84 results about "Foreground-background" patented technology

Apparatus and methods for target detection in hyperspectral images are disclosed. In one embodiment, a method of detecting a target in a hyperspectral image includes spectrally unmixing the hyperspectral image into segments, each segment having at least one of similar spectral composition, similar textural composition, and similar variation, and spectrally unmixing at least one of the segments. The method further includes creating a clutter rejection filter for at least one segment, filtering at least one segment, and calculating target abundances in at least one segment. In alternate embodiments, channel reduction can be performed on the hyperspectral image and also on at least one segment. In further embodiments, data associated with the location of possible targets in the segments may be compiled. In yet another embodiment, this data may be compressed by cross referencing data from all segments and eliminating redundancies.

The invention discloses a foreground data configuring method in network management system, firstly simulating the coursed of establishing relative configuration tables, data tables to be transmitted, foreground-background database relation tables and custom memory; the operating personnel sends a request for data synchronization, and the network management program reads the data in the configuration tables to be transmitted according to the data tables to be transmitted, making data conversion according to the above relation tables, and then transmitting the data to the foreground. It can save limited resources of CPU, memory, etc, enhance working efficiency of the foreground, and at the same time make full use of strong functions of the background relation database system, to make the configuration data more reliable.

The invention relates to a method of quickly segmenting a moving target in a non-restrictive scene based on a full convolution network, which belongs to the technical field of video object segmentation. The method comprises steps: firstly, framing is carried out on the video, and a result after framing is used for making a Ground Truth set S for a sample image; a full convolution neural network trained through a PASCAL VOC standard library is adopted to predict a target in each frame of the video, a deep feature estimator for an image foreground target is acquired, target maximum intra-class likelihood mapping information in all frames is obtained hereby, and initial prediction on the foreground and the background in the video frames is realized; and then, through a Markov random field, deep feature estimators for the foreground and the background are refined, and thus, segmentation on the video foreground moving target in the non-restrictive scene video can be realized. The information of the moving target can be effectively acquired, high-efficiency and accurate segmentation on the moving target can be realized, and the analysis precision of the video foreground-background information is improved.

The invention discloses a backlight image enhancement and denoising method based on foreground-background separation. The backlight image enhancement and denoising method comprises the steps that a backlight image is divided into a foreground area and a background area by adopting an interactive cutout algorithm; the pixel points in the foreground area are enhanced by adopting an improved Retinex algorithm; equalization processing is performed on the pixel points in the background area by adopting a CLAHE algorithm; denoising is performed on the foreground area after enhancement and the background area after equalization processing by adopting a multi-scale NLM algorithm; and weighted fusion is performed on the foreground area and the background area after denoising so that an enhanced and denoised backlight image is obtained. Different enhancement and denoising methods are respectively adopted for the foreground area and the background area of the backlight image so that detail enhancement of the foreground area of the backlight image can be realized, the background area can be protected from being excessively enhanced, the denoising effect is great and accuracy is high and thus the backlight image enhancement and denoising method can be widely applied to the field of backlight image processing.

A method for executing video encoding operations. The method includes encoding an incoming video stream into a plurality of macro blocks by using a video encoder and receiving a foreground-background slice map specification for the plurality of macro blocks. A plurality of critical coordinates are calculated for each rectangle comprising the foreground background slice map specification. Each of the plurality of critical coordinates are examined to assign group membership for their respective macro blocks. The furthest macro block of the respective macro blocks from a raster origination is designated as a last macro block of a group. The data comprising the group is transmitted out from the encoder once the last macro block has been processed.

