2308 results about "Visual positioning" patented technology

The present invention relates to an indoor mobile robot positioning system and method based on two-dimensional code. The system includes a two-dimensional code positioning controller mounted on a mobile robot, a two-dimensional code acquisition device and a two-dimensional code label distributed in the indoor environment. The two-dimensional code positioning controller is composed of a microprocessor and a communication interface that are connected together. The microprocessor is connected with the two-dimensional code acquisition device through the communication interface and is used for controlling the two-dimensional code acquisition device to acquire two-dimensional code images, receive the two-dimensional code images acquired by the two-dimensional code image acquisition device and realize precise positioning function. The method acquires an actual position of the mobile robot through photographing the indoor two-dimensional code labels, transforming coordinates and mapping code values. The method of the invention organically combines visual positioning technique, two-dimensional code positioning technology and two degree of freedom measuring technology to realize the function of precise positioning of the mobile robot and solve problems of complex image processing and inaccurate positioning of a traditional vision positioning system.

The invention discloses an unmanned aerial vehicle-based express delivery delivering system and method. The unmanned aerial vehicle-based express delivery delivering system comprises a ground control center, an unmanned aerial vehicle group and an intelligent express delivery cabinet net. During delivering processes, an express delivery company sends an express delivery delivering request to the ground control center, a specific intelligent express delivery cabinet is generated for the order, and a task flight route is generated for an unmanned aerial vehicle. After reaching a target position, the unmanned aerial vehicle applies to the express delivery cabinet for communication verification; after passing the verification, the unmanned aerial vehicle switches to a visual positioning module if the express delivery cabinet is unoccupied; after positioning operation is performed successfully, an electronic door of the express delivery cabinet is automatically opened, and the unmanned aerial vehicle hovers or lands on a landing stage for delivery operation. Deliveries can be transmitted to pre-distributed compartment by the intelligent express delivery cabinet, pick-up codes are generated and sent to users, and the users can pick up the deliveries based on the pick-up codes. Current express delivery delivering efficiency can be greatly improved via the unmanned aerial vehicle-based express delivery delivering system and method, manpower cost and time cost can be lowered, and security and privacy of express delivery can be well guaranteed.

The invention discloses an accurate visual positioning and orienting method for a rotor wing unmanned aerial vehicle on the basis of an artificial marker. The accurate visual positioning and orienting method includes the following steps that the marker with a special pattern is installed on the surface of an artificial facility or the surface of a natural object; a camera is calibrated; the proportion mapping relation among the actual size of the marker, the relative distance between the marker and the camera and the size, in camera imaging, of the marker is set up, and the keeping distance between the unmanned aerial vehicle and the marker is set; the unmanned aerial vehicle is guided to fly to the position where the unmanned aerial vehicle is to be suspended, the unmanned aerial vehicle is adjusted so that the marker pattern can enter the visual field of the camera, and a visual recognition function is started; a visual processing computer compares the geometrical characteristic of the pattern shot currently and a standard pattern through visual analysis to obtain difference and transmits the difference to a flight control computer to generate a control law so that the unmanned aerial vehicle can be adjusted to eliminate the deviation of the position, the height and the course, and accurate positioning and orienting suspension is achieved. The accurate visual positioning and orienting method is high in independence, good in stability, high in reliability and beneficial for safety operation, nearby the artificial facility the natural object, of the unmanned aerial vehicle.

The invention discloses a global positioning system (GPS) and machine vision-based integrated navigation and positioning system and a method. The system comprises a GPS positioning device which is utilized for carrying out GPS positioning process on a navigated vehicle, acquiring position coordinates, course angles and driving speed of the navigated vehicle and transmitting the acquired information to a fusion positioning device, a machine vision positioning device which is utilized for collecting images of farmland on a navigation path, carrying out image processing on the collected images, extracting the navigation path to obtain position coordinates of known points on the navigation path, and transmitting the position coordinates to the fusion positioning device, and the fusion positioning device which is utilized for carrying out spatial adjustment and temporal adjustment processes on information from the GPS positioning device and the machine vision positioning device and carrying out filtering processing to obtain final positioning information. The method and the system provided by the invention have the advantages of high positioning accuracy, simple operations and good applicability for real-time operation in field.

