16results about How to "Perceived effect is good" patented technology

The invention relates to the technical field of laser radars, in particular to an unmanned vehicle road obstacle sensing system based on a laser radar, and the system comprises a laser radar data collection module which adjusts the scanning frequency of the laser radar, collects point cloud data from static and dynamic obstacles, and obtains preliminary scanning data; and filtering the preliminary scanning data, and removing noise data. According to the invention, by calculating the dynamic characteristics of the point cloud data, the key point and the moving track of each obstacle are extracted, and the ability of sensing the obstacles in the dynamic environment is optimized. By adopting a time sequence analysis method, the moving state and track of the obstacle can be directly deduced according to the point cloud change, so that the ability of tracking the moving obstacle in a complex dynamic scene is improved. In the spatial reconstruction process, geometric subdivision is utilized to reconstruct point cloud data, and dynamic information is combined with a static point cloud structure, so that the analysis capability of spatial data is enhanced.

The invention relates to a multi-unmanned aerial vehicle auxiliary sensing integrated trajectory planning and resource allocation method, which comprises the following steps that a sensing integrated system comprising a plurality of unmanned aerial vehicles, a plurality of ground nodes and a plurality of mobile terminals is established, sensing integrated signals emitted by the unmanned aerial vehicles are received and reflected by the mobile terminals, and the sensing integrated signals are transmitted to the unmanned aerial vehicles; the reflected communication and inductance integrated signal is received and processed by a ground node; constructing a Cramer-Rao bound model of the mobile terminal at the target position of the mobile terminal according to the path loss of the flux-inductance integrated signal; establishing a joint optimization problem based on set constraint conditions by taking minimization of the maximum Cramer-Rao bound of all the mobile terminals at the target positions as a target; and solving the joint optimization problem to obtain the moving track and the transmitting power of the unmanned aerial vehicle and the corresponding ground node. According to the method, perception performance optimization under the constraint of communication performance is realized, and communication and calculation burden of data fusion is reduced on the premise of ensuring the perception performance.

The invention relates to a TPA-LSTM-based shunting area wet and slippery road surface vehicle type-based dynamic early warning and speed guiding method. The method comprises the following steps: S1, collecting traffic flow operation time sequence data in a highway shunting area wet and slippery road surface scene; s2, predicting speed limit values of different vehicle types for safe passing on the wet and slippery road surface in the shunting area; s3, formulating early warning information release content; s4, determining an early warning information issuing mode; s5, determining an information issuing position of the highway shunting area, wherein the information issuing position is comprehensively determined according to an existing shunting area ETC portal layout principle in combination with a warning information issuing standard; and S6, early warning information is pushed to the vehicle end, and the ETC door frame receives the optimal passing speed information of the wet and slippery road surface pushed by the traffic management background and issues the information to vehicle-mounted OBU equipment with a voice broadcast function of the vehicle. According to the method, the real-time performance, the dynamic adaptability, the personalized early warning and the driver response effect are remarkably improved, so that the occurrence rate of accidents in the diversion area in a wet and slippery road scene in rainy days is greatly reduced.

The invention relates to the technical field of wireless communication, and discloses a compromise design method for a communication-sensing integrated waveform, which comprises the following steps: acquiring a communication channel matrix at a transmitting end; splitting the total power according to the communication perception performance compromise coefficient to obtain power for optimizing perception and power for optimizing communication; maximizing the reachable sum rate by taking the optimized sensing power as a constraint to obtain a first frequency domain auto-covariance matrix; minimizing a Cramer-Rao lower bound by taking optimized communication power as a constraint to obtain a second time domain auto-covariance matrix; establishing an optimization problem of nonlinear programming; and combining the first frequency domain auto-covariance matrix and the second time domain auto-covariance matrix in a frequency domain to obtain a final transmitting signal frequency domain auto-covariance matrix, and deriving to obtain a final transmitting signal frequency domain precoding matrix by using a water injection algorithm. According to the method, the communication performance and the radar sensing performance are improved, and the technical problems that an existing waveform design method is imperfect in optimization and insufficient in consideration are solved.

The invention discloses a system and a method for voice mouth shape action matching of a dialogue robot, and relates to the technical field of voice matching, the method adopts a Bluetooth dual-channel technology, a time point array is transmitted to an Arduino mainboard of the dialogue robot through a first Bluetooth channel, a voice file is transmitted to sound equipment of the dialogue robot through a second Bluetooth channel, and the sound equipment of the dialogue robot is used for voice mouth shape action matching of the dialogue robot. High synchronization of voice playing and mechanical actions and synchronous transmission of voice files and time point arrays are achieved, close association between voice playing and mouth-shaped actions is ensured, and action lag caused by transmission delay or untimely hardware response is avoided. And each time point in the time point array can be accurately read and compared through a timer arranged in the Arduino mainboard, so that the steering engine can immediately respond at each set time point, and the opening and closing actions of the mouth of the conversation robot are driven. And when the time point arrives, an instruction is sent to control opening and closing of the mouth shape, so that the voice and the mouth shape action are highly consistent.

