591results about How to "Expand the field of view" patented technology

The invention discloses a method for splicing a video in real time based on multiple cameras, which comprises the following steps of: acquiring synchronous multi-path video data; preprocessing frame images at the same moment; converting a color image into a grayscale image; enhancing the image, and expanding the dynamic range of grayscale of the image by a histogram equalization method; extracting the characteristic points of corresponding frames by using a speeded up robust features (SURF) algorithm; solving matched characteristic point pairs among corresponding frame images of the video by using a nearest neighbor matching method and a random sample consensus matching algorithm; solving an optimal homography matrix of initial k frames of the video; determining splicing overlapping regions according to the matched characteristic point pairs; taking a homography matrix corresponding to a frame with highest overlapping region similarity as the optimal homography matrix, and splicing subsequent video frame scenes; and outputting the spliced video. The method can reduce the calculated amount of splicing the video frame single-frame image, improves the splicing speed of traffic monitoring videos and achieves real-time processing effect.

Method and device for self-regulated flux transfer from a source of magnetic energy into one or more ferromagnetic work pieces, wherein a plurality of magnets, each having at least one N-S pole pair defining a magnetization axis, are disposed in a medium having a first relative permeability, the magnets being arranged in an array in which gaps of predetermined distance are maintained between neighboring magnets in the array and in which the magnetization axes of the magnets are oriented such that immediately neighboring magnets face one another with opposite polarities, such arrangement representing a magnetic tank circuit in which internal flux paths through the medium exist between neighboring magnets and magnetic flux access portals are defined between oppositely polarized pole pieces of such neighboring magnets, and wherein at least one working circuit is created which has a reluctance that is lower than that of the magnetic tank circuit by bringing one or more of the magnetic flux access portals into close vicinity to or contact with a surface of a ferromagnetic body having a second relative permeability that is higher than the first relative permeability, whereby a limit of effective flux transfer from the magnetic tank circuit into the working circuit will be reached when the work piece approaches magnetic saturation and the reluctance of the work circuit substantially equals the reluctance of the tank circuit.

The invention belongs to the technical field of autonomous running and visual perception, particularly relates to a multi-camera visual perception system for a UGV (Unmanned Ground Vehicle) and aims to solve the problems of single perception algorithm, poor real-time performance, poor system expandability, inconvenience in debugging, limitation to the view field control and the like of an image processing system of the existing UGV and autonomous mobile robot. The system comprises a plurality of vehicle-mounted image processing industrial personal computers and one or a plurality of debugging monitoring computers, wherein each vehicle-mounted image processing industrial personal computer is connected with three cameras; one or a plurality of debugging monitoring computers are used for controlling the vehicle-mounted image processing industrial personal computers by a wireless router; and a control mode can be a redundancy control mode and also can be a respective control mode. In the system, an optimized visual perception method on the basis of multiple threads is adopted; and threads comprise a multi-camera video acquisition thread, a lane line perception thread, a barrier, cone bucket and signal lamp perception thread and the like. Compared with a conventional single-thread visual perception method, the optimized visual perception method on the basis of the multiple threads has higher real-time performance, stability and expandability.

The invention discloses a large-view-field depth measuring system and method based on omni-directional structured light. The system comprises a camera, a hyperboloid reflector, at least four projectors, a three-axis moving platform and a computer, wherein the projectors and the camera are respectively and fixedly arranged on the three-axis moving platform; the projectors are uniformly distributed around the camera; the three-axis moving platform can move along an x axis, a y axis and a z axis; coding structured light projected by the projectors irradiates a measured scene target object, is reflected by the hyperboloid reflector and then enters the camera for imaging; the formed image is acquired and processed by the computer to obtain scene depth information. By adoption of the hyperboloid reflector to reflect for imaging, the view field range of the camera is widened; by combining the large-view-field depth measurement with visual measurement of the structured light, visual three-dimensional perceived measurement of a wide view field is realized; the system is simple in structure and high in practicality; the measurement task can be finished by the camera and the projectors without perfect alignment; the calibration of the camera and the projectors is finished by adopting a plane white board; the simplicity in operation and higher calibration precision are realized.

The invention discloses a target following control method of a mobile robot. The target following control method comprises the steps of arranging a triangular camera set on the mobile robot, and distributing a corresponding ID number and a visual angle range; acquiring an identity characteristic of a following target, and performing uploading and storage of the identity characteristic; detecting the identity characteristic of a to-be-followed target and uploading the identity characteristic of the to-be-followed target to a cloud server, performing characteristic matching by the cloud server, when matching succeeds, determining and locking the to-be-followed target as the following target; tracking the locked following target by a person, and obtaining relative direction between the following target and the mobile robot; performing real-time detection on the locked following target for obtaining a relative distance through calculation; determining a moving route according to the obtained relative directions and relative distance between the following target and the mobile robot, and making the mobile robot move to the following object according to the moving route. The target following control method has higher characteristic detecting function and higher automatic control function. Furthermore the target following control method can be well used for a robot tracking process.

