190results about How to "Improve mapping accuracy" patented technology

The disclosure relates to a method and a device for single frame super resolution reconstruction based on sparse domain reconstruction, The disclosure mainly solves the technical problem in the prior art that the reconstructed image with high quality cannot be obtained by selecting the appropriate interpolation function according to the prior knowledge of the image. The disclosure adopts the first paradigm of the example mapping learning to train the mapping M of the low resolution feature on the sparse domain Bl to the high resolution feature on the sparse domain Bh and the mapping of the high resolution feature on the sparse domain Bh to the high resolution feature YS, equalizing the mapping error and the reconstruction error to the mapping operator M, the reconstructed high-resolution dictionary Φh and the reconstructed high-resolution sparse coefficient Bh, the better solution to the problem, can be used for graphics processing.

The invention relates to the technical field of three-dimensional reconstruction. The invention discloses a three-dimensional point cloud reconstruction method based on laser radar. The method comprises the following steps: data acquisition and preprocessing, feature extraction, feature matching, motion estimation, point cloud fusion and the like. The three dimensional environment real-time mapping function is achieved through a two-dimensional laser radar, and compared with the scheme based on a multi-line laser radar, the three-dimensional point cloud reconstruction method has the advantagesof being low in cost, good in motion distortion removing effect, high in real-time performance and high in mapping precision and has high practical significance for popularization and application ofthe three-dimensional environment reconstruction technology.

The invention provides a multi-sensor fusion based SLAM and obstacle avoidance mobile chassis capable of improving the mapping accuracy and achieving accurate obstacle avoidance, and belongs to the technical field of robots. The mobile chassis comprises: an environment sensing module configured to acquire environmental data around a chassis body through a laser sensor and a visual sensor; a bottomsensing module configured to acquire the rotation directional angular displacement of the chassis body and surrounding obstacle information; a control module configured to: process the environmentaldata to construct a map, determine a position of an obstacle according to the obstacle information, acquire a motion control instruction for the chassis body, transmit the command to a servo drive module to realize obstacle avoidance, and configured to receive a linear displacement of the chassis body returned by the servo drive module, and acquire a current pose of the chassis body according tothe rotation directional angular displacement; and the servo drive module configured to drive the chassis body according to the motion control command so as to achieve speed control, and acquire the linear displacement information of the chassis body.

A robot using an absolute azimuth to navigate and a mapping method thereof. The robot includes a control unit controlling a traveling direction of a body of the robot by using the absolute azimuth, which indicates an orientation of the body with respect to a specified reference axis, and a drive unit moving the body under the control of the control unit.

The invention discloses a computer surveying instrument for geological engineering construction. The computer surveying instrument comprises telescopic supporting feet, inserting holes, a locking screw I, a connecting seat, a fixing seat, a ball body, an upper dustproof layer, a mounting seat, an upper connecting head, a locking screw II, a pressing pad, a sliding block, a screw rod, a knob, an end cover, a lower dustproof layer, a lower connecting head, a threaded hole, external threads, a fixing sleeve, a connecting rod and a counterweight ball. The computer surveying instrument is reasonable and simple in structure, low in production cost, convenient to install and complete in function, wherein cone bodies are arranged at the bottoms of the telescopic supporting feet, and the stabilityand reliability of the support of the telescopic supporting feet are improved; according to the computer surveying instrument, the mounting seat on the upper side of the ball body is automatically adjusted to be in a horizontal state through the action of gravity; when the counterweight ball is in a static state, the knob is tightened to drive the sliding block to drive the pressing pad to press the ball body so that the ball body cannot rotate; and then an surveying instrument body can be directly mounted on the mounting seat, so that the mounting precision and efficiency are improved.

