142 results about "Person location" patented technology

The invention provides a lightweight AI personnel perception method and system based on a millimeter wave radar, and relates to the technical field of personnel perception, and the method comprises the steps: carrying out the phase compensation, amplitude calibration and bidirectional combined filtering processing of a millimeter wave echo signal, and constructing three-dimensional space point cloud data. Then, constructing a spatial distribution matrix based on the point cloud data, calculating the center position of a point cloud cluster, establishing an adaptive sampling radius to extract point cloud features, and calculating a motion vector and attitude parameters; and finally, inputting the motion vector and the attitude parameter into a double threshold judgment module, judging whether a person exists in the target area, generating a person position thermodynamic diagram based on the center position of the point cloud cluster, and outputting a person perception result. According to the method, the calculation complexity is reduced, the real-time performance and accuracy of personnel perception are improved, and the method is suitable for smart home, security monitoring and other scenes.

The invention relates to a bridge crane operation dangerous area personnel intrusion detection method and system, and the method comprises the steps: obtaining the real-time position and speed data of a hoisted object through a sensor, analyzing the motion trail of the hoisted object through a deep learning algorithm, and obtaining the prediction result of the motion trail of the hoisted object; calculating a dangerous area boundary by adopting a dynamic model according to a hoisting object motion trail prediction result in combination with load mass and rope length data, and determining a dynamic dangerous area range; acquiring image data of an operation area through an image acquisition device, and identifying personnel positions in the image to obtain personnel position data; and when it is judged that the personnel enter the dynamic dangerous area range according to the personnel position data, an early warning signal is generated, a three-dimensional visualization technology is adopted to superpose the early warning signal to the field real-time image, visual early warning information is obtained, and the visual early warning information is displayed through a display device. According to the invention, dynamic and accurate prevention and control of the dangerous area are realized through multi-dimensional technology fusion.

The invention relates to the technical field of intelligent lighting control, in particular to an LED lamp energy-saving control method and system, and the method comprises the steps: obtaining environment data and user data; constructing a scene knowledge graph, and pre-storing illumination parameters of different scenes; performing standardization processing on the environment data and the user data, and obtaining a state vector in combination with the scene knowledge graph; inputting the state vector into a three-dimensional comfort level model to calculate a comprehensive comfort level score; if the comprehensive comfort level score is lower than a target threshold value, an illumination adjustment strategy is output through a dual-network illumination adjustment agent, the LED lamp is adjusted according to the illumination adjustment strategy, and the illumination adjustment strategy comprises light intensity adjustment, color temperature adjustment and light beam angle adjustment; and if the comprehensive comfort level score is higher than a target threshold value, lightweight light intensity gradient optimization is carried out, and the light intensity of the LED lamp is dynamically adjusted according to the position of the person. Therefore, the problems of insufficient environmental adaptability, lack of comfort consideration and the like in the prior art are solved.

The invention provides a production park personnel positioning method and system, and the method comprises the steps: training a personnel behavior model through obtaining the historical motion track and historical behavior data of personnel in a production park; acquiring historical environment dynamic change data in the production park, and training an environment prediction model; the method comprises the following steps: acquiring multi-source data through each sensor, and preprocessing the multi-source data, the multi-source data comprising Wi-Fi signal strength indication data for representing position information of personnel in a production park, radio frequency data, visual data and inertial measurement data; according to a Kalman filtering algorithm, fusing the preprocessed multi-source data to obtain a first position; and calculating the position probability distribution of the personnel in the production park by adopting a Bayesian positioning algorithm in combination with the first position and the output results of the personnel behavior model and the environment prediction model, and determining the target position, thereby effectively realizing the accurate and real-time positioning of the personnel in the production park in the complex environment.

The invention relates to the technical field of mine monitoring, and provides an intelligent mine safety monitoring system and method, and the system comprises a path network modeling device, a multi-source risk monitoring device, a personnel positioning and tracking device, a dynamic path updating device, and an intelligent evacuation guiding device. When any path risk level exceeds a preset safety threshold value, triggering an emergency evacuation instruction: calculating and generating a personalized optimal evacuation path for each person based on the currently updated three-dimensional topology model and the person position information; outputting evacuation information; the evacuation information comprises an emergency evacuation alarm of a whole mine broadcast level; and a real-time dynamic pointing instruction facing each node, the pointing instruction being generated according to the personalized optimal evacuation path and being presented through a physical indication device deployed at the node or a terminal device carried by a person. According to the technical scheme disclosed by the invention, workers in the mine can be timely guided to be evacuated.

