24 results about "Person number" patented technology

The present application relates to a kind of coal mine underground number of people statistics method based on two-part graph, belong to artificial intelligence field.The image of coal mine entry or underground key place is used as input data, yolov5 is used as the main network of target detection, interval time T is obtained, and two-part graph of personnel in the coal mine entry area is formed, Hopcroft-Karp algorithm is used to match personnel at T1 and T2 time, and the number of people entering and leaving is counted;The present application is based on yolov5 lightweight personnel detection model, can realize rapid iteration and implementation deployment in field application under the condition of meeting the prediction accuracy.

A system is provided.SOLUTION: This system is provided with a means for collecting basic information on inheritance from a user, a means for collecting information on the number of persons concerned in the inheritance and relations, a means for automatically generating necessary documents based on the collected information, a means for presenting the confirmation and correction of the generated documents to the user, and a means for monitoring and managing the progress conditions of the presented documents.SELECTED DRAWING: Figure 1

An information processing apparatus, an information processing method, and an information processing program capable of acquiring the scale of the number of persons who contact information (reach) with high accuracy and a small processing load (for example, arithmetic operation amount) are provided. An information processing apparatus (1) includes: an individual reach acquisition unit (10) that acquires a first reach that is a scale of the number of persons who contact first information, a second reach that is a scale of the number of persons who contact second information,... and an N-th reach that is a scale of the number of persons who contact N-th information, when N is defined as a natural number of three or more; and a total reach acquisition unit (20) that acquires a total reach that is a union of the first reach, the second reach,... and the N-th reach, wherein the total reach acquisition unit (20) considers a component in which two of the first to N-th reaches have an overlapping relationship, while ignoring a component in which three or more reaches have an overlapping relationship, as an incremental reach that is a scale of the number of persons who do not contact one information and contact the other information.

The number of people who took a specific action after interacting with the target content will be determined, taking into account the circumstances at the time of interaction with the target content. [Solution] The information processing device of the present invention acquires, for each person who has come into contact with the target content, first location information indicating the location at the time of contact with the target content, associated with identification information assigned to the terminal used to come into contact with the target content, and also acquires behavioral information regarding actions after coming into contact with the target content, associated with identification information assigned to the terminal possessed by the person, identifies specific persons who have taken a specific action from among multiple persons, and outputs information corresponding to the number of specific persons, based on the first location information associated with the identification information of the terminal used by the specific person to come into contact with the target content and the behavioral information associated with the identification information of the terminal possessed by the specific person when they took the specific action, in correspondence with the location of the specific person at the time of contact with the target content.

This application provides a method, electronic device, storage medium, and program product for detecting the number of people. The method includes: acquiring a visible light image and an infrared image of a region to be identified; inputting the visible light image and infrared image into an image feature determination model to output a fused feature map, wherein the fused feature map includes N feature points; matching a target feature point in the fused feature map with at least one preset head count description vector to obtain a target head count description vector corresponding to the target feature point, wherein the target feature point is any feature point; determining the number of people corresponding to the target head count description vector as the number of people corresponding to the target feature point; labeling the fused feature map with the number of people corresponding to each feature point to obtain a fused density map; and determining the number of people based on the fused density map. This method reduces the influence of noise in the image and solves the problem of low accuracy in current personnel counting.

The invention provides a people counting system and a people counting method, and the system comprises a PIR sensor which is used for detecting whether a person passes through a preset area or not, and transmitting a trigger signal when detecting that the person passes through the preset area; the controller is awakened when the PIR sensor sends out the trigger signal, further awakens the event camera, and counts the number of wire passing people according to event data collected by the event camera; the event camera is used for collecting event data after being awakened; the method for counting the number of people passing the line comprises the following steps of: S1, decoding an accumulated event within a preset time length to generate a plurality of frames of original images; s2, identifying a target in the original image and performing trajectory tracking; s3, for each effective area, performing trajectory tracking by using a central point, and counting the number of people passing the line according to the obtained trajectory; according to the technical scheme, people counting is carried out by combining the PIR sensor and the event camera, low power consumption is achieved, and high accuracy is achieved.

The invention relates to an individual interpersonal contact number prediction method, system and device and a storage medium. The method comprises the following steps: obtaining questionnaire survey data of individual resident travel activities and interpersonal contact; extracting individual attribute features and travel activity features of individual residents from the questionnaire survey data; constructing and training an individual interpersonal contact mode prediction model by applying a machine learning algorithm based on the demographic features and the travel activity features; and performing individual interpersonal contact number prediction by using the trained individual interpersonal contact mode prediction model, and outputting an individual interpersonal contact number prediction value. According to the method, the dynamic travel activity features and the static demographic attributes are fused, and machine learning modeling is utilized, so that refined individual behaviors can be captured, the number of individual contact persons can be more reliably predicted, and the assessment accuracy of the disease transmission risk is improved.