The invention provides an outdoor large-scale scene three-dimensional mapping method fusing multiple sensors. The implementation process is divided into two modules, namely a visual inertia odometer module, and a laser odometer and mapping module. The visual inertia odometer module comprises optical flow tracking, IMU pre-integration, initialization, sliding window optimization, marginalization and word bag model establishment. The laser odometer and mapping module comprises point cloud segmentation, point cloud distortion removal, feature extraction and inter-frame matching, loopback detection and mapping. Compared with a single radar mapping scheme, the high-frequency pose of the visual inertia odometer is fused, and the method has the advantages of being good in point cloud distortion removal effect, high in loopback detection precision and high in mapping precision. The problem that an outdoor large-scene three-dimensional map is low in precision is solved, and a breakthrough is provided for further development of unmanned driving.

The invention relates to a distribution network data processing method based on a mobile GIS (Geographic Information System) and RTK (Real Time Kinematic) positioning. The method comprises the following steps: performing data preparation and storage; implementing a Web application server subsystem; implementing a geographic information subsystem; implementing a distribution network data management subsystem; implementing a task and form data management subsystem; implementing a document management subsystem; implementing a mobile terminal operation subsystem; implementing an RTK coordinate acquisition subsystem; and executing a distribution network patrol task. Through adoption of the distribution network data processing method, the working efficiency of data processing by distribution network equipment is increased; the production services of patrol, overhauling and the like are effectively extended to a job site; the service continuity and efficiency are realized; the on-site working quality and efficiency are improved; the mapping precision is increased; on-site working procedures are effectively standardized and guided; the operation cost is lowered; repeat operation is avoided; and a standard service flow combined with mobile operation is established.

The invention provides an SLAM drawing method and system based on multi-sensor fusion, and the method and system are used for a server. The method comprise the steps of: acquiring multiple sensor dataof a mobile platform related to the surrounding environment, wherein the multiple sensor data comprises point cloud data, image data, IMU data and GNSS data; performing hierarchical processing on themultiple sensor data to generate a plurality of pieces of positioning information; wherein one sensor data corresponds to one piece of positioning information; acquiring target positioning information of the mobile platform based on the plurality of pieces of positioning information; generating a local high-precision map based on the target positioning information; and performing closed-loop detection operation on the local high-precision map to obtain a high-precision global map of the mobile platform. The technical problem of low precision due to easy limitation by the surrounding environment in the prior art is eased.

The invention discloses a ground control and measurement stationing method based on an onboard interferometric synthetic aperture radar (InSAR). The method comprises the following steps of: 1, designing a flight line, namely determining a range of a region to be plotted according to pre-collected information of a detection region terrain and designing the number N of sorties required to fly and the flight line of each sortie according to the determined range of the region to be plotted and flight parameters during plotting; 2, arranging calibration fields, namely arranging one or two calibration fields for radiating and geometrically calibrating an onboard InSAR system inside or outside the detection region; 3, stationing plotting control points; and 4, scanning flight, namely after the N sorties fly in the calibration fields and the detection region, acquiring InSAR measurement data in the region to be plotted. By the method, the steps are rational in design, the use operation is simple, and the using effect is good; and the shortcoming that the onboard InSAR terrain plotting control and measurement cannot be instructed according to the technical rule of the conventional optical system is overcome.

The invention discloses an artificial intelligence-based method for establishing a real time part level model of a turbo shaft engine. A method for solving a co-working equation of the turbo shaft engine is solved by adopting intelligent mapping. The method comprises the steps of taking a part co-working balance equation initial residual as an intelligent mapping network input and a balance equation guess value correction as a network output, training an extreme learning machine (ELM), and adopting an ADE (adaptive difference evolution) algorithm to optimize parameters of the extreme learning machine, thus improving the network mapping degree. An adaptive zoom factor is adopted in the ADE algorithm, and the optimizing capacity of a DE algorithm is improved. Results show that the maximal model error of the artificial intelligence-based method for establishing the real time part level model of the turbo shaft engine is one third of that of a one-shot algorithm, and the model operation time consumption is one third of the one-shot algorithm.