The invention provides a man-machine interaction safety dynamic early warning method based on digital twinning and behavior prediction, and the method comprises the steps: S1, collecting the real-time data of a working site through a sensing layer, and enabling the data to comprise the personnel position, equipment state and environment information; s2, constructing a digital twin model based on the acquired data, wherein the model maps the dynamic state of a working site in real time; s3, generating a personnel behavior track and an equipment action range through a prediction algorithm, and calculating a dynamic risk field to evaluate space-time conflicts; s4, according to the risk value of the dynamic risk field, triggering a multi-stage early warning mechanism to reduce the risk of the operation field; and S5, displaying the real-time state and risk information in the digital twinborn model through a visual interface. According to the invention, through deep fusion of digital twinning and dynamic risk prediction, real-time monitoring and accurate prevention and control of the safety risk of the operation site are realized, and the safety management efficiency and the operation safety are greatly improved.

The invention discloses an electric power personnel illegal behavior identification method and system based on multi-frame multi-level joint discrimination, which is applied to the technical field of electric power operation safety supervision, and comprises the following steps: detecting the positions of all personnel in each frame of image in a video stream, adopting a ByteTrack algorithm as a core tracker, introducing a score grading matching strategy, and carrying out classification matching on the positions of all personnel in each frame of image in the video stream; taking the weighted sum of the spatial consistency and appearance feature similarity of the new detection frame as a final association degree quantity, distributing a unique identity code for a successfully associated personnel target, and recording track information in continuous frames; performing illegal behavior classification and illegal article detection on each frame of personnel area image; and calculating a joint confidence score of a frame where the personnel region image with the behavior category and the article category having a logic correspondence relationship is located, counting the number of frames exceeding a preset joint confidence threshold in each power personnel trajectory, and calculating an illegal behavior existence rate to judge an illegal behavior. According to the invention, the illegal behavior identification precision of the power personnel is effectively improved.

The invention provides a method, a system and equipment for positioning global personnel of a building based on digital twinning. The method comprises the following steps: acquiring video data shot by each camera in a multi-camera system; obtaining a mapping relation among the world coordinates, the pixel coordinates and the camera parameters; key point detection is carried out on personnel in the video to obtain personnel pixel coordinates; establishing a conversion relation between each camera coordinate system and a global world coordinate system based on multi-camera attitude transfer, and unifying personnel positions in the multiple cameras to the global world coordinate system; performing matching optimization on the same person observed by different cameras in the global world coordinate system based on distance constraint and epipolar constraint; finally, multi-source information fusion and personnel position and quantity perception under a global perspective are realized. According to the invention, the information shot by a plurality of monitoring cameras can be fused, the digital twinning technology is combined to realize the intelligent perception of the position and number information of people in the building scene, and the precision and real-time performance of crowd monitoring are improved.

The invention relates to the technical field of elevators, in particular to a quick positioning and information interaction system for elevator emergency rescue, which comprises a personnel detection module, a fault detection and judgment module, a quick positioning module, an information interaction module and a paperless operation module, the personnel detection module and the rapid positioning module work cooperatively, so that rescue personnel can rapidly determine the position of a trapped person and plan an optimal rescue route, the rescue response time is greatly shortened, the pain and danger of the trapped person are reduced, the information interaction module realizes multi-party real-time communication, accurate rescue instruction transmission and reasonable resource allocation are guaranteed, and the rescue efficiency is improved. And the fault detection and judgment module effectively supervises the maintenance process, false maintenance is avoided, it is ensured that the elevator reaches the safe operation standard after being maintained, secondary faults are prevented, and the follow-up safety of elevator passengers is guaranteed.

The invention discloses an intelligent monitoring system based on computer vision, and relates to the technical field of intelligent monitoring, and the system comprises the following components: an image collection module which collects the image and video data of a person in a monitoring area in real time through a high-precision camera, and the image and video data comprises facial expression details, body movements and person position relation information; according to the method, based on multi-dimensional data such as group member interaction behaviors and position relations, micro-expressions and behavior analysis results are combined, group behavior relations are modeled, the overall emotional atmosphere of a group can be perceived, the group behavior trend can be accurately predicted, and meanwhile, the group behavior analysis accuracy is improved. The early warning and processing module can generate an early warning signal in time according to a preset rule and send the early warning signal to a specified terminal device, thereby making up for the deficiency of an existing monitoring system in the aspect of group behavior trend prediction, enabling monitoring personnel to take measures in advance and deal with possible safety problems in time, and improving the monitoring efficiency. And the practicability and the emergency processing capability of the monitoring system are greatly enhanced.

