Patents
Literature
49 results about "Monocular slam" patented technology
Efficacy Topic
Property
Owner
Technical Advancement
Application Domain
Technology Topic
Technology Field Word
Patent Country/Region
Patent Type
Patent Status
Application Year
Inventor
Real-time dense monocular SLAM method and system based on online learning depth prediction network
ActiveCN107945265AGood effectImprove accuracyDetails involving processing stepsImage analysisStochastic gradient descentMonocular slam
The invention discloses a real-time dense monocular simultaneous localization and mapping (SLAM) method based on an online learning depth prediction network. The method comprises: optimization of a luminosity error of a minimized high gradient point is carried out to obtain a camera attitude of a key frame and the depth of the high gradient point is predicted by using a trigonometric survey methodto obtain a semi-dense map of a current frame; an online training image pair is selected, on-line training and updating of a CNN network model are carried out by using a block-by-block stochastic gradient descent method, and depth prediction is carried out on the current frame of picture by using the trained CNN network model to obtain a dense map; depth scale regression is carried out based on the semi-dense map of the current frame and the predicted dense map to obtain an absolute scale factor of depth information of the current frame; and with an NCC score voting method, all pixel depth prediction values of the current frame are selected based on two kinds of projection results to obtain a predicted depth map, and Gaussian fusion is carried out on the predicted depth map to obtain a final depth map. In addition, the invention also provides a corresponding real-time dense monocular SLAM system based on an online learning depth prediction network.
Owner:HUAZHONG UNIV OF SCI & TECH
Real augmented reality method based on ORB-SLAM and depth camera
InactiveCN106548519AEasy to handleReal experienceImage analysisCharacter and pattern recognitionMonocular slamBlock effect
A real augmented reality method based on ORB-SLAM and a depth camera comprises the following steps: (1) determining an initial coordinate plane by use of a Marker-less technology, and initializing a slam coordinate system with real scales; (2) importing a map, and combining a directly expressed map with a feature map according to extracted feature points; (3) using monocular SLAM o build a real scale map, and saving the map; (4) placing a virtual object in a scene, and calculating the distance between the virtual object and the camera through a 3D engine; and (5) using the depth camera to get scene depth data, and performing deep fusion according to the distance data of the virtual object obtained in the 3D engine to achieve a blocking effect and make the real object and a virtual model have strong interaction directly. The method is of very strong robustness, and realizes blocking interaction between a real object and virtual data.
Owner:上海玄彩美科网络科技有限公司
Dynamic scene visual positioning method based on image semantic segmentation
ActiveCN110084850AHigh positioning accuracyImprove robustnessImage analysisNeural architecturesMonocular slamImage segmentation
The invention discloses a dynamic scene visual positioning method based on image semantic segmentation, and belongs to the field of SLAM (Simultaneous Localization and Mapping). The method comprises the following steps: firstly, segmenting a dynamic object in an original image by adopting a supervised learning mode in deep learning to obtain a semantic image; on the basis, extracting ORB feature points from the original image, and removing the feature points of the dynamic object according to the semantic image; and finally, based on the removed feature points, positioning and tracking the camera motion by adopting a monocular SLAM method based on point features. A positioning result shows that compared with a traditional method, the method disclosed by the invention has the advantage thatthe positioning precision in a dynamic scene is improved by 13% to 30%.
Owner:SOUTHEAST UNIV
Initialization method and system of monocular SLAM algorithm
ActiveCN110060202AImprove stabilityImprove calculation accuracyImage analysisGeometric image transformationMonocular slamBinocular distance
The invention provides an initialization method and system of a monocular SLAM algorithm. The method comprises the following steps of selecting pixel points in the image overlapping area from the acquired image; converting the selected pixel points into pixel points corresponding to the binocular SLAM algorithm; and calculating the three-dimensional coordinates of the converted pixel points in theimage overlapping area based on a binocular SLAM algorithm, converting the three-dimensional coordinates of the pixel points into coordinate information of a camera coordinate system, and initializing the monocular SLAM algorithm according to the coordinate information of the camera coordinate system. Therefore, according to the embodiment of the invention, the monocular SLAM algorithm can be assisted to realize initialization according to the binocular SLAM algorithm, so that the monocular system corresponding to the monocular SLAM algorithm can realize initialization faster and better, andthe stability and the calculation precision of the monocular SLAM algorithm are improved.