The invention provides a coded target point based UAV positioning and attitude angle measuring method. The method comprises the following steps: shooting a plurality of coded target points which are pre-arranged at the ground through a camera which is mounted on an UAV, and obtaining and processing the shot images; calibrating the camera mounted on the UAV, and obtaining internal parameters of the camera; resolving a rotation matrix and a translation matrix of a world coordinate system relative to a camera coordinate system, the rotation matrix and the translation matrix of an UAV coordinate system relative to the camera coordinate system, and the rotation matrix and the translation matrix of the UAV coordinate system relative to the world coordinate system; and then calculating UAV attitude angles, including a pitching angle, a yaw angle and, an overturning angle, and the location coordinate of the UAV under the world coordinate system. According to the method, a binary coding cooperation points with primary points are adopted, and the coordinate transformation relation among the UAV coordinate system, the camera coordinate system and the world coordinate system are adopted, so that the algorithm is simple and easily realized, and meanwhile, the accuracy demand is met.

The invention provides a traveling information sharing system which is connected with a servo unit and installed on a first vehicle. The traveling information sharing system comprises a short-range network module and a remote-range network module, wherein the short-range network module is used for enabling the first vehicle to build local area network connection with a third party vehicle to achieve data transmission among vehicles; and the remote-range network module is used for enabling the first vehicle to build network connection with the servo unit to achieve data transmission between the first vehicle and the servo unit. When the first vehicle needs to acquire the road condition information around the third party vehicle, the remote-range network module builds network connection with the servo unit to obtain the network address information of the third party vehicle, and the short-range network module builds local area network connection with the third party vehicle according to the network address information to obtain the road condition information. The traveling information system reduces the load of data transmission between the servo unit and the vehicles to a certain extent and further improves the instantaneity and smoothness in sharing of the traveling information.

One moveable goal detecting equipment and method based on artificial compound belongs to artificial compound moveable goal detecting system. It relates to camera, outline border, standing pole, Yunnan and DSP processor. The moveable goal detecting method uses moveable goal division arithmetic to pick up and identify moveable goal form the video frequency picture having moveable goal. The dynamic and static state parameter testing method uses some cameras to screen the moveable goal to calculate the coordinate under the appointed world coordinate system and draw the movement track and speed. The moveable goal tracking method is about dividing up the dynamic and static state parameter of moveable goal to judge its movement trend, and run Yunnan to follow moveable goal by serial port. The panorama creating method takes the method gray-level relativity method and put multi-way overlap pictures together one large-scale seamless picture. It owns large watch field, high distinguish rate and delicacy rate.

The invention relates to a virtual camera and real camera switching system and method. The system comprises a real camera, wherein the real camera is connected with a chroma key device, a synthesis rendering server is connected with a virtual camera controller, a virtual camera parameter generating device connected with the real camera and the virtual camera controller is arranged inside the synthesis rendering server, a virtual camera and the virtual camera parameter generating device are connected with a synthesis device, the synthesis device is connected with the chroma key device, and a foreground generating device, a background generating device and an output device which are connected with the synthesis device are further arranged inside the synthesis rendering server. According to the method, virtual foregrounds, virtual backgrounds and virtual persons are fabricated in field and are fast synthesized, the switching of a field real scene and a virtual scene is realized through the operation of the virtual camera controller to the scene, the limitation of the real camera when the real camera shoots a virtual object is compensated, and the program expressive force of a virtual studio is greatly improved.

The invention discloses a control method of a monitoring ball machine. The method comprises the following steps of (1) vertically and horizontally dividing a to-be-monitored space into a plurality of small partitions, and setting a shooting focal distance for each small partition; (2) setting corresponding preset positions for a central point position and an edge point position of each small partition, and storing horizontal position information, vertical position information and shooting focal distance information of the ball machine; (3) reading a video frame, and performing target detection on the video frame; (4) according to direction information of a detected target in a monitoring scene, mapping the target to the corresponding preset position; (5) calling the preset position by the ball machine to acquire a monitored image. The defects that the automation degree of control is not high, the real-time property and the flexibility are not enough, and human manual interference is required in a ball machine of the traditional video monitoring system are overcome; the control method is convenient in operation, high in automation degree of control and good in instantaneity, and is particularly good in capture effect on the monitored image of a quickly moving target.