The invention discloses a method and a system for processing split online video on the basis of a depth sensor. The method includes: firstly, extracting the depth sensor features on the basis of a video frame and a depth image corresponding to the same, and subjecting the features to video frame foreground-background splitting to obtain binary images; secondly, subjecting foreground holes of the binary split images to detection and filling to obtain binary images with foreground holes filled; thirdly, subjecting the binary images with the foreground holes filled to border optimization to obtain optimized binary images; and fourthly, fusing the optimized binary images to a virtual background and the video frame to generate virtual-real fused images. The problems that the depth-sensor-based online video splitting easily errs at discontinuous depth positions and the prior art loses balance between accuracy and timeliness are solved. A depth-sensor-based online video post-splitting processing method and a virtual-real fusion system meeting the timeliness requirement and having high quality are provided.

The invention discloses a start control method, a start control device and a start control terminal. The start control method comprises the steps of obtaining using record information, resource occupancy information and program list information of an application program; regulating and controlling a self-starting value, a start order and the start time of the application program according to a preset regulating coefficient, the using record information, the resource occupancy information and the start list information. By implementing the start control method, the start control device and the start control terminal, disclosed by the invention, the situation of determining a start list, the start speed, the start order and a foreground-background operating state of a to-be-started program aiming at user demands and the state of current terminal equipment when start control on the terminal equipment is carried out is systematically realized, and thus the start parameter and the start state of the terminal equipment can be optimized on the premise that the using needs of a user are met.

The invention relates to a novel field device inspection system and an inspection method thereof. The system mainly comprises two parts including an inspection terminal system and a WEB server system; a foreground-background treatment mode is adopted, wherein a foreground inspection terminal consists of a two-dimensional code label, a two-dimensional code scanning gun and an inspection panel which are fixed on a field device; the WEB server system and a WIFI (wireless fidelity) wireless route form background data processing and device management; the inspection terminal system and the WEB server system adopt a C / S (Client / Server) structure; and the WEB server system and a client in a local area network adopt a B / S (browser / Server) structure. The technical scheme adopted by the invention not only achieves mobility, portability and flexibility of field inspection, but also realizes safety and accuracy of device inspection under the complex field working condition well.

The invention relates to an application data processing method and device. The application data processing method includes the steps that an exit instruction acting on sub-application is obtained; according to the exit instruction, sub-application identification of the sub-application and a corresponding sub-application task are obtained and stored to a memory, and the sub-application task includes sub-application page data; a foreground-background switching entry corresponding to the sub-application is generated, is displayed on a main application interface and used for obtaining the corresponding sub-application identification; the corresponding sub-application task is obtained from the memory according to the sub-application identification, the sub-application corresponding to the sub-application identification is fast switched to a foreground according to the sub-application task, the page state corresponding to the sub-application page data before exit is recovered, and the browsing state before the sub-application exits can be recovered fast.

The invention discloses an application program switching method and a device based on a mobile terminal. The method comprises the following steps: opening a motion sensing module on the mobile terminal; using the motion sensing module on the mobile terminal to detect whether the mobile terminal swings; and when detecting that the mobile terminal swings, carrying out foreground-background switching on the set application programs on the mobile terminal. The method and the device have the following beneficial effects: the touch screen and acceleration sensor on the mobile terminal are combined; and swing of the mobile terminal is sensed by the motion sensing module to directly carry out foreground-background switching on the set application programs on the mobile terminal, so the method is simple and convenient and the operation experience of the users is promoted.

The invention discloses a Web server foreground background association audition method and system thereof which realize the association of the background with the concrete http access happening on the foreground. The method comprises: acquiring the foreground and background access happening respectively though a safety audition equipment; implementing sequence division to the foreground and background access happenings; mining the sequential pattern of the divided happening sequences to find the time sequence relation between them; confirming the http access which triggers the background access according to the acquired relations. The system comprises: a sequence dividing module, a self-learning module and a real time monitoring module. The invention is adapted to the service audition for Web server.

