37 results about "Corner detector" patented technology

The method operates by estimating the differential movement of the scene picked up by a vertically-oriented camera. Estimation includes periodically and continuously updating a multiresolution representation of the pyramid of images type modeling a given picked-up image of the scene at different, successively-decreasing resolutions. For each new picked-up image, an iterative algorithm of the optical flow type is applied to said representation. The method also provides responding to the data produced by the optical-flow algorithm to obtain at least one texturing parameter representative of the level of microcontrasts in the picked-up scene and obtaining an approximation of the speed, to which parameters a battery of predetermined criteria are subsequently applied. If the battery of criteria is satisfied, then the system switches from the optical-flow algorithm to an algorithm of the corner detector type.

The invention refers to a method for assessing the horizontal speed of a drone, particularly of a drone capable of hovering on automatic pilot. The method operates by estimating the differential movement of the scene picked up by a vertically-oriented camera. Estimation includes periodically and continuously updating a multiresolution representation of the pyramid of images type modeling a given picked-up image of the scene at different, successively-decreasing resolutions. For each new picked-up image, an iterative algorithm of the optical flow type is applied to said representation. The method also provides responding to the data produced by the optical-flow algorithm to obtain at least one texturing parameter representative of the level of microcontrasts in the picked-up scene and obtaining an approximation of the speed, to which parameters a battery of predetermined criteria are subsequently applied. If the battery of criteria is satisfied, then the system switches from the optical-flow algorithm to an algorithm of the corner detector type.

The method operates by estimating the differential movement of the scene picked up by a vertically-oriented camera. Estimation includes periodically and continuously updating a multiresolution representation of the pyramid of images type modeling a given picked-up image of the scene at different, successively-decreasing resolutions. For each new picked-up image, an iterative algorithm of the optical flow type is applied to said representation. The method also provides responding to the data produced by the optical-flow algorithm to obtain at least one texturing parameter representative of the level of microcontrasts in the picked-up scene and obtaining an approximation of the speed, to which parameters a battery of predetermined criteria are subsequently applied. If the battery of criteria is satisfied, then the system switches from the optical-flow algorithm to an algorithm of the corner detector type.

The invention discloses a remote sensing image port ship detection method capable of multi-resolution hierarchical screening. For a ship in a port in a large-size high-resolution optical remote sensing image, a coarse-to-fine method is adopted for processing the image, a sudden anomaly detection method is combined with a Harris corner detector (Harris Corner Detector) detection method, and the efficient ship-in-port detection method is established. The remote sensing image port ship detection method comprises the steps of: firstly, carrying out sudden anomaly and multi-angle rotational sudden anomaly detection on a sampled image of the large-size image, judging suspected ship areas obtained by adopting the two methods, and subjecting the judging results to regional expansion to obtain a suspected salient region of a port region; and secondly, extracting the suspected salient region in the image at the original resolution, carrying out sudden anomaly and multi-angle rotational sudden anomaly detection on the suspected salient region at the original resolution, detecting bow features of a suspected ship obtained by adopting the two detection methods by using the Harris corner detector method, returning ship coordinates obtained through detection to the original high-definition image for marking, and finally acquiring a ship mark in the original high-definition image.

A directional anti-aliasing filter circuit includes an input node and an output node, a directional anti-aliasing filter having an input coupled to the input node, an adaptive gain control having an input coupled to an output of the directional anti-aliasing filter, a summer having a first input coupled to an output of the adaptive gain control, a second input coupled to the input node, and an output coupled to the output node, a texture detector for providing a texture adjust signal to the directional anti-aliasing filter and a texture adaptive gain signal to the adaptive gain control, an edge detector for providing an edge direction signal to the directional anti-aliasing filter, and a corner detector for providing a corner adaptive gain signal to the adaptive gain control.

