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

2204 results about "Width ratio" patented technology

The width/depth (W/D) ratio is defined as the ratio of the bankfull surface width to the mean depth of the bankfull channel. The width/depth ratio is key to understanding the distribution of available energy within a channel, and the ability of various discharges occurring within the channel to move sediment.

Pedestrian identification method under road traffic environment based on improved YOLOv3.

InactiveCN109325418AVerify the recognition effectSolve the problem of difficult and slow target detectionBiometric pattern recognitionCluster algorithmRoad traffic
The invention discloses a pedestrian identification method under a road traffic environment based on improved YOLOv3. The method comprises the following steps of: S1, acquiring and pre-processing an image, and making a pedestrian sample set; 2, calculating the length-width ratio of the pedestrian candidate frames by using a clustering algorithm and the training set; 3, inputting the training set into the YOLOv3 network for multi-task training and saving the trained weight file; S4, inputting a picture to be recognized into the YOLOv3 network to obtain a multi-scale characteristic map; S5, using a logistic function to activate the x, y, confidence degree and category probability of the network prediction, and obtaining the coordinates, confidence degree and category probability of all prediction frames by judging the threshold value; S6, generating a final target detection frame and a recognition result by carrying out the non-maximum value suppression processing on the above result. The method of the invention solves the problem of low detection accuracy of the prior method, realizes the multi-task training, does not need additional storage space, and is high in detection accuracyand fast in speed.
Owner:SOUTH CHINA UNIV OF TECH

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

Image type automatic analysis method for mesh adhesion rice corn

InactiveCN101281112AOvercoming problems that are difficult to analyze automaticallyRemove the restriction of non-stick placementImage analysisMaterial analysis by optical meansAutomatic segmentationSplit lines
The invention discloses an image automatic analysis method for reticulate adhesion rice. The method firstly images rice under the grade of a reference backlight, and enables the reticulate adhesion rice to belong to the different local regions separately through an automatic segmentation. Secondly, the automatic segmentation includes that fat circular rice is carried on a distance transformation and a watershed transformation to be divided, as well as to use a circular template to get the concave angle point of long rice after the long rice is carried out watershed transformation, and the separation line can be determined and the wrong separation line can be removed according to the concave angle point. Different colors is using to color complete polished rice, broken rice and the rice whose length is in the critical region and to color background and chalkiness so as to figure out the grain number, the length, the width and the length to width ratio of each grain, finally, and the entire polished rice rate, the broken rice rate, the chalkiness degree and the chalkiness grain rate, and to form an analysis report. The invention overcomes the problem that the reticulate adhesion rice is difficult to be carried on automated analysis, and removes the limit of the request analysis sample is not in adhesion placing.
Owner:ZHEJIANG SCI-TECH UNIV

Target detection method and device and computer readable storage medium

The invention discloses a target detection method which comprises the following steps of: acquiring a to-be-detected image, wherein the to-be-detected image is subjected to multi-layer convolution extraction of features in a neural network to generate a feature map; loading modified structural parameters in a neural network model, and generating corresponding anchor box coordinates on the basis ofthe structural parameters, wherein the preset structural parameters comprise a reference dimension of an anchor box, an anchor box scale and a length-width ratio of the anchor box; generating candidate box coordinates on the basis of a region nomination subnet, taking a corresponding region on the feature map according to the candidate coordinates, and by pooling of a ROI (Region Of Interest), obtaining corresponding features; and on the basis of the features, determining prediction box coordinates, and on the basis of the prediction box coordinates, determining a target object position. Theinvention further discloses a target detection device and a computer readable storage medium. According to the invention, a case of generating an optimized prediction box to determine a target objectis implemented, a small target can be detected, and a detection rate for the target is improved.
Owner:SHENZHEN ECHIEV AUTONOMOUS DRIVING TECH CO LTD

Organic carrier for silver paste and preparation method thereof as well as silver paste containing organic carrier and solar cell manufactured from silver paste

The invention discloses an organic carrier for conductive silver paste applied to a front face electrode and a grid line of a solar cell, a preparation method of the organic carrier, silver paste containing the organic carrier and a solar cell manufactured from the silver paste. The organic carrier comprises the following components in percentage by weight: 60-75 percent of solvent, 1-10 percent of thickener, 0.3-5 percent of thixotropic agent, 1-5 percent of surfactant and 10-30 percent of plasticizer. The preparation method of the organic carrier comprises the following steps of: weighing various raw materials; adding various aids into a solvent respectively; and heating and stirring until the aids are dissolved completely. The organic carrier has proper viscosity and a simple preparation process. Paste prepared from the organic carrier has proper viscosity, fineness, leveling property, thixotropy and chemical stability. After the paste is subjected to screen printing and sintering on a cell substrate, the thicknesses of a front face electrode and a grid line thick film of a cell panel can be over 20 micros, and the prepared electrode and the grid line thick film can obtain a higher height-width ratio.
Owner:湖南威能新材料科技有限公司

Two-dimensional code coding method, two-dimensional code decoding method and two-dimensional code print

ActiveCN104143109AHigh coding densityAdapt to the needs of different practical applicationsRecord carriers used with machinesSensing by electromagnetic radiationComputer hardwareCoding decoding
The invention discloses a two-dimensional code coding method, a two-dimensional code decoding method and a two-dimensional code print. The two-dimensional code coding method includes the steps that a coding mode of input data is determined; the input data are converted to data code word streams; the error correction level, the line number M and the column number N are determined; error correction code words are generated and added to the position behind the data code word streams; a horizontal cutting line and a vertical cutting line of a two-dimensional code are generated, and the area defined by an outer frame of the two-dimensional code is cut into coding area blocks through the horizontal cutting line and the vertical cutting line; data code words to which the error correction code words are added are added to the coding area blocks, The two-dimensional code decoding method includes the steps that the two-dimensional code is scanned and a binary image is generated; a boundary image is generated; a frame image is generated; the coordinates of the vertexes of the coding area blocks are distinguished; the data code word streams are obtained; error correction is conducted on decoding data code word streams; the data are restored. The two-dimensional code is printed on the print. According to the two-dimensional code coding method, the two-dimensional code decoding method and the two-dimensional code print, high coding density is achieved, the length-width ratio of the two-dimensional code can be adjusted by adjusting the line number and the column number of the two-dimensional code, and therefore the different requirements of practical application can be met.
Owner:SHENZHEN YLINK COMPUTING SYST

Closed hydrostatic slideway

The invention provides a closed hydrostatic slideway which comprises a base and a sliding block arranged on the base. The upper surface of the base is provided with a horizontal supporting slideway and a vertical supporting slideway in sequence from bottom to top; the sliding block is inlaid in a groove formed by the base, the horizontal supporting slideway and the vertical supporting slideway; a hydrostatic oil cavity is arranged between the upper surface of the sliding block and the lower surface of the vertical supporting slideway; a hydrostatic oil cavity is arranged between the lower surface of the sliding block and the upper surface of the base; and a hydrostatic oil cavity is arranged between the side surface of the sliding block and the side surface of the horizontal supporting slideway. In the closed hydrostatic slideway, a groove structure with a certain depth-to-width ratio is not adopted, and all main precision surfaces are all of a plane structure and can be ground, thereby reducing the processing difficulty of the slideway. Meanwhile, since the slideway and the base are both made of granite materials with good heat stability, the precision of the slideway is ensured. The straightness error of the closed hydrostatic slideway can be 0.1 mu m/100mm, and the rigidities of the slideway in horizontal and vertical directions are both larger than 10000N/mu m.
Owner:XI AN JIAOTONG UNIV +1
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