38 results about "Binocular distance" patented technology

The invention relates to the technical field of intelligent unmanned forklifts, in particular to an intelligent unmanned forklift system and method based on visual navigation, and the system comprises a forklift main body module, a binocular vision module, an image preprocessing unit, a binocular distance measurement module, a track prediction module, a pedestrian area detection module, a pedestrian area center calculation module and an obstacle avoidance module. The image preprocessing unit is connected with the binocular vision module, the binocular distance measurement module is connected with the image preprocessing unit, the track prediction module is connected with the binocular distance measurement module, and the pedestrian rectangular area detection module is connected with the track prediction module. The technical problems that in the complex environment, under the conditions that light changes, shelters exist and the like, the performance is limited, the positioning precision is reduced, and even safety accidents are possibly caused are solved.

The application discloses a binocular distance measuring method with three-layer filling of a parallax map, and is characterized in that the method comprises the following steps: 1) calibrating a binocular camera; 2) graying left and right pictures; 3) setting a parallax threshold t; 4) filling parallax values of E err ; 5) filling parallax values of B blo ; and 6) obtaining a depth map. The method processes different kinds of problems on the parallax map by using filling techniques respectively, and the processed parallax map retains details, the depth of each pixel point in the background exists, and conforms to a real image, and a target individual in the image is calculated to obtain a safe, effective and practical distance.

The invention discloses a pair of clamping force quantitative control type orthopedic reduction forceps, and relates to the technical field of orthopedic surgery. In order to solve the problems that in the prior art, a real-time feedback mechanism cannot be provided to monitor and adjust the change of clamping force, instant force balance detection and alarm functions are lacked, force unbalance or too large or too small clamping can be possibly caused, and the surgical effect is affected. Through the force sensor and the binocular distance measuring sensor, the clamping force and the distance between the tong heads in the resetting process are monitored in real time, visual feedback is conducted through the quantification display device and the distance display device, the accuracy of the resetting process is ensured, the difference of the clamping force on the two sides of the tong heads is monitored in real time, an alarm is given out when imbalance occurs, and the resetting precision is improved. The device is simple in structure and convenient to use, prevents reduction failure or fracture part injury caused by non-uniform clamping force, provides real-time remote monitoring and data analysis functions, and provides important support for risk management in the operation process, so that the operation success rate is increased, and complications are reduced.

The application discloses a kind of parameter adaptive matching binocular ranging method and system based on scene feature, it relates to image matching technical field.The application realizes the comprehensive promotion of ranging accuracy and robustness by introducing scene characteristic evaluation and parameter adaptive mechanism.Under the driving of scene feature, the key parameters of BM algorithm are dynamically adjusted, which avoids the problem of easy mismatching of traditional fixed parameters in different scenes, thereby ensuring stable ranging effect in light change, low texture or dynamic environment, and getting rid of the dependence on manual parameter adjustment, significantly reducing engineering deployment and maintenance cost.Combining YOLO model for target detection, the class, position and depth map information are fused to realize automatic identification and ranging of specific target.

The invention provides a distance measurement method, a binocular distance measurement system and laser online detection equipment. The distance measuring method comprises the following steps: irradiating the liquid level of molten metal by using laser to form a light spot; respectively acquiring N frames of liquid level images by using two cameras, and extracting pixel coordinates of light spots in the images; calculating the parallax of each frame of image according to the pixel coordinates; calculating an average parallax according to the parallax; calculating a sight distance standard deviation according to the parallax and the average parallax; judging the value range of the effective parallax according to the average parallax and the sight distance standard deviation, and calculating the average value of the effective parallax; the distance between the light spot and the base line is calculated according to the average value of the effective parallax, the focal length of the cameras and the length of the base line of the two cameras, so that the position of the liquid level is determined, the laser excitation position of the LIBS is adjusted in real time, errors caused by transient, irregular and violent fluctuation of the liquid level can be effectively reduced, and the laser detection precision is improved.

