288 results about "Stereopsis" patented technology

The invention discloses a vision-driven multi-mode fusion lightweight semantic map construction method and system. The method comprises the following steps: synchronously acquiring a binocular image pair sequence, IMU data and GNSS data of a target area; based on the acquired multi-modal data, performing multi-sensor joint state estimation through a differential weighted fusion strategy, and outputting camera global pose and scene depth information; based on a current frame and a historical frame in the binocular image pair sequence, combining a camera global pose, extracting geometric prior auxiliary time sequence cross-frame semantic feature fusion through stereoscopic vision, and outputting a two-dimensional semantic segmentation result of the current frame; and back-projecting the two-dimensional semantic segmentation result into a lightweight global three-dimensional semantic map based on camera pose and scene depth information, and carrying out maintenance and updating through a voxelization statistical mechanism. Compared with a traditional dense point cloud map, the method has the light weight effect that the storage space is greatly reduced.

The invention provides an injection molding part surface flaw detection method and device based on double-model collaboration, and the method comprises the steps: carrying out the local abnormal reflection feature analysis of a multi-view optical image collected on the surface of an injection molding part based on a first detection model, and obtaining a candidate flaw region; performing spatial positioning in the multi-view optical image based on the candidate flaw area to obtain a multi-view candidate image segment; performing surface geometric continuity analysis on the multi-view candidate image segments based on a second detection model to obtain a three-dimensional surface geometric consistency result; carrying out authenticity discrimination on the candidate flaw area based on a three-dimensional surface geometric consistency result to obtain a real flaw area; wherein the first detection model is used for capturing an optical response model of local abnormal reflection characteristics; the second detection model is a stereoscopic vision model for analyzing the geometric continuity of the multi-view lower surface. According to the invention, the false alarm rate of surface defect detection of the injection molded part under a complex surface condition is reduced.

The invention discloses an underwater image enhancement method and system based on binocular vision and polarization imaging. The method comprises the following steps: firstly, synchronously acquiring an orthogonal polarization image pair through a binocular polarization imaging unit, recovering scene depth information from the polarization image pair by using a binocular stereoscopic vision technology, and calculating a transmissivity graph; analyzing the polarization characteristic difference between target reflected light and backscattered light, establishing a polarization difference model, and separating background scattered light; solving an underwater imaging equation in combination with the depth information and a polarization difference model to obtain a preliminary restoration result of the target reflected light; and finally, further improving the image quality through the steps of multi-scale spectrum analysis, adaptive filter construction and post-processing by adopting a spectrum adaptive image enhancement technology. The system comprises a binocular polarization imaging unit, a calculation processing unit and an active illumination unit. According to the method, the problems of color distortion, low contrast and fuzzy details of the underwater image are solved, and the visual quality and usability of the underwater image are improved.

The invention discloses a multi-source information fusion-based tunneling equipment vision-assisted pose detection system and method, and relates to the technical field of exploration and engineering surveying, and the system comprises a binocular vision module, a strapdown inertial navigation module, a laser orientation instrument module and a data fusion processing module. The binocular vision module solves three-dimensional coordinates through stereoscopic vision; the strapdown inertial navigation module provides high-frequency dynamic attitude data; the laser orientation instrument modules are triangularly arranged to provide a global absolute position reference; and the data fusion processing module adopts an extended Kalman filtering dynamic fusion algorithm and combines dynamic weight adjustment to fuse multi-source data. The method comprises the steps of data acquisition, preprocessing and time-space synchronization, fusion calculation and pose information output. Through the multi-source collaborative fusion and dynamic environment adaptation technology, the detection precision and stability are improved, the automatic tracking and remote monitoring requirements of the tunneling equipment are met, and intelligent upgrading of coal mine tunneling is promoted.

