30 results about "Global vision" patented technology

The invention relates to a global measurement method for a large field of view using a coordinate tracking control board, belonging to the field of visual measurement, and relates to a global measurement method for a large field of view using a coordinate tracking control board. This measurement method adopts the coordinate tracking control board installed on the adapter bracket to realize the effective combination of the visual measurement equipment and the laser tracker in the case of non-common field of view, separate and calibrate the internal and external parameters of the left and right cameras, and establish the overall situation of the measurement site Coordinate system, so as to complete the global measurement based on the large field of view. This method can realize rapid and high-precision measurement of large parts and components under complex working conditions within a large field of view, and is a measurement method that combines multiple optical components. The measurement method has a large field of view, high efficiency, and is convenient for measuring the occluded part of the measured part, and quickly completes the global measurement of the large field of view at the industrial site.

This application discloses a high-altitude maintenance robot positioning method and device based on near-earth global vision. This application uses a dual vision system to obtain the global position coordinates of the robot body and the fault point through the first camera module, and according to the obtained global position coordinates Control the main body of the robot to perform initial positioning, and then obtain the local position coordinates of the fault point by the second camera module arranged at the end of the mechanical arm of the main body of the robot to control the main body of the robot to perform secondary precise positioning. The first camera module is set near the ground to prevent the global camera from being disturbed by the vibration of the mechanical arm during operation and the high-altitude wind after the global camera rises to the sky with the insulated bucket truck, thereby reducing the accuracy of the initial positioning of the global camera. Accuracy, which in turn affects the technical problem of the secondary positioning accuracy of the robot main body.

The invention discloses a global vision positioning method and system for a small-sized quadruped robot. The method comprises the following steps: calibrating a dual-camera system, calculating motion model parameters of the dual-camera system; obtaining an image of a target area captured by a calibrated fish-eye camera; The image of the target area is processed to obtain the position of the target to be located in the fisheye camera coordinate system, and the spatial position of the target to be located in the gimbal coordinate system is calculated through the kinematic model of the dual camera system, and the two-degree-of-freedom kinematics inverse solution is performed , to obtain the two-degree-of-freedom joint rotation angle; obtain the target image to be positioned, and detect the two-dimensional code in the target image to be positioned, obtain the two-dimensional coordinates of the center point of the two-dimensional code in the image to be positioned, and obtain the center of the two-dimensional code after transformation The two-dimensional coordinates of the point in the ground coordinate system; correct the two-dimensional coordinates of the center point of the two-dimensional code in the ground coordinate system to obtain the position and orientation of the target to be positioned in the ground coordinate system.

The invention discloses a warehouse navigation smart car dispatching method based on global vision, comprising the following steps: 1) using a top camera on the warehouse ceiling to take a global image; 2) processing the global image to track the smart car in the warehouse and using Convolutional neural network recognition to identify the number of each AGV; 3) Divide the warehouse into several areas, use the global controller to send instructions to control the AGV, so that the AGV runs according to the route; 4) Use the improved A* algorithm for regional path planning, Obtain the optimal path area set for the AGV to reach the target area from the current area; 5) use the time window algorithm to plan the path in the area, so that the AGV can safely drive out of the current area; 6) use the segmented PID control algorithm to enable the AGV to Complete the scheduled transportation tasks along the planned route. The invention fully distributes the AGV passing tasks to each area, and improves the operating efficiency of the AGV storage system.

The invention provides a global visual coordinate system and mechanical arm coordinate system mapping method and device. The method includes the following steps that: S1, the first ball center coordinate of the ball center of a target ball on the distal end of a mechanical arm under a mechanical arm coordinate system is acquired; S2, image recognition is performed on the target ball, the ball center is extracted from the image through a ball detection algorithm, and conversion is performed, so that the surface point coordinate of the target ball under a visual coordinate system is obtained; S3, the second ball center coordinate of the target ball in the visual coordinate system is calculated according to the surface point coordinate and radius of the target ball; S4, the position of the target ball is adjusted, the step S1 is executed again until a preset number of groups of first ball center coordinates and second ball center coordinates are obtained; and S5, and the preset number ofgroups of first ball center coordinates and second ball center coordinates are calculated through the least squares method, so that a mapping relationship between the two coordinate systems can be obtained. With the method and device of the invention adopted, automatic calculation can be realized efficiently and quickly, and mapping conversion precision is high.

The invention relates to a SDN network DDoS and DLDoS distributed space-time detection system comprising detection nodes arranged in various SDN switches. Each detection node comprises a data acquisition module, a space-time anomaly detection module, and an output module. The data acquisition module is used for acquiring network flow flowing across the SDN switch. The space-time anomaly detection module is used for detecting the network flow acquired by the data acquisition module in a spatial domain, determining whether suspicious flow exists, and confirming whether DDoS or DLDoS exists in a time domain on the basis of a detection result of the spatial domain. The output module is used for storing the detection result according to a set format. In view of the characteristics of the DDoS and the DLDoS, the detection system detects and discriminates the DDoS and the DLDoS in the network flow spatial domain and time domain, and achieves global vision in abnormity detection by using a distributed virtual ANN overlay network.

The invention discloses a multi-mobile-robot system collaborative experimental platform and a visual segmentation and location method of the collaborative experimental platform. The collaborative experimental platform is composed of a global vision monitoring system and a plurality of mobile robots the same in mechanism, wherein the global vision monitoring system is composed of an n-shaped support, a CCD camera, an image collection card and a monitoring host, and the CCD camera is installed on the n-shaped support and arranged corresponding to the mobile robots and connected with the image collection card installed in a PCI slot of the monitoring host through a video line. The visual segmentation method is combined with a frame difference method and a light stream method to segment a barrier. Threshold segmentation is performed based on a color code plate to achieve the visual location method. Experimental verification of collaborative technologies such as formation control, target search, task allocation and route planning in a multi-mobile-robot system can be met, and the multi-mobile-robot system collaborative experimental platform has the advantages of being low in cost and rapid to construct.

The invention discloses a robot vision guidance method and device based on the integration of global vision and local vision, which integrates the global vision system and the local vision system, first realizes the rough positioning of the processing target, and realizes that the processing target is divided into blocks, and Carry out road strength planning, and then combine the high-precision visual inspection system to accurately detect the target, and then guide the robot to implement high-precision and high-efficiency automatic grinding and polishing operations, thus meeting the precision requirements for high-efficiency processing of large-volume processing targets.