The invention provides an optical system for stereo mapping with a low base-height ratio, which is used in a bias-field, adopts a coaxial tri-mirror system in which a primary mirror, a secondary mirror, a tertiary mirror and a reflecting plane mirror are completely shared, and is formed by combining two independent optical imaging paths. Two groups of incident light rays each of which has an included angle of 1 to 6 degrees sequentially reach the primary mirror, the secondary mirror and the tertiary mirror; and finally, the incident light rays are respectively reflected to two independent receiving image planes for imaging by the reflecting plane mirror. By using the bifocal surface as well as the primary mirror, the secondary mirror, the tertiary mirror and the reflecting plane mirror which are simultaneously shared, the invention is capable of simultaneously imaging in front and rear fields of view, therefore, the stereoscopic mapping with a low base-height ratio and high precision can be achieved by the reflection-type optical system capable of imaging on a single-camera and double-channel basis. The optical system has the advantages of high optical-mechanical structural integrity, small size, light weight, convenient real-time on-orbit detection and high stability of inner orientation elements. Therefore, the optical system is particularly applicable to single-track push-broom stereo imaging and mapping by a satellite camera in surveying and mapping with a low base-height ratio.

A traffic accident site rapid mapping system based on image guiding comprises a homography matrix solution module, a space coordinate transformation module, a re-sampling module, a mapping and marking module and a file preserving and printing module. The homography matrix solution module builds a mapping relationship between a traffic accident site picture image plane and an actual road plane according to the two-dimensional direct linear transformation method, the space coordinate transformation module restores the position information of a traffic site picture in object space according to the homography matrix and scales the range of the traffic accident site to the size range of the original traffic accident site picture, the re-sampling module restores gray information of the traffic accident site picture in object space and achieves transformation from a perspective picture to an orthographic projection picture of the traffic accident site picture, the mapping and marking module achieves direct mapping and relevant size marking of the traffic accident site information on the orthographic projection picture, and the file preserving and printing module achieves functions of preservation and site printout of the traffic accident site picture. By means of the traffic accident site rapid mapping system, the accuracy of traffic accident site survey is improved, the on-site data processing and mapping time is saved, and the requirement of site picture printout on the traffic accident site is further satisfied.

The invention discloses a method and device for acquiring a high-precision submarine topographic and geomorphologic map. The method comprises the steps of acquiring navigation data, replacing navigation data in detection data of bathymetric sidescan sonar by using effective navigation data in the navigation data, acquiring rewritten detection data, and performing rejection, correction and filtering processing on the written detection data to acquire primary detection data; processing bathymetric data in the primary detection data to acquire processed bathymetric data; processing sidescan data in the primary detection data to acquire processed sidescan data; replacing the primary detection data by using the processed bathymetric data and the processed sidescan data to acquire final detection data; and mapping by using the final detection data to acquire a submarine topographic and geomorphologic map. The submarine topographic and geomorphologic map acquired according to the invention is closer to the real submarine topography and geomorphology, the image precision is higher, and the mapping speed is high.

The invention discloses a multi-area array aerial camera platform calibration method with a constraint condition. The method includes: employing a data acquisition strategy of multiple cross flying camera station exposure to acquire multiple groups of sub-images with an adjacent virtual image overlap degree of more than 80%; making use of the control point of a ground calibration field to calculate a photographing centre distance of sub-cameras and a sub-camera line element; during aerotriangulation, conducting bundle block adjustment, according to the control point coordinate, the connection points among matched sub-images, and the external orientation element initial value, establishing a model through a collinearity equation, adopting the photographing centre distance of the sub-cameras as a given value, i.e. taking the sub-camera line element constant as the constraint condition, and taking platform calibration parameters as a whole to perform calculation to solve the angle elements in the external orientation elements of the sub-images. According to the calibration method, a lot of uniformly distributed connection points are matched, precision of the platform calibration parameters is improved through the constraint condition, higher stitching precision of the generated virtual images can be guaranteed, and the mapping precision can be higher.