A calibration device of rotary angle detector for calibrating the operating force of vehicle steering wheel is composed of rotary angle calibration mechanism set on box shaped shell, locking unit and operating force calibration mechanism set on bottom of said shell, XSN series intelligent counter connected to signal of photoelectric coder on rotary angle calibration mechanism and XST series single input channel intelligent instrument connected to signal of force measuring transducer on operating force calibration mechanism.

The invention relates to a fisheye image correction method of a vehicle panoramic display system based on a unit square. The fisheye image correction method comprises the following steps: selecting a rectangular region A needing to be corrected in a certain direction of a vehicle according to panoramic display requirements; determining and correcting the size of the unit square needing to be used according to the size of the region A; putting a unit square combined frame into the region A; carrying out corner extraction on a fisheye image comprising n integrated unit squares by using a Harris corner detector; encoding each corner and recording the coordinate of each corner in the fisheye image; correcting each unit square in the region A of the image by using four corner coordinates of each unit square in the fisheye image and geometric constraints of the squares; and carrying out interpolation operation on non-integral points in a correction process by using a bilinear interpolation method to finally obtain a corrected image of the integral region A in the certain direction of the vehicle. The method is simple to realize, has low requirements on a processor, and has very strong commonality and instantaneity.

A directional anti-aliasing filter circuit includes an input node and an output node, a directional anti-aliasing filter having an input coupled to the input node, an adaptive gain control having an input coupled to an output of the directional anti-aliasing filter, a summer having a first input coupled to an output of the adaptive gain control, a second input coupled to the input node, and an output coupled to the output node, a texture detector for providing a texture adjust signal to the directional anti-aliasing filter and a texture adaptive gain signal to the adaptive gain control, an edge detector for providing an edge direction signal to the directional anti-aliasing filter, and a corner detector for providing a corner adaptive gain signal to the adaptive gain control.

The invention discloses an image contour corner detection method based on centroid distance calculation. An Euclidean distance positioning angular point area of each image contour point and a local area centroid formed by the image contour point is calculated; the method comprises the following specific steps: firstly, an edge contour is extracted, and the Euclidean distance between each pixel point of the image contour and the center of mass of a local region formed by the pixel point is calculated so that a distance set G is formed, upper and lower limit threshold processing and point numberthreshold processing are conducted on the G to form a set I, finally, a Harris angular corner detector is applied to each point in each element in the set I to calculate a response, and the coordinate of the corresponding point with the strongest response in each element is the angular corner. According to the invention, the Euclidean distance between each image contour point and the centroid ofthe local area formed by the image contour point is calculated to locate the angular point area; the calculation result is slightly influenced by the change of the image gray scale, the immunity to noise is enhanced, the generation of pseudo corners is reduced, and the method is suitable for the computer vision fields of image registration and matching, image fusion, target recognition and the like.

The invention discloses an intelligent motor vehicle running state and driver driving data integrated management system. The motor vehicle running state and driver driving data integrated management system comprises an IC card, a physiological data identifier, a card reader, a speed detector, a time manager, a braking detector, a central processor, a data export device, a display, a direction and corner detector, a distance detector, a data memory and a control switch, wherein the IC card is inserted into the card reader; the central processor is connected with the physiological data identifier, the card reader, the speed detector, the time manager, the braking detector, the direction and corner detector and the distance detector, and is further connected with the display and the data memory; the data export device is arranged on the central processor; and the control switch used for outputting a signal to control a motor vehicle is further arranged on the central processor. The intelligent motor vehicle running state and driver driving data integrated management system can be used for efficiently managing motor vehicles and drivers.

The invention discloses a packaged chip defect intelligent detection device, which comprises a chip pin defect detection device, the chip pin defect detection device mainly comprises an operation table, a transmission machine, a pin form detector, a pin power-on detector, an appearance image detector and a defective product rejection mechanism, the transmission machine is installed on the operation table, and the transmission machine is installed on the operation table. The pin shape detectors are installed on the operation table and located over the conveyor, each pin shape detector is composed of a first machine body shell, two pin corner detectors and a sprayer, the two pin corner detectors are symmetrically installed in the first machine body shell, and the sprayers are located on the back face of the first machine body shell. According to the equipment specially designed for detecting the defects of the pins of the packaged chip, the detection equipment adopts an automatic conveying and three-stage detection mode, and the physical form, the power-on condition and the image information of the pins can be obtained.