The invention discloses an unmanned driving scene generation method based on a StyleGAN-V algorithm, and the method comprises the implementation steps: firstly, collecting a real severe weather driving scene video, and carrying out the preprocessing of the video, and constructing a data set; then preliminarily constructing a video generation model; a time sequence feature extraction module combining time sequence excitation and time sequence displacement is constructed, and time sequence features of the video are extracted; introducing a joint loss function constraint in the generation process; and finally, calculating an improved loss function, updating video generation model parameters, and continuously training until the generation model is completed. According to the method, the driving scene in the severe weather can be realistically simulated, and through experimental verification, the method can effectively improve the continuity of the generated video and the capturing capability of dynamic characteristics, so that the authenticity of the driving simulation scene in the severe weather is improved, the sensing capability of subtle action changes in the video is improved, and the driving experience is improved. And better performance is achieved in the aspects of dynamic characteristics and picture continuity of the video.

The utility model discloses a child toy which comprises a seat body, a balance plate, a toy ball and a pressing assembly, and a long-strip-shaped containing groove is formed in the seat body; the balance plate is connected with the seat body, the surface of the balance plate forms at least one part of the bottom surface of the containing groove, and the balance plate can rotate relative to the seat body so as to adjust the gradient of the bottom surface of the containing groove; the toy ball is arranged in the containing groove and arranged on the balance plate in a rolling mode. And the pressing part is connected with the seat body and is configured to drive the balance plate to rotate. According to the child toy, by pressing and loosening the pressing assembly, the balance plate can be driven to be switched between the inclined state and the balance state, the small ball in the containing groove is driven to roll or keep still, the overall structure and operation are very simple, and the child toy is suitable for being played by young infants.

The utility model discloses a vehicle-mounted zoom camera, which comprises a camera main body and a zoom lens, and the zoom lens comprises a vibrating membrane, a piezoelectric actuator and a light-transmitting substrate. The vibrating membranes are made of a polydimethylsiloxane material, two opposite large surfaces of the light-transmitting substrate are both connected with the edge of one vibrating membrane in a sealing manner, the vibrating membranes and the light-transmitting substrate form a cavity, the cavity is filled with light-transmitting liquid, and the light-transmitting liquid is filled in the cavity. The piezoelectric actuator is attached to the side, away from the light-transmitting substrate, of the vibrating membrane, and a through hole is formed in the attaching position of the piezoelectric actuator and the vibrating membrane. The zoom function is integrated to a single camera, and the focal length is adjusted by using the vibrating diaphragm and the piezoelectric actuator, so that the number of cameras is reduced, the AI and logic computing power requirements are reduced, and the system performance is optimized.

The application belongs to the technical field of wireless communication and signal processing, and discloses a quantum heuristic joint optimization method suitable for a flow state antenna ISAC system, which comprises the following steps: 1, a MIMO-FAS model is constructed, and an equivalent downlink channel is given to realize unified expression of a communication link and a sensing link; 2, a weighted sum rate maximization problem P1, a minimum user SINR maximization problem P2 and a sensing signal-to-jamming noise ratio SCNR maximization problem P3 are constructed; 3, the weighted sum rate maximization problem P1 is solved; 4, the minimum user SINR maximization problem P2 is solved; 5, the sensing signal-to-jamming noise ratio SCNR maximization problem P3 is solved; and 6, a quantum heuristic simulation bifurcation method is adopted to perform port selection optimization to obtain a joint optimal port-beam configuration. The application realizes collaborative optimization of port configuration and beam design, effectively improves the communication rate and sensing accuracy of the system while guaranteeing the calculation efficiency and scalability.

According to the information transmission method and device for vehicle monitoring and the computer readable medium provided by the embodiment of the invention, an authentication mechanism of fingerprint information is constructed based on hardware information, and the fingerprint information is sensitive to changes of hardware such as a mainboard and a network card; therefore, it is ensured that only the authenticated vehicle-mounted equipment can perform heartbeat interaction with the server-side equipment and report data, the authenticity of a data source is ensured, data security risks caused by equipment cloning and the like can be prevented, a heartbeat interaction mechanism and a data reporting process are optimized, and the data reporting efficiency is improved. The problems that in an existing scheme, a large number of network resources are consumed in an unstable network environment, resource waste is caused, and data loss is prone to occurring are effectively solved.

This invention discloses a deep learning-based super-resolution reconstruction method for polarization images, which can be used to reconstruct corresponding high-resolution polarization images from low-resolution polarization images. The method includes: acquiring high-resolution polarization images using a polarization camera and preprocessing them to obtain low-resolution polarization images, creating a dataset; fusing feature information through a shallow convolutional neural network; performing dense feature fusion through a residual dense module; using an upscaling module to amplify the number of image feature channels to a corresponding magnification factor; obtaining the super-resolution polarization image through an output module; and optimizing the neural network using a polarization-aware and pixel-mixing loss function. This method, based on a deep learning convolutional neural network, constructs a super-resolution reconstruction neural network model and uses a polarization-aware and pixel-mixing loss function to train and optimize the neural network, enabling the reconstruction of super-resolution polarization images from low-resolution polarization images.