The invention discloses an underwater detection device for a turbid water area. The underwater detection device comprises a flexible wall-attaching module, an underwater device box, an optical image acquisition equipment module, an illumination module, a retractable cable device and a display control module, wherein the flexible wall-attaching module is connected with a front flange in the underwater device box through fastening bolts, and sealing is realized through an O-shaped sealing ring; the illumination module and a camera device are integrated and mounted on a rear cover of the underwater device box; signal wires of the illumination module and the camera device are led out, coiled on the retractable cable device and connected with the display control module, thereby being used for supplying power to the camera device and the illumination device and transmitting signals and data. A front flexible membrane is utilized for observing the underwater area with low visibility in a large range; high-definition image information is acquired by a high-definition camera and the luminance-adjustable illumination device. The device is simple to operate and convenient to carry, and desired high-definition video images of an invisible detection area can be obtained.

The invention discloses a pre-warning system and a pre-warning method for operation safety of railway maintenance. An image collecting unit is used for collecting image information in the construction site; a calculation control unit is used for treating the image information collected by the image collecting unit, performing matching calculation with a railway line equipment template stored in the calculation control unit and confirming the classification of the railway line equipment; the calculation control unit is also used for resolving a practical physical distance between the railway line equipment and the image collecting unit and sending warning and safety operation triggering information according to the practical physical distance between the railway line equipment and the image collecting unit and a corresponding warning and safety operation triggering distance of the railway line equipment; and a user interface unit is used for displaying information in the calculation control unit and setting parameters for the calculation control unit. According to the pre-warning system and the pre-warning method provided by the invention, the intelligent identification for the railway line equipment is realized and avoided; a user can set a construction safety limiting parameter according to the classification of large-size maintenance machinery; and the pre-warning system and the pre-warning method are excellent in adaptability.

The invention discloses a reality augmenting system which comprises a display screen, an imaging lens, a half-transparent and half-reflecting mirror, a first infrared camera, a second infrared camera and a processor. The display screen, the imaging lens and the half-transparent and half-reflecting mirror are sequentially arranged along an optical axis, the half-transparent and half-reflecting mirror and the optical axis form a certain angle, the position observed by a human eye is located in front of the half-transparent and half-reflecting mirror, and a light beam emitted by the display screen is transmitted by the imaging lens and reflected by the half-transparent and half-reflecting mirror and then enters the human eye so as to enable a user to observe a virtual image formed by the imaging lens in front of the human eye. The view field of the first infrared camera is similar to the view field which can be observed by the human eye and is used for detecting environment information of the first infrared camera within a view field range and transmitting the environment information to the processor. The second infrared camera is used for capturing a three-dimensional space coordinate of the intersection point of sight lines of the human eye and transmitting the three-dimensional space coordinate to the processor. The reality augmenting system has the advantage of having a large visual angle.

The invention, which belongs to the field of laser radar detection, proposes a two-dimensional MEMS scanning galvanometer laser radar system, thereby extending a receiving field of view and increasinga signal-to-noise ratio. A two-dimensional MEMS scanning galvanometer is a scanning mechanism. A control system controls the laser to emit high-frequency pulsed laser; the returned laser signal lightpasses through a filter and a large relative aperture optical lens successively and then is imaged on the incident end face of an image transmission fiber light cone; the image transmission fiber light cone transmits to the surface of an APD array detector. The image transmission fiber light cone is formed by arranging a cone-shaped optical fiber bundle. The APD array detector selects a corresponding APD detector unit to collect signals according to scanning angle of the two-dimensional MEMS scanning galvanometer and the position of a light spot outputted by corresponding echo light at the image transmission fiber light cone. Therefore, , when the caliber, focal length, and detector area of the receiving optical system are certain, the field of view of the MEMS laser radar can be extended, the interference of the ambient background light on the system can be reduced, and the signal-to-noise ratio of the signal receiving can be improved.

The invention is applicable to the field of vehicle-mounted all-round view, and provides a vehicle-mounted three-dimensional all-round display method, a computer readable storage medium and a system.The method comprises the following steps: establishing a three-dimensional grid model, and amplifying the three-dimensional grid model to world coordinates; acquiring fisheye images around the vehiclebody collected by a camera, and performing distortion correction to obtain corrected images and coordinates of an imaging center; calculating to obtain a camera internal reference matrix according tothe coordinates of the imaging center; determining an external parameter matrix of each camera under a vehicle body coordinate system; determining a mapping relation between each point in the three-dimensional space and a planar pixel coordinate; rendering the content of the corrected image into a three-dimensional grid model to realize a three-dimensional panoramic all-round view; and displayingthe three-dimensional panoramic all-round view. The stereoscopic environment around the vehicle can be displayed on the display window more clearly, the view field range of the vehicle-mounted stereoscopic panoramic display system is widened, and the safety performance is improved.