The invention discloses a binocular ranging method based on a YOLOv8-BiFPN network model, belongs to the technical field of computer vision and target detection, and particularly relates to the binocular ranging method based on the YOLOv8-BiFPN network model. The objective of the invention is to solve the problems that in the prior art, a feature pyramid fixed weight fusion mechanism is difficult to adapt to multi-scale target detection, features are lost in a dynamic shielding scene, and algorithm calculation complexity and real-time requirements are contradictory, and especially to overcome the defect that high-precision depth perception and real-time detection in a binocular vision system are difficult to consider at the same time. The method comprises the steps of 1, obtaining a training set; 2, a YOLOv8-BiFPN network model is constructed; 3, a trained YOLOv8-BiFPN network model is obtained; and 4, calculating the distance of the target object based on the binocular camera and the trained YOLOv8-BiFPN network model.

The application provides a crimping method, device and system for a condenser pipe ring of an air conditioner. The method comprises the following steps: obtaining a first image and a second image of the condenser pipe ring, the first image and the second image being two images of the condenser pipe ring captured by a binocular camera; identifying a center point of the condenser pipe ring in the first image to obtain a center point position; calculating a depth corresponding to the center point position by using a binocular distance measuring algorithm according to the first image and the second image, the depth corresponding to the center point position being a distance from an actual position of the center point position to the binocular camera; determining the actual position of the center point of the condenser pipe ring according to the center point position and the depth corresponding to the center point position; and controlling a terminal end of a mechanical arm to move to the actual position for crimping, thereby solving the problem of low yield of manual crimping of the condenser pipe ring in the prior art.

The application discloses a kind of deep water measurement method and system based on binocular ranging, method includes the following steps: S1, in air or ideal environment, the color calibration board image of known RGB value is collected by binocular camera, as color reference image;S2, color calibration board is placed at underwater target scene, and the first underwater image of color calibration board is collected by RGBW light supplement lamp cooperates binocular camera;S3, contrast first underwater image and color reference image, calculate the high intensity configuration parameter of RGBW light supplement lamp;S4, RGBW light supplement lamp is adjusted to high intensity configuration parameter, cooperates binocular camera and collects underwater target scene image and the second underwater image of color calibration board;S5, underwater target scene image is preprocessed, and underwater target scene actual image is obtained.The application solves the problem that the measurement accuracy is not enough in the application of existing measurement technology under deep water condition, and can realize the efficient operation of accurate identification and reliable analysis of underwater target.

The embodiment of the invention discloses a target distance measurement method and device based on a binocular image and a medium, and relates to the technical fields of target distance measurement, image matching and the like. The method comprises the following steps: taking a target frame of an object to be subjected to distance measurement in a reference image as a reference frame, and searching a first matching frame in a matching image by utilizing a template matching method; dividing the reference frame into a plurality of first sub-regions, searching a second sub-region which is most similar to each first sub-region in feature, and excluding the first sub-regions which are inconsistent in spatial distribution; determining a second matching frame of the reference frame according to the feature similarity of the remaining first sub-regions; selecting one of the first matching frame and the second matching frame, which has the maximum intersection-union ratio with the second target frame, as a final matching frame; and determining the parallax of the object in the binocular image according to the final coordinate offset of the matching frame and the reference frame, and determining the radial distance of the object according to the parallax. According to the embodiment, the accuracy and the stability of binocular distance measurement are improved.

Disclosed are a camera module device, a multi-camera camera module, a camera system, an electronic device, and an automatic zoom imaging method. The multi-camera camera module comprises a first camera unit having a zoom function, and a second camera unit having a preset relative positional relationship with the first camera unit, wherein a driving assembly of the first camera unit drives at least part of a lens in at least one lens group of the first camera unit based on an adjustment instruction to perform optical zoom, and the adjustment instruction is generated based on a distance between the multi-camera camera module and a target object, and the distance is obtained by the first camera module and the second camera module based on a binocular distance measurement principle. In this way, the structural configuration of the multi-camera camera module enables the multi-camera camera module to automatically perform optical zoom based on the distance between the multi-camera camera module and the target object, thereby providing a better shooting experience.