The invention discloses a software defect prediction method. According to the method, a sample with a class label and a sample without a class label are processed together, semi-supervised learning is utilized in the laplacian eigenmaps (LE), the LE method is improved, and meanwhile, in order to avoid that samples different in classification are mapped to a small low-dimensional neighbourhood, especially that defect samples are mapped to a defect-free sample neighbourhood, cost-sensitive information is introduced when the sample point distance is calculated through an LE algorithm. On the basis, the LE mapping precision is improved, and the discriminating performance of discriminating performance can be effectively improved through the method. The invention further provides a software defect prediction system. When the software defect prediction method and system are applied to an NASA database, it is proved through experiments that the effectiveness of the method is improved, and compared with other comparative methods, the classification performance of the method is improved to a certain extent.

The invention discloses a high-precision absolute distance measurement system based on an interferometric phase comparison method, belonging to the technical field of precision measurement. The system equals to the improvement on an absolute distance measurement system based on a traditional frequency scanning interferometry method, and comprises a single frequency tunable external cavity laser, a three-way optical heterodyne interferometer and a phase measurement comparison system. The single frequency tunable external cavity laser is used for laser frequency scanning, the three-way optical heterodyne interferometer is adopted for obtaining heterodyne interference signals of a reference interference arm, a measurement interference arm and a calibration interference arm in the process of laser frequency scanning, then the phase measurement comparison system is used for extracting interference phase drift distances of the calibration interference arm and the measurement interference arm in the frequency scanning process, the interference phase drift distances are in direct proportion with optical path differences of the interference arms, and therefore, the absolute distance can be measured by comparing the interference phase drift distances of the two paths of the interference arms. By adopting the three-way optical heterodyne interferometer and the phase measurement comparison system, the system does not need to measure an air refractive index when compared with the traditional frequency scanning absolute distance measurement systems, the system can overcome frequency drift and avoids the scanned range for measuring laser frequency, and therefore, frequency calibration devices, such as a Fabry-Perot cavity, and the like, are not needed.

The invention discloses a laser radar mapping method in an indoor scene. Parameters of all positions of a vehicle are collected, calculated and corrected through UWB and a laser radar odometer. The indoor positioning precision of the UWB positioning technology is not reduced along with the increase of time, the UWB positioning technology has the characteristics of being high in positioning precision, good in reliability, not prone to divergence and the like, but the positioning continuity of data is poor, the error of the attitude and position precision of the laser odometer is gradually increased along with the increase of time, and the positioning continuity is good. The UWB positioning technology is high in positioning precision, so that the positioning precision of the laser odometer can be remarkably improved through image optimization and fusion of the UWB positioning technology and the laser odometer, and then the indoor mapping precision is improved. In addition, the inventionalso provides a laser radar mapping device in an indoor scene , and equipment and a computer scale storage medium, which have the above beneficial effects.

The invention provides a time synchronization method and system of an LMCCD (line matrix CCD) camera, and relates to a time synchronization system. The time synchronization method and system are used for solving the problems that an existing stereoscopic plotting camera in scanning imaging generates positioning errors so as to cause that the positioning accuracy of a plotting image is low, the requirement on high time accuracy cannot be satisfied and the like. According to the time synchronization system, a time scale generation function module and a sensor timing sequence generation module are integrated in a same chip so as to shorten time delay in obtainment of a time scale and uncertain time of the time delay; a pure hardware working mode triggered by a counter is adopted by the time scale generation function module, so that additional time errors caused by adopting a software mode are avoided; timing deviations caused by frequency drifting of crystals are decreased by adopting a self-correcting working mode; the line period of a linear array CCD and the frame period of an area array CCD are calculated according to the height of a track, a pixel size, a principal distance and an intersection angle; and adjustment strategies of the frame period of the area array CCD are stipulated so as to ensure that camera shooting can be carried out by the area array CCD at an oriented moment while the synchronization of the area array CCD and the linear array CCD is maintained.

