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

323results about How to "Meet real-time requirements" patented technology

Method and system achieving integrated camera automatic focusing

The invention provides a method and system for achieving integrated camera automatic focusing, and provides a zooming tracking method based on a relationship type, namely for a shot object at a fixed object distance, according to the initial zooming multiple, the value of an initial focusing position and a plurality of zooming tracking curves stored in advance, the mapping relation between the object distance interval and the focusing position is constructed, and the position to be focused is calculated in real time. Then, a gradient control function obtained by the combination of the statistical law of a lot of experimental data is utilized to achieve mobility control over a zooming motor and a focusing motor, the value of the position to be focused is improved and amended to a certain degree, the value of the position to be focused is closer to a real zooming tracking curve, and an automatic focusing effect is more accurate. Meanwhile, the zooming tracking curves are not needed to be stored in advance, all the zooming tracking curves corresponding to different object distances are not needed to be calculated point by point, an algorithm is simple, it is possible that the zooming speed meets a real-time property, and the focusing effect can meet the requirement for clearness in the whole process.
Owner:SUZHOU KEDA TECH

Redundant robot dynamic obstacle avoidance method using pre-selected minimum distance index

The invention relates to a redundant robot dynamic obstacle avoidance route planning method using a pre-selected minimum distance index under an obstacle random motion environment. The method includes steps of using an oriented bounding box (OBB) to model a redundant robot and establishing the pre-selected minimum distance index; rejecting safe rod pieces through an intersection testing before a real-time distance is calculated; using a local mapping distance calculation method and target point coordinate values to directly obtain a real-time minimum distance and determining impact point positions in a local coordinate system of corresponding rod pieces; and on this basis, establishing obstacle avoidance gains and escape velocities relevant to the minimum distance and using a null space mapping matrix of the redundant robot to plan obstacle avoidance routes. According to the redundant robot dynamic obstacle avoidance route planning method, the safe rod pieces are rejected before dynamic obstacle avoidance planning, unnecessary trivial calculations are removed, a distance calculation method is optimized, planning efficiencies of dynamic obstacle avoidance are improved, and real-time requirements are met.
Owner:BEIJING UNIV OF POSTS & TELECOMM

Vehicle detection method based on laser and vision fusion

The invention discloses a vehicle detection method based on laser and vision fusion. The method comprises the following steps of 1) acquiring target detection information for an input image and laserpoint cloud; 2) performing optimal matching on the images of the front frame and the rear frame and the point cloud detection frame, and establishing a tracking sequence of an image and point cloud detection target; 3) fusing the tracking sequences of the image and the detection frame thereof and the tracking sequences of the point cloud and the detection frame thereof; 4) classifying all the target detection boxes, outputting a fusion list, and outputting a fusion result; and 5) obtaining the accurate position of the surrounding vehicle relative to the vehicle in the current frame, reading the next frame of image and the point cloud data, circulating the steps 1) to 5), and outputting a fusion detection result. According to the method, on the basis of point cloud and image target detection, the detection result is subjected to information tracking, the detection result is optimally matched, and the fusion result is preferentially input into the final fusion list, so that compared witha single sensor target detection method, the target detection precision is improved, and the false detection rate is reduced.
Owner:SOUTH CHINA UNIV OF TECH

Traffic sign detection method in natural scene

The invention provides a traffic sign detection method in a natural scene. The method comprises the steps that a detection image shot in the natural scene is acquired; luminance information of the detection image is subjected to statistical analysis, different luminance areas are divided according to grade luminance threshold values, pixel ratios of different luminance areas are calculated respectively, and the image is divided into a dark scene, a bright scene, a backlighting scene and a normal scene according to all the pixel ratios and scene classification threshold values; gamma parameter values are selected according to scene classification results, and an adaptive Gamma enhancement algorithm is adopted to perform image enhancement processing on a classification image; a partitioning algorithm is selected to perform image color partitioning according to different scenes in an RGB color space to obtain suspected target areas; a grayscale image obtained after color partitioning is subjected to binarization processing to obtain the suspected target areas after binarization; and the suspected target areas are screened through a feature screener to position traffic sign regions. Through the method, robustness and real-time performance of sign detection can be both considered.
Owner:SHANGHAI INST OF TECH

