34 results about "Background matching" patented technology

A digital video target moving object segmentation method and system is designed for processing a digital video stream for segmentation of every target moving object that appears in the video content. The proposed method and system is characterized by the operations of a multiple background imagery extraction process and a background imagery updating process for extracting characteristic background imagery whose content includes the motional background objects in addition to the static background scenes; and wherein the multiple background imagery extraction process is based on a background difference threshold comparison method, while the background imagery updating process is based on a background-matching and weight-counting method. This feature allows an object mask to be defined based on the characteristic background imagery, which can mask both the motional background objects as well as the static background scenes.

The invention provides a photo album showing system capable of matching background music. The system comprises a processor, a database module, a display output module and an audio output module, wherein the processor is used for performing detection analysis on picture contents in an acquired photo album file to obtain the theme style of a photo album, and reading the additional information of a music file stored in the database module to select the background music according to the theme style of the photo album; the display output module is used for displaying pictures of the photo album; and the audio output module is used for playing the background music. By the photo album showing system capable of matching the background music and the background music matching method thereof, themes of the pictures in the shown photo album can be identified and proper background music can be automatically found and played in matching with the themes of the pictures to save the work of manually repeatedly selecting the background music by a user.

The invention brings forward a method and apparatus for obtaining competence of a job seeker for an applied position. The method comprises the following steps: HR filling in position requirements and selecting a competence quality dimension needing to be possessed and a corresponding grade; the job seeker, when editing a resume or after applying for the position, finishing competence quality test questions, and a system background calculating the grade of the competence quality dimension and feeding the grade to the job seeker; after the job seeker applies for any one position, the system background respectively calculating the work type matching degree, the education background matching degree, the work seniority matching degree and the competence quality test matching degree of the job seeker, and calculating the position matching degree between the resume of a job seeker user and the applied position; and the HR, according to content displayed on the resume, determining whether the job seeker is competent for the applied position. By using the method and apparatus for obtaining the competence of the job seeker for the applied position, the method and the apparatus have the following advantages: the resume of the job seeker and an enterprise recruiting position can realize accurate matching, and the resume screening efficiency and the recruiting efficiency are quite high.

In the embodiment, the invention discloses a method for matching speech background and a device for carrying out the same. The method comprises the following steps of: identifying speech characteristics of a speaker and generating a speech characteristic parameter of the speaker; matching the speech characteristic parameter with a background characteristic parameter of a background material; and selecting the corresponding background material to play according to the matching result. With the invention, the problems of filtering and screening the background which conforms to meaning or emotion or body language of the speaker in an automatic switching process of an improvisational speech background are solved, thereby achieving the aim of matching speech effect by automatically changing the background and improving background auxiliary effect of the improvisational speech for the speaker.

The invention discloses a real-time car pooling system for a mobile terminal. The real-time car pooling system for the mobile terminal comprises a user terminal, a background matching system, a geographic information system and the like. Users use various network accessing manners such as text messages, multimedia messages and Internet to access to the system. When user data such as starting locations and target locations submitted by the users are acquired by the system, text locations are converted into coordinates represented in longitude and latitude and route coincidence and target location deviation of the users are calculated by the geographic information system, real-time calculation for matching the users according to users' requirements and system matching logics is performed, and matching results are sent to the user terminal in a short period of time. In addition, certain matching parameters can be set by the system or the users, and accordingly more precise matching objects can be provided for the users, and a real-time car pooling matching system simple to use is provided for the users.

An annotation support system (10) comprising at least one display device (20). A context extraction module (24, 36) determines a context of a current medical image from a current image study. A matching module (26, 38) compares the context of the current medical image to contexts of prior medical images from prior image studies. A display module (28, 40) displays at least one of context relevant annotations and context relevant medical images from the prior image studies which match the context of the current medical study.

The invention discloses a method for detecting a moving target region aiming at underwater microscopic video. The method comprises the following steps of: (1) acquiring the microscopic video, and generating scale invariant feature transform (SIFT) characteristic point vectors; (2) reducing the dimensions of the SIFT characteristic point vectors; (3) establishing an initialized hybrid Gaussian background model; and (4) matching the SIFT characteristic point low-dimensional vectors one by one, updating the hybrid Gaussian background model, and segmenting a foreground region from an image. According to the method, the SIFT characteristic point vectors of the video image are generated by using an SIFT algorithm, the background model in an SIFT characteristic point vector region is established through the hybrid Gaussian model, and target organisms in the video image are segmented by using the background model and the current video and adopting a background matching algorithm based on the SIFT characteristic point vector region, so that interference of movement of non-target objects to the detection can be effectively eliminated, and the detection accuracy of the target organisms is improved.