The invention discloses a synchronization method of a foreground-background database. The method comprises: the content of a task which is preset and used for completing the synchronization of a foreground-background database is obtained, and the content of the preset task is divided into a plurality of sub-tasks; the sub-tasks are grouped, wherein, each group comprises at least one sub-task; the sub-task in each group is implemented, wherein, the task of each group is implemented in parallel. Therefore, compared with the way that each sub-task is implemented in series in the prior art, the way that each sub-task belonging to different groups is implemented in parallel causes the sub-task in each group to be independent with each other, so the dependency among sub-tasks is reduced, the time needed by the implementation of the sub-task is shortened to a certain extent, and thus the efficiency for a foreground-background database synchronization flow is further improved effectively. The invention simultaneously discloses a server.

The invention provides a CAN (control area network) open slave station system based on a DSP (digital signal processor) 28335. The CAN open slave station system is based on a DSP 28335 hardware platform, can be applicable to an embedded operating system or a state machine system constructed on a foreground-background system, comprises a CAN communication management module, an object dictionary management module, a network management module, a timer management module, a communication object management module and the like, and completes basic tasks of the CAN open such as PDO(process data objects), SDO(service data objects), NMT(network management objects), synchronous message processing and the like. By the aid of the CAN open slave station system based on the DSP28335, a 301 protocol function in a CIA protocol is completely achieved. The CAN open with targeted optimization can be transported from node functions to a CPU of the same series after simple modification on the DSP28335 platform, so that transportability is achieved. Codes can be reduced, system resource occupation is low and timeliness is high. Due to high applicability, various node functions can be achieved only with simple configuration, and the CAN open slave station system is low in development cost and convenient in maintenance and function expansion.

A method for executing video encoding operations. The method includes encoding an incoming video stream into a plurality of macro blocks by using a video encoder and receiving a box out slice map specification for the plurality of macro blocks. The box out slice map specification is converted to a foreground-background slice map specification. The plurality of macro blocks are then processed in accordance with the foreground-background specification and by using a common hardware encoder front end.

The invention provides an implementation method of a phone payment terminal software platform. The method comprises the following steps of: setting a bottom layer, a second layer, a third layer and a top layer on the software platform of the products of the same model from bottom to top, setting a guide and upgrade program module, a power management module, a memory management module and an interruption foreground-background management module on the bottom layer, setting an event management module, a device management module, a hardware configuration module and a universal drive logic on the second layer, and setting a test program module on the top layer, wherein the constituent parts at the lower layers support the constituent parts of the upper layer, the constituent parts of the same layer can be dependent on each other. The software platform further comprises a database module and a financial service utility function library, which do not strictly belong to the second layer and the top layer. The phone payment terminal software platform based on the SunPlus 16-bit processor environment can effectively reduce the coupling degree of the upper application software and the hardware, simplify the upper software development details and accelerate migration on the hardware products of different models.

A method for propagating user-provided foreground-background constraint information for a first video frame to subsequent frames allows extraction of moving foreground objects with minimal user interaction. Video matting is performed wherein constraints derived from user input with respect to a first frame are propagated to subsequent frames using the estimated alpha matte of each frame. The matte of a frame is processed in order to arrive at a rough foreground-background segmentation which is then used for estimating the matte of the next frame. At each frame, the propagated constraints are used by an image matting method for estimating the corresponding matte which is in turn used for propagating the constraints to the next frame, and so on.

The invention relates to a distributed compressed sensing video encoding and decoding method based on foreground-background separation, comprising the following steps: dividing a video according to the frame sequence into key frames (I frames) and non-key frames (P frames) based on the requirements of reconstruction accuracy and real-time performance; for the I frames, selecting an appropriate observation matrix to measure the I frames; for the P frames, performing foreground-background separation on the P frames and the corresponding I frames and then using the same observation matrix to measure the separated foreground, completing foreground-background separation in a differential manner, introducing decoding mode judgment at an encoder, classifying the decoding modes of the P frame in a GOP into three categories: a skip mode, a normal mode and a dictionary learning mode, and using the same observation matrix to measure the difference. By using the method, the complexity of the encoder can be reduced.

