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

1927 results about "Slide window" patented technology

Rate control with picture-based lookahead window

A method of rate control using a picture-based lookahead sliding window in a dual-pass transcoder/encoder compressed video architecture extracts statistics from an input video signal according to a simple compression standard, the input video signal being a compressed video signal for transcoding or an uncompressed video signal for encoding. A trans-factor is calculated for a current picture based on previous pictures in a sliding window to predict the complexity of the current picture, the trans-factor being a ratio of global complexity measures for the simple compression standard versus a sophisticated compression standard. Bits for the current picture are then allocated based on the complexity of future pictures in the sliding window. After encoding the current picture according to the sophisticated compression standard, the target bits of and the picture complexity in the sliding window, as well as the trans-factor, are updated as the window is moved by one picture. The extraction of the statistics is achieved in a transcoder by using a simple compression standard decoder to produce the statistics from the compressed video signal as the input video signal, and in an encoder by using a simple compression encoder to generate the statistics from the uncompressed video signal as the input video signal.
Owner:GOOGLE TECH HLDG LLC

Fast just-in-time (JIT) scheduler

A just-in-time (JIT) compiler typically generates code from bytecodes that have a sequence of assembly instructions forming a "template". It has been discovered that a just-in-time (JIT) compiler generates a small number, approximately 2.3, assembly instructions per bytecode. It has also been discovered that, within a template, the assembly instructions are almost always dependent on the next assembly instruction. The absence of a dependence between instructions of different templates is exploited to increase the size of issue groups using scheduling. A fast method for scheduling program instructions is useful in just-in-time (JIT) compilers. Scheduling of instructions is generally useful for just-in-time (JIT) compilers that are targeted to in-order superscalar processors because the code generated by the JIT compilers is often sequential in nature. The disclosed fast scheduling method has a complexity, and therefore an execution time, that is proportional to the number of instructions in an instruction block (N complexity), a substantial improvement in comparison to the N2 complexity of conventional compiler schedulers. The described fast scheduler advantageously reorders instructions with a single pass, or few passes, through a basic instruction block while a conventional compiler scheduler such as the DAG scheduler must iterate over an instruction basic block many times. A fast scheduler operates using an analysis of a sliding window of three instructions, applying two rules within the three instruction window to determine when to reorder instructions. The analysis includes acquiring the opcodes and operands of each instruction in the three instruction window, and determining register usage and definition of the operands of each instruction with respect to the other instructions within the window. The rules are applied to determine ordering of the instructions within the window.
Owner:ORACLE INT CORP

Condition monitoring data stream anomaly detection method based on improved gaussian process regression model

The invention relates to a condition monitoring data stream anomaly detection method, in particular to a condition monitoring data stream anomaly detection method based on an improved gaussian process regression model. The problem that an existing method for processing monitoring data stream anomaly detection is poor in effect is solved. The method comprises the steps that firstly, the historical data sliding window size is determined; secondly, the types of a mean value function and a covariance function are determined; thirdly, the hyper-parameter initial value is set to be the random number from 0 to 1; fourthly, q data closest to the current time t are extracted; fifthly, the gaussian process regression model is determined; sixthly, prediction is conducted by means of the nature of the gaussian process regression model; seventhly, PI of normal data at the time t+1; eighthly, monitoring data are compared with the PI; ninthly, whether the real monitoring data need to be marked to be abnormal or not is judged; tenthly, beta (xt+1) corresponding to the monitoring value at the time t+1 is calculated; eleventhly, the real value or prediction value and the t+1 are added into DT; twelfthly, new DT is created. The condition monitoring data stream anomaly detection method based on the improved gaussian process regression model is applied in the field of network communication.
Owner:HARBIN INST OF TECH

Accompanying robot path planning method and system based on obstacle virtual expansion

The invention discloses an accompanying robot path planning method and system based on obstacle virtual expansion. The method includes a step of constructing an environment map, namely a step of constructing a two-dimensional occupancy grid map according to an actual scene, with each grid being labeled as an obstacle zone or a walkable zone; a step of setting initial coordinate positions of an accompanying robot and a movable target in the grid map; a step of constructing a sliding window for the robot; a step of subjecting the obstacle zones to expansion processing, namely a step of performing initial expansion on grids where an obstacle is according to a shortest distance between the center of the robot and a body edge, determining the number of grid layers expanded on the basis of the minimum impassable zone, adopting the grids in the expanded zones as obstacle virtual expansion grids, and labeling the grade of danger of obstacle influences on the obstacle virtual expansion grids; and a step of planning a path for the accompanying robot based on an A* algorithm and an incremental path planning process. Incremental path updating is performed by adopting a path of the last moment,thus saving path planning time and increasing the response speed of the accompanying robot.
Owner:QILU UNIV OF TECH