The invention belongs to the technical field of image processing, and relates to a multi-source target tracking measurement system and tracking method based on active vision. The system comprises a photoelectric assembly and a stable platform, wherein the photoelectric assembly is composed of a visible light camera, an infrared thermal imager, a laser range finder, an information processor and a photoelectric cabin structure; the visible light camera, the infrared thermal imager, the laser range finder and the information processor are all installed inside the photoelectric cabin structure; the stable platform consists of an orientation motion assembly, a pitching motion assembly and a control assembly; and the control assembly receives an instruction sent by the information processor, andcontrols the orientation motion assembly and the pitching motion assembly to enable visual axes to stably point to a target. The invention further provides the multi-source target tracking method based on the active vision. The orientation motion assembly and the pitching motion assembly are driven to rotate according to the control instruction, so that the visual axis of the visible light cameraand the visual axis of the infrared thermal imager point to the target, and the target is always kept in the center of a shot image.

The application discloses a shelf monitoring method and system and a shelf. The system comprises an image collection unit, a control unit, a driving unit and a communication unit. The image collectionunit comprises a slide rail mounted on a shelf, and a camera mounted on the slide rail and capable of sliding along the slide rail. The image collection unit is used for collecting an image of goodson the shelf and sending the goods image to the control unit. The driving unit is installed at one end of the slide rail, and is used for driving the camera to slide along the slide rail. The controlunit is used for controlling the driving unit, identifying the goods image sent by the camera, and sending the identification result to a background server through the communication unit when there isa lack of goods and/or the goods is wrongly placed. Through the scheme, the problem that there may be blind areas in image collection of goods by the camera can be solved, and the precision of detection on whether there is a lack of goods or the goods is wrongly placed is improved.

The present invention provides an air conditioner having an indoor device for allocating the human body detecting sensor to the position with sufficient view field. At lease one human body detecting sensor (26, 28, 30, 32, 34) is installed on the upper side of the indoor device for insuring if a person is detecting to control the running of the air conditioner.

A working mechanism (4) takes a traveling stance by a way that left and right boom cylinders (9, 10) are expanded to rotate a tip end of a first boom (5) to the rear side and a positioning cylinder (11) is compressed to rotate a tip end of a second boom (6) to the lower side. In the traveling stance of the working mechanism (4), a front surface plate (23A) of a right front housing cover (23) is inclined along a tilting angle (α) of the left and right boom cylinders (9, 10), and the front surface plate (23A) of the right front housing cover (23) is arranged in a position of lining with front ends (9A1, 10A1) of tubes (9A, 10A) in the left-right direction forming the respective boom cylinders (9, 10).

The embodiment of the invention provides a display base plate and a preparation method thereof as well as a display device and relates to the technical field of display, aiming at solving a view angle problem caused by the fact that the display device adopts optical gratings to realize color filtering. The display base plate comprises a colored filtering layer arranged on a substrate base plate; the colored filtering layer comprises a plurality of types of color filtering units which are arrayed in a matrix manner; each of the plurality of types of color filtering units is at least composed of a first optical grating, a second optical grating and a third optical grating; the three optical gratings are used for carrying out light filtering on incident light emitted to the display base plate respectively to obtain light with three base colors; the display base plate further comprises a lens structure; aiming at a region corresponding to any optical grating, the lens structure is used for enabling one part of light emitted from the display base plate to diverge relative to the incident light. The preparation of the display base plate and the display device comprising the display base plate is realized.

Provided is a helicopter rotor blade dynamic trajectory measuring method based on four-nocular stereo vision. The method comprises the following steps that 1, mark points are uniformly stuck to the two sides of each rotor blade of a helicopter; 2, four-nocular cameras are pairwise matched to form four binocular stereo vision systems, and calibration is conducted on each system; 3, conversion relations between coordinate systems of the four binocular stereo vision systems and a coordinate system of a total station are obtained by using the total station; 4, three-dimensional information of the mark points in rotor blade image pairs collected by the four binocular stereo vision systems is calculated; 5, the rotor blade mark point three-dimensional information obtained through measurement of the four binocular stereo vision systems is unified into the coordinate system of the total station, and rotor blade dynamic trajectory measurement based on the four-nocular stereo vision is achieved. The helicopter rotor blade dynamic trajectory measuring method based on the four-nocular stereo vision has the advantages that three-dimensional reconstruction on rotor blade motion trajectories can be completed, the field of view is wide, a non-contact type is achieved, the precision is high, and the safety is good.