12 results about "Binocular vision" patented technology

The invention discloses a mine road intelligent maintenance system for multi-source sensing of a mining dump truck. The mine road intelligent maintenance system comprises a mine car sensor array, an edge computing unit and an equipment collaboration network, the mine car sensor array, the edge computing unit and the equipment collaborative network are in signal connection in sequence; the mine car sensor array is used for collecting whole car and road data and comprises a load sensor, a six-axis IMU, a laser radar, a binocular vision sensor and a vibration sensor. According to the invention, real-time monitoring and dynamic maintenance of the mine road state are realized, and a manual inspection blind area is effectively eliminated. The accuracy of road degradation identification is improved through multi-dimensional data fusion, and resource waste caused by misjudgment is avoided. And an equipment cooperation mechanism solves the conflict problem of maintenance operation and transportation tasks, and the road use efficiency is remarkably improved. The edge computing architecture reduces the data transmission load, and ensures the stable operation of the system under a complex working condition.

The invention discloses a community organic garbage volume and fresh weight estimation method, which comprises the following steps of S1, training a community organic garbage image by using a Mask R-CNN deep neural network to obtain an instance segmentation model of community organic garbage for target identification and target instance segmentation; s2, a binocular camera is used for collecting community organic garbage depth images before and after the community organic garbage needs to be processed; s3, the community organic garbage depth image is segmented by using the instance segmentation model, garbage depth information after segmentation is acquired, and the garbage depth information is from a binocular camera; s4, combining the instance segmentation model and a binocular vision volume algorithm to construct a garbage volume prediction algorithm, and obtaining a garbage volume estimation result; and S5, a garbage volume and fresh weight relation model can be obtained in combination with the garbage fresh weight unary linear regression model, and the garbage fresh weight can be estimated. According to the method, the instance segmentation model and the binocular depth sensing technology are combined, the average relative error of the estimation results of the community organic garbage volume and fresh weight estimation method is 5.98%-18.71%, most of the estimation results are about 10%, the category of the community organic garbage can be effectively recognized, and the volume and fresh weight of the community organic garbage can be estimated.

The invention discloses a nitrogen-phosphorus-potassium fertilizer on-demand proportioning mixed application robot based on corn growth state rapid detection, and belongs to the technical field of agricultural intelligent equipment. Comprising a walking moving system, and a cockpit, a binocular vision detection system, a central control system, a stirring system and an independent nitrogen-phosphorus-potassium fertilizer discharging system which are mounted at the top of the walking moving system, and the binocular vision detection system comprises two electric push rods which are fixedly mounted at the front end of the top of the walking moving system. According to the nitrogen-phosphorus-potassium fertilizer on-demand matching mixed application robot based on rapid detection of the corn growth state, through the collaborative design of the binocular vision detection system and the nitrogen-phosphorus-potassium fertilizer independent fertilizer discharging system, accurate matching of the corn growth state and the fertilization amount is achieved; in a binocular vision detection system, two electric push rods can adjust the height of a binocular camera, a rotating motor can adjust the angle of the camera, a light supplementing lamp is matched to eliminate illumination interference, and a waterproof shell resists rainwater and dust in the field.

The invention discloses a visual training system which comprises a display device used for displaying a first image and a second image to a to-be-trained eye and a non-trained eye of a trainee respectively, the first image comprises a first sighting mark located at a non-central site in the first image, and the second image comprises a second sighting mark located at a central site of the second image; the control device is used for adjusting the physical attribute of the first sighting mark or / and the physical attribute of the second sighting mark so as to carry out training; and the interaction device is used for acquiring a training result fed back by the trainer, and the training result is a feedback result about the sighting mark located at the non-central site in the fused image perceived by the two eyes of the trainer. The second sighting mark located at the central site is displayed to the non-training eye, the first sighting mark located at the non-central site is displayed to the training eye, a trainer is promoted to drive the peripheral visual field vision of the training eye through the foveal vision of the non-training eye, and the visual perception ability of the peripheral visual field of the training eye is improved; and the visual difference of the two eyes of the trainee can be repaired.

The invention provides an auxiliary assembly positioning method and system for a helicopter lift force system. The method comprises the steps that auxiliary assembly racks are installed on a main propeller hub and a designated supporting arm of an automatic inclinator correspondingly; the target balls are installed on the main propeller hub, all supporting arms of the automatic inclinator and fork lug bolt connecting holes correspondingly; the target balls are installed on a main shaft, a cartridge receiver and supporting legs of the main speed reducer; a binocular vision scanning camera is placed on the side of the assembly area; the attitude tracking system locates the position of the workpiece and establishes a digital twin model; the path planning system determines an assembly path based on a digital twin model; the binocular vision scanning camera and the target ball are combined with the attitude tracking system, so that time domain and space domain information of the main speed reducer, the main propeller hub and the automatic inclinator can be collected and analyzed in real time, and position attitudes of the main speed reducer, the main propeller hub and the automatic inclinator are analyzed; the positioning precision is improved, the assembling and positioning time is shortened, and the safety is improved.