The invention relates to the technical field of unmanned aerial vehicle vision obstacle avoidance, in particular to an unmanned aerial vehicle binocular vision obstacle avoidance system and a distance measurement and obstacle avoidance method thereof, and solves the obstacle avoidance problem when light is weak or binocular vision is abnormal by adding a laser module in a double-unmanned aerial vehicle binocular vision obstacle avoidance system to emit customized patterns and combining with an optical filter. The laser module can supplement environment textures and light to enable binocular vision to work normally again, and can also project laser patterns to a reflecting surface of an obstacle by adopting a monocular distance measurement cooperation scheme because the closer the distance is, the smaller the projected patterns are, and the farther the distance is, the larger the projected patterns are. By utilizing the characteristic, monocular distance measurement and auxiliary binocular distance measurement are performed, the distance data of the front obstacle is more accurately provided, and the probability of obstacle avoidance failure is reduced. Flexible adaptation of binocular normal work and abnormal switching is achieved, and the obstacle avoidance stability and complex environment adaptability of the unmanned aerial vehicle are greatly improved.

The present invention provides a method and system for automatically measuring the distance of dangerous sources in a substation based on binocular ranging, wherein the method comprises: step 1: obtaining a substation image in the substation taken by a binocular camera; step 2: training a dangerous source detection neural network model; step 3: determining the dangerous source in the substation based on the dangerous source detection neural network model and according to the substation image; step 4: determining the relative distance between the dangerous source in the substation and the shooting position according to the shooting characteristics of the dangerous source in the substation. The method and system for automatically measuring the distance of dangerous sources in a substation based on binocular ranging of the present invention introduces the substation image in the substation taken by a binocular camera, and at the same time, trains the dangerous source detection neural network model. According to the substation image and the dangerous source detection neural network model, the dangerous source in the substation is determined. According to the shooting characteristics of the dangerous source in the substation, the relative distance between the dangerous source in the substation and the shooting position is determined, thereby improving the perception efficiency of the dangerous source distance and enhancing safety.

The invention provides a visual following method and system for an agricultural unmanned vehicle, a medium and an electronic terminal.The method comprises the steps that binocular images are collected through a binocular camera of the agricultural unmanned vehicle, and a human body frame is detected on a left eye image; two operation methods are adopted to realize following: one is based on a binocular distance measurement method, stereo matching and triangulation screening to obtain a following frame according with a preset adjustable following distance, and the other is based on the maximum-area human body frame as the following frame for following; according to the two operation methods, the following speed is adjusted through the area ratio of the current following frame to the previous following frame; according to the invention, the computing power is greatly saved, the response speed is increased, the operation efficiency is improved, the technical problems that the existing agricultural unmanned vehicle depends on manual remote control and the human-vehicle following scheme is insufficient to adapt to the agricultural scene are solved, real-time manual intervention is not needed, and the complex agricultural operation environment is efficiently adapted.

The invention provides a registration method, device and system and electronic equipment. The registration method comprises the following steps: acquiring relative poses of the navigation camera and the projection equipment; a first distance between the first virtual camera and the second virtual camera and a corrected focal length are determined according to the relative pose, a target image is obtained, the target image is an image obtained by shooting a target projection image through the navigation camera, and the target projection image is an image formed on the target object after projection of the projection equipment; according to a first target pixel coordinate of the target projection point on the target projection image, a second target pixel coordinate of the target projection point on the target image, the first distance and the corrected focal length, determining a first coordinate of the target projection point in a navigation camera coordinate system by using a binocular distance measurement model; and establishing a registration relation between the navigation camera coordinate system and the image coordinate system according to a corresponding relation between the first coordinate and the point cloud of the target object in the image coordinate system. The method can improve the calculation precision and the calculation efficiency.

The utility model relates to the technical field of machine vision detection, in particular to a machine vision camera with an adjustable binocular distance, which comprises a shell and an adjusting main body, a placing groove is arranged in the shell, the adjusting main body is arranged in the shell, a rotating block is arranged in front of the adjusting main body, the bottom of the rotating block is fixedly connected with a camera main body, and the camera main body is fixedly connected with the camera main body. According to the machine vision camera capable of adjusting the distance between the two eyes, through the arrangement of the rotating block, the cross rod, the limiting groove, the rubber plate, the limiting rod, the sliding groove, the push rod, the push plate, the positioning spring and the sliding block, after the rotating block leaves the rubber plate, the sliding block is pushed by the rotating block to slide in the sliding groove formed in the limiting rod, meanwhile, the rotating block can be rotated, and the distance between the two eyes can be adjusted. The position and angle of the camera main body are adjusted by adjusting the position and angle of the camera main body, the rotating block is driven by the positioning spring to be tightly attached to the rubber plate, and the rotating block and the camera main body are prevented from moving and rotating, so that the camera main body is adjusted to adapt to detection of products of different specifications.