The invention relates to a traffic accident road base map information processing method based on a topographic map and an image. The method comprises a first step of pre-processing topographic map data, a second step of pre-processing image data, a third step of matching the topographic map data processed by the first step and the second step with the image data, a fourth step of selecting various road information on the topographic map data and the image data according to set code requirements and automatically generating a road base map, and a fifth step of revising the road base map through field investigation and plotting. Compared with the prior art, the traffic accident road base map information processing method based on the topographic map and the image has the advantages of being high in mapping precision and full in data covering and the like. The data is easy to transfer and store, and traffic accident management time can be shortened.

The invention discloses a controlling method of an electric spark wire cutting machine and the machining parameters of the electric spark wire cutting machine are adjusted according to the image characteristics of spark discharge. Every time the machining scenes of electric spark wire cutting, such as the electrical parameters, the movement parameters, the materials and the like, are correspondingto the specific spark discharge forms, such as the spark count, the spark strength, the spark density and the like, so that it can be directly judged that the machining state is over feed, lack of feed or regular feed by the spark discharge forms which are the optical signals; compared with the conventional controlling production manner that the machining state is indirectly judged by the electrical signals, the manner of judging the machining state by the spark signals is directer, so that the cutting accuracy of the electric spark wire cutting machine can be further improved by using the controlling method; meanwhile, the prejudge of the short circuit can be realized by using the controlling method and the breakage of a wire electrode caused by the short circuit can be effectively reduced. Moreover, the invention further discloses the electric spark wire cutting machine and the effect is as above.

A vehicle position estimating apparatus may include a position estimation device that maps objects recognized by a sensor of the vehicle and located around of the vehicle to a parking lot map and estimates a position of the vehicle based on movement information related to the vehicle, a weight setting device that predicts a mapping accuracy of the objects using a detected result of a landmark mapped to the parking lot map by the sensor and gives a weight to each particle corresponding to an interest point of each object based on the predicted mapping accuracy of the objects, and a position correction device that corrects the estimated position of the vehicle using the each weighted particle.

The invention discloses a small-sized unmanned plane camera orientation calibrating device and a calibrating method. The small-sized unmanned plane camera orientation calibrating device comprises a base, a laser pen, and four pull rods. The central position of the upper surface of the base is provided with a laser emission rack, and the laser pen is vertically and fixedly disposed in the laser emission rack. One end of each of the four pull rods is rotatably connected with the side surface of the base, and an included angle between any two pull rods in a horizontal plane is 90degrees. The other ends of the pull rods are provided with mark points having eye-catching colors. The pull rods can be telescoped along an axial direction, and by taking the positions of the rotatable connection between the pull rods and the base as centers, the pull rods are bent upwards, and the states of the axes are changed from the horizontal states to the vertical states. The device provided by the invention is simple in structure, and is convenient in operation, and at the same time, by combing with the calibrating method provided by the invention, the fast and effective calibrating process of the orientation of the cradle head of the camera of the small-sized unmanned plane vertical to the ground is realized.

The invention discloses a method for extracting a feature point of a building based on oblique photogrammetry, a device and a storage medium. The method comprises the following steps: constructing a real three-dimensional model of an appointed building according to multiple oblique images; selecting three non-collinear points from external vertical walls of the real three-dimensional model, thereby calculating optimal planes corresponding to the external vertical walls; calculating an intersecting line of two adjacent external vertical walls according to the optimal planes corresponding to thetwo adjacent external vertical walls in the real three-dimensional model; extracting an intersection point of the intersecting line and the optimal planes of other external vertical walls in the realthree-dimensional model and taking the intersection point as the feature point of the real three-dimensional model. According to the method, the feature point of the building can be accurately extracted according to multiple oblique images, so that the surveying and mapping accuracy and efficiency of the building are increased.

