343results about How to "Resolve mismatch" patented technology

The invention relates to a method for extracting and identifying characteristics of an electro-ocular signal, which is characterized by comprising three stages, namely pretreatment of the electro-ocular signal, extraction of characteristic parameters of the electro-ocular signal and mode identification of the electro-ocular signal, wherein in the pretreatment stage, endpoint detection and bandpass filtering on the electro-ocular signal are carried out; in the characteristic parameter extraction stage, frame separation and windowing on the electro-ocular signal are carried out, and an electro-ocular characteristic parameter sequence changed along with time after converting the continuous electro-ocular signal into a plurality of sections of short-time electro-ocular signals is extracted; and in the mode identification stage, similarity comparison between the input electro-ocular characteristic parameter sequence and each template of a template base sequentially through a dynamic time normalization method is carried out so as to judge the corresponding eye movement of the operator. The method has the characteristics of high identification accuracy of the electro-ocular signal, certain antijamming capacity, strong application value and the like.

The invention discloses a method for enhancing a depth image of a Microsoft somatosensory device. The method comprises the following steps of: carrying out an edge detection on a color image and a depth image respectively, and obtaining a region at which an error pixel is located by using a region growing method in a mode of inputting two edge images; moving an error pixel depth value; constructing a smooth region around an invalid pixel by using the region growing method; estimating an invalid pixel depth value in the smooth region by using a bilateral filtering method; and estimating remaining invalid pixel depth values by using the bilateral filtering method so as to obtain the enhanced depth image. The invention points out that the problem that edges of the depth image and the corresponding color image are not matched is caused by error pixels for the first time, then provides a detection method for the error pixels, and can effectively fill cavity of a Kinect depth image; the problem that the edges of depth images are not matched is solved well, and quality of the Kinect depth image is improved greatly.

The present invention provides a trusted application download management, authentication, and execution method and system. A trusted application download management server according to the present invention includes a service loader, which accesses a device equipped with a trusted platform and establishes a data communication channel, and a service controller which controls the delegation of a download authority for a trusted application and allows the trusted application to be downloaded to the device when a trusted application download is requested by the device, thus totally managing the download of the trusted applications and allowing the trusted application to be securely downloaded.

A method for calibrating coordinates of a touch screen includes the steps of: providing a display panel, which includes display coordinates along a first axis and a first axis display coordinate; providing a capacitive sensor, which includes sensing electrodes disposed along the first axis and respectively corresponding to sensing coordinates, wherein capacitive sensor has a maximum sensing coordinate; detecting digital values corresponding to the sensing electrodes when the capacitive sensor is touched; multiplying the digital values by the sensing coordinates corresponding to the sensing electrodes to obtain a weighting value; dividing the weighting value by the maximum sensing coordinate to obtain an interpolated value; and multiplying the interpolated value by the first axis display coordinate to obtain a calibrated coordinate.

The invention discloses an image matching method suitable for automatically detecting the flight quality of the aerial photography. The method comprises the steps that firstly, images are preprocessed, denoising and filtering are respectively carried out on two digital images to be matched, and the two digital images to be matched are obtained with the aerial photography measuring method in the measured area and are two-dimensional images; secondly, SIFT characteristic extracting is carried out, the SIFT characteristic extraction is respectively carried out on the two digital images through a data processor, all characteristic points of the two digital images and SIFT characteristic descriptors of all the characteristic points are obtained; thirdly, a kd tree is established to carry out the bi-directional search to determine matching points; fourthly, gross error removing is carried out according to the RANSAC algorithm. According to the method, the steps are simple, design is reasonable, the achieving process is convenient, robustness and the using effect are good, and the method can effectively solve the problem that according to an existing method, matching is prone to failure matching or error matching.

The present invention discloses a moving target tracking method based on an optical flow. The method comprises: collecting a video image, and performing the preparation work prior to tracking such as target selection, template definition, variable initialization and the like; calculating the similarity RateMat of the target and the template, determining whether the template is required to update or not according to the RateMat value, and if the template is required to update, the update of the template is carried out; performing shielding determination according to the RateMat value, employing a corner matching tracking method to track when the shielding happens, and employing the optical flow matching tracking method based on the technologies such as the corner position filtering, optimized contour determination, abnormal region determination and processing and the like to perform tracking; and determining whether the tracking is going on or not according to the tracking result, the tracking is end if the target position is out of the range or a target is reselected by people, or else, calculating the similarity RateMat of the target and the template again and performing iteration tracking. The moving target tracking method based on optical flow greatly improves the tracking precision of a target and solves the problem of limited precision of the optical flow in the moving target tracking method.