The invention discloses a recognition method, device and equipment for personnel abnormal behavior monitoring and a medium, and relates to the technical field of camera monitoring. The method comprises the following steps: acquiring a shot image and preprocessing the shot image; detecting the preprocessed image through a head counting algorithm, identifying position information of all persons in the image, and generating a unique person number for each person; inputting the preprocessed image and the number and position information of the personnel into a large model, analyzing the personnel in the image by the large model according to at least one set problem, judging whether an abnormal behavior exists or not, and returning the number and position information of the person corresponding to the personnel judged to have the abnormal behavior; and drawing an annotation graph according to the figure number and the position information provided by the large model. According to the identification method and device for monitoring the abnormal behaviors of the personnel, the equipment and the medium provided by the invention, machine room deployment and a private line network are not needed, the hardware configuration requirement is low, and meanwhile, the dependence on high-quality annotation data is greatly reduced.

The present disclosure relates to a person detection device, a method, and a computer program product. The person detection device has: a detection section (31) that detects one or more person regions from an image; a consolidation section (33) that consolidates two or more person regions into one consolidated person region in a case where the two or more person regions overlap each other by a predetermined amount or more; a skeleton detection section (34) that determines a skeleton of an undetermined and foremost person among one or more persons included in the consolidated person region by inputting the consolidated person region to a skeleton detector; a mask section (35) that updates the consolidated person region by masking a region showing the foremost person within the consolidated person region based on the skeleton of the foremost person; and a repetition control section (36) that repeats the processing of the skeleton detection section and the mask section for the updated consolidated person region until a skeleton of a person is not detected, and counts the number of skeletons detected from the consolidated person region as the number of persons represented in the consolidated person region.

A multi-person attitude estimation method based on a commercial WiFi signal comprises the following steps: firstly, building a channel state information acquisition platform by using a transceiver, carrying out amplitude and phase preprocessing on data, then outputting a feature tensor through a data fusion module, and inputting a deep convolutional neural network to extract a person number feature and an attitude feature; and finally, dynamically controlling the number of human skeleton points in the posture branch by using the output result of the people number identification branch to realize posture estimation under different people numbers. According to the method, the postures of multiple persons can be estimated at lower cost, higher recognition accuracy can be obtained, and the method has certain application value for intelligent safety monitoring and the like under the condition of multiple persons indoors.

The invention relates to the technical field of people counting, and particularly provides an in-out people counting method and device, a storage medium and computer equipment. Under the condition that an intersection point is generated between the moving track of the target person and the virtual separation line, taking a video frame corresponding to the intersection point as a line-crossing frame, taking the position of the target person in the first N video frames of the line-crossing frame as a position before line-crossing, and taking the position of the target person in the last M video frames of the line-crossing frame as a position after line-crossing; and direction consistency judgment is carried out on the target personnel according to the N positions before line crossing and the M positions after line crossing. And when the target personnel are respectively located in different place areas before and after line crossing, and the target personnel are located in the second area continuously in multiple frames after line crossing, the number of people entering and exiting is triggered to be updated. Therefore, invalid line crossing behaviors caused by the conditions of edge wiping of the personnel identification frame, rapid turning-back after line crossing, repeated entering and exiting in a short time and the like can be filtered, and accurate statistics of the number of people entering and exiting is achieved.

The invention discloses a high-speed rail platform safe riding system and method, and belongs to the technical field of high-speed rails, and the method comprises the following steps: obtaining passenger flow information, the passenger flow information comprising theoretical boarding people number and theoretical getting-off people number; determining predicted boarding people number and predicted getting-off people number based on the passenger flow information; determining a predicted boarding luggage amount based on the predicted boarding number of people; predicting a get-off luggage amount based on the predicted get-off number of people; determining a space equivalent based on the predicted boarding number of people, the predicted getting-off number of people, the predicted boarding luggage amount and the predicted getting-off luggage amount; and determining the opening mode of the platform door based on the space equivalent, the first equivalent threshold and the second equivalent threshold. When the passenger flow volume is large, the situation that passengers walk in the length direction of the train and get on and off the train normally is influenced can be avoided, the passenger flow is separated, the probability of stampede events when the passenger flow volume is dense can be effectively reduced, and therefore the effect of improving the safety coefficient is achieved.

A headcount estimation system (1001) according to the present disclosure comprises an image capture unit (11), an image processing unit (21), a congestion level evaluation unit (22), and a correction unit (23). The image capture unit (11) captures an image of a prescribed area. On the basis of the image captured by the image capture unit (11), the image processing unit (21) calculates the number of people in the prescribed area and the number of people in each of a plurality of sections obtained by dividing the prescribed area. The congestion level evaluation unit (22) evaluates the level of congestion in the prescribed area. The correction unit (23) identifies the section to be referred to on the basis of the level of congestion, and corrects the number of people in the prescribed area on the basis of the identified section.

The present application provides an elevator device which, under certain conditions, allows a hall call registration for a single elevator other than a single elevator stopped at a hall, thereby improving the transportation efficiency. As information for relaxing the restriction on the hall call period of the next single elevator, the congestion degree of the certain single elevator is calculated, and the hall call registration is allowed as necessary, i.e., the hall call operation determination control is performed. In the group management control device (20), an average weight of an adult is used as one person, a load-person number conversion table is prepared in advance, and the number of persons is calculated based on the load detected by the load detection sensor (36).

