1154 results about "Vehicle identification" patented technology

The invention provides an unmanned aerial vehicle identification early warning method and system. The method comprises the following steps: acquiring RGB image data, thermal radiation data and spectral data of an unmanned aerial vehicle no-fly zone through a visible light camera, an infrared thermal imager and a multispectral imager; performing transmission preprocessing on the RGB image data, the thermal radiation data and the spectral data, and adaptively adjusting multi-level fusion of a fusion weight based on real-time environmental parameters to generate target fusion data; based on a deep learning model and a tracking prediction algorithm, performing unmanned aerial vehicle identification early warning on the target fusion data, and generating early warning data; and transmitting the target fusion data and the corresponding abnormal event log to a cloud server, and updating the deep learning model by adopting the target fusion data and the abnormal event log. Through cooperative work of a multi-mode sensor, visible light, infrared, multispectral and other wave bands are covered, all-weather and full-scene unmanned aerial vehicle detection is achieved, the fusion weight is adjusted in real time based on real-time environment parameters, and the accuracy of the recognition result under the complex air situation is ensured.

Systems and methods for automated unmanned aerial vehicle recognition. A multiplicity of receivers captures RF data and transmits the RF data to at least one node device. The at least one node device comprises a signal processing engine, a detection engine, a classification engine, and a direction finding engine. The at least one node device is configured with an artificial intelligence algorithm. The detection engine and classification engine are trained to detect and classify signals from unmanned vehicles and their controllers based on processed data from the signal processing engine. The direction finding engine is operable to provide lines of bearing for detected unmanned vehicles.

The invention relates to the technical field of intelligent traffic monitoring, in particular to a vehicle identification and traffic incident detection method and system based on the view angle of an unmanned aerial vehicle, and the method comprises the steps: obtaining the aerial traffic video data of the unmanned aerial vehicle and the flight control data of the unmanned aerial vehicle; performing target identification on the image in the video data by adopting a target detection algorithm to obtain vehicle information; tracking the vehicle in the video data by using a target tracking algorithm, and mapping the identified vehicle to a unified coordinate system in combination with the flight control data to generate vehicle trajectory data; constructing a comprehensive road description model based on the vehicle trajectory data and the vehicle information; and forming a traffic incident recognition module based on the comprehensive road description model, and recognizing the input aerial video according to a preset traffic incident recognition rule. According to the invention, by optimizing the vehicle identification algorithm, constructing the road description model and designing the efficient traffic event identification module, the application efficiency of the unmanned aerial vehicle aerial video in the traffic monitoring field is effectively improved.

The invention belongs to the technical field of automatic driving vehicle identification, and discloses an automatic driving vehicle point cloud identification method and system based on a laser radar. According to the method, an automatic driving vehicle point cloud recognition model is built, modular dynamic edge convolution based on a feature sensitivity layer number selection strategy is provided in the model, local geometric information is better captured by dynamically learning a local geometric structure, and the extraction capability of geometric feature information is enhanced. In order to prevent the problem of insufficient information extraction caused by layer number simplification of modular dynamic edge convolution, a selective kernel attention mechanism is introduced, a feature fusion mode is adjusted, residual connection is added, more comprehensive statistical information is captured while original information is reserved, and the multi-scale feature capture capability is improved, so that the classification performance of the model is improved. Especially in the face of noise, sparse data and complex object shapes, high classification accuracy can still be kept, and a more accurate environment perception capability is provided for an automatic driving system.

The invention discloses an intelligent parking space guiding system for a hospital parking lot, relates to the technical field of intelligent traffic, and is used for solving the problems that the hospital parking lot is seriously jammed in peak hours and special vehicles lack exclusive passing authority. The system comprises a parking space monitoring module, a vehicle identification module, an intelligent guiding module and a user interaction module. The parking space state is monitored in real time through the multi-mode sensor array; recognizing entering and exiting vehicles through a deep learning recognition algorithm based on cameras deployed at entrances and exits, and obtaining corresponding vehicle information; based on parking space state information and vehicle identification information, a route optimal value is dynamically calculated, and a whole-course navigation service from an entrance to a target parking space is provided for a driver, so that accurate detection of the parking space state, special vehicle priority distribution, high-low peak dynamic route planning and whole-process intelligent guidance are realized, the hospital parking efficiency is remarkably improved, and the hospital parking experience is improved. And the congestion condition in the peak period is relieved.