The invention discloses a stereoscopic vision optimization method and system for a naked-eye 3D large screen, and particularly relates to the technical field of naked-eye 3D vision optimizing.The method comprises the steps that environment illumination and audience positions are sensed in real time through multi-sensor fusion, and an environment light field model is established; glare crosstalk noise is predicted based on physical simulation, and self-adaptive suppression and compensation are carried out in combination with human eye visual sensitivity and image content features; a virtual camera is dynamically generated according to the real-time positions of the eyes of the audience, and a lightweight neural radiation field renderer is used for real-time re-rendering, so that motion parallax is realized; and finally, intelligently fusing the glare compensation layer and the perspective correction layer, coding and outputting to a screen. The system correspondingly comprises an environment perception module, a glare compensation module, a perspective rendering module and a fusion coding module. The naked-eye 3D large-screen display method effectively inhibits ambient light interference, improves the quality and immersion of a stereoscopic picture under different visual angles, and is suitable for naked-eye 3D large-screen display under outdoor and complex illumination environments.

The invention belongs to the technical field of medical robots and minimally invasive surgery, and provides a robot control system and method for blue laser vaporization surgery of prostatic hyperplasia. Mapping the nuclear magnetic image volume data to a deformation field under an ultrasonic acquisition coordinate system, and deforming the preoperative nuclear magnetic image to an intra-operative ultrasonic space by using the deformation field to complete image registration; fusing the registered image with a stereoscopic vision system; the spatial depth of the surface of the target tissue is obtained from the endoscopic image so as to supplement navigation information; according to the utility model, the prostate deformation and probe posture change adaptive capacity in an operation is improved, the real-time visual closed-loop regulation and control capacity is improved, and the characteristics of small light spots, shallow heat diffusion, excellent hemostasis and the like of blue laser are combined, so that the vaporization and hemostasis precision in a tiny blood vessel dense area is ensured, and the problems of large tissue trauma and the like are avoided.

The invention discloses a stereoscopic vision-based model attitude measurement method, belongs to the technical field of attitude measurement, aims to solve the problems of insufficient precision and expensive depth camera of traditional attitude estimation, realizes accurate measurement of model attitude, and has the core of fusing stereoscopic vision geometric characteristics and deep learning advantages. The method specifically comprises the steps of 1, forming a three-dimensional system by using at least two industrial cameras, calibrating internal and external parameters, and calculating a scene depth map through an improved SGBM algorithm to obtain object depth information, and 2, predicting coordinates of pixels in a target 3D coordinate system by using a pre-trained double-branch fusion network in combination with the depth map and left and right eye RGB images, the method comprises the steps of 1, generating a plurality of groups of candidate poses on the basis of association and spatial association, 2, restoring the candidate poses into virtual objects, comparing the virtual objects with real objects through geometric consistency verification to quantify scores, and 3, selecting the candidate pose with the highest score as a final result through a PoseSelection module. And large view field coverage and high-precision positioning are both considered.

The invention relates to the technical field of optical three-dimensional measurement and metering, and discloses a single-camera three-dimensional coordinate measurement method and system based on full-field distance measurement, and the method comprises the following steps: S1, building a calibration field containing a control point, shooting an image of the calibration field through a monocular camera, extracting the image coordinate of the control point, carrying out the camera calibration, and obtaining a calibration field; obtaining internal parameters and external orientation parameters of the camera; and S2, controlling the laser range finder to aim at the control point in the calibration field through the non-orthogonal double-axis turntable. Submillimeter-level high-precision measurement can still be realized under the condition of a short baseline, and the problems that the precision in the depth direction is insufficient, the baseline requirement is long, parameters are easy to drift and the like in traditional stereoscopic vision measurement are effectively solved. By introducing a non-orthogonal double-shaft turntable and a visual guidance laser aiming mechanism, autonomous, rapid and accurate measurement of multiple measurement points in a large field of view is realized, and the automation degree and reliability of measurement in a complex environment are remarkably improved.