A robot comprises a base, a first-stage slope trunk, a second-stage slope trunk, a third-stage slope trunk and a robot head. The robot head is located on a third-stage rotary top disc. A top disc of the first-stage slope trunk, a top disc of the second-stage slope trunk and the top disc of the third-stage slope trunk are all orbicular, and the diameters of all stages of top discs are gradually decreased from bottom to top. Any two stages of trunks can rotate by 360 degrees relatively. Corner detectors of all stages of trunks are arranged and used for transmitting a detection signal to a main controller. The main controller is further connected with a third-stage motor, a second-stage motor, a first-stage motor and a base motor in a controlling mode. The body language actions of the robot are smooth and high in amplitude, the structure is simple, and control is convenient.

The present invention discloses a circuit used for indicating process corner and extreme temperature. It mainly comprises a proportional to absolute temperature (PTAT) current source, a negative to absolute temperature (NTAT) current source, a constant to absolute temperature (CTAT) current source, a corner detector, a poly detector, an extreme temperature detector. The circuit can save more power consumption without trade-off. In debug phase, the suspect sample can read out which state is and can run simulation check quickly to identify the real problem. In production phase, process indicator can easy read out at CP station. In the mean time, the large quantity of data can be easy collected and analyzed.

A robot comprises a base, a first-stage slope trunk, a second-stage slope trunk, a third-stage slope trunk and a robot head. The robot head is located on a third-stage rotary top disc. A top disc of the first-stage slope trunk, a top disc of the second-stage slope trunk and the top disc of the third-stage slope trunk are all orbicular, and the diameters of all stages of top discs are gradually decreased from bottom to top. Any two stages of trunks can rotate by 360 degrees relatively. Corner detectors of all stages of trunks are arranged and used for transmitting a detection signal to a main controller. The main controller is further connected with a third-stage motor, a second-stage motor, a first-stage motor and a base motor in a controlling mode. The body language actions of the robot are smooth and high in amplitude, the structure is simple, and control is convenient.

The image signal generating apparatus for a liquid crystal display element. A corner detector detects, when an input image signal contains multiple frame images each of which includes a first image area having a first tone and including a corner portion and a second image area having a second tone higher than the first tone and being adjacent in vertical, horizontal and oblique directions to the corner portion, the corner portion in each frame image, a tone provider generates an output image signal by providing a third tone lower than the second tone to one specific pixel adjacent in the oblique direction to a vertex of the corner portion in at least one of the multiple frame images. The tone provider provides the third tone to the specific pixel when the input image signal is a moving image signal.

The invention relates to a ray detection apparatus and a corner detector assembly thereof. The corner detector assembly comprises a corner base and a corner detector; the corner base is used for beingarranged at the inner side corner of a detector array; the inner side corner is formed by the ends, close to each other, of the transverse arm detector array and the longitudinal arm detector array;and the corner detector is mounted on the corner base and forms a corner detector array, and the corner detector array is used for filling a detection missing area between the transverse arm detectorarray and the longitudinal arm detector array, so that complete imaging at the inner side corner is obtained. According to the scheme, the problems of large mounting space requirement and inconvenience in mounting and maintenance due to the fact that corners of the vertical detection arm and the transverse detection arm of existing ray detection equipment need to be overlapped are solved.