The invention discloses a lane line detection method, and relates to the technical field of intelligent driving. The method comprises the following steps: acquiring a data sequence of a road acquired by a vehicle-mounted sensor, and performing feature processing on the data sequence to obtain a target aerial view feature map sequence; performing feature fusion on the historical frame aerial view feature map and the current frame aerial view feature map in the target aerial view feature map sequence to obtain an enhanced aerial view feature map; extracting a map feature map from a road map of a vehicle driving road, and performing feature fusion on the enhanced aerial view feature map and the map feature map to obtain a target fusion feature map; and performing lane line detection on the target fusion feature map to obtain a lane line of a vehicle driving road. The lane line detection method has better road information perception capability aiming at the complex problem of rapid change of road light and road surface conditions, so that the continuity, accuracy and stability of lane line detection are improved, and the lane line detection method is suitable for lane line detection of long-distance roads.

The utility model relates to the technical field of fan quality inspection equipment, and discloses fan blade rotation detection equipment, which comprises a detection mechanism, the detection mechanism comprises an annular seat, a driving mechanism is arranged in the middle of the annular seat, a detection analysis mechanism is arranged at the top end of the annular seat, and the driving mechanism comprises a driving motor arranged at the central position in the annular seat. And the driving end above the driving motor is fixedly connected with a fan blade mounting mechanism. According to the utility model, the high-precision sensing detection structure design is adopted, the optical fiber sensors with higher sensitivity and resolution ratio are selected to replace the traditional strain gauge type sensors, the optical fiber sensors have better sensing ability to micro strain and displacement changes, and the four optical fiber sensors are arranged at the same time, so that the detection accuracy is improved; the four optical fiber sensors are arranged below the fan blade mounting mechanism of the driving mechanism in an equal-angle shape, and the data processing host is arranged in a matched mode and connected with the four optical fiber sensors through connecting wires, so that the detection precision can be improved.

The application provides a sensing method, a communication device and a computer readable storage medium. The sensing method comprises: obtaining a transmitting signal and an echo signal of the transmitting signal; constructing a channel information matrix according to the transmitting signal and the echo signal, the channel information matrix comprising a pilot part and a data part; performing two-dimensional Fourier transform on the pilot part to obtain a sensing result; judging whether the sensing result meets a sensing resolution requirement; if the sensing result does not meet the sensing resolution requirement, performing phase compensation on the channel information matrix according to the sensing result; performing two-dimensional Fourier transform on the pilot part and / or the data part in the compensated channel information matrix to obtain an updated sensing result, and returning to the step of judging whether the sensing result meets the sensing resolution requirement until the updated sensing result meets the sensing resolution requirement, and obtaining a final sensing result. The application can improve the sensing accuracy of the estimated sensing result.

This invention discloses an AR multi-person collaborative interactive projection system and method for public spaces, belonging to the field of AR multi-person collaborative interactive projection technology. It includes a multi-source spatial calibration module configured to extract static physical feature point clouds in the public space based on real-time environmental images and depth data collected by multiple AR devices, and to perform global registration of the feature point clouds using a weighted nearest neighbor iterative algorithm to generate a unified world coordinate system. This invention utilizes the multi-source spatial calibration module to perform global registration of static physical feature point clouds collected by multiple AR devices using a weighted nearest neighbor iterative algorithm to generate a unified world coordinate system, and detects the relative pose deviation between each AR device. When the deviation exceeds a preset threshold, a dynamic recalibration process is triggered, effectively solving the problem of inconsistent coordinate systems among multiple AR devices in public spaces, and significantly improving the spatial consistency and registration accuracy of multi-person collaboration.

The invention discloses a concrete mixing quality evaluation and early warning method for a concrete faced rockfill dam, which comprises the following steps: in a mix proportion design stage, acquiring concrete mixing process parameters, and carrying out a concrete test block test to obtain panel concrete performance indexes; a concrete performance prediction model is constructed and trained; in the panel construction process stage, concrete actual mixing process parameter collection and actual meteorological condition collection are synchronously carried out, and panel concrete performance prediction indexes under the current meteorological condition are obtained through the concrete performance prediction model; comprehensively considering comparison conditions of actual concrete mixing process parameters and design parameters, and establishing a concrete mixing process parameter grading early warning model; and based on the panel concrete performance prediction index and the design performance index, performing deviation analysis on the concrete performance index, and establishing a deviation early warning model. According to the method, the influence of the mixing process parameters on the concrete performance can be obtained, so that data support is provided for feedback control of on-site construction quality.