The invention provides a multi-system switching method applied to a terminal equipment operating environment including a main control system and at least two sub systems, wherein the multi-system switching method comprises the steps of obtaining sub system identification information corresponding to each sub system through the main control system when a trigger operation for foreground-background switching of the sub systems is detected; displaying the sub system identification information of each sub system on a screen in a predetermined screen display manner; and performing foreground-background switching for the sub systems through the main control system based on a selection operation when the selection operation for the sub system identification information of any one sub system is detected from a user.

Techniques are disclosed for creating a background model of a scene using both a pixel based approach and a context based approach. The combined approach provides an effective technique for segmenting scene foreground from background in frames of a video stream. Further, this approach can scale to process large numbers of camera feeds simultaneously, e.g., using parallel processing architectures, while still generating an accurate background model. Further, using both a pixel based approach and context based approach ensures that the video analytics system can effectively and efficiently respond to changes in a scene, without overly increasing computational complexity. In addition, techniques are disclosed for updating the background model, from frame-to-frame, by absorbing foreground pixels into the background model via an absorption window, and dynamically updating background / foreground thresholds.

The invention discloses a wireless transmission video monitoring system and a wireless transmission video monitoring method. The system comprises a video acquisition module, a video digital signal coding module, a network sending adaptive module, a control transmission module, a video receiving decoding module and a monitoring terminal, wherein the video acquisition module is used for acquiring video data through a video acquisition terminal; the video digital signal coding module is used for acquiring the video data acquired by the video acquisition module and compressing and coding the video data by using an image group bit distribution method and a foreground-background decomposing and coding method; the network sending adaptive module is used for adaptively selecting a network environment aiming at different network environments of gateway routing equipment to perform communication; the control transmission module is used for managing network state reports generated by each independent network monitoring; the video receiving decoding module is used for receiving real-time video data from a network, identifying the source of each path of video data in multi-path transmission and analyzing and decoding the received video data; and the monitoring terminal is used for acquiring the decoded real-time video data and playing the decoded real-time video data through a player. The scheme of the invention can perform good wireless transmission under a narrowband network environment.

The invention discloses a page display method and device, and belongs to the technical field of terminals. The page display method comprises the following steps: acquiring a page picture to be displayed; sending the page picture to be displayed to a notification bar process; generating a picture notification message through the notification bar process, wherein the picture notification message is used for displaying the page picture; displaying the picture notification message when an operation for checking a notification bar is detected. The page display device comprises an acquisition module, a sending module, a generation module and a display module. According to the method and the device, the page picture to be displayed can be acquired at any scene in which switching of application pages is required, and the page picture is provided in the notification bar, so that a user can check the page picture without any operation for foreground-background switching of applications conveniently, and the operation efficiency is improved.

The invention provides a system and method for processing signaling information reporting. And the system comprises: configuration parameter module, foreground-background communication module, buffer region signaling information processing module, overflow buffer region signaling information processing module and fixed-time detection module; and the method adopts a file to store signaling information beyond signaling information buffer region capacity configuration, and then periodically checks number of pieces of signaling in the signaling information buffer region, and when the number of pieces of signaling is lower than a preset threshold, writes the signaling information stored in the file into the signaling information buffer region in batches according to the preset number of pieces of information. And the invention reduces the loss probability of signaling information and largely improves the processing ability of the background signaling tracking tool, so as to improve the reliability and failure locating ability of the signaling tracking tool.

Embodiments are provided for achieving multi-view video foreground-background segmentation with spatial-temporal graph cuts. A multi-view segmentation algorithm is used where a four-dimensional (4D) graph-cut is constructed by adding links across neighboring views over space and for consecutive frames over time. The segmentation uses both the color values of each input image and the image difference between the input image and the background image to obtain an initial graph-cut, before adding the temporal and spatial links. By using the background subtraction results as the initial segmentation seed, no user annotation is needed to perform multi-view segmentation.