The invention discloses a binocular vision-based fish body quality non-contact estimation method, which comprises the following steps of: in a land-based facility circulating water high-density culture environment in which a fish body freely swims and is easy to block, firstly, obtaining a fish head local image through fish head region segmentation, and carrying out position alignment and scale normalization processing on the fish head local image; constructing a stable fish head geometric anchor point; then, the fish head anchor point is used as condition input, and a generative model is used for inferring and complementing the overall shape of the fish body so as to recover a continuous geometric structure of the fish body; on the basis, binocular stereo vision is combined to carry out stereo matching on key points of the head and the tail of the fish body, and the length of the fish body is obtained through triangulation; finally, based on the mapping relation between the body length and the quality, automatic estimation of the fish body quality is achieved, manual contact with the fish body is not needed, stable and automatic measurement of the fish body quality can be achieved in a complex breeding scene, and the method has the advantages of being high in adaptability, low in stress risk and high in application value.

The present invention relates to the technical field of industrial process control and detection. Disclosed is a method for real-time measurement of length-width size distribution of a crystal population in a crystallization reactor using binocular telecentric cameras. In-situ environment calibration is performed for a binocular telecentric stereo vision system, a calibration rod capable of probing into an in-situ environment (a reactor / glass tube) is designed, a binocular telecentric stereo vision imaging model is established, and a simple calibration method of rotating the calibration rod suitable for an in-situ limited space and a calibration plate design scheme are proposed. In order to improve binocular matching efficiency, a simplified telecentric stereo epipolar rectification method is further provided, so as to ensure accurate matching of on-site snapshot image pairs. On the basis of the matched image pairs, a three-dimensional reconstruction method using analytical solution-based ray intersection is provided to measure the three-dimensional pose of particles within a crystallizer. Finally, the three-dimensional length and width of a crystal are quantitatively evaluated by means of statistical data of Euclidean distances of pairs of length and width feature points of the crystal. The present invention has high operability, and can achieve the effect of automatically measuring the three-dimensional size of crystals.

The invention discloses a pair of binocular visual function training glasses used after strabismus operation, and relates to the technical field of visual rehabilitation training. The interpupillary distance adjusting mechanism is mounted on the upper side of the inner wall of the glasses frame; the two angle adjusting mechanisms are mounted on the two sides of the bottom end of the interpupillary distance adjusting mechanism respectively; the angle adjusting mechanism comprises an adjusting frame, a pitch angle driving assembly, a rotating frame, a lens cone and a miniature display screen. The angle and the position of the visual training pattern displayed by the micro display screen can be dynamically adjusted according to the specific strabismus type and the postoperative recovery condition of a patient, so that the capacity of coordinating the two eyes of the brain visual center is actively exercised and awakened, recovery of the visual functions of the two eyes is promoted, and the recovery effect is improved. By means of the design, the defect of a fixed parameter training lens in the aspect of adaptability is overcome, the binocular cooperation function of the visual center is actively activated through personalized parameter adjustment, and the postoperative binocular fusion capacity and the recovery efficiency of stereoscopic vision are remarkably improved.

The invention relates to the technical field of stereoscopic vision, and discloses a synchronous speed visual matching method and system, electronic equipment and a storage medium, and the method comprises the steps: synchronously collecting a stereoscopic video sequence with a predefined frame rate; executing multi-target hybrid tracking and motion induction detection, and outputting target motion information including position and velocity vectors; extracting hierarchical motion features of the target from continuous multiple frames of the stereoscopic video sequence, and performing unified space-time coding; under geometric constraints of stereoscopic vision, scale cosine similarity, direction similarity and trajectory consistency measurement are calculated and serve as observation evidences to be input into the probabilistic reasoning model for fusion, and a posterior probability representing matching reliability is output; the weight distribution of the speed similarity and the direction similarity is adjusted according to the motion characteristics of the targets in the scene, and the stable corresponding matching relation between the left view target and the right view target is established. According to the method, high-time-resolution information can be utilized, motion features and geometric constraints can be effectively fused, and the method has self-adaptive capacity.

