115 results about "Visual navigation system" patented technology

The invention discloses a lane line detection and GIS map information development-based vision navigation method. The method comprises the following steps: acquiring GIS map information, preprocessing, carrying out real-time image acquisition and lane line detection to generate a GIS local map in real-time, carrying out coupling verification on a track line detection result and the GIS local map through an ICP algorithm, and generating a high-credibility track line result according to the coupling result. The method can realize the credibility evaluation of the lane line detection through a geographic information system, corrects when false detection or missing inspection appears, expands the application range of the lane detection algorithm, and also can improve the map positioning precision through visual perception information, so the performances of a vision navigation system in a whole intelligent driving and aided driving system are improved, thereby the system can adapt to more complex environments.

The invention discloses a collaborative interaction method for an unmanned plane cluster and a visual navigation system of an unmanned plane. The collaborative interaction method for the unmanned plane cluster comprises the following steps of: determining unmanned planes satisfying a collaborative condition in a communication coverage area of a certain unmanned plane by the unmanned plane in the unmanned plane cluster, and establishing an unmanned plane collaboration group according to the unmanned planes satisfying the collaborative condition; determining inter-plane routes of multiple unmanned planes in the unmanned plane collaboration group; allocating collaborative tasks to multiple unmanned planes in the unmanned plane collaboration group according to link state information of the inter-plane routes; and evaluating the link state according to the motion state of multiple unmanned planes in the unmanned plane collaboration group, and updating unmanned planes in the unmanned plane collaboration group and the collaborative task of each unmanned plane according to an evaluation result. The collaborative interaction method for the unmanned plane cluster is good in real-time, strong in reliability and high in communication quality, and can better adapt to an unmanned plane cluster communication environment during visual navigation.

The invention discloses a parking position visual navigation system based on indoor precise real-time localization, comprising an indoor precise real-time localization system, an indoor wireless communication system, a navigator and a parking lot management server. An automobile driver receives a hand-hold navigator when entering a parking lot or directly enters the parking lot by using an onboard navigator; the indoor precise real-time localization system determines the precise position of the driver according to a localization label arranged in the navigator and transmits the precise position to the parking lot management server by the indoor wireless communication system; the parking lot management server determines the optimal parking position according to the position of the driver and the vacancy situation of the parking lot, and then the optimal parking position navigating route is transmitted to the navigator by the indoor communicating system and is displayed on the screen of the navigator. The invention does not need to install a parking position detector at each parking position and can carry out precise visual navigation on the parking position, thereby ensuring that a parker can quickly and accurately find the parking position. The invention is especially suitable for the management of large-sized parking lots.

The invention discloses an integrated navigation system applied to a pilotless aircraft, which adopts a sensor comprising an inertial sensor, a radio altimeter, a communication module, a camera and the like, wherein the inertial sensor is used for acquiring motion acceleration and angular velocity of a carrier, and providing the motion acceleration and the angular velocity for an inertial navigation system and a vision navigation system in the unknown environment for setting up a system equation, thus further providing the current location information and matched trigger signals for scene matching navigation. The method integrates four combination ways which are inertial navigation, cellular wireless location navigation, vision navigation in the unknown environment and the scene matching navigation, and the four combination ways form each subsystem of the integrated navigation system and can be independently used for estimating the state of the aircraft; then, fault diagnosis and fusion estimation are carried out on the data output by the subsystems by a main filter, so that the accurate estimation of the state of the aircraft is obtained.

The invention relates to a three-dimensional (3D) visual navigation method based on multi-sensor information fusion. The multi-sensor data registration and fusion are finished based on acquiring multi-sensor data by means of a photoelectric sensor (infrared and visible lights), an airport radar monitor system (air traffic control radar and ground surveillance radar) and navigation positioning systems (radio navigation positioning system and global positioning system); and the detection, identification, track and behavior prediction are carried out on the targets (obstacles, humans, vehicles and planes) in the air or on the ground; the plane safety take-off and straight-in approach optimization information is automatically generated according to the target information in the air or on the ground; the target information and the plane safety take-off and straight-in approach optimization information are fused and displayed in an airport 3D scene to form a 3D visual navigation; and the system can automatically generate the 3D visual navigation information and transmits the navigation information to the aircraft via the GPS to realize the 3D visual navigation on the aircraft. The realization of the method comprises the following specific steps of: firstly, acquiring the multi-sensor data; secondly, registering and fusing the multi-sensor data; thirdly, detecting, identifying and tracking the targets in the air or on the ground by utilizing the fused data, and predicting the behavior of the targets; fourthly, establishing a 3D model of the airport, and fusing the targets and the behavior prediction data thereof and displaying the data in the airport 3D scene to form a 3D visual navigation system; and finally, carrying out the 3D visual navigation on the aircraft by means of the 3D visual navigation system to realize the safe take-off or approach of the aircraft.