The invention relates to the technical field of elevators, in particular to an elevator fault accurate detection and early warning system based on an edge computing gateway, which comprises a data acquisition module, a data transmission module, a fault detection module, a fault early warning module, a maintenance management module, a data analysis module and a platform interaction module. Through the real-time monitoring and fault pre-judging functions of the edge computing gateway, various potential safety hazards in the elevator running process can be found in time, early warning can be given out in advance, maintenance personnel can handle faults before the faults occur, the elevator fault rate is effectively reduced, safety accidents are reduced, the life safety of elevator taking personnel is guaranteed, and the service life of the elevator taking personnel is prolonged. Rescue workers are helped to quickly locate the position of the trapped person and accurately judge the fault reason, the rescue efficiency is improved, and panic and danger of the trapped person are reduced to the maximum extent.

The invention provides a man-hour determination method and device in a flexible operation scene, and belongs to the technical field of man-hour determination, and the method comprises the steps: obtaining an operation region video collected based on a collection device, and recognizing task personnel in the operation region video and the personnel positions of the task personnel; when the task worker is matched with the task worker, determining a target operation area in the operation area based on the worker position and the duration of the task worker in the worker position; and determining the video duration of the task personnel meeting the man-hour counting condition in the target operation area, and taking the video duration as the operation man-hour of the task personnel. According to the method, the target operation areas of different tasks can be determined in the flexible operation scene, and then the working hours of the target operation areas are counted, so that the working hours of task personnel under different tasks can be obtained, and the accuracy of the determined working hours under the flexible operation scene is improved.

The present invention discloses a Bluetooth positioning-driven factory personnel tracking and management method and system, relating to the field of personnel tracking technology. The method comprises: when a Bluetooth device worn by a factory worker is disconnected, recording the spatial location at the time of disconnection and automatically tracking the worker's movement trajectory; when the Bluetooth is reconnected, processing the movement data during the disconnection period and generating a coordinate sequence through the Bluetooth blind spot positioning network, thereby achieving accurate tracking and management of the worker's location during the disconnection period. This method solves the technical problem of existing Bluetooth-based factory personnel real-time positioning systems being unable to continuously and accurately track the worker's location during Bluetooth disconnection, achieving the technical effect of continuously and accurately tracking the worker's location during Bluetooth disconnection.

A system includes non-transitory computer-readable storage media configured to store instructions and processors communicatively coupled to the non-transitory computer-readable storage media. The processors may execute instructions, which may cause the system to perform operations. The operations may include obtaining first data associated with a person location, where the first data may be a subset of a collection of person location data. The operations may also include obtaining second data associated with one or more displays in a venue, where the second data may be a subset of a collection of display data. The operations may further include determining a first weight corresponding to the first data relative to the collection of person location data and a second weight corresponding to the second data relative to the collection of display data. The operations may also include obtaining an estimate of the viewership data using the first data and the second data.

The invention provides a trapped person position state analysis method and system, and relates to the field of data processing. According to the method, building structure distribution, conductive fluid flow channels and metal component distribution in a disaster target area are constructed to form a background entropy flow ground state, and noise intensity probability distribution, a channel joint fluctuation relation and a time stability index are counted to generate a background entropy flow field. In the search and rescue stage, a background entropy flow field is converted into a controlled mode through active disturbance, multi-physical channel noise responses before and after disturbance are collected through a multi-field passive sensor network, and a multi-dimensional local entropy response vector is constructed. And combining the consistency, directivity and duration of the multi-noise channel to identify an initial suspected region and extract an entropy anomaly core region, finally inferring metabolic activity and posture limitation conditions according to a local entropy response cooperative relationship in different disturbance modes, and outputting a position state result of the trapped person. By implementing the technical scheme provided by the invention, the position state of the trapped person can be accurately identified.

The present invention provides a lightweight AI personnel perception method and system based on millimeter-wave radar, which relates to the technical field of personnel perception. It includes constructing three-dimensional spatial point cloud data by performing phase compensation, amplitude calibration, and bidirectional joint filtering on millimeter-wave echo signals. Then, based on the point cloud data, a spatial distribution matrix is constructed, the center position of the point cloud cluster is calculated, and an adaptive sampling radius is established to extract point cloud features, and the motion vector and attitude parameters are calculated. Finally, the motion vector and attitude parameters are input into a dual-threshold decision module to determine whether there are personnel in the target area, and a personnel position heat map is generated based on the center position of the point cloud cluster to output the personnel perception result. The present invention reduces the computational complexity, improves the real-time performance and accuracy of personnel perception, and is applicable to scenarios such as smart homes and security monitoring.