Owner:ECARX (HUBEI) TECHCO LTD
Pseudo rgb-d for self-improving monocular slam and depth prediction
A method for improving geometry-based monocular structure from motion (SfM) by exploiting depth maps predicted by convolutional neural networks (CNNs) is presented. The method includes capturing a sequence of RGB images from an unlabeled monocular video stream obtained by a monocular camera, feeding the RGB images into a depth estimation / refinement module, outputting depth maps, feeding the depth maps and the RGB images to a pose estimation / refinement module, the depths maps and the RGB images collectively defining pseudo RGB-D images, outputting camera poses and point clouds, and constructing a 3D map of a surrounding environment displayed on a visualization device.
Owner:NEC CORP
Improved nonlinear optimization method of monocular inertial navigation SLAM
PendingCN110726406AAddressing Scale UncertaintyRestore scale factorNavigation by speed/acceleration measurementsPattern recognitionMonocular slam
The invention discloses an improved nonlinear optimization method of monocular inertial navigation SLAM. On the basis of the VINS-Mono engineering, the nonlinear optimization method is used for coupling IMU data in a tight coupling manner. The method comprises the steps of: image and IMU preprocessing; initialization; back-end sliding window optimization; and closed-loop detection and optimization. According to the improved nonlinear optimization method disclosed by the invention, algorithm improvement is performed based on the existing VINS.mono, a test is performed on a public data set EuRoC, and contrastive analysis is performed on the previous VINS.mono scheme. The results show that the IMU initialization can well restore a scale factor of the system, solve the problem of monocular SLAM scale uncertainty, can complete the initialization faster and more accurately, and can robustly perform real-time motion estimation and sparse map construction, and the accuracy and the robustness of the improved system are effectively improved.
Owner:BEIJING UNIV OF CIVIL ENG & ARCHITECTURE
Feature based monocular SLAM (Simultaneous Localization and Mapping) quick initialization method
ActiveCN106570913ASmall amount of calculationImprove initialization speed2D-image generationMonocular slamDepth of field
The invention relates to a feature based monocular SLAM (Simultaneous Localization and Mapping) quick initialization method, which comprises the steps of 1) starting SLAM, acquiring a first frame picture and extracting ORB feature points P(x, y) for the picture; 2) performing image distortion removing on the ORB feature points P(x, y); 3) performing normalization on image coordinates of the distortion removed feature points in the step 2); 4) building a random depth for each feature point in the step 3); 5) combining results of the step 3) and the step 4) so as to build map points corresponding to the feature points, and acquiring an initial map; and 6) performing optimization on a matching result of subsequent adjacent frames and an existing map, and executing the normal feature SLAM process for each next newly increased frame so as to continuously adjust and expand the map and realize continuous tracking for SLAM. The feature based monocular SLAM quick initialization method provided by the invention is high in speed, small in calculation amount and not restricted by the depth of field.
Owner:上海玄彩美科网络科技有限公司
A monocular SLAM initialization method and system based on a wheel type encoder
InactiveCN109671120APlay a complementary roleHigh positioning accuracyImage analysis3D-image renderingFeature matchingMonocular slam
The invention discloses a monocular SLAM initialization method and system based on a wheel type encoder, and the method comprises the steps of selecting a first key frame and a second key frame in anSLAM initialization image sequence, carrying out the feature matching, calculating the world coordinate system coordinates of all matching points in the first key frame, and building an initial pointcloud map; and determining the camera pose of the second key frame by using the displacement information of the wheel type encoder, fixing the camera poses of the first key frame and the second key frame during optimization, and not performing local bundling adjustment on the camera poses of the two frames. According to the present invention, the displacement information of the wheel type encoderis combined with the point characteristics of image information of the visual sensor to play a role in information complementation, the camera pose of the second key frame can be determined very accurately, the scale information of the real world is reserved, the positioning precision of the camera is improved, the operation is simplified, and the response speed is increased.