A visual navigation system and method based on structured light are provided. The visual navigation system at least includes at least one projector for generating a specific path pattern formed by structured light, and a visual server. In addition to facilitating the visual navigation system to detect an obstacle, the pattern formed by the structured light provides a specific path pattern followed by robots during the navigation. In the visual navigation method, when detecting the obstacle, the visual server routes a virtual path and issues a movement-control command to the robots, which in turn follow the virtual path. The present invention is capable of raising the accuracy for the robot navigation and reducing operation burden of the visual server by using the structured light to guide the robots.

The invention relates to a visual navigation system of a wall climbing robot for weld inspection, a welding and locating method of a welding seam and a method of obtaining welding seam offset. According to the invention, the problem that in the place with a bad natural environment, the overhauling and maintaining work for a tower cylinder in a teaching reappearing way cannot be realized by using the prior art is solved. A charge coupled camera and a cross-shaped laser transmitter of the visual navigation system are fixedly arranged at the front end of the head part of the wall climbing robot, the cross-shaped laser transmitter is arranged right above the charge coupled camera, laser transmitted by the cross-shaped laser transmitter irradiates on the surface of a welding workpiece to form a cross-shaped light spot, the charge coupled camera is used for photographing the cross-shaped light spot on the surface of the welding workpiece, and a data output end of the charge coupled camera is connected with a data input end of a computer. The visual navigation system, the welding and locating method and the method of obtaining the welding seam offset, disclosed by the invention, are suitable for the field of overhauling and maintaining the tower cylinder.

An embedded monocular visual navigation system based on navigation line recognition, the system includes the following processing steps: the first step, video signal acquisition, the single-chip microcomputer carries out video signal acquisition; the second step, distortion correction, the image collected by the camera is processed Vertical and horizontal distortion correction; the third step, path recognition and extraction, separating and extracting the navigation line from the background image; the fourth step, steering control, building a steering model to calculate the relationship between the turning radius of the smart car and the steering gear swing angle , to provide data for the steering control of the smart car; the fifth step, steering gear control, to realize the smart car moving along the navigation line; the sixth step, speed control, using the PID control method to control the running speed of the smart car; the present invention collects and navigates with a camera The line information has good visual foresight, which effectively improves the performance of the navigation system. The invention realizes image dynamic threshold calculation and self-adaptive adjustment in complex environment, and has better stability under complex light.

The invention provides a method for processing motion pattern recognition and action recognition of a moving target based on a light stream direction sequence. The method comprises the following steps of: detecting the target by using background subtraction, tracking the target by using mean shift tracking algorithm, calculating a light flow value, respectively acquiring light stream directions of a rigid body and a non-rigid body, acquiring time series of the light stream directions after quantization, then building a Hidden Markov Model by using the time series, and finally processing the motion pattern recognition and the action recognition by using the Hidden Markov Model. The method provided by the invention can simutaneously process the motion pattern recognition and the action recognition of the moving target through the light stream directions, and can be widely applied to various civil or military systems such as a video monitoring system, a video conference system, an industrial product testing system, a robot visual navigation system, a military target testing classification system, thus having broad market prospect and application value.

The invention provides a low-cost, high efficiency and intelligent visual navigation system and a navigation method thereof for an agricultural vehicle. The visual navigation system for the agricultural vehicle of the invention, comprises a visual navigation platform module, and a navigation path detection module, a steering control module and a safety early-warning module which are connected with the visual navigation platform module; wherein the navigation path detection module is used for real-time acquiring, treating and analyzing images to obtain navigation path parameters; the steering control module is used for obtaining the work speed and turning angle state of a directive wheel of the agricultural vehicle, and implementing steering with a prescribed angle based on the navigation path parameters; and the safety early-warning module is used for detecting circumference environment information for alarming by analysis and contrast. The visual navigation system and a navigation method thereof for an agricultural vehicle of the invention can achieve the purpose of auxiliary drive, can enhance work precision and work efficiency, can reduce labor intensity of a driver, can reduce energy consumption, and can raise intelligentized level.