A management system (100) for managing the state of an object and the environment in an indoor monitoring space (1) comprises: an environment measurement means for measuring a gas environment within the space; a person measurement means for measuring a person present in the space; a position measurement means for measuring the position of an object moving within the space; an apparatus state measurement means for measuring the operation state of an apparatus within the space; a spatial state calculation unit for calculating the spatial state within the space from the measured gas environment data and the measured person data; a position information management unit for managing the position information pertaining to the object in accordance with the measured position data of the object; an apparatus state management unit for managing the operation state of the apparatus in accordance with the operation data of the apparatus; and a display control unit that superimposes the spatial state, the position information pertaining to the object, and the operation state of the apparatus on an image indicating the shape of the monitoring space (1), and displays the superimposed image on a display means.

We provide the system. [Solution] A means for acquiring video data and analyzing the location of workers within the office, A means for designing the optimal traffic flow based on the above analysis results, A means of outputting the designed movement flow information, A system that includes this.

The present application discloses a supervision method for bridge maintenance operations, belonging to construction site management, including: respectively establishing a sensor model, a personnel model and a bridge BIM model; registering the sensor model and the bridge BIM model by using a geographic coordinate system; integrating the personnel model, the registered sensor model and the bridge BIM model through a GIS platform to obtain a digital twin scenario based on BIM+GIS; obtaining the GPS coordinate data of the operating personnel through an intelligent safety helmet and converting the GPS coordinate data into coordinate data in a Cartesian coordinate system; establishing a multi-source data correction mechanism to correct the coordinate data in the Cartesian coordinate system; and displaying the positions of the operating personnel in real time in the digital twin scenario through the personnel model according to the corrected coordinate data. Aiming at the low positioning accuracy of operating personnel caused by GPS signal drift in bridge maintenance, the present application improves the supervision positioning accuracy.

The invention discloses an operator position monitoring method, device and equipment and a medium, and the method comprises the steps: binding pre-obtained target operator information with corresponding business data, and generating a safety constraint of a target operator according to the business data; acquiring multi-source positioning data of the target operator in real time through a positioning terminal worn by the target operator, and inputting the multi-source positioning data into a preset neural network, so that the neural network performs data fusion on the multi-source positioning data to generate a correction position of the target operator; and through a preset reinforcement learning algorithm, according to the correction position and the security constraint, generating an optimal security path, and according to the optimal security path, carrying out monitoring and risk assessment on the current correction position of the target operator. According to the invention, the real-time performance and accuracy of the position monitoring of the operating personnel can be improved.

The present invention discloses an indoor positioning method and system based on multi-sensor fusion, which relates to the field of indoor positioning technology, and includes the following steps: deploying Wi-Fi transceiver equipment and various sensors; detecting the range of the Wi-Fi CSI area to be measured; refining the detection of the sub-area by the PIR sensor; calculating the centroid positioning coordinates; accurately positioning by ultrasonic ranging; fusing the positioning results of the sensors. The technical method of the present application deploys sensors, collects CSI information, voltage signals of PIR sensors, and ultrasonic signals, refines the personnel detection in the sub-area by a dual dynamic threshold method, performs weighted positioning based on the signal strength of the PIR sensor, and calculates the relative position of the personnel in the area. Combined with the centimeter-level precise ranging of the ultrasonic sensor, the precise two-dimensional coordinates of the personnel are obtained by triangulation. Finally, the results of PIR centroid positioning and ultrasonic ranging are fused by the Kalman filter algorithm to achieve real-time updating and dynamic tracking, and output high-precision personnel location information.

The invention discloses an AED first aid method based on a humanoid robot and a related product, and the method comprises the steps: obtaining a target monitoring video, and determining a target person to be subjected to first aid according to the target monitoring video; acquiring a personnel position, personnel identity information and an abnormal starting moment of the target personnel to be subjected to emergency treatment; the humanoid robot is controlled to obtain target AED equipment, and attribute information of the target equipment is obtained; acquiring a target position of the humanoid robot at the current moment; generating a target first-aid route between the target position and the personnel position; estimating a target consumed time length according to the target first-aid route; determining a target emergency strategy according to the target equipment attribute information, the personnel identity information and the target consumed duration; and controlling the humanoid robot to go to the personnel position, and controlling the humanoid robot to use the target AED equipment to perform first aid on the target personnel to be subjected to first aid according to the target first aid strategy. By adopting the embodiment of the invention, the first-aid efficiency of the AED equipment is improved.