The invention discloses a winding machine blanking visual detection method. The method comprises the following steps of S1, acquiring a gray level image of the surface of a part at a blanking port of a winding machine, and transmitting an image signal to an image preprocessing module; S2, processing noise and distortion contained in the image signal by adopting a Gaussian smooth filtering method, inhibiting unnecessary deformation and enhancing image features; S3, using a Canny algorithm to carry out contour extraction on a part needing to be detected; S4, segmenting the image signal into fine paragraphs, then respectively measuring the paragraphs, and carrying out corner detection on the image signal through a KD corner detector; and S5, converting the actual curve segment of the image plane into a specific geometric parameter, and comparing the converted geometric parameter with the actual geometric parameter of the part so as to judge whether the part is qualified or not. The method is advantaged in that not only is a problem of universality solved, but also respective measurement of a plurality of quantities is realized at the same time.

A transmission controller includes: a corner detector that detects a corner; a predictor to predict a rolling amount based upon road data when the corner is detected and an accelerator opening degree is fully closed; a device to determine a first necessary engine braking amount in accordance with the rolling amount; a device to determine a first required speed change stage corresponding to the first necessary engine braking amount; a calculator to calculate a second necessary engine braking amount when the corner is detected and the accelerator opening degree is fully closed based upon a minimum required inter-vehicle distance with the vehicle ahead; a device to determine a second required speed change stage corresponding to the second engine braking amount; and a transmission controller to select, as a target speed change stage, either smaller one of the first or second required speed change stage, and then perform downshift control.

A transmission controller includes: a corner detector that detects a corner; a predictor to predict a rolling amount based upon road data when the corner is detected and an accelerator opening degree is fully closed; a device to determine a first necessary engine braking amount in accordance with the rolling amount; a device to determine a first required speed change stage corresponding to the first necessary engine braking amount; a calculator to calculate a second necessary engine braking amount when the corner is detected and the accelerator opening degree is fully closed based upon a minimum required inter-vehicle distance with the vehicle ahead; a device to determine a second required speed change stage corresponding to the second engine braking amount; and a transmission controller to select, as a target speed change stage, either smaller one of the first or second required speed change stage, and then perform downshift control.

An image forming apparatus includes: an image former that forms a document image including a correction image; an image reader; and a calibrator, and performing correction, wherein the document image is designed so that main register marks and a subsidiary register mark are provided, and the calibrator includes a four-corner detector that detects four corners of a sheet of paper, a main register mark reference position detector that detects reference positions of the main register marks, a subsidiary register mark prediction position determiner that predicts and determines prediction positions of the subsidiary register marks, a subsidiary register mark reference position detector that detects a reference position of the subsidiary register mark, a correction image prediction position determiner that predicts and determines a prediction position of the correction image, a measured value obtainer, and a correction value calculator.

A monitoring apparatus and method for measuring light output gradient of a faceplate panel includes a top plate having a center detector and a plurality of corner detectors mounted along a major surface thereof. Lenses are optically coupled to a respective detector, and radiometers are electrically coupled to a respective detector. A bottom plate spaced apart from the top plate has a plurality of light outputs mounted along a major surface thereof and positioned to be opposite each detector. A light source is optically coupled to each light output through a splitter. A computer is electrically coupled to the light source for receiving feedback therefrom and for controlling the light source. The computer is also electrically coupled to each radiometer for recording data therefrom.During monitoring, a faceplate panel having a matrix applied thereto is accurately positioned between the top and bottom plates such that the center detector is located approximately above the center of the faceplate panel. Light is passed from the light sources through the faceplate panel to the detectors under control of the computer. The light output measurements at each detector are recorded by the computer and calculation is made of a light output gradient based upon a comparison of the light output at the center detector to the light output at the corner detector.

A circuit used for indicating process corner and extreme temperature mainly comprises a proportional to absolute temperature (PTAT) current source, a negative to absolute temperature (NTAT) current source, a constant to absolute temperature (CTAT) current source, a corner detector, a poly detector, an extreme temperature detector. The circuit can improve more power consumption without trade-off. In debug phase, the circuit can read out a state of a suspect sample and can run simulation check quickly to identify the real problem. In production phase, the circuit can easily read out at a processing station. In the mean time, a large quantity of data can be easily collected and analyzed.