The embodiment of the invention discloses a method and device for converting an article into a video, a storage medium and equipment, and belongs to the technical field of computers. The method comprises the steps of obtaining materials in a to-be-converted article; converting text materials in the materials into audios; obtaining a video template matched with the category to which the article belongs from a template library, wherein the template library comprises at least one video template, the video template matched with the category to which the article comprising the text material belongscomprises a typesetting template and a background picture, and the background picture is matched with the category to which the article belongs; and synthesizing the text material, the background picture and the audio according to the typesetting template to obtain a video. According to the embodiment of the invention, the method solves a problem that the text material and the background picturein the video are not matched because the pictures searched according to the keywords are not accurate when an article comprises the text material, guarantees the matching degree of the text material and the background picture, and improves the quality of the video.

The invention provides a system and method for updating a language model (LM). The system comprises a local text set generation unit and an LM updating unit, wherein the local text set generation unit is used for generating a local text set by using text data input to a mobile device and the text data received by the mobile device; and the LM updating unit is used for updating a previously installed initial LM in the mobile device based on the local text set. According to the system and the method, the problem of mismatching between the LM and application requirements in the prior art is solved; and according to the system and method for updating the LM, the LM can be dynamically and frequently updated according to codes of language and concerned topics of a specific user and occurring language phenomenon.

The invention discloses a landmark building identification and detection method based on deep learning. The method comprises the following steps of inputting a to-be-identified landmark building imageinto a DenseNet network to obtain a feature block diagram containing the target building feature information, and then sending the feature block diagram into a region suggestion network to predict abinary category of the feature block diagram and the coordinates of a target building in an original image; completely mapping a prediction candidate box to the feature block diagram by using a RoI Agign method; finally, carrying out classification and frame regression on the more accurate feature block diagrams to obtain the prediction probabilities and the coordinate positions of different landmark buildings, removing the redundant candidate frames through a non-maximum suppression method, fusing the diagrams with the wider coverage regions, and finally realizing the identification and detection of the landmark buildings. According to the method, the prediction of the landmark building candidate frames is more accurate, the prediction range is larger, and the method has the better identification capability on the landmark building images in the complex environment.

The invention provides a method and device for performing N bit parallel baseband processing on a transmission block in a system for coding a channel by using a block coding algorithm. The method comprises the following steps of: performing bit filling operation on the transmission block, then performing error check operation, and finally performing code block partition operation. The bit fillingoperation in the code block partition operation in the prior art is independent and performed before the error check operation, thus N bit parallel baseband processing of a single circuit can be realized before Turbo coding under the condition that extra control signaling and hardware implementation complexity are not increased.

Embodiments of the invention provide a method and a device for searching merchant names. The method comprises: segmenting words for a to-be-searched merchant name, and aimed at each segmented word, according to the word meaning of the segmented word, determining word meaning probability that the segmented word is used as each element; according to the word meaning probability that the segmented word is used as each element and position probability of each element in a merchant name, determining an element attribute of the segmented word; finally, according to the element attribute of each segmented word, searching a matched merchant name of the to-be-searched merchant name from a search library. In the method, after word segmentation is performed on the to-be-searched merchant name, element attribute of each segmented word is determined according to the word meaning and position of each segmented word, and then according to the element attribute of each segmented word, the merchant name matched with the to-be-searched merchant name is searched. Compared with a conventional keyword search and matching algorithm, the method based on element attribute determines significance of the segmented word according to element attribute. The method gets rid of dependence on word frequency or search frequency, so that a problem of mismatching of a similar merchant name is effectively solved.

The invention discloses a continuous sign language recognition method, and relates to processing of a recording carrier for identifying graphics. The method is a continuous sign language recognition method based on multi-modal image sequence feature fusion and a coding and decoding network of a self-attention mechanism. The method comprises the following steps: obtaining an optical flow image sequence; extracting spatial-temporal features of an original sign language image sequence and an optical flow image sequence and fusing the spatial-temporal features of a multi-modal image sequence; extracting a text feature sequence of a sign language sentence label; and inputting the fused multi-modal image sequence spatial-temporal features and the extracted text feature sequence of the sign language sentence label into the coding and decoding network based on a self-attention mechanism to perform sign language label prediction output, thereby overcoming the defects of single feature and videosegmentation requirement in the prior art.

The invention provides ballast adhesive resin as well as a preparation method and applications thereof. The resin comprises a composite A and a composite B, wherein the composite A comprises polyolefin polyol and/or polyether polyol and prepolymer of isocyanate, and the composite B comprises polyether polyol and /or polyether polyol and filling system. The ballast adhesive resin adopts double-composite design, can smoothly penetrate inside a ballast bed due to lower initial viscosity after mixing at temperature of 15-40 DEG C, thus ensuring fast curing of the resin and not influencing the normal running of a railway. In the invention, the polyolefin polyol is used as main raw materials, the water resistance and aging resistance of the material can be greatly improved. In addition, the mixed volume ratio of the two composites is 1:1, so that the problem that the ballast adhesive resin is matched with spraying equipment is solved.