Systems and methods for automated unmanned aerial vehicle recognition. A multiplicity of receivers captures RF data and transmits the RF data to at least one node device. The at least one node device comprises a signal processing engine, a detection engine, a classification engine, and a direction finding engine. The at least one node device is configured with an artificial intelligence algorithm. The detection engine and classification engine are trained to detect and classify signals from unmanned vehicles and their controllers based on processed data from the signal processing engine. The direction finding engine is operable to provide lines of bearing for detected unmanned vehicles.

The invention relates to the technical field of vehicle image recognition, and discloses a multi-modal data enhanced vehicle recognition method and system based on a generative adversarial network, and the method comprises the steps: collecting vehicle multi-modal data (a visible light image, a thermal infrared image and three-dimensional laser point cloud data), and constructing a vehicle multi-modal data set; performing preprocessing and feature alignment on the data set to obtain standardized multi-modal data; constructing a cross-modal generator based on an adaptive attention mechanism, learning inter-modal feature association through a dynamic weight distribution module, and generating vehicle feature fusion data; designing a dual discriminator structure consisting of a perception consistency discriminator and a semantic fidelity discriminator, and optimizing the generator by adopting an alternate adversarial training strategy; generating a supplementary data sample for the complex scene by using the optimized generator, and constructing an enhanced data set; and constructing a multi-mode cooperative vehicle identification model based on the enhanced data set, and realizing high-precision vehicle attribute identification.

The invention belongs to the field of computer vision, and particularly relates to a high-robustness vehicle identification method based on target area constraint, which comprises the following steps of: acquiring original vehicle image data, and obtaining a training image data set with a vehicle target area mask; constructing an improved convolutional neural network as a classification backbone network, and inputting the training image data set into the network for feature extraction to obtain a feature map; constructing an attention region constraint module, and forming attention region constraint loss by calculating Dice loss between the target vehicle mask and the attention thermodynamic diagram; the feature map is input to a target guide segmentation module, a segmentation prediction map of the target vehicle is generated, and segmentation loss is calculated; and updating parameters of the improved convolutional neural network by using a total loss function obtained by combining constraint loss and segmentation loss, thereby realizing high-robustness vehicle identification. According to the method, the robustness and accuracy of vehicle identification under the foreground vehicle shielding condition are effectively improved while high-efficiency calculation of the model is kept.

A method for creating high-resolution environment maps for a vehicle having an autonomous driving function. The method includes: providing environment image data of a recognition system of the vehicle, wherein the recognition system includes an environmental sensor for detecting a vehicle environment while the vehicle is traveling; providing domain knowledge of the vehicle environment in the form of a trained knowledge graph; and creating the high-resolution environment maps of the vehicle environment by supplementing the environment image data by means of the provided domain knowledge of the trained knowledge graph.

The invention relates to the field of unmanned aerial vehicle identification, and discloses an interference method for a slight unmanned aerial vehicle identification mark, which comprises the following steps of: pre-embedding a secondary disturbance primitive at the periphery of the identification mark by constructing a pseudo-structure surface compatible with a multi-mode reflection level; performing pseudo-static layer fusion on a region with abnormal view angle focusing offset in the disturbance sensitivity map, and introducing an adjustable gray scale transmission domain mask and a multi-frequency interference texture in the fusion process to form a disturbance reconstruction domain which is subjected to boundary folding with the edge contour of the original mark; on the basis of the disturbance reconstruction domain, pseudo-random disturbance iteration aligned with the flight path prediction model is executed; mapping the interference identification probability reverse offset curved surface into the visible light disturbance superposition graph; and performing time sequence flexible interference control on the target area based on the light interference stability enhancement unit, and performing dynamic reconstruction on the pseudo-primitive layout density, the shading fine tuning node and the polarization interference structure. The method has the advantage that stable slight interference on the identification mark under the condition of a specific visual angle is improved.