The invention provides a structured light visual navigation system and a method thereof; wherein, the visual light navigation system at least comprises at least a projector which generates a specific path pattern formed by the structured light, and a visual server. The patter formed by the structured light can assist the structured light visual navigation system to detect a barrier, meanwhile, provides the specific path pattern which must be followed by a robot when in navigation. In the structured light visual navigation method, when the barrier is detected, the visual server can plan a virtual route and sends out motion control commands to the robot to cause that the robot follows the virtual route to go forward. The invention navigates the robot by the structured light so as to increase the navigation precision of the robot and reduce the heavy operation of the visual server.

The invention discloses a combined navigation method and device for an unmanned aerial vehicle based on expanded auto-adaptive interval Kalman. The method comprises the following steps: measuring an inertial navigation parameter of the unmanned aerial vehicle by using a micro electro mechanical system inertial measurement unit and measuring a visual navigation parameter of the unmanned aerial vehicle by a visual navigation system; and by taking a digital signal processing module as a navigation computer, obtaining the optimum estimation of the navigation parameter of the system by taking an expanded auto-adaptive interval Kalman filter technology as a combined method fused with inertial and visual navigation parameters. The device disclosed by the invention is easy to realize, low in cost, relatively small in mass, relatively small in power consumption and suitable for being popularized in the civil field. A linear system model can be obtained by means of the expanded auto-adaptive interval Kalman filter technology. A time-varying parameter of the system is modeled as an auto-adaptive interval model, so that the capability of the navigation system operating the navigation positioning task during temperature variation, frequent gesture variation of a transporter and unsatisfactory lighting condition or in complex and severe conditions that a visual sensor is hard to fix the focus is improved.

A visual navigation system and method based on structured light are provided. The visual navigation system at least includes at least one projector for generating a specific path pattern formed by structured light, and a visual server. In addition to facilitating the visual navigation system to detect an obstacle, the pattern formed by the structured light provides a specific path pattern followed by robots during the navigation. In the visual navigation method, when detecting the obstacle, the visual server routes a virtual path and issues a movement-control command to the robots, which in turn follow the virtual path. The present invention is capable of raising the accuracy for the robot navigation and reducing operation burden of the visual server by using the structured light to guide the robots.

The invention relates to a visual navigation system of an orchard robot. The visual navigation system comprises four parts, namely, a navigation reference line recognition module, a two-dimensional code positioning module, an ultrasonic obstacle avoiding module and a singlechip microcomputer control module. According to the visual navigation system, navigation reference line recognition based on natural environments and positioning based on two-dimensional code marking are combined for visual navigation, an ultrasonic sensor is adopted for safe obstacle avoidance, and finally a singlechip microcomputer is adopted for walking control on the orchard robot. The visual navigation system has important significances for lowering navigation cost, solving the problem of poor turning adaptability of visual navigation in orchards merely on the basis of natural environments, and improving navigation reliability and practicability.

The invention discloses a three-dimensional and visual indoor navigation system suitable for theaters and libraries. The three-dimensional and visual indoor navigation system comprises an indoor BIM three-dimensional simulation system, a positioning module and a handheld terminal, wherein the indoor BIM three-dimensional simulation system is used for performing coordinate conversion on positioning information acquired by a user, adding the positioning information to three-dimensional building information so that position information and navigation information of the user are formed in a virtual reality manner and sending the indoor three-dimensional navigation information to the handheld terminal for display; the positioning module is arranged in rooms of the theaters or libraries and used for acquiring positioning information of a corresponding position through the handheld terminal; the handheld terminal is used for sending the current position positioning information acquired with a two-dimensional code scanning technique to the indoor BIM three-dimensional simulation system and receiving and displaying indoor three-dimensional navigation information sent by the indoor BIM three-dimensional simulation system. The visual navigation system with high reality sense is provided for people and can provide rapid and accurate indoor guidance and positioning services for users.