The invention provides an unmanned aerial vehicle aerial image accurate matching method based on island edge characteristics and relates to the field of computer graphics. The unmanned aerial vehicle aerial image accurate matching method solves the problem of dislocation easily occurring during splicing of unmanned aerial vehicle aerial images for island edges. Anisotropic Gaussian filters and weighted median filters in weight dynamic allocation are adopted to filter noises in island aerial images, a chordal distance fixed point self-adaption linear fitting method is utilized to detect edge angular points, a maximum likelihood estimation sample consensus (MLESAC) algorithm is utilized to screen matching points, the screened matching points are substituted into an affine transformation model to solve parameters, and matched modified functions are utilized to perform accurate registration on the images. According to the unmanned aerial vehicle aerial image accurate matching method, island edge details are effective reserved, the extracted island edges are clear, and the edge angular points can be extracted rapidly. A screening and correction process of the angular points is designed, the island images are matched accurately, and the matching effect is good.

The invention discloses a batch upgrading method and system of a multi-board device. The method includes the steps of receiving software files needing to be updated and storing the files in an EMMC according to a batch upgrading request sent by a user; analyzing veneer information involved in the batch upgrade by the file name of the software file; detecting the on-line status of the single boardand the type of the single board of the equipment to be upgraded, comparing with the resolved information of the single board to be upgraded, determining which single boards need to be upgraded, querying the software version information currently running on the single board and saving; determining the priority order of the batch upgrade according to the upgrade information of the single board, the single board type, the master-slave relationship and the business relationship between the single boards; reading the software files from EMMC according to the priority order to upgrade the single board; after all the single board software updates are completed, controlling the single board reset, and upgrading the software of the multi-board device in batch. The method and the system can realize the parallel upgrading of a plurality of types of single boards on the multi-board device, a user does not need to participate in judging the upgrading order, and the equipment software updating efficiency is high.

The invention discloses an LNG gasification system based on a double-heat-source heat pump. The LNG gasification system comprises an LNG gasification heating expansion main circuit, an expansion electricity generation unit, a double-heat-source heat pump unit and an automatic control unit. According to the LNG gasification system, the double-heat-source heat pump is introduced, solar energy and air energy serve as gasification system base load heat sources to supply needed heat for LNG gasification, and therefore efficient LNG gasification is achieved; LNG cold energy electricity generation is utilized for supplying energy for power utilization equipment like a compressor and a process pump in the system and supplying cold for an optimized cold energy user end outside the system in a cold air or chilled water or other modes, and therefore reasonable recycle of the LNG cold energy can be achieved flexibly; according to hourly gas requirements and hourly cold supply requirements of a typical design day of a natural gas user end and the optimized cold energy user, a cold storage tank, an inverter compressor, a standby heater and various flow regulation components are adopted, and the system can operate stably under different working conditions through multiple adjustments by a control system.

The invention relates to a DAC calibrating circuit and a calibrating method thereof. The DAC calibrating circuit comprises a first switch, a second switch, a first comparator, a second comparator, a capacitor and a calibrating module, wherein the first switch is connected between an LSB (Least Significant Bit) unit and the capacitor in order to enable the LSB unit to charge the capacitor based onthe control of a first signal; the second switch is connected between the MSB unit and the capacitor in order to enable the MSB unit to charge the capacitor based on the control of a second signal; the in-phase end of the first comparator is connected with connecting points among the MSB unit, the LSB unit and the capacitor; the reversed-phase end of the first comparator is a first fixed voltage;the in-phase end of the second comparator is connected with the in-phase end of the first comparator, the reversed-phase end of the second comparator is a second fixed voltage; and the calibrating module receives a comparative result of the first comparator and the second comparator and regulates the current of the MSB unit and/or the LSB unit in real time. The invention has high calibration accuracy and can be widely used for high-accuracy DAC.

The invention relates to a universal international multi-functional environment-friendly extension power supply connecting device which comprises a shell, an electricity lead-out plug, a socket and a first power supply switching module. The shell is provided with a bottom face which is provided with a containing groove. The electricity lead-out plug is arranged in the containing groove in the bottom face and can move in the containing groove. The socket is arranged on the surface of the shell and comprises a plurality of socket units conforming to specifications of multiple nations. The first power supply switching module is arranged in the shell and provided with a first input end and a first output end. The first input end is electrically connected with the electricity lead-out plug, the first output end is electrically connected with the socket, and therefore the mains supply power supply led out through the electricity lead-out plug is converted into power supplies with specifications corresponding to the specifications of the multiple socket units. In the connecting device, the electricity lead-out plug can move in the containing groove; for the sockets of different specifications, the plug can be inserted into the socket when the electricity lead-out plug is moved to correspond to insertion holes of the socket in position, and applicability of the power supply connecting device is improved.