50 results about "3D radar" patented technology

A low cost, all weather, high definition RF radar system for an autonomous vehicle is described. The high definition RF radar system generates true target object data suitable for imaging, scene understanding, and all weather navigation of the autonomous vehicle. The high definition RF radar system includes a pair of independent orthogonal linear arrays. Data from both linear arrays is fed to a processor that performs data association to form true target detections and target positions. A Boolean association method for determining true target detections and target positions reduces many of the ghosts or incorrect detections that can produce image artifacts. The high definition RF radar system provides near optimal imaging in any dense scene for autonomous vehicle navigation, including during visually obscured weather conditions such as fog.

The invention relates to a medical unit comprises a 3D radar array for the detection of positional or movement data of objects in an examination space and a processing unit for the evaluation of the detected data, with the processing unit being connected to the medical unit and to the 3D radar array, and with the evaluated data being used to control the medical unit or for post-processing data acquired by the medical diagnostic or therapeutic unit. The invention also relates to a method for improving examination or treatment workflows with the medical unit, comprising: detecting positional or movement data of objects in the examination space by the 3D radar array; generating control commands for the medical unit based on the detected data; and post-processing image or spectroscopy data received by the medical based on the detected data. The medical unit is a medical diagnostic or therapeutic unit.

The invention discloses a target tracking method based on measurement conversion Kalman filtering state fusion, which belongs to the field of radar target tracking, and particularly relates to a statistical property calculation method utilizing Doppler radar measurement conversion errors. The state fusion target tracking method comprises the steps of: calculating statistical properties of converted measurement errors based on a predicted value measurement conversion method, regarding a position predicted value in a rectangular coordinate system as a condition to obtain a mean value and a covariance of the converted measurement errors, and eliminating correlation between the covariance of the converted measurement errors and measurement errors; and then performing state estimation on a position and Doppler measurement, and finally using a least mean square error criterion to fuse estimation results of the position and Doppler measurement, so as to obtain a final state estimation. The tracking method can be further extended to CV and CA motion models of a 3D radar.

A method of generating a three-dimensional radar image of a body part having multiple image points. The method comprises receiving radiation information (11) obtained at an array of scan locations relative to the body part, surface profile information (12) relating to the body part, and estimates of body part properties (13). The method further comprises constructing each image point by: determining the minimum optical paths between each scan location and the image point based on the scan locations, surface profile information and body part properties; phase-shifting the radiation information based on the minimum optical paths to equalise the radiation information; and then summing the equalised radiation information to provide a value for the image point. The 3D radar image of the body part is then generated based on the values of each of the image points.

A belt material flow control system comprises a driving motor, carrier rollers, a conveying belt, a fixing bracket, a 3D radar scanner, a speed sensor, a radioactive density meter, a controller and anupper computer; the driving motor is used for driving the conveying belt to rotate; the conveying belt is arranged on the carrier rollers; the 3D radar scanner is fixed to the fixing bracket and located above the conveying belt; the 3D radar scanner, the speed sensor, the radioactive density meter and the driving motor are in communication connection with the controller, and the controller is incommunication connection with the upper computer; the 3D radar scanner is used for measuring 3D contour line information of a material; the speed sensor is used for measuring speed information of theconveying belt; the radioactive density meter is used for measuring density information of the material; and the controller is used for selectively controlling the rotation speed of the driving motoraccording to the material mass or material volume. Thus, data of the material on the conveying belt can be precisely measured, the speed of the conveying belt is controlled, thus, the material flow onthe belt can be the best, energy saving and consumption reducing are achieved, and the service life of a belt conveyor is prolonged.

A novel system that allows for 3D radar detection that simultaneously captures the lateral and depth features of a target is disclosed. This system uses only a single transceiver, a set of delay-lines, and a passive antenna array, all without requiring mechanical rotation. By using the delay lines, a set of beat frequencies corresponding to the target presence can be generated in continuous wave radar systems. Likewise, in pulsed radar systems, the delays also allow the system to determine the 3D aspects of the target(s). Compared to existing solutions, the invention, in embodiments, allows for the implementation of simple, reliable, and power efficient 3D radars.