The invention provides a linear machine for improving eye position deviation and improving monocular and binocular visual quality, comprising a wearable sensing unit which is configured to be worn by a user and comprises a myoelectricity sensing assembly used for collecting myoelectricity signals of temporalis of the user; a wireless transmitting module; the desktop type execution unit is physically separated from the wearable sensing unit and communicates with the wearable sensing unit through a wireless communication link, and the desktop type execution unit comprises a sighting mark assembly capable of moving along a motion track; the driving assembly is used for driving the sighting mark assembly to move; the wireless receiving module is used for receiving data from the wearable sensing unit; the second processing module is configured to control the driving assembly according to the data received from the wireless receiving module and a training mode of a preset logic so as to achieve movement or on-site stopping of the sighting mark assembly, the heavy driving part is completely separated from the light sensing part, and therefore the sighting mark assembly can be conveniently moved. And the problems of load-bearing feeling, pressure feeling and discomfort caused by traditional integrated equipment are solved.

The application discloses an intelligent sound control method and system based on sound field adaptive adjustment, relates to the technical field of sound control, and comprises the following steps: after intercepting a real-time audio stream, performing time-frequency analysis on the real-time audio stream, and matching a real-time sound field template; positioning a real-time spatial pose coordinate of a user according to binocular vision sensing data; performing listening area sound wave propagation attenuation analysis based on the real-time spatial pose, and outputting a four-dimensional sound image space vector; performing spatial sound field mapping operation on the real-time sound field template by using the four-dimensional sound image space vector, and obtaining a real-time scene sound field; performing sound field parameter precalculation based on trajectory prediction according to a spatial pose sequence obtained by camera skeleton time sequence tracking, and performing low-delay update on the real-time scene sound field according to a calculation result. The application solves the technical problem that the prior art cannot adjust a sound field in real time according to user positions and environmental changes, and achieves the technical effect of accurately and dynamically adjusting a sound field.

The present application relates to the field of sports information technology, in particular to a kind of sports teaching intelligent sports testing system.The system: data acquisition module real-time acquisition student's movement image, depth information and identity radio frequency signal;Edge computing module receives real-time data, uses human body posture estimation technology to extract skeletal key points, and combines finite state machine model to determine the standard degree and automatically count the actions such as chin-ups, sit-ups and the like;Precise measurement of standing long jump is realized using binocular vision or depth ranging algorithm;Identity verification and anti-cheating monitoring are carried out in the test by monitoring module;Cloud management module receives the data transmitted by edge computing module through data transmission module for statistical analysis, and generates personalized exercise program according to the analysis result.The present application effectively prevents cheating and irregular behavior through biometric detection, trajectory tracking and behavior analysis technology, and solves the problems of low efficiency, large subjective error of manual judge and difficult to prevent cheating in traditional sports testing.

The invention provides a ceramic matrix composite product machining cutter location point self-adaptive correction method. The method comprises the steps that a five-axis machining cutter location file is generated based on a theoretical model of a ceramic matrix composite product, and theoretical machining cutter location point set data are extracted from the five-axis machining cutter location file; the theoretical machining cutter location point set data comprises coordinates and normal vectors of machining cutter location points in a theoretical model coordinate system; scanning by adopting a binocular vision method to obtain profile point cloud data of the to-be-processed blank, and preprocessing the profile point cloud data of the to-be-processed blank, removing noisy points and reducing the number of sampling points; rigid registration is carried out on the theoretical machining cutter location point and the to-be-machined blank point cloud; according to the registered theoretical machining cutter location point and the blank point cloud, the machining allowance of the to-be-machined blank piece is calculated, an undercut area is recognized according to the machining allowance, and an undercut area point cloud in the theoretical machining cutter location point is exported; and carrying out adaptive deformation correction on the point cloud of the undercut area in the theoretical machining cutter location points, and generating a five-axis machining cutter location file based on a corrected theoretical machining cutter location point set to guide product machining.

The invention relates to a method and device for analyzing visual and neural function changes after visual training, and relates to the technical field of visual neural function evaluation.The method comprises the steps that in the visual training process of a target object, visual brain physiological data of different training groups and trained binocular visual functions are synchronously collected through EEG-fNIRS, and the visual brain physiological data are obtained; the method comprises the following steps of: acquiring physiological data signals, performing preprocessing and feature extraction on the acquired physiological data signals to obtain corresponding signal features, performing analysis based on the extracted signal features to determine a first analysis result and a second analysis result, and finally analyzing dynamic interaction of electroencephalogram and brain oxygen by utilizing EEG-fNIRS in combination with the two analysis results and binocular visual functions. According to the method, the change analysis result of the visual and neurological functions after visual training is obtained, the examination of organically combining the traditional visual function with the neurological function is realized, the improvement of the visual function is analyzed, and the influence of the visual function on the brain function can be revealed from the neurophysiology level.