The invention relates to the technical field of vehicle safety, and discloses an integrated motorcycle auxiliary driving system and method. The method comprises the following steps: synchronously acquiring vehicle kinematics parameters and environment three-dimensional point cloud data through a multi-source sensing system of a motorcycle; executing a dynamic risk mapping operation by using the collected data to generate a risk probability distribution diagram; acquiring a color image and a depth image of a road scene through a stereoscopic vision camera, inputting the color image and the depth image into the multi-scale feature extraction network for analysis in combination with the risk probability distribution map, and outputting a comprehensive risk score; performing obstacle trajectory prediction according to the comprehensive risk score to obtain an obstacle prediction trajectory, scanning a target area by using an infrared sensor, processing point cloud data by using a point cloud segmentation algorithm based on the prediction trajectory, and extracting actual obstacle attributes; and inputting the comprehensive risk score and the actual obstacle attribute into a fuzzy logic controller for data fusion, and finally generating an integrated motorcycle aided driving control instruction.

The invention discloses a visual training method, system and device for myopia prevention and control and correction based on a naked-eye 3D display, and a storage medium, relates to the technical field of three-dimensional image generation and display control, and comprises the field of visual training of myopia prevention and control constructed on a naked-eye 3D display interface, a first visual training area and a second sensing and integrating area, in the first visual training area, through 3D interlaced pictures and videos, fine or dynamic stereoscopic vision is stimulated, front and back intersections of sight lines are adjusted, and split vision training is carried out; in the second perception and integration area, through perception, spatial positioning, binocular coordination and deep perception training, the spatial ability and response ability of eyes are stimulated; in combination with a three-dimensional display mechanism, displaying a naked eye three-dimensional image on a display, acquiring eyeball position information by adopting a human eye tracking technology, and dynamically adjusting a three-dimensional image display area; according to the method, the visual content structured organization and three-dimensional generation cooperative control is realized, and the three-dimensional display interaction matching precision is improved.

Optical sensors (e.g., cameras) and (e.g., IR) illumination sources may be distributed in an environment (e.g., an interior space such as a cabin or cockpit of an ego-machine) and synchronized to generate frames of sensor data, which may be used to reconstruct 3D geometry and / or 3D pose of an occupant, operator, or other object in the environment. For example, stereo vision may be used to generate one or more depth maps from image data generated using different cameras, the depth map(s) may be transformed into a 3D point cloud, and surface reconstruction may be applied to reconstruct the 3D geometry of surface(s) in the environment. A 3D pose, one or more keypoints (e.g., facial landmarks), or some other representation of the shape of the reconstructed surface(s) may be extracted from the reconstructed surface and used in one or more downstream tasks, such as driver and / or occupant monitoring tasks.

The invention belongs to the technical field of intelligent navigation of agricultural machinery, and particularly relates to an autonomous navigation system of field unmanned transportation equipment after potatoes (such as potatoes and sweet potatoes) are harvested, in particular to a potato operation line identification method based on binocular camera multi-modal information dynamic weighting. Aiming at a complex field environment (soil is loosened and turned over, scattered potato blocks / weeds are mixed, and an original ridge-shaped structure is locally damaged) after the operation of a harvester, a ridge line track required by the driving of a transport vehicle is difficult to stably identify in a scene of strong light overexposure, weak light noisy points and shadow alternation by a traditional visual method. According to the method, an IntelRealSenseD456 active stereoscopic vision binocular camera is carried, RGB images and depth information are fused in real time, and multi-modal data are dynamically weighted based on illumination intensity, so that the robust perception capability of the unmanned transport vehicle on the geometric boundary of the potato ridge is improved, the vehicle is ensured to accurately run along a harvested field ridge operation line, and the situation that the potato blocks are rolled and scattered or deviated from a path is avoided.

The invention relates to the technical field of data line performance testing, in particular to a data line tensile property testing device and method. The data line tensile property testing device comprises a base, a static clamp, a linear guide rail, a driving mechanism, a sliding platform, a force value sensor, a dynamic clamp, a displacement sensor and a visual inspection mechanism. The device is used for continuously recording the whole stretching test process, real-time visual recording of the apparent deformation and damage process of the data line is achieved, the defect that process monitoring is incomplete is overcome, meanwhile, after the test is finished, the height of the annular mounting frame is adjusted through the position adjusting assembly, and the measurement accuracy is improved. According to the method, the high-resolution area-array camera is close to the failure part of the data line, so that a high-definition image is obtained, a data basis is provided for three-dimensional reconstruction by adopting a photogrammetry or stereoscopic vision algorithm, high-precision three-dimensional shape analysis of the failure part of the data line is realized, and the problem of inaccurate analysis is solved.