One variation of a preferred system for rendering content on a vehicle includes a display, a memory, a communication module, and a processor. The display is configured to mount adjacent an exterior surface of a vehicle. The memory is configured to store a plurality of executable applications including a vehicle identification application and an application elected by a user. The communication module is configured to download the user-elected application to the memory. The processor is configured to selectively execute applications to control visual content rendered on the display, wherein the display renders vehicle identification information when the vehicle identification application executes, and wherein the display renders additional visual content when the user-elected application executes.

The invention provides a multi-modal feature vector fused vehicle cross-lens ReID matching method and system, and relates to the technical field of vehicle identification, and the method comprises the steps: collecting a vehicle image through a camera, and extracting triple features, including a bottom-layer visual feature, a middle-layer semantic feature and a high-layer character feature; in combination with vehicle space-time metadata at adjacent acquisition cameras, generating space-time trajectory feature vectors, and capturing a time sequence rule of a vehicle driving path; the missing features are complemented by adopting an AI generation technology, and the complementation precision is optimized through adaptive learning; inputting the triple feature, the time sequence rule and the complementation feature into a Transform fusion network to generate a fusion feature vector; calculating the cosine similarity of the to-be-matched vehicle according to the fusion feature vector, and carrying out cross-border head matching; according to the method, the problem of insufficient distinction degree of single-modal features is solved, the track feature vector is generated by combining the space-time metadata of the camera, the driving time sequence rule of the vehicle between different lenses is captured, and the space-time constraint of cross-scene matching is enhanced.

The invention discloses a control method and device of a vehicle cloud cooperative system and a vehicle, and relates to the technical field of vehicles. The method comprises the steps that a vehicle twinning request is acquired, and the vehicle twinning request carries a vehicle identifier and operation state data of a vehicle; based on the vehicle twinning request, virtual twinning and a channel key are generated, the virtual twinning is a virtual mirror image matched with the running state of the vehicle, and the virtual twinning is used for simulating the running state of the vehicle and predicting future behaviors of the vehicle; establishing a communication channel based on the channel key, and transmitting the current operation state data and the target demand of the vehicle based on the communication channel; analyzing the current operation state data and the target demand based on the virtual twinning to obtain an analysis result; and determining a target decision based on the analysis result, and controlling vehicle driving based on the target decision. According to the invention, the technical problems of unstable network connection, delayed state synchronization and limitation of an intelligent decision-making mechanism of a vehicle cloud cooperative system in the related technology are solved.

The invention provides a new energy vehicle parking charging scheduling management method and system, and relates to the technical field of new energy charging management, and the method comprises the steps: receiving a charging reservation request sent by a new energy vehicle, including a vehicle identification code, a battery remaining capacity and an expected charging time period, obtaining a vehicle charging characteristic parameter, and combining with environment temperature correction; and the actual required charging time is accurately calculated. And on the basis of the charging duration, the expected charging time period and the charging pile operation state, a dynamic scoring method is adopted, a comprehensive score is calculated through duration matching score and reliability score weighting, and an optimal charging pile is selected for distribution according to a scoring result. According to the method, a weighted dynamic scoring method of the duration matching score and the reliability score is adopted, the user demand, the operation state of the charging pile and the environmental influence are comprehensively considered, the optimal distribution of the charging pile resources is ensured, and the overall operation efficiency and the service quality of the charging station are remarkably improved.

The invention discloses a highway hazardous chemical substance liquid leakage accident monitoring method and a highway hazardous chemical substance liquid leakage accident monitoring system based on computer vision. The method comprises the following steps: arranging and installing an identifier configured for hazardous chemical substance vehicle identification on a vehicle for loading and transporting hazardous chemical substances; the identifier comprises an optical identifier configured to be used for improving the visual identification degree of the dangerous goods vehicle and a digital identifier configured to realize encrypted storage and quick reading of vehicle information; on the basis of an existing road monitoring system, a lightweight identification model configured for detecting the states of an optical identifier and a digital identifier in real time is deployed and loaded in the existing road monitoring system; performing visual positioning on the road surface projection pattern through a camera, and calculating the real-time position of the vehicle by combining map coordinates so as to supplement the positioning blind area of the GPS in the tunnel mountain area; accident probability calculation is carried out based on the identification state to determine whether the vehicle is suspected to have an accident; and when the accident is judged to be suspected, triggering an accident response process. And the accident response efficiency is obviously improved.