Electromyographic signal gesture recognition method based on deep learning and attention mechanism

The invention discloses an electromyographic signal gesture recognition method based on deep learning and attention mechanisms. The method comprises the following steps: performing noise reduction filtering on electromyographic signals; extracting one classic characteristic set from each wind datum by using a sliding window, and establishing a new electromyographic image based on characteristics;designing a deep learning frame based on a convolutional neural network, a circulation neural network and an attention mechanisms, and optimizing network structure parameters of the deep learning frame; performing training with the designed deep learning frame and the training data so as to obtain a classifier model; inputting testing data into the trained deep learning network model, and according to likelihood of a last layer of output, maximally likelihooding corresponding types, that is, recognition types. By adopting the method, electromyographic gesture signals can be recognized on the basis of new characteristic images and deep learning frames based on attention mechanisms. By adopting the electromyographic signal gesture recognition method based on deep learning and attention mechanisms, multiple different gestures of a same subject can be accurately recognized.
Owner:ZHEJIANG UNIV

Multidirectional water meter reading area detection algorithm employing full convolution neural network

The invention discloses a multidirectional water meter reading area detection algorithm employing a full convolution neural network, and the algorithm comprises the following steps: S1, obtaining training data which comprises a water meter image and reading region mark information; S2, training the full convolution neural network through the mark information for the extraction of multilayer cascading features, and obtaining a multichannel characteristic image; S3, carrying out the sliding window scanning of the characteristic image, taking a full connection neural network as a classifier and a regression device, and screening out a rectangular candidate window of a water meter reading region preliminarily; S4, extracting the features of a corresponding region in the characteristic image according to the region position information of the candidate window, taking a second full connection neural network as the classifier and the regression device, and obtaining the center, length, width and angle information of the water meter reading region; S5, finally obtaining a detection result of the multidirectional water meter reading area in a manner of a rotating rectangular frame. The algorithm is accurate, robust and practical.
Owner:CHONGQING AOXIONG INFORMATION TECH

Binocular vision indoor positioning and mapping method and device

The invention discloses a binocular vision indoor positioning and mapping method and device. The method comprises the following steps of collecting left and right images in real time, and calculatingthe initial pose of the camera; collecting angular velocity information and acceleration information in real time, and pre-integrating to obtain the state of an inertial measurement unit; constructinga sliding window containing several image frames, and nonlinearly optimizing the initial pose of the camera by taking the visual error term between the image frames and the error term of the measurement value of the inertial measurement unit as constraints to obtain the optimized pose of the camera and measurement value of the inertial measurement unit; constructing word bag models for loop detection, and correcting the optimized pose of the camera; extracting and converting features of the left and right image into words for matching with the word bags of the offline map, optimizing and solving to obtain the optimized pose of the camera if the match is successful, and re-collecting the left and right images and matching the word bags if the match is unsuccessful. The binocular vision indoor positioning and mapping method and device provided by the invention can realize positioning and mapping in an unknown environment and the positioning function in the already constructed scene, andhas good precision and robustness.
Owner:SOUTHEAST UNIV

Target tracking method based on TLD (Tracking-Learning-Detection) algorithm

The invention relates to a target tracking method based on a TLD (Tracking-Learning-Detection) algorithm. The method comprises the steps of: initially selecting a target region from a first frame of image; by adopting a mid-value optical flow method, according to target region information in a previous frame of image, predicting a determined prediction target as a target tracking result; judging whether a number of pixel points in a current frame of image, which are occupied by the target region in the previous frame of image, is greater than a pixel threshold value; if yes, shortening the target region in the previous frame of image and the current frame of image according to a certain length-width ratio, and carrying out global traversal in a mode of a sliding window so as to obtain to-be-selected targets; if no, carrying out local region partitioning on the current frame of image, and carrying out local traversal in a mode of the sliding window so as to obtain to-be-selected targets; processing at least one to-be-selected target to form a target detection result; and according to the target tracking result and the target detection result, determining a target tracking region. According to the target tracking method disclosed by the invention, a detection module and a learning module of the TLD algorithm are improved, and real-time performance of target tracking is improved.
Owner:XIDIAN UNIV
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