The invention provides a time display method and a time display device. The method includes the steps that a mapping relation between a terminal screen and a time shaft is established according to preset rules; slide signals on the terminal screen are tracked, and the slide positions of all the slide signals are sequentially determined; on the basis of the mapping relation, time nodes, corresponding to the slide positions, on the time shaft are sought according to the time sequence of the slide signals, and picture backgrounds are configured for different time nodes; times of the sought time nodes and the picture backgrounds matched with the times are displayed on the terminal screen. By means of the time display method and the time display device, time needed by a user can be fast displayed, time needed for setting time is saved, a friendly interactive interface is provided, and multi-dimensional management is achieved.

The invention relates to a sea surface small target detection method based on an airborne infrared camera aerially-photographed image and belongs to the technical field of target detection. The sea surface small target detection method based on the airborne infrared camera aerially-photographed image is characterized by in view of a characteristic that an infrared image aerially photographed by an airborne camera has coexisting sea surface and land and the sea surface has a clutter background, detecting a coast line by using a gradient detection method and Hough transform in order to segment the land and the sea surface; further, applying an adaptive background matching method based on a gray-level co-occurrence matrix to the sea surface, automatically establishing a template database from the pictures extracted onsite; performing template matching and difference operation based on sea clutter texture; and finally detecting a target by using automatic threshold segmentation technology. The method may effectively solve a problem that sea clutter interference appears in the sea image photographed by the airborne infrared camera and the sea surface and the land are uneasy to distinguish.

The invention discloses a noninductive payment method and system applied to a parking place, and relates to the technical field of payment of charges of the parking place, aiming at solving the problem that in the prior art, a user needs to wait for a gate to open or close and thus time consumed for entering or quitting the parking place is prolonged. The main point of the technical scheme is as follows: when a vehicle is in an entrance collection area and an entrance preset area, the system performs information collection and identity identification on the vehicle, once the vehicle is successfully identified, the entrance gate is opened to release the vehicle. When the vehicle is driven out of the parking place, the system performs information collection and identification on the vehicleonce again, a background matches the information of the vehicle entering and quitting the parking place and compares the same, opens the entrance gate after the identity is identified, then computes apayment amount, and automatically deducts the corresponding amount from an account bound with the vehicle to complete payment. According to noninductive payment method and system, the effect that theuser time for waiting the gate to open or close is avoided and thus the efficiency of entering and quitting the parking place is improved is achieved.

The invention discloses a virtual framing and photographing device for a camera. According to the virtual framing and photographing device for the camera, foreground and background pictures in a data storage unit of the device are called and are processed into an image which has been subjected to picture matting and background matching when framing signals of the camera are acquired, and then, the image is output to a virtual framing and displaying unit for displaying, so that a photographer can frame and photograph. When the signals are received by a photographing synchronous signal acquisition unit, the device imports a photograph into a multi-task processor from a photograph data acquisition unit, carries out corresponding picture matting and background matching work on the photograph, and stores the photograph into the data storage unit of the device. The virtual framing and photographing device for the camera can help the photographer frame and photograph by virtue of the processed image which has been subjected to picture matting and background matching when a mono-color background is photographed, so that a lot of money and time for background making are saved for studios, photography studios, photo galleries and the like, and a preferable background color effect is obtained.

The invention discloses a moving target detection method under a dynamic background and an apparatus thereof. The method is characterized by according to position transformation of corresponding pixel points in front and back frames of images, using a phase correlation algorithm to determine a global motion parameter; using the global motion parameter to carry out background matching on the front and back frames of images, and converting detection of a moving target under the dynamic background into detection of the moving target under a static background; and using an inter-frame difference method to segment a moving target outline, and using a morphological method to detect the moving target. By using the moving target detection method under the dynamic background and the apparatus thereof, problems that background interference is large and detection precision is low in existing moving target detection under the dynamic background can be solved; and the moving target can be accurately and effectively detected under the dynamic background.

The invention discloses a system and method for quickening an application starting response. The method comprises a first step of presetting starting contents and starting background of each application; a second step of causing cloud to take contents during application quitted last time by a client as next-time application starting contents, updating application starting background in real time according to application background matched with the application contents, and pushing the starting contents and the starting background to the client; a third step of starting an application; a fourth step of causing an application starting window to obtain starting information of the application, loading the application starting contents, and adding starting background; a fifth step of cutting out application background screenshot and saving the application background screenshot, and causing the client to report the application contents and the background data to the cloud; and a sixth step of quitting the application. According to the system and method for quickening the application starting response, application starting response time is greatly shortened, the applied range is large, and user experience is greatly improved.