The application discloses a kind of based on binocular ranging technology's asphalt foaming performance evaluation method, belong to highway asphalt mixture test technical field.It includes using two micro cameras to simultaneously continuously shoot foam asphalt image;Image recognition is carried out to two photos at the same time;Division foam asphalt barrel wall adhesion area and effective inflation area;Obtain foam asphalt image pixel parallax value;Calculate the height confidence interval limit value of foam asphalt in different regions;Calculate the representative value of foam asphalt height;Obtain foam asphalt space index and time index;The foaming performance of asphalt is evaluated.The application obtains the height data of multiple points on the surface of foam asphalt according to the characteristics of foam asphalt using binocular ranging technology, and comprehensively considers the inflation height of foam asphalt in different regions, evaluates the foaming performance of asphalt from the angles of asphalt inflation capacity and foam stability, which is rigorous, scientific and highly reliable.

The application provides a power transmission line extraction method and device and a binocular distance measurement method. The power transmission line extraction method comprises the following steps: acquiring an original image; performing smoothing processing on the original image to obtain a noise reduction image; performing sharpening processing on the noise reduction image to obtain an enhanced image; performing edge detection on the enhanced image to obtain a contour image; and extracting a power transmission line image from the contour image by using a straight line detection algorithm. The power transmission line extraction method, device and binocular distance measurement method can consume less computing resources.

The invention provides a large amphibious vehicle overwater garage entering guiding system and method based on target recognition, and belongs to the optical guiding and image recognition technology, and the system is composed of a light source guiding system, a two-channel binocular distance measuring module and an image processing and calculating system. The light source guiding system comprises three square narrow-band red light sources which are mounted at specific positions of the cabin door; the two-channel binocular distance measurement module comprises a narrow-bandwidth red light binocular channel and a visible light binocular channel, is installed on a car roof and provides synchronous images. The image system is used for processing images and calculating warehousing parameters. The LED lamp has the capability of resisting severe environments such as water vapor, salt mist and surge, and is high in illumination adaptability; the structure is simple, the cost is low, and electromagnetic interference is resisted; a large number of environmental samples are not needed, and various vehicle models and garage doors are adapted; and through dual-channel image cross validation, the recognition accuracy and the system reliability are improved.

The invention provides a power equipment safety distance monitoring method based on SGBM and binocular distance measurement. The method comprises the following steps: calibrating a binocular camera to obtain an internal and external parameter matrix; collecting left and right images in a power construction scene by using a binocular camera and performing stereo correction on the left and right images; during stereo correction, the correction matrix is used for carrying out reprojection on the pixels, so that the problem of image distortion caused by radial distortion and tangential distortion is solved, and the precision of subsequent size measurement is improved; generating a disparity map by using OpenCV and SGBM, and then calculating the distance from each object in the power construction scene to the binocular camera; the distance between the power equipment and the worker and the binocular camera in the power construction scene is utilized, and the three-dimensional coordinate of the object in the world coordinate system is calculated through the depth calculation formula, so that the distance between the power equipment and the worker is accurately measured in real time, and potential safety hazards in construction site operation are effectively prevented.

The invention discloses a bank customer identification method and device, electronic equipment and a product, and relates to the technical field of face identification. Comprising; determining a left eye region, a right eye region and a mouth region in the head region grayscale image through grayscale image conversion, multi-threshold binarization processing, binary image merging and row connected domain analysis; the method comprises the following steps: determining a left eye iris center point coordinate and a right eye iris center point coordinate according to pixel point gray level distribution, carrying out plane rotation correction on each frame of head area gray level image, and then determining a lip point coordinate through horizontal integral projection; and finally, taking the lip point, the mouth region boundary point, the left eye region boundary point and the right eye region boundary point as facial recognition key points to obtain a plurality of groups of key point distances, and determining a bank customer recognition result of the target user based on a ratio of the plurality of groups of key point distances to binocular distances. According to the invention, the target user can be identified very conveniently and quickly, and the user can use self-service conveniently.