The invention belongs to the technical field of robot visual navigation, and discloses a real-time field robot visual navigation method based on FPGA and a real-time field robot visual navigation system based on FPGA. Green crops are segmented from an acquired field image through preprocessing of the acquired field image; ridge line information in a field crop ridge line image is detected, whereinthe ridge line information comprises position information and slope of two neighboring ridge lines; navigation information of a robot is calculated and extracted through the ridge line information, and the navigation information is used for controlling walking of the robot; an image processing module, an image storage module, a field ridge line detection module and a navigation parameter extraction module are provided. Compared with the existing algorithm, average accuracy rate of the optimized algorithm is up to 89.7%; compared with a truth value, a F-score value is 91.1%, time is only 16ms,and 2824 triggers, 4625 lookup tables and 4kb registers (BRAM) are occupied; and the navigation parameter extraction module only occupies 372 triggers and 1013 lookup tables.

The invention studies a flight path synthetic method in an unmanned aerial vehicle visual navigation system. During navigation information acquisition by image characteristic matching, the rotation problem of the unmanned aerial vehicle can not be ignored. According to the invention, euler angles and angular velocity measured by an inertial navigation system is used for the compensation of rotation effect, and then a complete flight path based on visual information is synthesized according to a movement track of a road sign in the image. The position information of the unmanned aerial vehicle is resolved by the image (pixel displacement) coordinate transformation relation of the natural road sign within a certain time interval. The flight path synthetic method in unmanned aerial vehicle visual navigation studied in the invention is suitable for the characteristics of high positioning precision, micromation and low cost of small and medium-size unmanned aerial vehicles, and has theoretic and practical value.

The present invention discloses a road dangerous section visual navigation system, comprising a plurality of traffic guidance units, wherein the traffic guidance units are connected through a communication module, each traffic guidance unit comprises a guiding lamp system, a vehicle detection system, a lane detection system and an on-site master control system; the vehicle detection system is connected with the on-site master control system and is used for monitoring whether there is a vehicle passing; the lane detection system is connected with the on-site master control system and is used for detecting a driving lane; the guiding lamp system is connected with the on-site master control system and is used for emitting light (displaying warning characters, warning figures or other guiding patterns) according to a command of the on-site master control system. The road dangerous section visual navigation system can targetedly display corresponding guiding contents according to different road statuses and weather statuses, and can provide warning guidance for the following vehicles while performing safe driving guidance for the current driving vehicle, thereby avoiding occurrence of serious traffic accidents such as rear collision.

The invention relates to an inertia / vision / astronomy / laser ranging combined navigation method suitable for a lunar lander. The method includes: firstly, according to mechanical arrangement of inertialnavigation under a lunar fixed connection coordinate system, taking an inertial navigation error equation as a state model, and then taking the relative position and attitude error obtained by an inertial / visual navigation system, the starlight vector obtained by an astronomical navigation system and the distance obtained by a laser range finder as measurement quantities; then respectively establishing measurement models of relative position and attitude errors, starlight vectors and laser ranging of the inertial / visual navigation system according to the measurements; and finally, estimatingthe position, the speed and the attitude of the lander by using UKF filtering, and correcting the attitude error and the inertial device error of the lunar lander. The invention belongs to the field of deep space probe autonomous navigation, can provide high-precision position, speed and attitude information for a lunar lander, and has important practical significance for deep space detection.

The invention relates to a non-radiation perspective visual navigation method and a non-radiation perspective visual navigation system for assisting the orthopedic surgery. According to the system, the integral three-dimensional shape of a surgical site is acquired by utilizing conventional three-dimensional scanning data before the surgery, and the operation path of a surgical instrument is planned in advance; during the surgery process, a three-dimensional reconstruction device on the surgical instrument reconstructs the local three-dimensional shape of the exposed surgical site in real time, the local three-dimensional shape is matched with the integral three-dimensional shape, and thus the position relation between the surgical instrument and the operation path is determined; the surgical instrument is guided to carry out surgical operation along the pre-planned operation path according to the position relation. The invention provides the navigation method and the navigation system for the orthopedic surgery, which are simple and accurate, and are free of radiation injuries; with the navigation method and the navigation system, the accuracy of internal fixation placement of the orthopedic department can be obviously improved, the navigation process is simplified, the navigation matching time is shortened, the cost of navigation equipment is reduced, the radiation injuries during the surgery are avoided, and thus the accuracy and success rate of the internal fixation technology of the orthopedic department are comprehensively improved.

