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 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.

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 relates to a shopping system adopting a virtual reality technology. The shopping system is operated in a smart device, the system comprises: a virtual space generator, an Augmented Reality (AR) and a positioning module, the system is mainly used for generating a virtual space and guiding an augmented reality image into the virtual space, positioning the use position of the intelligent device and importing the use position into the virtual space to change the moving position in the virtual space; meanwhile, by combining the commodity service unit and the shopping guide module, theproduct reality image in the commodity service unit can be imported into a virtual space; according to the invention, the product can be known in the virtual space in real time and background matching is carried out on the product, the shopping guide module is used for purchasing and ordering, the reality sense of shopping of consumers can be improved, consumption fun is increased, and the commodity can be directly matched with the living state, so that the return rate is reduced.

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.

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.

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.