Owner:NANJING HUAJIE IMI TECH CO LTD
Monocular SLAM (Simultaneous Localization and Mapping) method capable of creating large-scale map
InactiveCN105825520ADetect and correct for cumulative drift in scaleRun in real timeImage analysisMonocular slamImage alignment
The present invention provides a monocular SLAM method that can create large-scale maps by using direct image alignment correction, explicit absorption and detection of scale drift; then adding filter-based semi-dense depth map estimation to achieve continuous With large-scale environment maps, the method not only tracks camera motion locally, but also maintains and tracks it on a global map of the environment. At the same time, the method can also run in real time on the CPU of an ordinary PC, and as a ranging method, it can even run on modern smartphones.
Owner:BEIJING ROBOTLEO INTELLIGENT TECH
Real-time puzzle method based on monocular SLAM fused with GPS
The invention discloses a real-time puzzle method based on monocular SLAM (Simultaneous Localization and Mapping) fused with GPS (Global Positioning System), which is characterized in that an unmanned aerial vehicle is utilized to load a camera to shoot an image sequence under the camera and a GPS module is utilized to receive latitude and longitude signals, and high-precision real-time tracking and map construction of an outdoor large scene are realized by optimizing a feature extraction and matching algorithm of monocular ORBSLA3. Generating a sparse point cloud map and a position attitude of the key frame; a GPS module signal is subjected to UTM coordinate conversion, and fusion of the GPS module signal and key frame information is realized through linear search of a difference value; the key frame position attitude is converted to global UTM geographic coordinates through fusion transformation; overlapping region fusion is carried out on key frames with close spatial positions by using a Laplacian Gaussian pyramid to obtain an accurate panorama; according to the method, large-scene image splicing can be realized, the overlapping region splicing effect is good, the splicing real-time performance is good, and the method is suitable for application occasion requirements in multiple fields of outdoor aerial photography, aerial survey and the like.
Owner:XIAN INNO AVIATION TECH CO LTD
Monocular SLAM initialization method
PendingCN109636852AFast initialization speedFast initialization method has higher accuracy than existing methodsImage analysisMonocular slamHomography
The invention discloses a monocular SLAM initialization method. The method comprises: feature points of a template picture are extracted, poses of the camera and the template picture are transmitted to a configuration file; collecting a picture containing a template as a first frame of picture; extracting ORB feature points of the first frame of picture and matching the ORB feature points with thefeature points on the template picture; a homography matrix is calculated; projecting known points defined in the template picture into the first frame of picture by using a homography matrix; calculating the pose of the first frame of picture relative to the template picture, and finally calculating the spatial coordinates of the feature points reserved in the feature points, matched with the first frame of picture, on the template picture according to the established self-defined coordinate system, and taking the spatial coordinates as corresponding map points in the SLAM map to complete initialization. Compared with an existing method, the rapid initialization method provided by the invention has higher precision and faster initialization speed, and greatly reduces the calculation costof initialization.
Owner:ZHEJIANG UNIV OF TECH
Binocular point cloud generation method and system
ActiveCN110084851AImprove accuracyAccurate scaleImage enhancementImage analysisPoint cloudMonocular slam
The invention provides a binocular point cloud generation method and system. The method comprises the following steps of: selecting pixel points in an image overlapping area from the acquired image according to a monocular SLAM algorithm; converting the selected pixel points into pixel points corresponding to a binocular SLAM algorithm; calculating the three-dimensional coordinates of the converted pixel points in the image overlapping region based on a binocular SLAM algorithm; and converting the three-dimensional coordinates of the pixel points into coordinate information of a camera coordinate system, calculating the three-dimensional coordinates of the pixel points in the non-overlapping area of the image based on the coordinate information of the camera coordinate system by using themonocular SLAM algorithm, and generating a point cloud according to the three-dimensional coordinates of the pixel points in the non-overlapping area and the overlapping area of the image. According to the scheme of the invention, scale calculation is carried out according to the pixel point information in the image overlapping area of the collected image, and the pixel point information of the non-overlapping area of the image is obtained. The binocular SLAM algorithm is used for assisting the monocular SLAM algorithm to obtain mature points in the image faster and more accurately, and the point cloud generation stability and the object real scale obtaining accuracy are improved.