The invention provides a railway loading metering method and system based on 3D radar material level scanners. The method comprises the steps: enabling mineral aggregate to enter a carriage of a mine car from a mineral aggregate bin, scanning the carriage through a plurality of 3D radar material level scanners in a multi-radar beam and multi-point scanning measurement mode, and obtaining the holographic information of a material surface in the carriage, wherein the holographic information comprising the material level of the mineral aggregate; according to the holographic information of the charge level in the carriage of the mine car, obtaining the mass of mineral aggregate in the carriage; and monitoring the mass of the mineral aggregate in the carriage, so that the final weight of the mineral aggregate in the carriage is not greater than the limited load of the carriage. The 3D radar material level scanners can be used to accurately and truly reflect the material level change condition of the ore, and the ore conveying index is improved.

The invention relates to a method and device for detecting obstacles in 3D radar point cloud continuous frame data, electronic equipment and a computer readable storage medium. The method comprises the following steps: collecting continuous frames of point cloud data, and dividing the point cloud data of the current frame into a ground point set and an obstacle point set; obtaining a road edge of the current frame according to the ground point set; according to the road edge, obtaining the position of the obstacle, wherein the position comprises a road surface and a non-road surface; and on the basis of the position information of the obstacles, detecting categories of all the obstacles contained in the current frame. The category of the object is detected in advance through an algorithm, so that the workload of subsequent manual labeling is reduced, and the labeling efficiency is improved; and a road edge detection method is introduced, the whole detection scene is classified into a road surface area and a non-road surface area, the precision and efficiency of obstacle category detection are improved through priori knowledge, and the method is suitable for task scenes with high real-time performance requirements.

The invention discloses an ice sublayer structure extraction method based on a multi-scale attention mechanism, and relates to the field of computer vision. The invention provides a novel MsANet network, the network takes a double-branch convolutional network as a backbone network, not only fuses multi-scale features, but also uses a 3D attention mechanism to further carry out additional feature modeling on unique features of different ice layers in a 3D radar topological sequence, so that refining processing of spatial relationships of different ice layers is realized. The attention multi-scale module formed by the 3D attention mechanism and the multi-scale module enables detected important ice layer features to obtain richer scale features by using the multi-scale module, and further strengthens the modeling capability of the key ice layer features. According to the method, the positions of a plurality of ice layers are detected at the same time as different tasks, the unique features of the ice layers at different positions are learned through the two branch structures respectively, and finally a rapid and high-precision ice layer structure extraction algorithm based on the MsANet network is achieved.

The invention discloses an automatic classification method and device for the precipitation cloud type based on diversified 3D radar echo characteristics. The method comprises the following steps: analyzing networking radar data to obtain a plurality of radar echo characteristics, randomly selecting two echo characteristics from the plurality of echo characteristics, obtaining an optimal solutionof a cost function by using a neural network model, and drawing a learning curve graph; calculating a high variance and a high deviation based on the drawn learning curve graph, increasing the numberof training samples of the neural network when the high variance condition is met, inputting the increased training samples of the neural network into the neural network model, and drawing the learning curve graph again; when the high deviation condition is met, increasing the number of echo characteristics; inputting the added echo characteristics into the neural network model, and drawing a learning curve graph again; when the high variance condition is not met and the high deviation condition is not met, an optimization model is obtained; obtaining the optimized characteristics and the optimized characteristic quantity for training; and inputting data to be classified into the trained model, and carrying out classification to obtain a classification result. Thus, automatic cloud body classification of high recognition accuracy and speed is realized.

An embodiment of the invention provides a compartment congestion degree detecting method, a compartment congestion degree detecting device and a compartment congestion degree detecting system based on3D radar scanning. The compartment congestion degree detecting method comprises the steps of: acquiring point cloud data of passengers getting on and off scanned by means of 3D radars installed abovecompartment doors, acquiring two-dimensional feature data from the point cloud data, and marking target two-dimensional feature data corresponding to the passengers from the two-dimensional feature data by means of a pre-trained identification model; and tracking a walking direction of the passenger corresponding to each piece of target two-dimensional feature data, further counting numbers of people getting on and off at a current station according to the walking directions of the passengers, calculating a number of passengers in the compartments when a train leaves the station, transmittingthe number of passengers to a next station, and displaying the number of passengers in the next station. According to the compartment congestion degree detecting method, the counted number of the passengers in the compartments is displayed before the passengers arrives at the next station, such that the waiting passengers can select platforms according to the number of passengers in the compartments, thereby avoiding blindly waiting for the train, and improving the carrying capacity of the train.

