Abstract: Disclosed is an intelligent micromanipulation system based on machine vision, including a base, wherein a microscope, a rotating table and two lifting tables are arranged on the base, the microscope is located right above the rotating table, the two lifting tables are arranged at two sides of the rotating table, respectively, and each is provided with a mechanical arm, each of the two manipulators is provided with an end effector, the mechanical arm is capable of driving the corresponding end effector to perform fine adjustment in x, y and z directions, one of the end effectors clamps a suction holding needle in communication with a suction pump, while the other end effector clamps an injection needle in communication with an injection pump; and the rotating table includes a tray, a rotating mechanism and a driving device, and the driving device drives the tray to rotate via the rotating mechanism.

Abstract: The present invention provides an ultra-microinjection detection and control device based on lensless imaging and a method thereof. A lensless optical liquid level sensor is used to measure a change of a liquid level in an injection needle. A microinjection control unit is used to track the change of the liquid level and correct an injection pressure of the injection pump. Transmitted light generated by a parallel light source passes through a transparent glass tube of the injection needle. Then the transmitted light passes through a light filtering film to reduce the intensity of the parallel light source to a photosensitivity range of a micro linear array image sensor chip. Finally, the transmitted light enters the micro linear array image sensor chip, so that the micro linear array image sensor chip measures the change of the liquid level in the injection needle.

Abstract: The present disclosure relates to a visual servoing method based on fusion of distance space and image feature space. The method includes: constructing an image Jacobian matrix; constructing a depth Jacobian matrix; fusing the image Jacobian matrix and the depth Jacobian matrix, to obtain a hybrid visual servoing Jacobian matrix; and obtaining a robot motion control amount according to the hybrid visual servoing Jacobian matrix by using a control algorithm, to enable a robot to move to a target position, to complete precise positioning.

Abstract: The present disclosure relates to an indoor monocular navigation method based on cross-sensor transfer learning and a system thereof. Determining an preliminary autonomous navigation model according to simulated laser radar data; acquiring actual single-line laser radar data and monocular camera data of the mobile robot simultaneously in an actual environment; determining the heading angle of the mobile robot according to the actual laser radar data; determining a laser radar monocular vision navigation model, according to the generated heading angle of the mobile robot and the monocular camera data at a the same moment and by using a Resnet18 network and a pre-trained YOLO v3 network; determining a heading angle of the mobile robot at the current moment, according to the acquired monocular camera data and by using the laser radar monocular vision navigation model; performing navigation of the mobile robot.

Abstract: Provided is the use of as SUMF2 gene therapy target for preventing and/or treating an allergic asthma attack and reducing airway hyperresponsiveness. It is verified that the abnormal metabolic pathway of SUMF1/GAG causes epithelial cells to produce a similar immune memory and the epithelial cells can promote TH2 response when exposed to allergens again. In the present disclosure, SUMF2 gene in airway epithelial cells from a mouse is overexpressed using the adeno-associated virus vector 20 days before the induction of asthma. Compared with a control group, the present disclosure can significantly improve the lung airway inflammation in an asthmatic mouse. Therefore, the overexpression of SUMF2 can be used as a gene therapy target to prevent allergic asthma and reduce airway hyperresponsiveness. Therefore, the use of an adeno-associated virus to overexpress SUMF2 for the prevention of allergic asthma has broad use values and market prospects.

Abstract: The present invention relates to an indoor monocular navigation method based on cross-sensor transfer learning and a system thereof. Determining an preliminary autonomous navigation model according to simulated laser radar data; acquiring actual single-line laser radar data and monocular camera data of the mobile robot simultaneously in an actual environment; determining the heading angle of the mobile robot according to the actual laser radar data; determining a laser radar monocular vision navigation model, according to the generated heading angle of the mobile robot and the monocular camera data at a the same moment and by using a Resnet18 network and a pre-trained YOLO v3 network; determining a heading angle of the mobile robot at the current moment, according to the acquired monocular camera data and by using the laser radar monocular vision navigation model; performing navigation of the mobile robot.

Abstract: Disclosed is an intelligent micromanipulation system based on machine vision, including a base, wherein a microscope, a rotating table and two lifting tables are arranged on the base, the microscope is located right above the rotating table, the two lifting tables are arranged at two sides of the rotating table, respectively, and each is provided with a mechanical arm, each of the two manipulators is provided with an end effector, the mechanical arm is capable of driving the corresponding end effector to perform fine adjustment in x, y and z directions, one of the end effectors clamps a suction holding needle in communication with a suction pump, while the other end effector clamps an injection needle in communication with an injection pump; and the rotating table includes a tray, a rotating mechanism and a driving device, and the driving device drives the tray to rotate via the rotating mechanism.

Abstract: The present disclosure relates to a visual servoing method based on fusion of distance space and image feature space. The method includes: constructing an image Jacobian matrix; constructing a depth Jacobian matrix; fusing the image Jacobian matrix and the depth Jacobian matrix, to obtain a hybrid visual servoing Jacobian matrix; and obtaining a robot motion control amount according to the hybrid visual servoing Jacobian matrix by using a control algorithm, to enable a robot to move to a target position, to complete precise positioning.