Owner:ECARX (HUBEI) TECHCO LTD
Monocular SLAM initialization method and device and electronic equipment
PendingCN113129366AImprove initialization efficiencyAvoid triangulationImage analysisComplex mathematical operationsImaging processingMonocular slam
The embodiment of the invention provides a monocular SLAM initialization method and device and electronic equipment, and belongs to the technical field of image processing. The method comprises the following steps: acquiring multiple frames of continuous images collected by a target camera; calculating a homography matrix among multiple frames of continuous images; obtaining a homography matrix between every two images by using the homography matrix between the multiple frames of continuous images; and obtaining pose data and a plane normal vector of the target camera according to all the homography matrix optimization variables. In the initialization process, multi-frame information is used, and an original method for solving the camera pose and the plane normal vector through matrix decomposition is replaced with variable optimization. According to the method, the parameter quantity is small, the camera pose and the plane normal direction are calculated by using the result of variable optimization, the spatial position of the feature point is calculated by using the plane normal direction and the normalized distance from the camera to the plane, triangularization and PnP are avoided, and the efficiency of monocular SLAM initialization is improved.
Owner:BEIJING BYTEDANCE NETWORK TECH CO LTD
Method for densifying monocular SLAM feature point map
ActiveCN111861874APrecise NavigationAdjust sparsityInternal combustion piston enginesGeometric image transformationMonocular slamSurgical robot
The invention discloses a method for densifying a monocular SLAM feature point map, which is characterized by comprising the following steps: S1, carrying out Delaunay triangulation on feature pointsin each frame of key frame to obtain a triangulated key frame; s2, projecting the triangulated key frame to a three-dimensional space to obtain coordinates of the triangulated key frame in a space coordinate system, and constructing a three-dimensional image of the key frame; s3, setting a triangular side length threshold of the triangulation, and filtering abnormal points in the three-dimensionalimage to obtain an optimized three-dimensional image; and S4, performing uniform point supplement on each triangle in the optimized three-dimensional image to obtain a dense monocular SLAM feature point map. Accurate navigation of the surgical robot can be realized.
Owner:SUZHOU UNIV +1
Monocular SLAM scale recovery method
PendingCN111862120AGood effectHigh precisionImage analysisInternal combustion piston enginesHuman bodyMonocular slam
The invention discloses a monocular SLAM scale recovery method, which comprises the following steps: manufacturing a calibration box, wherein a rectangular through hole is formed in the calibration box in a penetrating mode; placing a calibration box at the visual field of the monocular camera, wherein the monocular camera models a target object after passing through a through hole of the calibration box; enabling the monocular camera to perform image acquisition on the inner wall of the calibration box, and performing region segmentation to obtain upper and lower surface images of the inner wall of the calibration box in the first few key frames generated by the SLAM; obtaining three-dimensional map point coordinates of the upper and lower images of the inner wall of the calibration box according to the corresponding relation between the feature points and the three-dimensional map points in the SLAM; fitting three-dimensional map point coordinates of the upper and lower surfaces of the inner wall of the calibration box by using two-plane horizontal behavior constraint conditions, and calculating and obtaining distances between the upper and lower surfaces of the inner wall of thecalibration box in a three-dimensional map; calculating a scale factor; and recovering the whole three-dimensional map scale by using the scale factor F. The monocular SLAM scale in the human intestinal environment can be automatically recovered, the effect is good, and the precision is high.
Owner:SUZHOU UNIV +1
Small robot indoor passable area obtaining method and device
The invention discloses a small robot indoor passable area modeling method, and the method comprises the following steps: (10) monocular SLAM: obtaining an indoor environment image through a monocularcamera on the robot, inputting the indoor environment image into a monocular SLAM system, and obtaining the pose and sparse feature point cloud of the camera; (20) image segmentation: segmenting theindoor environment image to obtain a ground area; (30) ground plane fitting: extracting points in the ground area, performing filtering and fitting to obtain a ground plane; (40) segmented image screening: screening the segmented ground area by using the ground plane position to obtain a ground area meeting the requirement; and (50) dense ground modeling: projecting the ground segmentation image to the ground plane to obtain a dense ground point cloud model. The method and the device are low in cost, good in real-time performance and good in modeling effect.