The invention relates to the technical field of computer vision, and discloses a catering consumption automatic settlement method based on image recognition, and the method comprises the steps: obtaining multi-scale image data through a multi-level image quality evaluation and self-adaptive preprocessing technology; target detection and instance segmentation are realized by adopting hierarchical feature extraction and dish template matching; carrying out dish three-dimensional measurement and volume calculation based on a stereoscopic vision and shape recovery method; realizing classification and identification of dishes through multi-modal feature fusion and an attention mechanism; performing nutrient component analysis and health assessment based on nutrition database matching and image feature analysis; and intelligent settlement is realized through price calculation, nutrition statistics, intelligent recommendation and settlement processing. According to the invention, dish identification, nutrition analysis and dynamic pricing can be rapidly completed, and a complete technical solution is provided for intelligent catering service.

The invention discloses a non-contact measurement system and method for full-field deformation of a fuselage in an airplane crash test, and belongs to the technical field of airplane structure strength testing, and the method comprises the steps: making a high-quality speckle pattern on the surface of the fuselage, and laying cooperation mark points; a binocular camera flexible self-calibration method is used for completing calibration of the stereo measurement system; unification of global coordinates of multiple systems is assisted through unmanned aerial vehicle photogrammetry; a synchronous controller is adopted to trigger multiple sets of systems to synchronously collect images in the falling and collision process; obtaining the motion trail and speed of the key measuring point based on a mark point positioning tracking and stereoscopic vision principle; acquiring a full-field three-dimensional displacement field and a strain field based on a digital image correlation method guided by a control point and a stereoscopic vision principle; and deformation visualization representation is realized through image splicing and data fusion. According to the invention, non-contact, high-precision and full-field dynamic measurement of the three-dimensional deformation field in the falling and collision process of the whole large aircraft is realized, and technical support is provided for analysis and evaluation of falling adaptability of the aircraft structure and verification of anti-falling and anti-collision design.

The invention discloses a photovoltaic power generation prediction error correction device and method, and relates to the technical field of photovoltaic power generation. Sky vision data, irradiance data, photovoltaic power station power data and environment data are collected, and time synchronization is performed on the collected data; inputting the simulated irradiance field distribution diagram and the cloud cluster motion vector prediction data into a trained space-time diagram convolutional network used for outputting power prediction errors of the photovoltaic power station; and outputting a photovoltaic power generation power prediction error by the space-time diagram convolutional network. According to the invention, the three-dimensional space coordinates and contours of the cloud cluster can be accurately obtained through the combination of the multi-view high-speed camera array and the stereoscopic vision algorithm; according to the method, a dense optical flow algorithm and an LSTM network are combined, accurate prediction of a future cloud cluster movement track is realized, optical thickness and light transmittance are inversed through a mapping relation between a cloud cluster gray value and actually measured irradiance, cloud cluster modeling is upgraded from abstract data representation to concrete physical entity, and high-precision physical model support is provided for subsequent photon transport simulation.

The invention belongs to the technical field of intelligent cleaning, and discloses an intelligent cleaning system for a passenger cabin. Comprising a stereoscopic vision positioning module used for acquiring a stereoscopic vision image in a passenger cabin; extracting three-dimensional information of the stain area; the image enhancement sub-module based on the generative adversarial network is used for preprocessing the stereoscopic vision image; the laser scanning and positioning module is used for shooting the whole environment of the passenger cabin and constructing a first point cloud map; the data fusion positioning module is used for receiving the three-dimensional information of the blotted area, performing data registration with the first point cloud map and outputting accurate three-dimensional coordinates of the blotted area; and the cleaning execution module is connected with the data fusion positioning module and is used for receiving the accurate three-dimensional coordinates of the dirty area and controlling a cleaning execution mechanism to clean point by point according to the three-dimensional coordinates so as to adapt to a complex environment, and the efficiency and the quality of passenger cabin cleaning are greatly improved.