Abstract: An adaptive automobile meter detection method based on character segmentation cascade classifier which processes threshold segmentation, morphology and connected components analysis on the original image; extracts the pointer based on the contour analysis method, establishes a pointer information list; constructs a character segmentation cascade classifier by combining a HOG/SVM character segmentation classifier, a character filter and a CNN digit classifier. The character segmentation cascade classifiers is used to identify the digit character area of the automobile meter. Region analysis is performed to extract tick marks based on the center of the digit character area. The angular position corresponding to the tick mark is determined. The response value corresponding to the pointer is determined by establishing the Newton interpolation linear description relationship between the pointer angle and the response value and then the meter is classified as pass or fail.

Abstract: The present invention provides an ultra-microinjection detection and control device based on lensless imaging and a method thereof. A lensless optical liquid level sensor is used to measure a change of a liquid level in an injection needle. A microinjection control unit is used to track the change of the liquid level and correct an injection pressure of the injection pump. Transmitted light generated by a parallel light source passes through a transparent glass tube of the injection needle. Then the transmitted light passes through a light filtering film to reduce the intensity of the parallel light source to a photosensitivity range of a micro linear array image sensor chip. Finally, the transmitted light enters the micro linear array image sensor chip, so that the micro linear array image sensor chip measures the change of the liquid level in the injection needle.

Abstract: An optimization approach for placement heads tasks assignment of beam-type single-gantry surface mounter is disclosed, building a comprehensive framework that simultaneously achieves all optimization objectives in reasonably short time. Specific steps are as follows: (a) importing user-defined production parameters and forming raw production data, (b) pre-processing the raw production data and obtaining the intermediate production data that facilitates the subsequent processing, (c) verifying the loop condition of the “placement heads tasks assignment”, (d) performing nozzle assignment, (e) confirming all the nozzle assignment exchange possibilities, (f) verifying whether the loop condition of “component allocation” are fulfilled, (g) performing component allocation, and (h) outputting the optimal placement heads tasks assignment results.

Abstract: A positioning method of rectangular pin element based on vertex points includes the steps of: obtaining component information and classifying components of a model into two classes; extracting feature descriptors of each vertex point of pin element of the model; obtaining a real image of the component and extracting feature points and an angle between two straight lines where the feature points are located and the positive direction of the X-axis respectively; obtaining a rotation angle and an precise feature point position; determining an precise feature point position corresponding to all the vertex points; obtaining feature descriptor of the vertex points of the actual component pin, a weight value of the vertex points of the component in the model, the vertex points of the actual component corresponding to feature point; and determining the final position of the center of the chip and a precise rotation angle of the chip.

Abstract: The present application relates to a method for selecting a wave height threshold, based on a target location, original wave height samples are acquired, and a wave height threshold interval are obtained; combined with wave height threshold and based on GPD and specified return period, a design wave height Hsi,j corresponding to each threshold within the wave height threshold interval is calculated according to the sample wave height values which are greater that the threshold; a difference is calculated to obtain a stable threshold interval, and a threshold within the stable threshold interval is selected as a reasonable threshold for design wave height estimation. In this method, the stability of estimated values can be determined directly and objectively to realize wave height threshold selection.

Abstract: An optimization approach for placement heads tasks assignment of beam-type single-gantry surface mounter is disclosed, building a comprehensive framework that simultaneously achieves all optimization objectives in reasonably short time. Specific steps are as follows: (a) importing user-defined production parameters and forming raw production data, (b) pre-processing the raw production data and obtaining the intermediate production data that facilitates the subsequent processing, (c) verifying the loop condition of the “placement heads tasks assignment”, (d) performing nozzle assignment, (e) confirming all the nozzle assignment exchange possibilities, (f) verifying whether the loop condition of “component allocation” are fulfilled, (g) performing component allocation, and (h) outputting the optimal placement heads tasks assignment results.

Abstract: The present application relates to a method for selecting a wave height threshold, based on a target location, original wave height samples are acquired, and a wave height threshold interval are obtained; combined with wave height threshold and based on GPD and specified return period, a design wave height Hsi,j corresponding to each threshold within the wave height threshold interval is calculated according to the sample wave height values which are greater that the threshold; a difference is calculated to obtain a stable threshold interval, and a threshold within the stable threshold interval is selected as a reasonable threshold for design wave height estimation. In this method, the stability of estimated values can be determined directly and objectively to realize wave height threshold selection.

Abstract: A positioning method of rectangular pin element based on vertex points. The positioning method of rectangular pin element of the present invention solves the problems of weak robustness, low precision, poor versatility and low real-time performance of the on-line positioning algorithm of the patch-type rectangular lead component.

Abstract: An adaptive automobile meter detection method based on character segmentation cascade classifier which processes threshold segmentation, morphology and connected components analysis on the original image; extracts the pointer based on the contour analysis method, establishes a pointer information list; constructs a character segmentation cascade classifier by combining a HOG/SVM character segmentation classifier, a character filter and a CNN digit classifier. The character segmentation cascade classifiers is used to identify the digit character area of the automobile meter. Region analysis is performed to extract tick marks based on the center of the digit character area. The angular position corresponding to the tick mark is determined. The response value corresponding to the pointer is determined by establishing the Newton interpolation linear description relationship between the pointer angle and the response value and then the meter is classified as pass or fail.

Abstract: A multi-type BGA chip visual recognition method using line based clustering to solve the problems of BGA inspection algorithms which have limited applicability, low flexibility caused by template matching, poor robustness to illumination and interferences and high time complexity.

Abstract: A multi-type BGA chip visual recognition method using line based clustering to solve the problems of BGA inspection algorithms which have limited applicability, low flexibility caused by template matching, poor robustness to illumination and interferences and high time complexity.