This invention relates to the field of power transmission line technology. To address the problem of object occlusion and blind spots affecting the perception of monitoring scenes, it provides a split-type binocular ranging method and system for power transmission lines. The method includes: predicting a corresponding dense depth map based on jointly calibrated original images; obtaining a true depth map from two original images and using it to calibrate the two dense depth maps to obtain a corresponding monocular depth map; identifying potential 3D objects from any original image and calculating a sparse 3D point cloud; selecting any original image as a projection surface image and extracting its semantic and texture features, then combining the sparse depth map with a global structural prior for depth completion to obtain a completed dense depth map of the 3D object region; and fusing the completed dense depth map of the 3D object region with the background region of its corresponding monocular depth map to generate a final dense depth map covering the entire monitoring scene. This enables dense depth perception across the entire scene.

The invention provides a binocular distance measurement method for intelligent driving of a vehicle, and the method comprises the steps: obtaining a first video image and a second video image which have the same starting and ending time, the first video image being an image shot by a first camera, and the second video image being an image shot by a second camera; determining a first distance between the first camera and the obstacle at the first time node according to the first video image; determining a second distance between the second camera and the obstacle at the first time node according to the second video image; obtaining a picture of the first time node in the first video image and the second video image; generating a first half body model of the obstacle based on the first video picture and the second video picture; and determining a first target distance between the vehicle and the obstacle based on the first half body model, the first distance and the second distance. The invention further provides a binocular ranging camera for intelligent driving of the vehicle.

The invention discloses a road traffic vehicle detection method based on binocular vision, and the method comprises the steps: obtaining a left image and a right image collected by a binocular camera, and carrying out the distortion removal processing and stereo correction; target space position information is obtained through binocular distance measurement, and a three-dimensional target detection network is constructed; judging whether the target depth estimation error is lower than a preset threshold, and if so, optimizing detection by using a multi-level cost body network based on an attention mechanism; and constructing a target speed learning module based on the LSTM network according to the illumination change and the target shielding, predicting the future position and speed of the target, judging whether the trajectory deviation is lower than a preset threshold value or not, and if so, completing the target positioning and tracking. According to the method, three-dimensional detection and tracking of the vehicle in a complex environment can be rapidly and stably realized, and the detection precision and robustness are improved.

The application discloses a target recognition and distance measurement method and system for a heterogeneous binocular manta ray robot, and belongs to the field of intelligent perception of underwater robots. The method comprises the following steps: encoding original event stream data of a dynamic vision sensor into images; calibrating camera parameters of multiple images generated by encoding of the dynamic vision sensor and multiple images of an industrial camera, so as to obtain the focal lengths of the two cameras and the positional relationship between the two cameras; performing target recognition on the images generated by event encoding of the dynamic vision sensor and the images of the industrial camera through a deep learning algorithm, marking the image area of the target, and obtaining the image coordinates of the target area center; and calculating the distance between the target manta ray robot and the heterogeneous binocular camera by using a binocular distance estimation algorithm according to the target feature center coordinates, the internal parameters and the external parameters of the two cameras. The application can obtain more effective data underwater, and improves the information transmission efficiency.

The present application discloses a method, system and electronic device for detecting misidentification of ground reflections based on parallax, wherein the method includes: obtaining a target frame in a left image based on a deep learning model detection, calculating a first distance value and a second distance value using monocular ranging and binocular ranging respectively; calculating the distance difference between the first distance value and the second distance value, and when the distance difference is greater than a difference threshold, calculating the disparity distribution interval within the target frame range in the disparity map; performing regional growth in the disparity map based on the target frame and the disparity distribution interval to determine the disparity growth frame; when the difference between the target frame and the disparity growth frame in the height direction is greater than the height threshold, determining that the target to be identified corresponding to the target frame is a ground reflection. Through the technical solution in the present application, it is possible to effectively detect misidentification of ground reflections based on parallax, which helps to ensure the driving safety of autonomous driving vehicles.