The invention provides a visual positioning method for robot transport operation, which comprises a two-dimensional visual positioning method and a three-dimensional visual positioning method, whereinthe two-dimensional visual sense realizes that workpieces are free from mechanical precision positioning, and a robot can automatically compensate the grabbing function; and the three-dimensional visual sense solves the problem that automation production cannot be carried out by the positional deviation of positioning surfaces of the workpieces. The visual positioning method comprehensively applies two-dimensional visual positioning and three-dimensional visual positioning, solves the problems that workpieces to be processed are blank pieces, positions where the workpieces are grabbed are blank surface simultaneously, and the workpieces grabbed by the robot can not be fed accurately, improves the feasibility of production, has high flexibility, saves labor cost, and reduces labor intensity.

The invention discloses a navigation information acquisition method and an intelligent space system with multiple mobile robots. The intelligent space system comprises a distributed vision system and a Zigbee technology based wireless sensor network system. The method includes: carrying out image stitching based on a maximum gradient similar curve and an affine transformation model, and then carrying out image segmentation based on Otsu threshold segmentation and the mathematical morphology so that an environmental map is obtained. The mobile robots in navigation are positioned mainly by means of visual positioning, and Zigbee and DR (dead reckoning) combined positioning are used for making up visual blind zones in visual positioning supplementarily. The visual positioning refers to that positioning is realized by processing images including robot positions and direction signs mainly based on an HIS color model and the mathematical morphology. Combined positioning refers to that information fusion positioning of Zigbee and DR is achieved by the aid of a federal Kalman filter.

The invention discloses a binocular vision positioning method and a binocular vision positioning device for robots, and a storage medium. The binocular vision positioning method includes acquiring current binocular images and current positions and posture of the robots; acquiring historical key images from key libraries if the current binocular images are key images; splicing the current binocularimages and the historical key images according to the current positions and posture and historical key positions and posture to obtain vision point cloud maps; acquiring preliminarily built laser point cloud maps; optimizing the current positions and posture according to the vision point cloud maps and the laser point cloud maps. The historical key images acquired from the key libraries and the current binocular images have overlapped visual fields, and the historical key images are related to the historical key positions and posture. The binocular vision positioning method, the binocular vision positioning device and the storage medium have the advantages that position and posture estimated values are optimized by the aid of the preliminarily built laser point cloud maps at moments corresponding to key frames, and accordingly position and posture estimation cumulative errors can be continuously corrected in long-term robot operation procedures; information of the accurate laser pointcloud maps is imported in optimization procedures, and accordingly the binocular vision positioning method and the binocular vision positioning device are high in positioning accuracy.

The invention relates to a method for real-time vision positioning for a monocular camera, which belongs to the field of computer vision. The method comprises the following steps: firstly, acquiring an object image characteristic point set to establish an object image database and perform real-time trainings; secondly, modeling the camera to acquire model parameters of the camera; and thirdly, extracting a real-time image characteristic point set by the camera, matching real-time image characteristic points with the characteristic point set in the object database, and removing error matching and performing an affine inspection to acquire characteristic point pairs and object type information. The characteristic point pairs and the object type information are used to perform characteristic tracking, and accurate tracking characteristic points of the object image are combined with the model parameters of the camera so as to acquire three-dimensional poses of the camera. The method can achieve the functions of self-positioning and navigation by using a single camera only, thus the system complexity and the cost are reduced.

The present invention discloses a laser and vision-based hybrid location method for a mobile robot. The mobile robot comprises a laser radar and a vision sensor. According to the technical scheme of the invention, the weight of each particle at a predicted position is updated based on the collected data of the laser radar and the collected data of the vision sensor. After that, particles of higher weights are re-sampled, so that the real location distribution of the mobile robot at the moment t can be obtained. Compared with the prior art, the above technical scheme integrates the high accuracy of the laser radar with the information integrity of the vision sensor, thus being wider in application range. Meanwhile, the defect that the visual location is unstable is overcome. In addition, in one embodiment of the present invention, a conventional particle filtering sampling model is improved, so that the diversity of particles is ensured.

The invention provides a positioning and navigating method and device and processing equipment, and relates to the technical field of navigation. The method comprises the following steps that re-positioning is conducted by a visual off-line map to obtain primary position gesture information, wherein the visual off-line map is obtained by fusion mapping based on a visual device and an inertial measurement unit; a laser map established by a laser radar device is obtained; and positioning and navigating are conducted based on the primary position gesture information, target position information and the later map. The embodiment of the invention provides the positioning method and device and the processing equipment. Positioning and mapping are conducted simultaneously by the laser radar device and the visual device, excellent re-positioning performance of visual positioning is used for providing primary position and gesture for the laser map, positioning and mapping can be achieved in theunknown environment, the positioning and autonomous navigating functions in a mapped scenario are achieved, and excellent accuracy and robustness are achieved.