Owner:ARMY ENG UNIV OF PLA
Method for recovering monocular SLAM scale through detection and calibration
PendingCN112348869AAchieve recoveryReduce complexityImage enhancementImage analysisMonocular slamRadiology
The invention discloses a method for recovering a monocular SLAM scale through detection and calibration, and the method comprises the steps: calibrating a camera, obtaining a first depth from a pointto the camera on a visual plane by perspective transformation calculation, detecting and setting a Marker, and detecting and setting a second depth from the Marker to the camera through a deep learning module; adding the first depth and the second depth into the SLAM back-end optimization process to obtain the monocular SLAM scale, so that the monocular SLAM scale is recovered, the calculation process is effectively simplified, and the algorithm complexity and related calculation amount are effectively reduced.
Owner:的卢技术有限公司
Method and system for recovering monocular SLAM scale through detection and calibration
InactiveCN112348868AReduce the amount of calculationReduce complexityImage analysisNeural architecturesMonocular slamRadiology
The invention discloses a method and system for recovering a monocular SLAM scale through detection and calibration, and the method comprises the following steps: a camera is calibrated by a calibration module; a calculation module calculates the depth of the point distance camera on the plane; a detection module is used for detecting the marker based on deep learning; and a scale recovery moduleperforms SLAM back-end optimization to obtain the scale of the monocular SLAM. The invention has the advantages that the calibration and detection method is adopted for scale recovery, the markers areplaced on the road for scale recovery, and the calculated amount and complexity of the algorithm are greatly reduced.
Owner:的卢技术有限公司
Monocular SLAM system initialization algorithm based on dot-line unified framework
ActiveCN110473258AImprove scene adaptabilityAvoid inherent problemsImage analysisDrawing from basic elementsMonocular slamAlgorithm
The invention discloses a monocular SLAM system initialization algorithm based on a dot-line unified framework. The algorithm comprises the following steps: 1, setting an index container with unifieddot-line features, and enabling the obtained dot-line features to be matched and unified in a subsequent random sampling consistency algorithm for calculating F and H matrixes; 2, unifying the line features in a matrix calculation framework, and calculating F and H matrixes and corresponding scores by threads according to the midpoints of the preprocessed line features; and 3, determining a current effective matrix according to the score, and recovering corresponding 3D dot-line features based on the matrix, thereby completing initialization of the monocular SLAM system. The invention providesan initialization method for unifying dot-line characteristics, which ensures that a monocular SLAM system can fully utilize image information, reduces the system initialization difficulty and realizes high-precision initialization.
Owner:NORTHWESTERN POLYTECHNICAL UNIV
Method for carrying out pose optimization by utilizing Kalman filtering based on monocular SLAM algorithm
ActiveCN111044054AReduce computationReduce time consumptionNavigational calculation instrumentsMonocular slamAlgorithm
The invention provides a method for carrying out pose optimization by utilizing Kalman filtering based on a monocular SLAM algorithm. The method comprises the following steps: calculating update values of a rotation vector and a translation vector; and taking the update values of the rotation vector and the translation vector as optimized poses. According to the method, by modifying the pose optimization algorithm, a calculation amount and time consumption of ORB-SLAM are reduced, accurate and efficient positioning is provided for an upper-layer application, the calculation amount is reduced by replacing an original complex BA optimization method with a simple Kalman filtering method, and the time consumption of a pose optimization part is remarkably reduced. Compared with ORB-SLAM, the method provided by the invention has an advantage that real-time performance is improved.
Owner:HARBIN INST OF TECH
Monocular SLAM system for high-voltage transmission line inspection
InactiveCN112183411AFault foundFound the situationImage enhancementImage analysisForeign matterVisual technology
The invention relates to the technical field of power line inspection, and discloses a monocular SLAM system for high-voltage power transmission line inspection. The system is characterized in that anoverhead power transmission line inspection robot uses a visible light and infrared double-light fusion nacelle, so that a visible light image and an infrared image of the same scene can be obtainedat the same time, wherein pixel points of the visible light image and the infrared image are in one-to-one correspondence; an inspector or an automatic fault identification algorithm checks whether faults such as rusting, cracking, falling and the like exist on the surface of hardware, whether foreign matters exist on a high-voltage power transmission line and whether bird nests and the like existon a tower to influence the power transmission safety according to the images; whether the temperature of the power transmission line is abnormal is judged through the infrared image so as to determine whether the power transmission line is abnormal; three-dimensional reconstruction is performed on a power transmission line channel through a visual SLAM technology; and whether the power transmission safety is affected can be known through a three-dimensional map.