The invention discloses a chaotic characteristic parameter-based motion mode video segmentation and traffic condition identification method, which comprises the following steps of: 1, calculating a characteristic vector matrix; 2, segmenting a video; 3, comparing clustering results; 4, retrieving the video; and 5, classifying the video. Characteristic parameters of the video are extracted, and new characteristic vectors are formed, so that the dynamic information of the video can be well described, and the method can be widely applied to various civil and military systems such as video monitoring systems, video conference systems, industrial product detection systems, robot visual navigation systems and military target detection and classification systems, and has broad market prospect and high application value.

The invention provides an automatic driving system of a tractor, a control method and a crawler-type tractor. The automatic driving system comprises a GNSS navigation positioning system, a visual navigation system, a controller and an actuator; wherein the GNSS navigation positioning system and the visual navigation system are respectively connected with the controller; the actuator is connected with the controller; the controller controls the operation of the tractor through the actuator; the GNSS navigation positioning system is used for acquiring the longitude and latitude geographic position, the satellite differential information and the operation boundary information of the tractor; and the visual navigation system is used for acquiring the running path, the obstacle and the crop information of the tractor and judging the running path of the tractor. When the scheme is adopted, the operation accuracy of the crawler-type tractor can be improved, the operation error is reduced, thestandardization degree of agricultural production can be improved, and the land utilization rate and the agricultural production efficiency can be improved. The production cost is reduced, the fatigue degree of a driver is reduced, and the labor force is saved.

The present invention relates to a simple and rapid lane line detection method based on the dynamic area of interest. The method comprises: performing preprocessing of an original image to obtain an edge detection result graph; calculating a dynamic area of interest; obtaining the lane line detection result of the previous frame image, and generating a mask graph according to the lane line detection result of the previous frame image; employing the mask graph and the edge detection result graph for operation, and obtaining the local image only having the dynamic area of interest; using the Progressive Probabilistic Hough Transform to detect the line in the local image; traversing all the lines, calculating the length thereof, and if the length is smaller than a threshold value, skipping the line; or else, calculating the distance from the line to the middle point of the image bottom edge; traversing the line set after sorting, and calculating the line slope and color and the deviation degree with the previous frame lane line position; and if the deviation degree is located in each range, taking the line as this frame lane line; and or else, going on searching backwards. The simple and rapid lane line detection method based on the dynamic area of interest can better satisfy the requirement of the vision navigation system on the universality, the timeliness and the robustness.

The invention discloses a GPS visual navigation system of a smart car. The GPS visual navigation system comprises an AGV (automated guided vehicle) vehicle-mounted subsystem, a GPS visual navigation server, two-dimensional code identifiers arranged on all the driving sections of an AGV trolley, and colored paper tape guiding strips arranged on all the driving sections of the AGV trolley. The AGV vehicle-mounted subsystem includes a GPS positioning module, a two-dimensional code scanner, an image acquisition module, a ranging sensor, an ARM processor, a vehicle-mounted communication module, anAGV universal controller, and an AGV driving device. The invention develops a transportation route of the AGV trolley to a transportation destination through the GPS visual navigation server, and guides vehicle driving based on the two-dimensional code identifiers and the colored paper tape guiding strips arranged on all the driving sections during transportation, is simple in path setting, can easily maintain and change the path, and is free from external electromagnetic interference.

The invention discloses a four-rotor unmanned aerial vehicle visual navigation system and method based on Raspberry Pi. The system comprises a flight control panel, a driving module, a power supply detection module, a visual processing module, a height measurement module, a remote controller control module and a wireless communication module, wherein the flight control panel comprises a flight control processor, a communication module and an attitude acquisition module. The method comprises the following steps: controlling the unmanned aerial vehicle to fly to a stable height, and switching toan automatic control mode; acquiring a camera image by using the Raspberry Pi to extract a target, calculating the position deviation of a target relative to the unmanned aerial vehicle, transmittingthe position deviation information to a flight control processor, and compensating the position deviation information by using attitude angle information to acquire final deviation information; and finally, calculating a control output value by using a PID algorithm and the deviation information, and controlling the unmanned aerial vehicle to perform tracking flight. The system is high in transportability and low in cost, the method is simple and convenient, and autonomous navigation of the unmanned aerial vehicle can be performed without GPS signals.