The invention provides an effective map merging method based on context description conforming to corresponding extension, and relates to the technical field of mobile robots, navigation positioning and computer vision. The context-based effective map merging method with description conforming to corresponding extension is divided into four parts: 1) detecting points of interest for each grid map by a Harr i s corner detector; 2) calculating a context-based descriptor (sigma, N, D) of the interest point f and establishing an original matching pair, wherein (sigma, N, D) respectively represents a proportional radius, a vector based on a feature value and a matrix based on a feature vector; 3) designing matching pair expansion based on scale proportion, and expanding each original matching pair into a feature matching set for estimating an affine transformation; and 4) defining a measurement function to confirm optimal similarity conversion, and refining through an STr I CP algorithm to realize accurate grid map merging. The problem that an existing single robot is only suitable for building small and medium-sized environment maps is solved.

A calibration device of rotary angle detector for calibrating the operating force of vehicle steering wheel is composed of rotary angle calibration mechanism set on box shaped shell, locking unit and operating force calibration mechanism set on bottom of said shell, XSN series intelligent counter connected to signal of photoelectric coder on rotary angle calibration mechanism and XST series single input channel intelligent instrument connected to signal of force measuring transducer on operating force calibration mechanism.

The invention belongs to the technical fields of image enhancement and feature detection and particularly relates to a camera calibration relevant technology in the three-dimensional measurement field. A sub-pixel checkerboard corner detection method based on color constancy comprises the steps that a, a Harris corner detector with color constancy is proposed; and b, the sub-pixel precision cornerdetection method with illumination and color offset invariance is proposed. By the adoption of the technical characteristics, almost identical pixel precision corner positions can be obtained relative to illumination and color changes.

An image forming apparatus includes: an image former that forms a document image including a correction image; an image reader; and a calibrator, and performing correction, wherein the document image is designed so that main register marks and a subsidiary register mark are provided, and the calibrator includes a four-corner detector that detects four corners of a sheet of paper, a main register mark reference position detector that detects reference positions of the main register marks, a subsidiary register mark prediction position determiner that predicts and determines prediction positions of the subsidiary register marks, a subsidiary register mark reference position detector that detects a reference position of the subsidiary register mark, a correction image prediction position determiner that predicts and determines a prediction position of the correction image, a measured value obtainer, and a correction value calculator.

The invention discloses an intelligent type turnover plate type dual-layer dust discharge valve which comprises an upper valve body, a lower valve body and a middle box body. An upper valve plate is installed in the upper valve body, one side of the upper valve plate is provided with a sealing plate, a first driving device is installed inside the upper valve body, the output end of the first driving device is connected with a valve plate driving main shaft, the bottom of the upper valve body is provided with the middle box body, the bottom of the middle box body is provided with a lower valvebody, a conveying channel is installed between the lower valve body and the middle box body, the upper valve plate and a lower valve plate are independently driven and controlled, system air leakage is reduced, the turnover type valve plates have no impact on a sealing base under a speed-adjustable driving device, the axial torsion of the driving shaft is greatly reduced, the service life is long,a driver can be in three modes of a speed-adjustable gear motor, an electro-hydraulic corner detector and a pneumatic executor, and the driving mode meets on-site working conditions.

The invention discloses an image contour corner point detection method based on centroid distance calculation. The corner point area is located by calculating the Euclidean distance between each image contour point and the centroid of the local area formed by it. The specific steps are as follows: first read the image, and extract the edge Contour, calculate the Euclidean distance between each pixel of the image contour and the centroid of the local area formed to form a distance set G, use upper and lower limit threshold processing and point threshold processing on G to form a set I, and finally for each element in I Each point applies the Harris corner detector to calculate the response, and the coordinates of the corresponding point with the strongest response in each element are the corner points. The present invention locates the corner area by calculating the Euclidean distance between each image contour point and the centroid of the local area formed, and the calculation result is less affected by the gray scale change of the image, which strengthens the immunity to noise and reduces the generation of false corner points. This method is suitable for computer vision fields such as image registration and matching, image fusion and object recognition.