Navigation and remote monitoring system for miniature agricultural machine based on DSP (Digital Signal Processor) and binocular vision

InactiveCN102339062AReal-time monitoring of job statusImprove accuracyProgramme controlComputer controlMicrocontrollerDigital video
The invention discloses a navigation and remote monitoring system for a miniature agricultural machine based on a DSP (Digital Signal Processor) and binocular vision. The navigation and remote monitoring system comprises a binocular vision navigation subsystem and a remote monitoring subsystem, wherein the binocular vision navigation subsystem comprises an image acquisition device, a DSP image processing device and a control device. The image acquisition device is a binocular vision CCD (Charge Coupled Device) camera which is used for transmitting the acquired analog video signal to a video decoder and converting the acquired analog video signal into a digital video signal; the digital video signal is processed by the DSP image processing device according to a binocular vision technology to obtain three-dimensional coordinates of a navigation path and a barrier; the three-dimensional coordinates are calibrated by the camera to obtain a navigation parameter which is output to the control device, that is to say, the navigation parameter is decoded by a singlechip computer; and a control signal is transmitted to a hydraulic system for further controlling on/off of a corresponding hydraulic oil path so as to realize advance and left-right steering of the miniature agricultural machine and lifting of machines and tools. Meanwhile, image information can be transmitted to a remote PC (Personal Computer) in a real time; and if emergency situations (such as failure of an automatic navigation system, barrier appearing in front and the like) occur, the machine can be remotely controlled by a user.
Owner:NORTHWEST A & F UNIV

Signal processing equipment of PET detector based on neural network localizer

InactiveCN101606846AImproved real-time performance of signal processingHighly integratedComputerised tomographsTomographyPeak valueProper time
The invention provides signal processing equipment of a PET detector based on a neural network localizer. The equipment integrates and realizes procedures for processing a series of signals from a photoelectric switching signal outputted by a detector to the action position coordinate of the gamma ray counted by a neural network in real time. The equipment comprises a compression read processing circuit to an array pixel signal outputted by a photoelectric switching device, an analog-digital switching circuit, an energy identifying and timing circuit, a proper time judging circuit, a base line recovery circuit, a signal peak value estimating circuit, a neural network real-time computing circuit, a USB interface circuit, etc. Due to the realization of the technology for processing various digital nuclear signals based on FPCA and especially the real-time computing of the neural network, the instantaneity and the integration level of the system are greatly improved. The invention has compact structure, complete performance, strong on-line data processing performance, and can be conveniently assembled into an integral detector module with the PET detector, wherein the detector module is important intermediate equipment for researching and developing novel PET imaging equipment based on neural network positioning.
Owner:UNIV OF SCI & TECH OF CHINA

License plate location method based on color change points and color density

The invention discloses a license plate location method based on color change points and color density. The method mainly aims at reducing influence on locating a license plate caused by inconsonant background and size of the license plate and tilting of the license plate, thereby quickly and accurately capturing an image of a license plate region from a license plate image. The method comprises the following implementation steps of: firstly, classifying image colors in an HSV (hue saturation value) space according to the distance between the colors, and converting the image to only contain eight base colors; then, performing color binaryzation on the license plate image to get four binary images, and judging whether the image contains the license plate according to the number of white pixels; later, initially locating the position of the license plate according to the color change points and bottom color information of the license plate; removing small connected regions in the binaryimages; and finally, continuously shrinking the license plate region according to the color density and the connected region information, until the position of the license plate is accurately positioned. The whole location process has no operations with higher computational complexity, and is excellent in real time property.
Owner:海安江理工技术转移中心有限公司 +1

Data stream anomaly detection system based on empirical features and convolution neural network