The present disclosure provides a display device, an autostereoscopic display method, and an eye positioning method, for use in positioning the spatial positions of eyes by means of a binocular distance measurement algorithm and the deviation state of a human face, and on the basis of the positioned spatial positions, arranging images and performing autostereoscopic picture display. The display device comprises a display unit and a control circuit. A processor is used for reading a program in a memory and performing the following steps: acquiring an image pair, the image pair comprising a first view and a second view; on the basis of the first view and the second view, using a binocular distance measurement algorithm to determine the depth of eyes of a human face, wherein the depth of the eyes represents the distance from the eyes to a display unit; determining a deviation state of the human face relative to a center position, wherein the center position is determined on the basis of the center of a binocular camera which photographs the human face; and determining the spatial positions of the eyes of the human face on the basis of the depth of the eyes and the deviation state, and performing stereoscopic picture display on the basis of the spatial positions of the eyes.

The application provides an intelligent blind guiding method and a helmet system based on FPGA, and steps are as follows: calling a blind navigation map and a GPS / Beidou navigation module, planning a walking route; a binocular camera collects images in real time; a FPGA processing module performs target detection on the input images through a multi-target detection algorithm, performs instance segmentation on road targets, and performs binocular distance measurement through a binocular distance measurement algorithm; the FPGA processing module performs hardware acceleration on the multi-target detection algorithm; accurate distance measurement of close-range obstacles is performed; navigation information, multi-target detection results, binocular distance measurement results and ultrasonic distance measurement results are fused, decision algorithm analysis is performed, and navigation voice prompts are given; when an image picture changes slightly, binocular and target detection are not performed. The application accelerates multi-target detection and binocular distance measurement based on FPGA, reduces power consumption while ensuring detection accuracy and real-time performance.

This invention discloses a method and apparatus for measuring the velocity of a debris flow faucet based on binocular ranging. The method involves locating the movement area of ​​the debris flow faucet through motion detection; extracting feature points from the binocular image using the SIFT algorithm at the faucet location and matching all feature points in the image; calculating the distance from all matched points to the binocular camera using binocular ranging and taking the average as the distance value at time t1; obtaining the distance value at time t2 and calculating the difference between it and the distance value at time t1 as the debris flow distance from time t1 to time t2, dividing by the time difference to obtain the average velocity of the debris flow during that period. The apparatus can run all the steps of the method for measuring the velocity of a debris flow faucet based on binocular ranging. This invention effectively improves the accuracy of debris flow faucet velocity measurement.

The invention discloses an array type iris face multi-mode acquisition and recognition system, which belongs to the technical field of biological feature recognition and comprises a main control board and a multi-core processor adopting an ARM framework. The main control board is connected with a binocular face enhancement camera, a binocular distance measurement camera, 16 groups of iris acquisition modules, 16 groups of near-infrared light supplement lamps, a three-color LED indicating lamp, a touch display screen and a real-time living body detection and anti-fraud module based on deep learning. According to the method, the iris features and the face features are deeply fused by adopting a multi-dimensional feature fusion and matching algorithm, so that comprehensive and accurate identity feature vectors are formed. The iris has extremely high uniqueness and stability, the face feature provides an additional identity information dimension, and the fusion of the iris and the face feature greatly improves the accuracy of identity recognition. Meanwhile, the real-time living body detection and anti-fraud module based on deep learning is trained by a large number of real samples and fraud samples, and has strong feature extraction and classification capabilities.

The application relates to the field of display adjustment, in particular to a self-adjusting liquid crystal display based on multi-source data analysis and an adjusting method thereof, which comprises the following steps: constructing an eyeball recognition model based on a YOLOv8 framework, and constructing a comprehensive loss function, wherein a weighted Focal loss term is determined according to environmental light intensity and a real eyeball diameter, an eyeball boundary constraint term is determined based on the real eyeball diameter and a predicted eyeball diameter, a binocular constraint term is determined based on a binocular distance, and the predicted eyeball diameter and the binocular distance are determined by calculating an eyeball recognition area; determining an eyeball change area and a blink frequency value of a user through the eyeball recognition model; calculating an expected brightness value, and performing brightness self-adjusting control of the liquid crystal display based on the expected brightness value. The application realizes a self-adjusting liquid crystal display based on environment light and vision, can combine multi-source data such as a user eyeball state and environmental light intensity, realizes accurate brightness adjustment, and thus improves user experience and reduces visual fatigue.