The invention relates to an self-adjusting foundation bed of level and theodolite, which is characterized in that it arranges horizon sensor on the adjusted base including a Y-type insulating triplet pipe with conductive liquid arranged on the surface of the base; each end of the pipe arranges a slope detesting switch with one contact is conductive liquid, while the other contact is a conductive needle which is fixed on the upper part of the conductive liquid and laid on the pipe end of the triplet pipe; it arranges height adjuster on the corresponding location of the base which is driven by the motor and which is a screw mechanism of the pipe end height of the triplet pipe; the motor uses the switch signal outputted form the corresponding pipe end slope testing switch as opening and ending control signal. The invention improves the surveying and mapping precision of level and theodolite.

The invention discloses a mapping method and system based on visual semantic point cloud, which can extract semantic information through deep learning frameworks such as semantic segmentation, targetdetection and the like, can add point cloud registration constraints into an SLAM system and perform post-processing on a point cloud map in combination with an octree map, effectively improves the mapping accuracy; According to the method and device, after the octree is used for filtering the original point cloud, the central coordinates of the occupied voxel and the semantic information of the voxel of the octree map are converted into the semantic point cloud map again, so that redundant points in the original map are greatly reduced, the storage space is saved, and subsequent computing resource consumption is reduced; meanwhile, the problem that the map is difficult to use after being converted into the octree structure is also solved.

The invention discloses a joint topographic mapping method based on a space-borne SAR image and an optical image. The method comprises the following steps: constructing a SAR positioning model to realize high-precision positioning of the SAR image; constructing a space-borne SAR stereo model, and acquiring topographic map elements based on the stereo model; establishing a registration model of theSAR image and the optical image with relatively low resolution to realize matching of the optical image with the pixel level of the SAR image positioned in the step S1; and jointly performing automatic extraction of a ground object target based on the low-resolution optical image and the SAR image after registration, and fusing an extracted element vector with the acquired element vector of the SAR stereo model to integrate a digital line drawing result. The method can be applied to domestic high-resolution No.3 SAR images and foreign SAR images, reduce the cost of production using airborne SAR image mapping, promotes domestic SAR satellite application, improves mapping accuracy, and has important theoretical significance and application popularization value.

The invention discloses a mapping method and device for patent data and industrial data. The method comprises the steps that the patent data and the industrial data are acquired, wherein the patent data comprises at least one patent class, literature data contained in each patent class and class annotation data of each patent class, and the industrial data comprises at least one industrial class and class annotation data of each industrial class; a first similarity between the class annotation data of the industrial classes and the literature data contained in the patent classes and a second similarity between the class annotation data of the industrial classes and the class annotation data of the patent classes are calculated; and a mapping relation between the patent data and the industrial data is established according to the first similarity and the second similarity. Through the mapping method and device, the technical problems that a mapping relation determined through an existing mapping method needs to be adjusted manually, and the existing mapping method is low in accuracy are solved.

The invention discloses a multi-aircraft cooperative high-precision mapping and positioning system for unmanned aerial vehicles, belongs to the field of algorithms of unmanned aerial vehicle cluster control strategy planning, particularly relates to a multi-aircraft cooperative mapping and positioning system for the unmanned aerial vehicles, and solves the problem that in the existing mapping process, mapping of the dynamic environment cannot be achieved stereoscopically and rapidly. The multi-aircraft cooperative high-precision mapping and positioning system comprises a communication base station, a wireless local area network is established through utilizing the wireless base station, and the wireless local area network covers a target region; an unmanned aerial vehicle environment sensing system acquires target region point cloud data, unmanned aerial vehicle height data and unmanned aerial vehicle positioning data in a point cloud scanning mode; a control system is used for controlling the flight speed, angle and pose of each unmanned aerial vehicle according to the positions of the multiple unmanned aerial vehicles at different moments; and an unmanned aerial vehicle cooperative mapping control system plans flight paths of the unmanned aerial vehicles according to the target region, establishes a coordinate system, and fuses the point cloud data scanned by the multiple unmanned aerial vehicles to obtain a three-dimensional image of the target area. The multi-aircraft cooperative high-precision mapping and positioning system is suitable for mapping of unknown regions.