The application discloses a kind of semi-structured orchard field ridge area detection method, this method is by picking robot along field ridge with stereo vision camera Real-time acquisition field ridge area image, utilize field ridge shadow area and the different of non-shadow area color and gradient field feature, combined with Gaussian mixture model can realize the detection of shadow area, again through the shadow color weighting compensation algorithm proposed in this paper to remove shadow area, finally through to image denoising filtering, by to image secondary segmentation, again after morphological processing, finally get complete field ridge area;Finally, through edge detection operator to the image after segmentation Edge detection, again to edge point optimization fitting, based on least squares method is carried out edge point fitting, obtains the edge line of field ridge area.This method can be under any illumination conditions 100% detection field ridge area.

The application discloses a stereovision-based slurry and slag identification method, and belongs to the technical field of tunnel construction, and specifically comprises the following steps: two same cameras are placed above the slurry and slag, fixed after being adjusted to the same height and the imaging half-frames are overlapped; a calibration plate is shot to obtain the baseline distance of the optical centers of the two cameras; the exposure time is determined in combination with the camera accuracy, the slurry and slag movement speed and the imaging magnification; two images of the slurry and slag are synchronously shot, the coordinate system is established, the sight distance difference and the imaging point spacing are calculated, the object distance is solved based on the geometric relationship constructed by the Gaussian imaging formula and the slurry and slag point position and the imaging plane and the camera optical center; finally, the three-dimensional point cloud model is established according to the object distance, and the slurry and slag shape, volume and surface area are output. The application solves the problems of motion blur, image distortion and the inability to accurately identify the size of the slurry and slag in the identification of the slurry and slag, can improve the identification accuracy, and meets the intelligent and refined construction requirements of large shield projects.

The present application relates to the technical field of packaging box verification, and discloses a multi-source information verification system for product packaging boxes before storage. The system comprises a multi-source information acquisition module, which acquires packaging box stereo vision sequences, weight dynamic sampling and three-dimensional point cloud measurement data; a multi-modal feature learning module learns multi-scale space-time features from the vision data to generate vision space-time feature tensors; a dynamic weight analysis module decomposes the weight data in the frequency domain to generate weight frequency domain feature maps. A graph structure fusion module constructs a heterogeneous information graph from the two, generates a fusion verification graph feature through a graph neural network, an abnormal pattern recognition module generates an abnormal confidence distribution through a pre-trained variational autoencoder, an intelligent decision module outputs abnormal positioning and defect classification results accordingly, and an adaptive optimization module generates parameter adjustment strategies and transmits them to the storage system. The system realizes deep fusion of multi-source information, improves verification accuracy and intelligent level, and helps optimize the warehouse process.

The invention relates to a belt conveyor material flow real-time analysis system based on active 4D stereoscopic vision. The system comprises a 3D laser vision module, wherein the 3D laser vision module comprises three groups of 3D high-frame-rate industrial cameras and corresponding laser emitters; the 3D high-frame-rate industrial cameras are arranged at the head part, the middle part and the tail part of a belt conveyor and are synchronously triggered in time; the motion compensation modules are arranged at the head and the tail of the belt conveyor; the data processing terminal is respectively connected with the 3D laser vision module and the motion compensation module through special cables; and the data display and control terminal is in communication connection with the data processing terminal and is used for receiving the processing result and displaying the 4D dynamic model, the flow data and the alarm information in real time. By means of the software and hardware collaborative design and algorithm innovation, high-precision, real-time and non-contact three-dimensional visual monitoring and intelligent analysis of the material flow of the belt conveyor are achieved.

