33results about How to "To achieve the purpose of tracking" patented technology

The invention relates to a welding track detection and control method of plate butt weld based on laser ranging, including the following steps: A. track detection is carried out; B. track identification and extraction are carried out; C. track control is carried out; D. the relative position relation between a welding gun and a welding seam is adjusted at last by performing mechanism actions. In the invention, the information of welding seam profile is obtained by transverse scanning of a laser sensor, and welding seam is rebuilt after effective wave filtering treatment to realize three-dimensional detection of the welding seam; simultaneously, the welding track curve is obtained by fit while detecting welding seam by using dynamic B spline fit algorithm, and the track control is carried out in combination with constant speed B spline track interpolation algorithm, thereby fundamentally solving the problem of track detection and control in automatic welding of plate butt weld. By using the method in the invention, the field test welding has welding profile identification precision of 0.15mm and welding track identification precision of 0.2mm, and the welding speed is more than four times of common manual welding.

The invention discloses a motor producing quality monitoring and managing system and a corresponding method. The system comprises a quality monitoring subsystem and a material circulating subsystem. The quality monitoring subsystem comprises a workshop control center, a master control center, a workshop electronic display board, producing lines and unit quality detecting points. The material circulating subsystem comprises turnover boxes of products in process on the producing lines, turnover boxes of qualified products of the detecting points and defective product turnover box. Batch processing of turnover boxes with pasted RFID electronic labels is used during the producing process, and products with the same model number in the same batch use the same turnover box. The RFID electronic labels on the turnover boxes at the working positions are read and written, so that production information of each procedure is recorded, and when product reject ratio exceeds an alarming value, alarming information is timely generated. After production, the producing record of a product of each model number of each worker during the producing process is analyzed, so that next production arrangement is helped to be optimized, productivity is arranged reasonably, and the fact that producing quality is improved stably is guaranteed.

The invention relates to a robust lane line detection method based on a dynamic region of interest, comprising the following steps: S10, initializing a dynamic region of interest of the lane; S20, dividing the lane line interested region in the current frame from near to far into a straight line identifying region and a curve identifying region; S30, pre-extracting that characteristic point of thelane line edge for the straight line recognition area and the curve recognition area, obtaining the straight line lane parameter of the straight line recognition area and the curve lane parameters ofthe curve recognition area through a fitting algorithm, and drawing a fitting lane line; S40, according to the fitting lane line parameters of the current frame, the dynamic region of interest DROI in the next frame image is predicted by using the Kalman filter. The invention is based on DROI, adopts RANSAC algorithm, can effectively extract lane line inner side edge information under complex working conditions, and the anti-jamming performance and accuracy of the method are obviously improved and improved. At the same time, the real-time and robust lane tracking can be realized by using Kalman prediction and inter-frame correlation constraint.

The invention discloses a navigation positioning method for a tour inspection robot of a transformer substation. The imaging positions of tracking navigation lamps in an infrared thermal imager are detected, so that the moving direction of a trolley is determined, and the aim of tracking is fulfilled; in order to position the robot in a moving process, a cradle head is horizontally rotated until an image of a positioning navigation lamp in the infrared thermal imager is in the center, the distance to the next fixed point is calculated according to the horizontal rotating angle of the cradle head and the moving distance of the trolley is calculated according to the sizes of images of the tracking navigation lamps in the infrared thermal imager, so that the aim of positioning is fulfilled.

The invention discloses a transformer substation complex environment cross-field-of-view target tracking method based on a three-dimensional digital model. The technical scheme is that monitoring cameras are arranged in the area of a transformer substation requiring monitoring in a spaced way, the adjacent monitoring cameras photograph the position and the state of work personnel and maintenance equipment in a cross way, a nonlinear system is linearized by using extended Kalman filtering through Taylor series, and the original system model is converted into a station equation and an observation equation expressed in the form of error under the condition of neglecting high-order error; and the motion equation of the moving target is constructed under a transformer substation three-dimensional coordinate system by using a second-order kinetic model, multiple monitoring cameras are utilized to perform initial positioning and the result acts as the initial value of EKF tracking after the target is monitored for the first time, then the detection value of the corresponding image space target is utilized to convert the position error of the three-dimensional coordinates and substitute inthe state equation for iteration, and the filter estimates the position of the target in case of temporarily removing out of the field of view of the target or switching of the field of view so thathigh tracking precision can be acquired.

The invention discloses a chiral-acid/alkali-stimulation-responsive difunctional fluorescence molecular initiator, and a preparation method and application thereof. The structure of the initiator is disclosed as the following general formula. The chiral center and chromophore are introduced into the initiator; the initiator can perform hybrid polymerization on isonitrile and lactide or epsilon-caprolactone monomers by a one-pot process, has the advantages of favorable self-sorting polymerizing power and high stability, and can be used for active/controllable polymerization of isonitrile, lactide, epsilon-caprolactone and other monomers; and the obtained polyisonitrile, polylactide homopolymer and block copolymers thereof have controllable molecular weight and narrow molecular weight distribution.

The invention discloses a crankshaft follow-up grinding online measuring instrument which comprises a measuring instrument base. A swing arm support is borne on the measuring instrument base in a sliding manner. A measuring swing arm is hinged to the swing arm support. A swing arm oil cylinder is connected between the top end of the oil cylinder support and the measuring swing arm. A center fixed gear is fixedly arranged at the stretching end of the measuring swing arm, a following swing frame is further mounted on the stretching end of the measuring swing arm, and a planet swing gear mounted at the output shaft end of a following swing motor is engaged with the center fixed gear. A measuring tool support is fixedly mounted on a measuring tool following swing arm, two measuring clamping blocks and a displacement sensor are mounted on the measuring tool support, the two measuring clamping blocks are located on two inclined face of a V-shaped base level correspondingly, the displacement sensor is located on the symmetric line of the V-shaped base level, and the inclined included angle alpha of the V-shaped base level is equal to 68 degrees to 72 degrees. The crankshaft follow-up grinding online measuring instrument can achieve real-time online measurement and is high in detecting sensitivity and machining precision.

