embedding graph is formed through manifold learning, and other cases in a circle with the radius smaller than A are found in the two-dimensional embedding graph by taking the current case as a core and taking a threshold value A as the radius; secondly, the Euclidean distances between the other cases in the circle with the radius smaller than A and the current case are computed, and computing results are sorted; finally, the first N cases which have the smallest Euclidean distances with the current case are selected as recommended cases to be recommended to a doctor. The extraction method has the advantages of being high in recommended case precision and matching speed.

The invention discloses a method and system for extracting image fingerprints based on a representative local mode, and relates to the field of image processing. The method comprises: performing image attack analog processing of database images to generate new database images; extracting key points of the database images and the new database images; obtaining local blocks according to the key points; generating local modes and establishing a local mode database according to the local blocks; obtaining the representative local mode from the local mode database; establishing image fingerprints of the database images and the new database images according to the representative local mode; storing the image fingerprints into an image fingerprint database; obtaining a new image and extracting fingerprints of the new image; comparing the fingerprints of the new image with the image fingerprints in the image fingerprint database; and searching an image corresponding to the new image in the database images. According to the invention, the required memory is small; accelerated matching is performed by using an optimized machine instruction; the method and system are suitable for massive image copying and detection.