The invention discloses a wireless positioning method based on improved particle filter in a complex indoor environment, characterized in that a handheld mobile terminal acts as a mobile node to periodically collect received signal strength index values from respective wireless access nodes detected by the same, and to periodically report the received signal strength index values; after receivingthe RSSI value reported at any time, the background matches the RSSI value with a wireless fingerprint database on each location collected in a database in advance to estimate a current location thereof; and if the mobile node integrates nine-axis inertial navigation modules or the like of a three-axis accelerometer, a three-axis gyroscope and a three-axis magnetometer at the same time, the mobilenode can be further used for the estimation of pedestrian navigation location. According to the method disclosed by the invention, an improved particle filter algorithm is combined in a wireless fingerprint positioning system, so that a higher gain of the positioning accuracy of a handheld moving target can be obtained in a non-Gaussian nonlinear complex indoor environment.

The invention discloses a bus taxi system with real-time route planning. The bus taxi system comprises a client, a background and a driver end. According to the scheme, first a GIS model is established according to a map, the GIS model comprises all streets and the GPS parameters of the streets, a driver positions the position of the vehicle of the driver through a GPS of the driver end, a user selects an origin and a destination in the GIS model through a user end, and finally a background matches the user end and the driver end. The system has the advantages that the participation of a passenger car with a large passenger capacity in taxi software is supported, the matching of the driver and a passenger is optimized, and the efficiency of taking a taxi is high.

The present invention relates to a stereo object-tracking method and system. The method for adaptively controlling a stereo object-tracking system that is composed of a first image input device and a second input device comprises the steps of detecting a target object included within at least two input images, which the first image input device picks up sequentially, through a background matching of the two input images; separating the target object by the use of a target projection mask from the two input images; generating a reference image including the target object; extracting first locational coordinates by comparing at least one target image, which the second image input device picks up, with the reference image; and controlling the second image input device with the first locational coordinates.

The invention discloses an image processing method which is used for an electronic device to process a combined image. The combined image is formed by combining a predetermined 3D background image anda character area image in a scene image of a current user in a real scene. The image processing method includes the following steps: processing multiple frames of scene images to get optical flow data; judging the position change information of a character area image according to the optical flow data; and adjusting a predetermined 3D background image according to the position change informationto make the predetermined 3D background match the position change information. The invention further discloses an image processing device, an electronic device, and a computer readable storage medium.According to the image processing method, the image processing device, the electronic device and the computer readable storage medium provided by the embodiments of the invention, the position changeof the character image is detected according to the optical flow information, and the background image is adjusted in such a way that the background image matches the motion information of the character image. Therefore, the visual effect of the combined image is more realistic, and the user experience is improved.

The invention discloses a wireless framing-filming device used between a camera and a computer. The wireless framing-filming device comprises a main engine fixedly connected with the camera and an auxiliary engine connected with the computer, wherein the auxiliary engine receives camera framing image signals wirelessly sent by the main engine and transmits the camera framing image signals to the computer, the camera framing image signals are processed to be an image which is subjected to cutout and has a matched background and then are wirelessly sent by the auxiliary engine to be received and displayed by the main engine so as to be framed and filmed by a photographer, the wireless operation control on the program of the computer can be completed simultaneously when the shooting is conducted, and after the shooting, the image data is wirelessly transmitted to the computer to complete the cutout and background matching work of the image. The wireless framing-filming device can perform framing and filming by the image which is subjected to cutout and has the matched background through a wireless manner when a monochrome background is shot, so that the constraining of a cable is eliminated thoroughly, the photographer is facilitated greatly, the large amount of background making cost and time can be saved for photo studios, film studios and the like, and a better background color effect can be obtained.

The invention discloses a method for property protection based on video image background matching, which comprises the steps of acquiring video frames containing a protected object; initializing an initial video frame image, dividing the initial video frame image into a foreground region, a background region and a reference region, and extracting feature vectors Fbk and Fct of the background region and the reference region; calculating a matching ratio threshold T* of the extracting feature vectors Fbk and Fct so as to act as a reference threshold for final decision making; receiving and initializing a next frame image, extracting a feature vector Ffg of a foreground region of the next frame image, and calculating the matching ratio lambda of the feature vector Ffg and the feature vector Fbk; and making an alarm decision according to the matching ratio lambda and the matching ratio threshold T*. When the matching ratio lambda is greater than the matching ratio threshold T*, features of the foreground region are matched with features of the background region, the protected object is lost; and otherwise, the protected object is not lost. According to the method disclosed by the invention, a new idea of foreground-background matching is used, effective protection for properties in a complex environment is realized, and complete shielding and loss can be distinguished.