The invention discloses an indoor robot navigation device which is characterized by comprising a circuit board, wherein a motion control module, a navigation and location module, a map management and path planning module, an image acquisition and processing module, a safety module and a man-machine interaction management module. The invention also provides an indoor robot navigation technology. The technology is characterized by comprising the following steps of: (a) establishing a map and planning a motion path of the robot; (b) refining a area and setting a visual signpost; (c) acquiring and processing the visual signpost, and performing motion location and correction; (d) storing and querying area and signpost information. The device has the advantages of autonomous navigation, high interference resistance capacity, zero track movement and the like, and the problem that most of the conventional navigation modes are low in positioning precision is solved through visual positioning correction.

The invention discloses a pole tower model matching and visual navigation-based power unmanned aerial vehicle and an inspection method. In an unmanned aerial vehicle, a depth image of a front end of the unmanned aerial vehicle is acquired by a dual-eye visual sensor, distance between the unmanned aerial vehicle and a front object is further measured, a surrounding image is acquired by a cloud deckand a camera, the object is further identified, and the flight gesture of the unmanned aerial vehicle is controlled by flight control of unmanned aerial vehicle. The method comprises the steps of performing pole tower model building on different types of power transmission line pole towers; automatically identifying the power transmission line pole towers and pole tower types by the unmanned aerial vehicle during the flight process, matching and loading a pre-built pole tower model; performing visual positioning on the power transmission line pole towers by the unmanned aerial vehicle, and acquiring relative positions of the unmanned aerial vehicle and the pole towers; and performing flight inspection by the unmanned aerial vehicle according to optimal flight path. By the unmanned aerialvehicle, the modeling workload is greatly reduced, and the model universality is improved; and the inspection method does not dependent on absolute coordinate flight, the flexibility is greatly improved, the cost is reduced, and the power facility safety is improved.

The invention discloses a virtual robot and real robot integration based picking system. The virtual robot and real robot integration based picking system comprises a vision positioning system, a real robot and a virtual robot simulation system; a picking target is positioned through the vision positioning system and the real-time picking of the real robot is guided after the three-dimensional space coordinate information of the picking target is obtained; meanwhile the obtained three-dimensional space coordinate information is transmitted to the virtual robot simulation system through a data transmission line and the real-time simulation is performed on the picking process through a virtual robot. According to the virtual robot and real robot integration based picking system and method, a virtual simulation technology is combined with a machine vision technology, the robot under the virtual environment and the real robot are driven based on calculation data of a binocular vision system to perform the visual positioning and the picking behavior simultaneously, and accordingly the contrast of the accuracy of the vision positioning and the effectiveness validation of the picking behavior are implemented.

The embodiment of the invention discloses a vision localization method and device. In the method, according to a preset camera device, a preset scene is shot to obtain image data; on the one hand, according to first feature points of an image and spatial feature points in a semantic space map, vector information matching is conducted, and a first matching point set is obtained; on the other hand,second feature points, containing second semantic information, in the image data are extracted, the second feature points and the spatial feature points are subjected to semantic information matching,and a second matching point set is obtained; according to the first matching point set and the second matching point set, the target pose information and the target position information of the presetcamera device are obtained. In the method, the texture information and the semantic information of the image are utilized at the same time to extract the feature points, more feature points which aresuccessfully matched with the spatial feature points in the semantic space map can be found in the image data, a more reliable data basis is provided for calculating the target pose information and the target position information of the preset camera device, and the localization precision is higher.

The invention provides a task collaborative visual navigation method of two unmanned aerial vehicles. The method comprises the following steps: determining an interactive communication mode between a first unmanned aerial vehicle and a second unmanned aerial vehicle, wherein the first unmanned aerial vehicle is used to perform visual positioning, and the second unmanned aerial vehicle is used to perform environment identification route planning; performing fusion processing on visual positioning information generated by the first unmanned aerial vehicle and route information generated by the second unmanned aerial vehicle to generate respective flight control instruction information of the first and second unmanned aerial vehicles at all times; transferring the flight control instruction information to the corresponding first and second unmanned aerial vehicles respectively by the interactive communication mode so as to perform visual navigation safe flight. The method provided in the invention can effectively control information transmission volume of real-time videos and image transmission in cooperative visual navigation of the unmanned aerial vehicles, has advantages of good match capability and good reliability, and is an effective technology for implementing cooperative visual navigation of unmanned aerial vehicles cluster to avoid risks, barriers and the like.