The invention provides a vehicle target automatic labeling method and system based on deep learning. The method comprises the steps of obtaining video stream monitoring data collected by a road camera; based on the video stream monitoring data, utilizing a pre-trained vehicle identification model to automatically label a vehicle target in the video stream monitoring data to obtain a preliminary labeling result; performing uncertainty evaluation on the preliminary labeling result through an adversarial sample generation strategy to obtain an uncertainty score; when the uncertainty score does not exceed a preset threshold value, taking the preliminary labeling result as a final labeling result of the vehicle target; according to the invention, by using the pre-trained convolutional neural network model, large-scale video stream data can be quickly processed and preliminary annotation can be completed, so that the dependence on manual annotation is reduced; uncertainty evaluation is carried out on the preliminary labeling result through an adversarial sample generation strategy, errors or low-confidence-coefficient areas possibly existing in the labeling result can be effectively recognized, and the accuracy of the final labeling result can be guaranteed.

The invention provides a vehicle energy management method and system and a vehicle, and belongs to the technical field of vehicles, and the method comprises the steps: transmitting vehicle identification information to a cloud after the vehicle is powered on, enabling the cloud to obtain the historical driving data of the vehicle based on the vehicle identification information to obtain driving route data, and training a preset first energy management model, target model parameters are obtained, and then a target energy management model is obtained; and determining a target driving route from the plurality of historical driving routes through the application core based on the route data of the plurality of historical driving routes and the current working condition data of the vehicle, and obtaining control parameters for controlling the vehicle to drive on the target driving route based on the target energy management model and the feature data corresponding to the target driving route, and the control parameters are sent to the execution core so that the execution assembly can control the vehicle based on the control parameters. Through the method provided by the invention, the inherent defects of a traditional fixed strategy and a single deployment architecture can be overcome.

Recent location and control information received from “lead” vehicles that traveled over a segment of land, sea, or air is captured to inform, via aggregated data, subsequent “trailing” vehicles that travel over that same segment of land, sea, or air. The aggregated data may provide the trailing vehicles with annotated road information that identifies obstacles. In some embodiments, at least some sensor control data may be provided to the subsequent vehicles to assist those vehicles in identifying the obstacles and / or performing other tasks. Besides, obstacles, the location and control information may enable determining areas traveled by vehicles that are not included in conventional maps, as well as vehicle actions associated with particular locations, such as places where vehicles park or make other maneuvers.

Systems and methods for automated unmanned aerial vehicle recognition. A multiplicity of receivers captures RF data and transmits the RF data to at least one node device. The at least one node device comprises a signal processing engine, a detection engine, a classification engine, and a direction finding engine. The at least one node device is configured with an artificial intelligence algorithm. The detection engine and classification engine are trained to detect and classify signals from unmanned vehicles and their controllers based on processed data from the signal processing engine. The direction finding engine is operable to provide lines of bearing for detected unmanned vehicles.

The invention relates to a vehicle-mounted wireless charging control method and device based on NFC and a vehicle, and the method comprises the steps: obtaining the equipment identification information of terminal equipment disposed on a wireless charging panel based on NFC; determining whether the equipment identification information exists in a charging safety white list or not; if the equipment identification information exists in the security white list, generating a dynamic key according to the identification information of the vehicle and the hardware random number; encrypting the dynamic secret key and transmitting the encrypted dynamic secret key to terminal equipment through NFC; after feedback information returned by the terminal equipment is received, verifying whether the feedback information is correct or not; and if the feedback information is correct, controlling to charge the terminal equipment through the wireless charging panel. The method is used for effectively avoiding leakage of private data, so that the effect of improving the safety of vehicle-mounted wireless charging is achieved.

The invention relates to the technical field of intelligent traffic, and discloses an intelligent servo barrier gate management system. According to the system, vehicle identification information, detection information, environmental parameters and a barrier gate equipment state are acquired in real time through the data acquisition unit, comprehensive monitoring of traffic flow is ensured, the processing and analysis unit processes the acquired data by using a deep learning model, a control instruction is quickly generated, and the vehicle passing efficiency is evaluated, so that the traffic flow is ensured. The servo control unit is combined with an adaptive control algorithm to dynamically adjust the switching speed, the torque and the acceleration of the barrier gate, the vehicle passing experience is optimized, the queuing time is reduced, the bidirectional communication capability of the communication unit realizes remote monitoring and adjustment of the state of the barrier gate, and the traffic management decision making efficiency is improved. A manager can timely respond to sudden traffic conditions, the response speed and accuracy of the system are improved, the intelligent system effectively relieves the bottleneck of traditional barrier gate management, and the intelligent level of urban traffic is improved.