Provided is an on-line three-dimensional display method for disaster information spatio-temporal data. The on-line three-dimensional display method for the disaster information spatio-temporal data comprises the steps that the disaster information data are obtained from a disaster messenger website through a network; a three-dimensional earth model is drawn in an on-line mode by using a WebGL framework technology and a virtual texture technology through a browser; the disaster information spatio-temporal data are preprocessed according to the time series, and the disaster information spatio-temporal data are transmitted to the browser; the browser directly draws a three-dimensional disaster model through the WebGL framework technology and by calling a computer display card; the browser builds a three-dimensional disaster model framework in a matched mode by using the three-dimensional earth model as the background according to position information data, and the three-dimensional disaster model framework is displayed on the browser. The problems that a three-dimensional visualization technology can only be achieved by using a browser plug-in or extension when being used for disaster information demonstration, backtracking query of historical disaster information cannot be carried out in the aspect of three-dimensional disaster display, and comparison between the historical disaster information and real disaster information is poor are solved.

The invention discloses a property protection method based on video image background matching, comprising the following steps: acquiring a video frame containing a protected object; initializing the initial video frame image and dividing it into a foreground area, a background area and a reference area, and extracting the background respectively The feature vectors Fbk and Fct of the area and reference area; calculate the matching rate threshold T* of Fbk and Fct as the reference threshold for the final decision; when receiving the next frame image, extract the feature vector of the foreground area of ​​the next frame image after initialization Ffg, calculate the matching rate λ of Ffg and Fbk; make an alarm decision based on the matching rate λ and the matching rate threshold T*: when λ is greater than T*, the features of the foreground area match the features of the background area, that is, the protected object has been lost; Otherwise, the object of protection is not lost. The method of the present invention utilizes a new idea of ​​"foreground-background" matching to realize effective protection of property in a complex environment, and can distinguish between total occlusion and loss.

The invention discloses a dynamic background matching method for moving target detection, which relates to the technical field of image processing. Only four matching blocks at four corners of an image and one random matching block are used for background matching, and local matching of images is sufficient. To achieve the overall matching of the background. In the occasions where the computing power of the hardware is relatively low, the method provided by the present application can also be used to realize simple target detection in a dynamic background. The present invention provides a dynamic background matching method for moving target detection. After the background matching is performed, the frame difference method is used to detect the moving target, and the target can be successfully and quickly detected when the camera shakes, rotates and pitches greatly. Use simple local area blocks for matching, maintain high background matching accuracy, and simplify the background modeling algorithm.

The invention relates to a sea surface small target detection method based on an airborne infrared camera aerially-photographed image and belongs to the technical field of target detection. The sea surface small target detection method based on the airborne infrared camera aerially-photographed image is characterized by in view of a characteristic that an infrared image aerially photographed by an airborne camera has coexisting sea surface and land and the sea surface has a clutter background, detecting a coast line by using a gradient detection method and Hough transform in order to segment the land and the sea surface; further, applying an adaptive background matching method based on a gray-level co-occurrence matrix to the sea surface, automatically establishing a template database from the pictures extracted onsite; performing template matching and difference operation based on sea clutter texture; and finally detecting a target by using automatic threshold segmentation technology. The method may effectively solve a problem that sea clutter interference appears in the sea image photographed by the airborne infrared camera and the sea surface and the land are uneasy to distinguish.

A shoe transaction system capable of matching shoes suitable for foot types of a user for the user to select comprises a user terminal, a merchant terminal, a background matching system and a shoe transaction platform. The user terminal and the merchant terminal are terminal equipment with scanning and photographing functions and are used for respectively transmitting the acquired user foot shapedata and shoe tree mold data to the background matching system; The background matching system matches the foot shape data of the user with shoe tree and mold data of a merchant, and transmits a matching result to the shoe transaction platform; And the shoe transaction platform transmits a matching result back to the user terminal and the merchant terminal for the user to select, purchase and customize. According to the invention, a user can buy shoes suitable for the foot shape of the user more conveniently, so that the time cost and the logistics cost for the user to buy shoes are saved, andthe embarrassing problem that the user does not fit feet even if trying to wear all sizes of one type of shoes is avoided. Meanwhile, shoe merchants can find their target users more accurately.