The invention provides an urban area and indoor high-precision visual positioning system and method. The image information of a surrounding environment is acquired based on a visual sensor to realize high-precision urban area and indoor positioning. The method comprises the steps that the distinguishing feature information of an image is calculated and extracted after the visual sensor captures the scene image information; according to the distinguishing feature information, similarity degree recognition and matching are carried out in the feature information base of a digital three-dimensional model; according to matching coordinate information recorded in an image feature matching process, a geometrical mapping relation from a three-dimensional scene to a two-dimensional image is restored, and a camera intersection model from a two-dimensional image coordinate to a three-dimensional space coordinate is established to determine the three-dimensional position and attitude information of the visual sensor and a dynamic user; multi-source image information captured by the visual sensor is received; a digital three-dimensional model corresponding to a real scene is reconstructed or updated; and the feature information base is updated. According to the invention, robust and sustainable positioning ability is provided when the surrounding environment changes.

The invention discloses a binocular vision positioning and three-dimensional mapping method for an indoor mobile robot. A binocular vision positioning and three-dimensional mapping system for the indoor mobile robot is mainly composed of a two-wheeled mobile robot platform, an odometer module, an analog camera, an FPGA core module, an image acquisition module, a wireless communication module, a storage module, a USB module and a remote data processing host computer. The FPGA core module controls the image acquisition module to collect information of a left image and a right image and sends the information of the left image and the right image to the remote data processing host computer. Distance information between images and the robot is obtained on the remote data processing host computer according to the information of the left image and the right image in a fast belief propagation algorithm, a three-dimensional environmental map is established in the remote data processing host computer, recognition of a specific marker is realized in an improved SIFT algorithm, and then the position of the mobile robot is determined through information integration in a particle filter algorithm. The binocular vision positioning and three-dimensional mapping system is compact in structure and capable of having access to an intelligent space system so that the indoor mobile robot can detect the environment in real time and provide more and accurate services according to the corresponding position information at the same time.

The invention discloses a combination manufacturing method and device for an injection mold with a conformal cooling water path. The device comprises a light beam focusing system, a close wave length coaxial vision positioning system, a powder pavement system and a gas protection system. The gas protection system comprises a sealed forming chamber, a shielding gas device and a powder purification device, wherein the shielding gas device is connected to one side of the sealed forming chamber, and the powder purification device is connected to the other side of the sealed forming chamber. The method is a combination processing method combined with the laser region selection fusion technology and the precision cutting processing technology, the advantages of the laser region selection fusion flexible processing are retained, and the feature that the precision of the high-speed cutting processing is good is given to play. In the process of region selection laser fusion processing, laser surface refusion processing is carried out on each layer, and the compactness and the surface quality of the mold are improved. The technique of density changing rapid manufacturing is adopted, and manufacturing efficiency is improved. Precision mold components with the interior special-shape cooling water path and the complex inner cavity structure can be integrally processed at a time.

The invention provides an indoor positioning method, and relates to a wireless communication network technology for network management. A method combining positioning based on a WiFi fingerprint and visual positioning based on a label is adopted. The method comprises the following steps: firstly, acquiring a WiFi positioning range and a WiFi positioning coordinate by using a WiFi position fingerprint positioning algorithm; secondly, acquiring a visual positioning coordinate according to feature matching and visual positioning of a tested image; lastly, combining WiFi position fingerprint positioning with visual positioning to realize high-accuracy indoor positioning. By adopting method, the defects that the conventional WiFi fingerprint positioning technology has low accuracy and the conventional single visual positioning method technology is not suitable for indoor positioning are overcome.

A visual positioning and multi-functional safety monitoring network system used in a mine well adopts a method of radio frequency information identification positioning. Workers and mobile equipment in the well are equipped with a radio frequency identification card. A single-stage or multi-stage information acquisition base stations are arranged in the well according to the distribution of operating districts, and various sensors are connected to sensor ports at the base stations based on the requirement of mine monitoring items. As a person carries the identification card when entering the well and the information acquisition base stations are arranged from a well inlet to every operating points, the card carried by the person will be read when the person passes each information acquisition base station, and the station will transmit the positioning information read from the card and the information of all monitoring parameters acquired by the sensors to a monitoring mainframe on the ground. Moreover, a set of multi-functional comprehensive monitoring system application software is used to realize the dynamic management and all-round safety monitoring of the person in the well.