The invention discloses a vehicle identification method and system based on dynamic behavior analysis and federated learning, the method is applied to local ends in one-to-one correspondence with pre-detection areas, and the method comprises the steps: detecting a vehicle entering the pre-detection area, and obtaining the first multi-mode perception data of the vehicle; inputting the first multi-modal perception data of the vehicle into a trained exclusive identification model to extract exclusive identification features of the vehicle for identification to obtain an identification result of the vehicle, the identification result being used for indicating a model type, a behavior type and a virtual identity label of the vehicle; wherein the exclusive recognition model and the universal recognition model are jointly trained under the constraint of a total loss function, basic parameters of the universal recognition model are standard universal parameters issued by the cloud end at the last time, and the standard universal parameters are obtained by the cloud end through aggregating fuzzy network parameters of all the universal recognition models based on federal learning. The method is better in recognition effect and has no risk of privacy leakage.

The invention discloses a multi-model fusion target vehicle identification analysis method and system based on machine vision, and the method comprises the steps: A, capturing and collecting a road vehicle video / image through an unmanned plane, and transmitting the video / image to a streaming media server in a wireless manner; b, an improved target vehicle detection model is adopted, a multi-task cooperative detection framework is constructed, and vehicle illegal parking is judged by applying a multi-model fusion detection mechanism; c, designing a lightweight detection network, reducing the problems of high reasoning delay and large resource occupation in the multi-model cooperative detection process, and reducing the complexity of a detection algorithm; and D, carrying out intelligent alarm and event pushing. According to the invention, the method can improve the recognition accuracy of vehicle illegal parking behaviors in a complex scene, and improves the real-time performance and stability of a single-model monitoring system for vehicle target detection.

Systems and methods for automated unmanned aerial vehicle recognition. A multiplicity of receivers captures RF data and transmits the RF data to at least one node device. The at least one node device comprises a signal processing engine, a detection engine, a classification engine, and a direction finding engine. The at least one node device is configured with an artificial intelligence algorithm. The detection engine and classification engine are trained to detect and classify signals from unmanned vehicles and their controllers based on processed data from the signal processing engine. The direction finding engine is operable to provide lines of bearing for detected unmanned vehicles.

The invention belongs to the field of risk prediction, and relates to a wet and slippery road risk assessment method based on vehicle trajectory identification by an unmanned aerial vehicle, which comprises the following steps: extracting video data of a vehicle driving trajectory of a dangerous road section by adopting a mode of carrying a holder on a high-resolution unmanned aerial vehicle, and mapping the video data to obtain a vehicle ground trajectory sequence; calculating parameter indexes of the normal sample and the wet and slippery road according to the reference trajectory curve, comparing the wet and slippery road with the normal sample, and outputting a distribution difference; self-adaptively adjusting a threshold index under the wet and slippery road based on the meteorological coefficient, and calculating a weighted threshold proportion and duration exceeding 95% quantile of normal weather; and judging the adjacency consistency and the intra-segment space coherence, and finally forming a segment-level risk score and a risk level. The accuracy, the real-time performance and the interpretability of risk early warning are remarkably improved, and the false alarm rate caused by environment misjudgment or equipment errors is effectively reduced.

The invention relates to a charging control method and device, a vehicle, a charging pile and a charging system. The method comprises the steps that under the condition that a first message sent by a charging pile is received, if first verification information in the first message passes verification, a second message is sent to the charging pile, and the second message comprises second verification information, a vehicle identification code and current offset; executing a charging handshake process with the charging pile; and under the condition that the charging handshake process is completed, the current offset in the second message is utilized to adjust the charging current value requested by the vehicle. Therefore, on the premise of ensuring that the current offsets at the two ends are matched, the hardware potential of the vehicle and the charging pile can be fully utilized, the inherent current limitation is broken through through the current offsets, the charging current value is increased, the charging time of the electric vehicle is shortened, the charging safety is synchronously guaranteed, the rapid charging requirement of a user is met, wrong charging pile access is prevented, and the charging efficiency is improved. Charging safety is guaranteed, and tampering and counterfeiting are prevented.