The invention relates to a method and device for detecting ground points in 3D radar point cloud data and a medium. The method for detecting the ground points in the 3D radar point cloud data comprises the following steps: acquiring point cloud data to be subjected to ground detection; determining a reference plane based on the point cloud data; taking the projection of the radar center of the point cloud data on the reference plane as a polar coordinate circle center point, and performing grid division on the reference plane to obtain a plurality of grids to be detected; and determining ground point cloud data in the point cloud data based on the height distance of each point data in the plurality of grids to be detected on the Z axis. According to the method for detecting the ground point in the 3D radar point cloud data provided by the invention, the ground point cloud data in the point cloud data to be subjected to ground detection is determined based on the height distance of each point data on the Z axis, so that the obtained ground point cloud data is more accurate and better fits the real road surface height, and the applicability of the ground point cloud data is enhanced.

The invention is applicable to the technical field of radars and provides with a millimeter wave 3D radar system and signal processing flow. The millimeter wave 3D radar system comprises a signal source, an emission signal source power dividing network, a receiving signal source power dividing network, a control module, an array radio frequency front end and a digital rear end. The millimeter wave3D radar system has the advantages that the millimeter wave 3D radar system is designed by using the time division multiplexing-multiple-input-multiple-output technology and the two-dimensional planar thinned array technology, three-dimensional detection can be performed on fixed targets, low-speed targets and the like in a complex environment can be achieved, and the hardware complexity and costof the radar system are lowered greatly.

The invention discloses a cement bin material level height detection device. A 3D radar scanner (2) is arranged at the top end in a cement bin (1), a radar meter head (9) is arranged on the radar scanner (2), and the radar meter head (9) is installed on a machine body of the 3D radar scanner (2) through a transmission mechanism (8). By adopting the technical scheme, the rotary 3D radar scanner isstable in echo data, high in resolution, good in charge level simulation degree and high in reliability, and the production safety is improved; meanwhile, the rotary 3D radar scanner can bear the influence of high temperature, pressure and dust; the data can be recovered according to the data stored in history; historical curve change rules of the materials can be checked, and a basis is providedfor arrangement of the production schedule.

The invention discloses an optical 3D and infrared dual-mode composite video accurate measurement monitoring system comprising a monitoring system housing, wherein an optical 3D radar mirror group isarranged on a position at the right end surface in the monitoring system housing; an infrared detector mirror group is disposed at a position on the bottom of the optical 3D radar mirror group and onthe right end surface in the monitoring system housing; an optical 3D radar imaging circuit module is disposed at a position on the center in the monitoring system housing and on the left side of theoptical 3D radar mirror group; an infrared focal plane detector is disposed at a position on the center in the monitoring system housing and on the left side of an infrared detector; and an integratedprocessing circuit is disposed at a position close to the left side in the monitoring system housing. The optical 3D and infrared dual-mode composite video accurate measurement monitoring system notonly enables high-frame-rate 3D measurement, but also measures and monitors the surface temperature of a measured object, and integrates dual-mode data to automatically identify, track, and monitor specific targets.

The invention discloses a 3D radar material level monitor, which is characterized in that a first checking insertion column, a second checking insertion column, a first checking circular groove, a second checking circular groove and an elastic checking auxiliary block are arranged, so that when the material level monitor is subjected to initial position installation and arrangement work, the arrangement positions of the monitor can be accurately positioned, the position checking work can be performed, and the monitor can be accurately arranged at the target position so as to ensure the accuracy of material level monitoring work of the monitor and improved the working quality of the monitor; and through the arrangement of the accurate positioning and locking mechanism, the arrangement position of the material level monitor is locked and fixed, so that the accurate position stability of the monitor is ensured, the normal operation of the monitor in accurate work is ensured, and the workeconomic benefit is well ensured.