The invention discloses an intraocular pressure tracking measuring instrument which can reduce harm to eyeballs and is convenient to use. The intraocular pressure tracking measuring instrument comprises an eyeshade body and one or two probe assemblies which are fixedly arranged on the eyeshade body and correspond to eyes of a subject, a inflatable air bag is arranged in the eyeshade body, at leastpart material of the eyeshade body is a flexible material to deform after the air bag is inflated so as to allow the air bag to push the one or two probe assemblies to move to exert pressure to eyeballs, and each probe assembly comprises an ultrasonic sensor for detecting whether tops of the eyeballs are pressed to be flat and a pressure sensor connected with the ultrasonic sensor.

The invention discloses a door access identity tracking method and device, an identifying and tracking system and a door access system. The method is used for tracking at least one person passing the door access system and includes: receiving the human face feature information of all people at the entrance of the door access system, and comparing the human face feature information with human face samples in a human face feature information library to judge the identity legitimacy of the people at the entrance of the door access system and generate corresponding identification marks; correspondingly binding the identification marks to the people at the entrance of the door access system according to the human face feature information; tracking the positions of the people according to the tracking algorithm of features; outputting the identification marks and real-time position information of the people. By the method, the identification marks, which can be displayed, of illegal and legal people can move along with the people, and identity tracking can be achieved.

Disclosed is a guardrail plate automatically welding device. The guardrail plate automatically welding device comprises a pressing wheel, a wheel seat, a jacking device and a displacement sensor. The wheel seat is provided with the pressing wheel; the jacking device comprises an oil cylinder or steam cylinder; the bottom of the wheel seat is connected with the jacking device; the displacement sensor is connected with the piston of the oil cylinder or steam cylinder or the wheel seat. According to the guardrail plate automatically welding device, force exerted on the pressing wheel by the oil cylinder or steam cylinder can keep the same, so that pressure between the pressing wheel and a ring piece has no significant change, the problem that the quality of the ring piece is affected by overhigh pressure of the pressing wheel can be voided; the displacement of the pressing wheel can be obtained through accurate measurement of an encoder, so that the measuring precision can be effectively improved, and errors can be effectively reduced.

The embodiment of the invention discloses an information transmission tracking method. The method comprises steps: based on first address information acquired by user equipment, first unique identification code information for characterizing a transmission identification code of the first information is acquired, wherein the first information is the information acquired by the user equipment via the acquired address information; and according to the first unique identification code information, first group user information formed by other user equipment except the user equipment corresponding to the first information is acquired, and an information transmission trajectory based on the first information is acquired. The embodiment of the invention also discloses an information transmission tracking device.

The invention discloses an infrared ship video tracking method based on a convolutional neural network, and the method improves the model recognition efficiency through fusing three to five layers of a SiamRPN feature extraction network to increase the spatial information of output features. A spatial transformation network composed of a positioning network, a grid generator and a sampler is added to a search branch so as to rotate and zoom the feature map, and the influence of target rotation and zoom on the recognition rate is reduced. In addition, aiming at the problem of lack of an infrared ship video tracking data set, the invention also constructs a data set containing 3000 infrared ship target images. According to the method, more accurate infrared target features are extracted through the multi-layer fusion network and the spatial change network, so that the tracking accuracy is improved; the method is high in operability and expandability and suitable for infrared ship target tracking of the sea surface background.

The invention provides a device and method for automatically identifying a wafer iron gridiron and reading an ID, the device comprises an automatic code scanning device and a sorting machine upper computer system, the automatic code scanning device is arranged on a wafer loading and unloading machine and used for reading the ID of the wafer iron gridiron arranged on a wafer loading and unloading machine panel and sending the ID to the sorting machine upper computer system, the upper computer system of the sorting machine automatically identifies whether the iron gridiron is placed on the current wafer loading and unloading machine according to the ID information sent by the automatic code scanning device, judges the size of the current iron gridiron and reports the ID information of the iron gridiron, so that the purpose of wafer tracking is achieved. The problem of automatic identification of the iron gridiron in a semiconductor customer factory is solved, automation is realized on the basis of the original process which cannot be used for automation, the labor cost of customers is reduced, the wafer breakage rate caused by human errors is reduced, and the compatibility of automatic wafer boat identification of the wafer loading and unloading machine is improved.

The invention relates to a data processing method and system, belongs to the technical field of telecommunication data processing, in particular to the telecommunication grid data processing method and system. The method and system take data mining as the core, provide analysis of operation decision and prediction, provide intelligence for management, achieve a 'flattening' management mode for operation to solve a management timeliness problem, meet functions of grid clustering, grid label reference value signing, grid sign post management, grid marketing timing management and the like, and achieve the purpose of displaying and tracking object completion situation.

The invention discloses a human eye tracking visual system, which belongs to the technical field of communication and comprises a light source, a controller and a power supply, An image of an object shot by the camera is focused through a lens, charges of a corresponding proportion are accumulated according to the intensity of light, the charges accumulated by all pixels are subjected to video shift, and video signal output is formed after filtering and amplification processing; And system software of the computer adopts a LabVIEW 8.5 platform, and visual auxiliary software MAX and Vision Asset 8.5 software are used as assistance. The human-computer interaction platform has the advantages that the machine vision technology and the virtual instrument are combined to build the human-computerinteraction platform which is simple and effective in human eye tracking. According to the invention, the machine vision technology and the virtual instrument are applied to human eye tracking at lowcost.