The invention provides a real-time visual navigation system in orthopaedic minimally invasive surgery based on virtual-real fusion. The real-time visual navigation system based on virtual-real fusioncomprises an NDIPolaris optical tracking device, a virtual-real fusion device and a navigation device, wherein the NDIPolaris optical tracking device is used for acquiring six-degree-of-freedom pose information of a mark point in a real three-dimensional space; an optical tracking equipment bracket used for supporting optical tracking equipment (NDIPolaris) so that the optical tracking equipment is placed at a pointing position at any angle; a depth camera used for acquiring video data and video depth information in normal and lateral directions in an operation; a display used for displaying the poses of the tracked surgical instrument in the front side video, the side video and the three-dimensional virtual model in real time so as to realize visualization of the minimally invasive surgery; a video equipment bracket used for supporting the depth camera and the display equipment and fixing the depth camera and the display equipment at specified positions; and a video navigation calculation device is used for processing data acquired by the optical tracking equipment and the depth camera, calculating video navigation data and sending the video navigation data to the display.

The invention discloses an all-terrain all-source combined navigation system for intelligent agricultural machinery and relates to the field of agricultural machinery operation. The all-terrain all-source combined navigation system comprises a laser radar navigation module, a Beidou satellite navigation module, an inertia navigation module, a visual navigation module, a route planning system, a data management module, a comprehensive environment sensing module and a navigation mode switching module, wherein the comprehensive environment sensing module can obtain environment data provided by alaser radar navigation system and a visual navigation system to construct a high-accuracy electronic map and can perform terrain match with navigation data; the data management module specifically comprises a data processing unit, a data synchronizing unit, a data sending unit and a data fusing unit and can provide high-accuracy and high-quality navigation data superior to a single sensor; the navigation mode switching module is mainly formed by a light intensity sensor, a satellite signal detection sensor, operation environment data and the like and can provide reference for navigation mode switching decision.

The invention discloses a robot based on vision and voice intelligent control, which includes an intelligent command system and a main control system connected by two-way communication, a visual navigation system and a voice interaction system; wherein the voice interaction system includes a connected voice processing module and Pickup module; The voice processing module is connected with the intelligent command system; The pickup module includes three pickups that are arranged on the body part front face of the robot body and are distributed in an equilateral triangle structure; The visual navigation system and the intelligent command system connection; and the main control system is provided with a signal control circuit for receiving the control signal of the intelligent command system; the body part is also provided with a first driving motor; the first driving motor is connected with the main control system respectively The system is connected to a pair of drive wheels arranged on the legs of the robot body.

The invention discloses a fault processing method for monocular vision navigation feature point losing and belongs to the field of vision relative navigation. The method disclosed by the invention comprises the following steps: when navigation feature points are lost, firstly carrying out rough reconstitution of virtual coordinates of the fault feature points through an image matching method and a geometric method; amending the virtual coordinates of the reconstituted fault feature points on a camera imaging sensitive element by adopting an ant colony searching method according to measurement information of gyro attitude angular velocity in combination with the distance between feature points, the azimuth information and the estimated results of a visual navigation system at the previous moment, and solving the relative position and attitude of a target by adopting a vision navigation iterative algorithm. The processing method disclosed by the invention has the advantages that the method is simple; the effect is obviously improved; the robustness of the visual navigation system is increased; the method can be applied to space missions such as spacecraft ground physical simulation three-degree-of-freedom or five-degree-of-freedom air floating platforms and spacecraft on-orbit services; high-reliability relative position and attitude measurement is provided.

The present invention relates to visual navigation system and method for intelligent endoscope. The system includes one endoscope, one lens deflecting mechanism, one automatic intervening mechanism, and one PC with image acquiring controller connected to the above said parts for processing image signal, displaying, and controlling lens deflection and automatic intervening. The system has simple composition, several manual and automatic switchable functions and convenient use; and the operation is fast, precise and timely.