The present invention discloses a method, a system and a storage medium for inspecting a construction environment. In each inspection cycle, the construction risk coefficient, the personnel location information and the camera information of at least one target person in the construction environment are obtained, and then these data are input into a pre-trained inspection planning model to output the inspection probability of each target person. The target person corresponding to the maximum value among all the inspection probabilities is selected as the inspection target for the current inspection cycle. Then, in the current inspection cycle, the focusing direction of the target camera is controlled to be aligned with the inspection target until all inspection cycles are completed. By adopting the embodiment of the present invention, the inspection resources can be utilized most effectively, blind inspection is avoided, and the pertinence and efficiency of inspection are improved.

The invention provides a method for dynamically tracking personnel in a grain depot. The method comprises the following steps: training a target detection algorithm in advance; intercepting an image sequence in a video stream of a camera at the front end of the granary at a certain time interval; inputting the image sequence into a target detection algorithm to obtain a personnel position coordinate set, a bin gate region set and a grain surface region set; inputting the personnel position coordinate set into an improved Deep-sort multi-target tracking algorithm, tracking personnel trajectories and identifying personnel IDs (Identity); obtaining a personnel gravity center position set through the personnel position coordinate set, and judging whether the personnel enter and exit from the warehouse or not according to the position relation between the personnel gravity center position set and the warehouse door area set and the grain surface area set; according to the invention, dynamic statistics is carried out on the number of people in the grain depot based on the improved Deep-sort multi-target tracking algorithm, and the number of people and dynamic changes can be accurately identified.

This invention discloses a method, apparatus, device, medium, and program product for pushing delivery information. It includes: acquiring delivery video content information, delivery person location information, and identity authentication information; generating a delivery video ringback tone based on the delivery video content information, delivery person location information, and identity authentication information when a delivery call is initiated; and pushing the delivery video ringback tone to the receiving end of the delivery call. When a delivery person initiates a delivery call to a user, a delivery video ringback tone containing various delivery-related information is generated and pushed to the user, allowing the user to securely and fully obtain delivery information without having to answer the delivery person's call, improving the delivery rate of delivery information, and simultaneously enhancing the accuracy and transmissibility of the delivery information obtained by the user.

The invention discloses a safety detection system and method for a sealing ring flat vulcanizing machine, and solves the problems that a traditional static protection system is single in detection and poor in adaptability, the system comprises a detection module, a processing module, an early warning execution module and a self-learning module, acquiring the position and posture of a person and the motion trail of an equipment part in real time; the processing module generates a double-track dynamic comparison model and calculates a real-time risk, and dynamically adjusts a safe distance threshold value in combination with the self-learning module; according to the method, closed-loop control is formed through track comparison, distance verification, data collection and threshold value optimization, the system supports operator identity recognition and personalized safety strategies, intelligent safety protection in a complex human-computer interaction scene is achieved, and the safety of the human-computer interaction scene is improved. The detection precision and the response flexibility are obviously improved, and the production safety and the equipment operation efficiency are balanced.

The invention relates to the technical field of the Internet of Things, in particular to an intelligent personnel scheduling management method based on the Internet of Things, which comprises the following steps of: acquiring multi-source data such as positions, physiology and behaviors of personnel, and calculating individual risk scores by fusing surrounding personnel and historical relationships; generating an aggregation risk topological graph from the risk scores through a preset kernel function; and analyzing a risk peak value in the graph, matching an optimal executor through a multi-objective optimization algorithm, and generating a scheduling instruction. According to the method, discrete individual risks are converted into a visual global risk view, automation and optimization of scheduling decisions are realized based on dynamic analysis of the risk situation, and the risk early warning accuracy and the emergency response efficiency are improved.

A robot assembly for safe operation in a manufacturing setting with humans including a sensor for detecting movement of the robot assembly and a human location. A positional apparatus including at least one tag located on the robot apparatus and at least one detector for detecting the tag. Posture nodes associated with a human saved in memory. A method that includes, generating a task movement plan based on images captured by the sensors, tags detected by the detector, and posture nodes of a nearby human captured by the sensor.

The invention relates to the technical field of monitoring, in particular to an intelligent monitoring method and system for residential area security. According to the technical scheme, the method comprises the following steps that identity information of a visitor is obtained and verified, a visitor information file is established after verification is passed, and an activity permission area is distributed; monitoring data are collected and preprocessed, and monitoring information data and visitor position information are obtained. Dangerous action recognition is performed on the monitoring information data, and danger recognition factors are obtained in combination with the position information of the visitor. And judging whether the danger identification factor is greater than a preset standard factor, if so, sending an alarm signal, and if not, not sending the alarm signal. The dangerous action recognition precision is high, the recognition accuracy is higher, the response speed is higher, and potential safety hazards can be found in time. Excessive manual intervention is not needed, the labor cost is effectively reduced, careless omission of manual guarding is avoided, and the intelligent level of security work of the residential area is improved.