The invention relates to an e-government form model configuration system with a foreground and background separation function. For modeling of e-government forms, common general business attributes are integrated in a form model, so that the foreground-background separation type design of the e-government forms is realized; and after release, the forms can run in an html environment through consistent responsive presentation mode and behavior logics, so that one set of e-government system can support display and operation of html government documents. Through modeling, interface design, event editing and special e-government form generation, the manual hard coding work of the forms is completely avoided, the problem that front-end codes and rear-end codes need to be written is avoided, and the development work of the e-government forms is really transferred to configuration work; and the system can finish quick and large-batch configuration through a copy function, so that the research and development and implementation cycles are greatly shortened.

A central redundancy control system for a rail transit platform screen door comprises a main central controller, a standby central controller, a main input-output device, a standby input-output device, a main network module and a standby network module. The main central controller and the standby central controller are connected with the main network module and the standby network module in a communication manner respectively, and are connected with the main input-output device and the standby input-output device in a communication manner respectively through the main network module and the standby network module; and the main central controller is connected with the standby central controller in a bidirectional communication manner through a synchronous cable. The two central controllers are used for realizing foreground-background simultaneous working redundancy technology, and the two input-output devices are used for realizing activated or deactivated working redundancy technology. When each of the central controllers, the input-output devices, a power module or the network modules goes wrong or fails, the system can be ensured to work normally and stably, and reliability of the system is improved.

The invention provides a communication method during multi-system switching. The communication method comprises the steps of when detecting an operation for triggering the foreground-background switching of two systems in a multi-system, extracting the call related information of a current call in the first system in the foreground; transmitting the call related information to the second system in the background from the first system; then performing system foreground-background switching process on the first system and the second system, wherein the system foreground-background switching process comprises control switching process on a call related control port; and at last based on the received call related information, making a call through the call related control port by the second system. According to the communication method, it can ensure that when the multi-system is subjected to system switching, the current call controlled and processed by the first system before switching can be correspondingly switched to be controlled and processed by the second system along with the foreground system which is switched from the first system into the second system, and the current call keeps a continuous processing state without being influenced by the multi-system switching.

The invention provides an image synergistic segmentation method based on foreground background estimation and hierarchical region association. The method comprises the following steps: S1, obtaining the super pixel sets of all images at different scales; S2, estimating each super pixel class label and pixel class label in each image; S3, estimating a foreground Gaussian mixture model and a background Gaussian mixture model of all images; S4, training an appearance model corresponding to each image by using a texture classifier model; 5, according to that foreground Gaussian mixture model, thebackground Gaussian mixture model, the texture classifier model and the consistency of the superpixel label among the images of the image set, estimating the pixel / superpixel labeling of the image; S6, updating the superpixel class label and the pixel class label of all the estimated images; 7, judging whether that update is complete. The above method overcomes the prior constraint of obvious foreground and background difference, and has more robustness.

A method for enhancing a textual image for undergoing optical character recognition begins by receiving an image that includes native lines of text. A background line profile is determined which represents an average background intensity along the native lines in the image. Likewise, a foreground line profile is determined which represents an average foreground background intensity along the native lines in the image. The pixels in the image are assigned to either a background or foreground portion of the image based at least in part on the background line profile and the foreground line profile. The intensity of the pixels designated to the background portion of the image is adjusted to a maximum brightness so as to represent a portion of the image that does not include text.

The invention relates to a method, a device and an input method system with a function of correcting an input error quickly. The device comprises an instruction module and an input method program foreground-background; and the working principle briefly comprises the steps that any character with a number is input, press keys corresponding to error characters are input, that is, the error characters are positioned quickly, and the positioned characters are corrected on various conditions. With the adoption of the method, the device and the input method system with the function of correcting the input error quickly, no matter what is the number of the error characters which are input once, whether a plurality of error characters are consecutive, and whether the characters are surplus or absent, the error character position can be quickly and directly positioned through a manner of inputting the press key corresponding to the number, and accordingly, the direct correction is achieved without deleting or correcting other correct characters. Compared with the traditional correcting method, the method, the device and the input method system are directly improved, the applicable range is wide, and great convenience can be provided for work and life of people.