The invention provides an optical machine assembly angle calculation method and device, computer equipment and a storage medium, and the method comprises the steps: calculating a first rotation matrix of an optical machine and a light receiver through a rotation vector according to the light transmission characteristics of an optical waveguide, and calculating a second rotation matrix of the optical machine according to the optical axis vectors of the light receiver and a stereoscopic vision camera; calculating a second rotation matrix between the stereoscopic vision camera and the ray machine, and determining an attitude transformation relation between the stereoscopic vision camera and the ray machine; and calculating a third attitude matrix of the ray machine according to the attitude matrix of the stereoscopic vision camera, the second rotation matrix and the first rotation matrix, thereby determining the assembly angle of the ray machine according to the third attitude matrix. By accurately calculating the rotation matrix and the attitude matrix, high-precision alignment of poses among the light machine, the light receiver and the stereoscopic vision camera can be ensured, accumulated errors in the assembly angle calculation process can be minimized through distributed calculation and calibration, and reliability and accuracy of an assembly angle calculation result are improved.

The invention discloses an intelligent detection method and system for garment quality inspection, and relates to the technical field of computer vision and intelligent manufacturing. The method comprises the following steps: carrying out pixel-level feature analysis on two-dimensional image data, identifying a sewing line and a printing area, and mapping the sewing line and the printing area to a unified space coordinate system; reconstructing the three-dimensional surface form of the garment based on a stereoscopic vision algorithm, and calculating the dimensional deviation of key parts; converting the spectral data into a CIELAB color space, and carrying out optical distortion correction on local chromatic aberration in combination with a three-dimensional curvature; and under a unified space coordinate system, performing correlation analysis on the stitches, the dimensional deviation and the corrected space distribution, identifying a composite defect which cannot be judged by a single defect, generating a correlation defect identifier, and finally forming a quality report. The technical problems that in the prior art, local chromatic aberration is easily influenced by three-dimensional curved surface deformation and optical distortion of ready-made clothes, information such as dimensional deviation, sewing and printing defects and the local chromatic aberration is isolated, comprehensive correlation analysis is lacked, and consequently the detection accuracy is insufficient are solved.

The invention discloses a control system and method for an oral surgery robot, and relates to the technical field of medical robot control, and the method comprises the steps: collecting preoperative medical image data of a laryngeal cavity region, and generating a static laryngeal cavity three-dimensional structural body through anatomical segmentation, contour extraction and three-dimensional reconstruction; according to the static laryngeal cavity three-dimensional structural body, zero calibration is carried out on the oral surgical robot, and RCM constraints are established; under the constraint of RCM, a three-dimensional endoscope is used for collecting an operation area image in real time, a real-time laryngeal cavity local three-dimensional point cloud is generated through stereoscopic vision reconstruction, geometric registration is conducted on the real-time laryngeal cavity local three-dimensional point cloud and a static laryngeal cavity three-dimensional structural body, and the real-time tail end pose is determined; and the primary control quantity and the three types of real-time monitoring data are fused together, a comprehensive risk index is calculated, the autonomous control proportion of the robot is adjusted by using the comprehensive risk index, and a risk guidance control quantity is generated. The safety, accuracy and flexibility of the operation are improved, and finally more efficient and safer oral operation is achieved.

Optical sensors (e.g., cameras) and (e.g., IR) illumination sources may be distributed in an environment (e.g., an interior space such as a cabin or cockpit of an ego-machine) and synchronized to generate frames of sensor data, which may be used to reconstruct 3D geometry and / or 3D pose of an occupant, operator, or other object in the environment. For example, stereo vision may be used to generate one or more depth maps from image data generated using different cameras, the depth map(s) may be transformed into a 3D point cloud, and surface reconstruction may be applied to reconstruct the 3D geometry of surface(s) in the environment. A 3D pose, one or more keypoints (e.g., facial landmarks), or some other representation of the shape of the reconstructed surface(s) may be extracted from the reconstructed surface and used in one or more downstream tasks, such as driver and / or occupant monitoring tasks.

The invention discloses a smudginess detection method, device and equipment, and the method comprises the steps: carrying out the detection operation of a ground image obtained in real time, and obtaining one or more local regions; for each local area, respectively acquiring height information corresponding to each point in the local area based on parallax of stereoscopic vision; and respectively executing a screening operation in each local area, and determining one or more points of which the height information meets a preset range in the local area. According to the technical scheme, the ground points meeting the preset height are detected, and dirt detection can be efficiently and reliably carried out in real time in various complex scenes.