The invention discloses a data stream anomaly detection system based on empirical characteristics and convolution neural network. The system includes an empirical feature extraction module, which is used to identify statistical features and header features as features based on artificial experience, which play a more important role in data packet anomaly recognition; a bit stream conversion picture module used to convert the data stream into the form of two-dimensional gray-scale picture, and then through the convolutional neural network perception, the global high-level perception features are extracted; a fusion splicing module used for fusing the above modules as the data stream characteristics and identifying abnormal data streams by using the full connection layer of the neural network; a distillation model module that replaces complex networks in actual deployment; a concept drift fine-tuning module updates the detection model of concept drift; an update experience database module adding new network attacks or hidden attack instructions to the artificial experience database. The invention accurately and efficiently detects abnormal behaviors such as network failure, user misoperation, network attack and the like.
Owner:ARMY ENG UNIV OF PLA

Rapid distortion correction method based on Bayer image

The present invention provides a rapid distortion correction method based on a Bayer image. The method comprises the steps of firstly, inputting the Bayer image acquired by a fish-eye lens and a CMOS sensor in an FPGA module, adopting an equidistant internal reference model to map a fish-eye image to a three dimensional spherical surface, utilizing a longitude and latitude mode to describe the three dimensional spherical surface, and obtaining a longitude and latitude coordinate transformation relation of the fish-eye image plane coordinate points and the corresponding mapping points of the three dimensional spherical surface; secondly, adopting a vertical fish-eye projection method to obtain a calculation formula of projecting the mapping points on the three dimensional spherical surface to the corresponding projection points in a two dimensional plane, and projecting the three dimensional spherical surface to the two dimensional plane again; and finally, adopting a transverse scanning interpolation method to transform the two dimensional Bayer image interpolation into a one-dimensional image interpolation, utilizing the multi-channel correlation of the Bayer image to divide an interpolation section into a plurality of segment sections, solving a cubic polynomial curve of the to-be-fitted variables in each section separately to obtain the pixel values of the to-be-interpolated points, and carrying out the interpolation on a corrected two dimensional plane image, thereby improving the Bayer image distortion correction precision.
Owner:湖南优象科技有限公司

Realizing method of multi-mode GNSS (Global Navigation Satellite System) software receiver based on multi-core processor

The invention discloses a realizing method of a multi-mode GNSS (Global Navigation Satellite System) software receiver based on a multi-core processor. One of N available cores is distributed to be used as a scheduling core for scheduling and controlling a multi-mode GNSS receiver, and the rest N-1 cores are used as processing cores for processing intermediate-frequency signals of the receiver. The realizing method comprises the steps of: firstly, distributing all the processing cores to form a related operation module by the scheduling core for completing satellite search of a GNSS, feeding the searched result back to the scheduling core; and then scheduling the processing cores by the scheduling core according to the searched result, reserving partial processing cores to maintain the work of the related operation module, forming a data channel consisting of a satellite tracking channel module and a positioning resolving module through the rest processing cores to complete the processing of the intermediate-frequency signal of the GNSS for realizing positioning navigation. By using strong processing capacity of the multi-core processor, the traditional GNSS hardware baseband chipis replaced with the multi-core processor for processing navigation signals of different types of satellites of multiple systems, and flexible configuration and scheduling can be realized.
Owner:SOUTH CHINA UNIV OF TECH

Wave front correction method based on defocused image training

The invention discloses a wave front correction method based on defocused image training, and a device used by the method comprises an image acquisition module, a neural network module, a voltage conversion module and an actuating mechanism. The method comprises the following steps that the incident light is converged into defocused light spots through an optical prism; the image acquisition module is responsible for acquiring defocused light spots; after a large number of defocused light spot image training, the neural network module fits corresponding Zernike coefficients according to the image characteristics transmitted by the image acquisition module; the voltage conversion module establishes the relationship between the Zernike coefficient and a driving voltage; and finally, an execution mechanism realizes the correction of the wave front distortion generated by the atmospheric turbulence according to the fitted Zernike coefficients. The wave front correction method based on defocused image training does not need to use a Hartmann wave front detector and the like, and improves the utilization rate of light beam energy. The loop iteration process is not needed, the bandwidth is high, and the requirement of real-time performance is met. Only a single defocused image is needed to be collected for neural network training, so that the workload of image collection is reduced, and the information quantity of sample light spots is increased.
Owner:INST OF OPTICS & ELECTRONICS - CHINESE ACAD OF SCI