Owner:浙江港创智能机器人有限公司
Monocular high-quality three-dimensional reconstruction method combined with deep learning in inner cavity environment
The invention discloses a monocular high-quality three-dimensional reconstruction method combined with deep learning in an inner cavity environment, and belongs to the field of medical image processing. The method comprises the following steps: constructing a lightweight blood vessel branch feature extraction network (SuperVessel) based on a transfer learning strategy, performing dynamic upsampling operation by adopting a double-branch decoding structure and a mixed attention mechanism, and performing end-to-end training in combination with a pseudo-gold standard blood vessel feature point data set to realize joint detection of blood vessel branch points and descriptors; a SuperVessel and LightGlue matching model is integrated to an ORB-SLAN3 front-end framework, the feature matching robustness is improved by dynamically adjusting network computing resources, and camera pose tracking is optimized; an EndoDAC self-supervised depth estimation model is introduced, an improved truncated symbol distance function (TSDF) fusion algorithm is combined, TSDF field fusion is optimized through bilateral filtering denoising, bilinear interpolation and a MarchingCubes algorithm, high-precision incremental three-dimensional reconstruction of an inner cavity environment is achieved, and the positioning precision, tracking stability and reconstruction detail quality of an inner cavity environment monocular SLAM system are improved.
Owner:HARBIN UNIV OF SCI & TECH
Online luminosity calibration method based on direct method monocular SLAM
PendingCN111553954AGuaranteed real-timeImprove performanceImage enhancementImage analysisMonocular slamComputer graphics (images)
The invention relates to an on-line luminosity calibration method based on direct method monocular SLAM. The method comprises the steps that feature point tracking is conducted on an on-line image sequence, and a luminosity error model is constructed for an initial frame image to obtain initial optimization parameters; the initial optimization parameters are written into an online parameter database, an online luminosity error model for an online frame window is subsequently constructed according to the online parameter database to perform online luminosity calibration, and meanwhile, parameter updating is performed on the online parameter database in the background. According to the method, online luminosity calibration is carried out on the online image sequence, the luminosity calibration effect is more accurate and robust, and the performance of the direct method monocular SLAM can be remarkably improved.
Owner:DONGHUA UNIV
Monocular SLAM (Simultaneous Localization and Mapping) method capable of creating large-scale map
PendingCN113793417AEnsure comprehensivenessHigh resolutionImage enhancementImage analysisMonocular slamRadiology
The invention discloses a monocular SLAM method capable of creating a large-scale map, and the method comprises the steps: obtaining the upper end image information of a space needing to be mapped through an image collection device, obtaining the non-upper end image information of the space needing to be mapped through a 3D laser radar, and carrying out the data processing of an environment image, and constructing an initial environment map and identifying the pose of the image acquisition device. Wide-angle rotary scanning and fixed-point detection are achieved through the 3d laser radar, a large-distance blind area is avoided in the detection process, the comprehensiveness and high resolution of detection data are guaranteed, the positioning precision of monocular SLAM is optimized, richer map information is created, two initial images are obtained through shooting of the two image acquisition devices, the initial SLAM map is constructed by utilizing the mutually matched feature points in the initial image, and after the initialization is successful, the image is shot by utilizing the image acquisition device so as to perform monocular SLAM mapping, so that the mapping success rate is improved, and the information loss in the map is reduced.