The invention discloses a berth positioning system and method based on video recognition, and relates to the technical field of intelligent transportation, and the system comprises a calibration module which generates berth calibration data based on a berth type, and stores the data to a cloud server; the edge calculation service module is configured to judge the spatial relationship between the vehicle and the berth through a berth type adaptive algorithm based on the real-time latitude and longitude coordinates of the inspection vehicle and the berth calibration data; and the vehicle identification module records license plate information when determining that the vehicle is in the berth, and actively snapshots an empty berth image when no vehicle is in the berth and uploads the empty berth image to the cloud. According to the scheme of the invention, the accuracy, environmental adaptability and long-term operation stability of parking state recognition can be remarkably improved, and a comprehensive solution with high robustness and low misjudgment rate is provided for urban intelligent parking management.

The invention provides an intelligent traffic cone barrel anti-collision early warning method based on binocular vision, and aims to improve the safety of a road construction operation area. And accurate data are provided for subsequent detection and analysis through a binocular camera high-precision calibration technology based on circle detection. In combination with a data acquisition and enhancement technology, high-quality training data is provided for an improved RT-DETR algorithm, and the accuracy and efficiency of vehicle identification are significantly improved. A binocular vision depth perception and StrongSORT multi-target tracking algorithm is utilized to realize real-time speed measurement and distance measurement of a vehicle, and accurate input is provided for track prediction. Based on a GAN multi-modal trajectory prediction technology, a plurality of future trajectories are generated, and a multi-level early warning decision is realized through a comprehensive collision risk index (CRI). According to the method, the limitation of an existing prediction method in a complex road scene is effectively solved, the vehicle behavior intention is predicted and analyzed through the multi-modal trajectory, and reliable early warning information can be provided under various complex road conditions.

The invention belongs to the technical field of radio frequency identification, and particularly relates to an unmanned aerial vehicle radio frequency fingerprint identification method for different signal-to-noise ratios based on a time-frequency graph. The invention provides a radio frequency fingerprint identification method for different signal-to-noise ratios based on a time-frequency graph and a YOLOV8 image identification technology on the basis of a traditional unmanned aerial vehicle radio frequency signal fingerprint identification technology, and the method mainly comprises the steps: constructing a new training data structure, specifically, converting an IQ signal into the time-frequency graph, and carrying out the recognition of the time-frequency graph and the YOLOV8 image identification technology. And then performing arrangement according to the unmanned aerial vehicle type (J), the signal bandwidth (B), the signal frequency band (F) and the signal-to-noise ratio (R) to obtain a structured data set, and performing identification by using an improved YOLOV8 model. Compared with the prior art, the method further improves the accuracy and speed of unmanned aerial vehicle identification, and is a scheme for identifying the model of the unmanned aerial vehicle on the hardware level without information matching. According to the method, high sensitivity of the model to a low-signal-to-noise-ratio signal is kept, and meanwhile, a large amount of misrecognition caused by low confidence is effectively inhibited.

The invention relates to a label extraction model training method and device, a vehicle label extraction method and device and electronic equipment, and the method comprises the steps: inputting a current sample vehicle image into a preset multi-modal model, and obtaining a sample description text; performing grammar analysis processing on the sample description text to obtain at least one segmented word, the part-of-speech of the at least one segmented word and the dependency relationship between the at least one segmented word; performing noun merging based on the at least one segmented word, the part of speech of the at least one segmented word and the dependency relationship among the at least one segmented word to obtain a sample description tag; based on a preset filtering word, filtering the sample description label to obtain a real description label; and training a to-be-trained label extraction model based on the current sample vehicle image and the real description label to obtain a label extraction model. According to the embodiment of the invention, the method can meet the multi-dimensional demands of vehicle recognition, is adaptive to a multi-label scene, greatly improves the readability of a vehicle recognition result, and reduces the decision errors.