A multiple-subarea matching method constraint by a space relation

The invention discloses a multiple-subarea matching method constraint by a space relation. A plurality of subareas are selected in a matching template as sub-templates, and the sub-templates are separately and simultaneously matched with to-be-matched images. Space position relations among the sub-templates are utilized to realize the accurate matching of the images. The method comprises the following steps: the plurality of subareas are selected in the matching template respectively as the sub-templates; the space relations among the sub-templates are determined; the plurality of sub-templates keep the space position relations unchanged to form combined templates; matching is carried out by utilizing the mobile searching performed by the combined templates on the to-be-matched images, and a plurality of similarity values of the combined templates are obtained; the plurality of similarity values are compared, and a position where a maximum similarity value exists is regarded as an optimum matching position to complete the matching. The method of the invention utilizes the mutual space relations among the plurality of sub-templates to reach the requirements for accuracy and precision of matching. The object identifying performance of the method is substantially improved in real-time performance compared with the conventional large-template gray scale or contour matching algorithms.
Owner:HUAZHONG UNIV OF SCI & TECH

Communication method of application layer of FlexRay bus for small satellite

The invention relates to a communication method of an application layer of a FlexRay bus for a small satellite. Transmission information of an electronic system on the satellite is divided into two types firstly, one type of the information belongs to information transmitted in a normal mode of the electronic system on the satellite and is transmitted through a static section of the FlexRay bus, and the other type of the information belongs to information which is transmitted in an abnormal model of the electronic system on the satellite and is transmitted through a dynamic section of the FlexRay bus. According to the amount of information flow of the electronic system on the satellite, speed of the FlexRay bus, the size of a time slot in the static section, the size of a time slot in the dynamic section, and distribution of the time slots are reasonably formulated, and then a time dispatch list of the FlexRay bus is formulated to provide basis for authoring satellite-borne FlexRay bus software. The communication method resolves the problem of communication interaction of satellite application of the FlexRay bus, software programming of each node of the FlexRay bus has rules to follow, and the using rate of transmission of the FlexRay bus is also improved.
Owner:AEROSPACE DONGFANGHONG SATELLITE

Arbitration device for double computer redundancy hot backup computer

InactiveCN104111881ARealize the arbitration functionMeet the control abilityRedundant hardware error correctionData synchronizationSynchronizer
The invention discloses an arbitration device for a double computer redundancy hot backup computer. The arbitration device for the double computer redundancy hot backup computer comprises an arbitration controller (7), a state control monitor (5) and a network switcher (8), and further comprises a milestone information synchronizer (6), an IO switching module (10), an RS422 switching module (11), a KVM switching controller (9), a work host computer dual port RAM interface (3) and a backup host computer dual port RAM interface. In the initial phase of booting the double computer redundancy hot backup computer, the arbitration device firstly confirms a host computer on duty between a work host computer and a backup host computer, and secondly performs booting synchronization. In the running process after booting the double computer redundancy hot backup computer, the arbitration device firstly performs task synchronization and data synchronization on the work host computer and the backup host computer, and secondly performs switching operation so as to obtain a work shift between the work host computer and the backup host computer. The arbitration device for the double computer redundancy hot backup computer meets the requirements of a display and control platform of a modern naval ship auxiliary device for manipulation ability and timeliness of the double computer redundancy hot backup computer.
Owner:706 INST SECOND RES INST OF CHINAAEROSPACE SCI & IND
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