Owner:NORTHEAST FORESTRY UNIVERSITY
A binocular point cloud generation method and system
ActiveCN110084851BImprove accuracyAccurate scaleImage enhancementImage analysisPattern recognitionPoint cloud
Owner:ECARX (HUBEI) TECHCO LTD
Capsule endoscope real-time positioning method based on non-rigid monocular SLAM
The invention discloses a capsule endoscope real-time positioning method based on non-rigid monocular SLAM (Simultaneous Localization and Mapping), which comprises the following steps of: calibrating a monocular camera carried by a capsule endoscope to obtain internal reference and external reference information of the camera; performing frame extraction on a real-time picture shot by the capsule endoscope as input, and performing data association on the gastrointestinal tract image; estimating a camera pose according to a data association result and updating the dynamic deformation graph; after the dynamic deformation graph is updated, a new key frame is determined through medium-term data management; performing triangulation on associated pixel points of adjacent frames of the key frame, obtaining three-position information of the associated pixel points, and performing calculation to obtain a time-varying point cloud; and after the deformable beam is adjusted, real-time pose information of the camera and a map modeling result are output. According to the method, high-precision and robust real-time capsule positioning and gastrointestinal tract scene modeling under the gastrointestinal tract environment are realized, the positioning precision of the capsule endoscope under the non-rigid deformation condition of the gastrointestinal tract is remarkably improved, and feature mismatching and error accumulation are effectively inhibited.
Owner:ZHEJIANG UNIV OF TECH
Monocular SLAM static initialization method and device, unmanned aerial vehicle and storage medium
ActiveCN119129627Astatic initialization implementationSensing by electromagnetic radiationPattern recognitionMonocular slam
The invention discloses a monocular SLAM static initialization method and device, an unmanned aerial vehicle and a storage medium. The method comprises the steps of obtaining a monocular image of a two-dimensional code target; based on the feature points of the two-dimensional code target in the monocular image, obtaining the pose of the camera coordinate system under the two-dimensional code world coordinate system and the scale information of the feature points by using a PnP algorithm; obtaining a depth map and a plurality of planes by utilizing a PlaneRecNet model, and calculating an equation and a normal vector of each plane by utilizing an RANSAC (Random Sample Consensus) algorithm; screening out a plurality of normal vectors according with pairwise orthogonality from the normal vectors so as to determine the normal vector corresponding to the horizontal plane and obtain a gravity vector; rotating the camera coordinate system to enable the Z-axis direction to be parallel to the gravity vector direction to obtain a world coordinate system; and completing initialization based on the world coordinate system, the depth map and the scale information. According to the scheme, static initialization of monocular vision SLAM is achieved, meanwhile, scale information is recovered, and gravity alignment is achieved.
Owner:ZHUOYI ZHINENG
Monocular slam method and device combined with deep learning
The invention discloses a monocular SLAM method and device combined with deep learning, wherein the method includes the following steps: using CNN to process an input image to obtain initial depth information; using the depth map as an initial value to initialize monocular simultaneous positioning and map construction SLAM system, combined with the optimized depth map to obtain a high-precision depth map; select and optimize key frames based on the high-precision depth map, and use the optimized key frames to optimize positioning and mapping, and obtain the final simultaneous positioning and map construction results. . This method uses the depth information obtained by the CNN network as the initial value of the image depth, which greatly improves the initialization speed of the SLAM system and the accuracy of subsequent joint optimization.
Owner:TSINGHUA UNIV
Feature-based fast initialization method for monocular slam
ActiveCN106570913BSmall amount of calculationImprove initialization speed2D-image generationMonocular slamDepth of field
The invention relates to a feature based monocular SLAM (Simultaneous Localization and Mapping) quick initialization method, which comprises the steps of 1) starting SLAM, acquiring a first frame picture and extracting ORB feature points P(x, y) for the picture; 2) performing image distortion removing on the ORB feature points P(x, y); 3) performing normalization on image coordinates of the distortion removed feature points in the step 2); 4) building a random depth for each feature point in the step 3); 5) combining results of the step 3) and the step 4) so as to build map points corresponding to the feature points, and acquiring an initial map; and 6) performing optimization on a matching result of subsequent adjacent frames and an existing map, and executing the normal feature SLAM process for each next newly increased frame so as to continuously adjust and expand the map and realize continuous tracking for SLAM. The feature based monocular SLAM quick initialization method provided by the invention is high in speed, small in calculation amount and not restricted by the depth of field.
Owner:上海玄彩美科网络科技有限公司