The invention provides a detection method for rectangular pin component visual positioning, and relates to the field of visual positioning and detection of rectangular pin components. The method aims to solve the problems that a traditional rectangular pin component detection method is low in positioning precision, pins break in images and deviation and deviation angles are detected separately. The method is characterized in that a measured component image is obtained by means of a chip mounter visual system, an image after binary pre-processing is obtained through threshold segmentation, a communication area of the component pins is marked, the shape of the component pins is judged, pixel-level Harris angular point coordinates of the pin image are extracted, sub-pixels of Harris angular points are solved and classified, the deviation angles of components are calculated, the pin image is matched with a standard image, and the deviation of the component is calculated. The method is mainly used for pin detection, deviation angle detection and deviation detection of the rectangular pin components.

The invention provides a network training method. The invention discloses an incremental mapping method, device and equipment, and relates to the technical field of visual positioning, and the methodcomprises the steps: obtaining a training sample, enabling the images in a first image set and the images in a second image set in the training sample to be similar images, and enabling the images inthe first image set and the images in a third image set to be non-similar images; Inputting the training sample into a scene recognition network, wherein the scene recognition network comprises threedeep hash-based lightweight neural networks which have the same structure and share parameters; And training the scene recognition network by using the training sample until the loss function converges, and taking the corresponding parameter when the loss function converges as the parameter of the scene recognition network. The network training method, the incremental mapping method, the positioning method, the positioning device and the equipment provided by the embodiment of the invention can run on a low-end processor in real time, so that the degree of dependence on hardware is reduced.

The invention relates to a transformer substation inspection robot path planning navigation method. The method comprises the steps that a robot walks one circle around a transformer substation, and a two-dimensional grid map of the transformer substation is generated; transformer substation equipment image information is scanned, and a feature image is selected to serve as a road and equipment identification basis; an optimal inspection path is planned; surrounding environment information is scanned to generate a two-dimensional grid map of the surrounding environment, the position where the inspection robot is located is identified by comparing the surrounding environment map with the transformer substation map, and rough positioning is achieved; surrounding equipment image information is acquired, the equipment position is identified by comparing the surrounding environment image information with an equipment feature image, errors generated in the map matching link are corrected, and then higher-precision positioning is achieved; whether map matching positioning and visual positioning are in a same area or not is inspected, if yes, it is proved that positioning is accurate, and if not, it shows that positioning is wrong, and then map matching positioning and visual positioning are conducted again. Therefore, the positioning navigation reliability and accuracy are greatly improved.

The invention relates to an independent sound source searching and positioning method which is based on a mobile robot and comprises the following steps: firstly, a microphone array is utilized to carry out initial positioning to a target sound source: an array which consists of four microphones is arranged at the simulated head part of the mobile robot, wherein, the four microphones are respectively distributed and arranged on the four vertex positions of the biggest inscribed square of the exterior frame circle of the simulated head part of the robot, the distance among the microphones are equal and the left and right ears of the mobile robot are formed to be used for respectively collecting two-way aural signals of the target sound source, then the initial position of the target sound source can be obtained after the two-way aural signals are treated with mathematical treatment based on time delay; secondly, aural positioning and visual positioning are fused: namely, after the initial position of the target sound source is obtained, the simulated head part of the robot is horizontally rotated by utilizing azimuth angle information and rotated up and down by utilizing pitch angle information, or the mobile robot body is simultaneously moved so as to cause the target sound source to be within the visual field of the robot; finally, visual signals are utilized to carry out accurate visual positioning to the target sound source.

The invention provides a visual SLAM algorithm based on instance segmentation, and the algorithm comprises the steps: firstly extracting feature points of an input image, and carrying out the instancesegmentation of the image through employing a convolutional neural network; secondly, using instance segmentation information for assisting in positioning, removing feature points prone to causing mismatching, and reducing a feature matching area; and finally, constructing a semantic map by using the semantic information segmented by the instance, thereby realizing reuse and man-machine interaction of the established map by the robot. According to the method, experimental verification is carried out on image instance segmentation, visual positioning and semantic map construction by using a TUM data set. Experimental results show that the robustness of image feature matching can be improved by combining image instance segmentation with visual SLAM, the feature matching speed is increased,and the positioning accuracy of the mobile robot is improved; and the algorithm can generate an accurate semantic map, so that the requirement of the robot for executing advanced tasks is met.