The application relates to the technical field of data and image processing, and particularly provides a de-duplication person number counting method, aiming to solve the problem of influencing counting accuracy in the case that human bodies are seriously blocked with each other or personnel are similarly dressed. For the purpose, the de-duplication person number counting method comprises the following steps: a target image is intercepted from a target video every preset time interval, each face image in the target image and each human body image belonging to the same person as the face image are detected; a face feature vector of each face image is calculated, and a human body feature vector of each human body image is calculated; the face feature vector and the human body feature vector are spliced to obtain a to-be-counted feature vector of each person in the target image; a target similarity of each to-be-counted feature vector and a counted feature vector in a counted feature library is obtained; and the person number of a person with a target similarity less than a preset similarity threshold is counted. Through the above method, the accuracy of de-duplication counting can be significantly improved.

The application relates to the technical field of intelligent security and access control, in particular to an access control method for preventing tailing applied to an AB door structure, which binds a personalized portable number of people label value M for each user, and takes the M value as a dynamic threshold for buffer number verification, replacing the rigid rules of a fixed number threshold or comparison of the number of entering people in the prior art. The method enables the access control system to flexibly determine the number of people to release according to the specific authority of the currently authenticated user, strictly implements the basic security strategy of preventing tailing, provides a legal channel for reasonable accompanying needs, and achieves a good balance between safety and convenience.

System and methods for counting people in a space that is monitored by a plurality of distributed sensors are disclosed. In some embodiments, the method includes receiving a people count value output by a first sensor monitoring a portion of a space. The first sensor is one of a plurality of distributed sensors monitoring non-overlapping portions of the space. The method further includes waiting to receive additional people count values output by other sensors monitoring other portions of the space and then determining a total count of people in the space in response to receiving the additional people count values and determining that the received people count values are synchronized in time. In response to determining the total count of people in the space, one or more actions may be performed.

This application provides a method, apparatus, and system for detecting target personnel. The method includes: detecting personnel within the public area of ​​a preset location that meet preset number and distance conditions using captured images of the public area; obtaining groups of multiple people that meet the preset number and distance conditions; these groups can be considered as individuals engaged in discussion; if the discussion is a normal discussion about a project, then the discussion should occur in a non-public area of ​​the preset location, not in the public area. Therefore, the discussion is considered an abnormal discussion about the project, and the identities of personnel exhibiting targeted behavior can be detected.

The utility model discloses a construction elevator people number detection and early warning system based on an infrared technology, belongs to the technical field of construction elevators, and solves the problem that the existing construction elevator people number detection device is difficult to accurately detect the number of passengers while ensuring low cost. The system comprises a construction elevator, the inner top of the construction elevator is provided with an alarm used for warning that the number of people is overloaded and an infrared thermal imaging thermal sensor used for detecting the number of heat sources, and an elevator door of the construction elevator is provided with a plurality of sets of infrared photoelectric sensors. The infrared thermal imaging thermal sensor is used for detecting the number of heat sources of constructors to reflect the number of people in the construction elevator, and the multiple sets of infrared photoelectric sensors are used for detecting the time when the constructors go in and out of the construction elevator, so that the infrared thermal imaging thermal sensor updates data; the number of people in the construction elevator is accurately detected while low cost is guaranteed, meanwhile, if the number of people is overloaded, the alarm is triggered to give an alarm, and the operation safety of the construction elevator is improved.

To provide a person estimation program, a person estimation method, and a person estimation device that improve estimation accuracy of a person.SOLUTION: A person estimation program causes a computer to execute steps: detecting, when receiving a captured image including a person, on the basis of a predetermined object detection method, an area of the person from the captured image; determining, on the basis of a predetermined skeleton estimation method, whether or not orientation of a face included in the area of the person is the front side; identifying, when the orientation of the face is not the front side, on the basis of the predetermined skeleton estimation method, a clothing area for each clothing type of the person from the area of the person; extracting a first color of the clothing area for each clothing type; referring to a storage unit that stores the person and a second color for each clothing type of the clothing area in association with each person; calculating a similarity between the first color and the second color; and estimating, on the basis of the similarity, the person.SELECTED DRAWING: Figure 13

A method for securing an access to a location using a gate system including an entrance door and an exit door that opens onto the location, comprising:obtaining a number of persons who will form a group to pass through the gate system together,opening the entrance door,counting the number of persons present between the entrance door and the exit door using an overhead sensor,verifying, using biometric data, that all the persons present between the entrance door and the exit door are authorized, andtriggering opening the exit door if the counted number of persons and the obtained number of persons are equal and if all the persons present in the gate system are authorized.

The aim is to improve the utilization rate of each of the one or more areas and to revitalize communication among users. [Solution] The information processing method is a computer information processing method that includes: acquiring area information which is information relating to one or more areas; estimating at least one of the number of people conversing in each area and the amount of conversation in each area based on sensing information obtained by sensing in each area; calculating a first indicator that shows the scale of communication in each area based on at least one of the number of people and the amount of conversation; and outputting information showing the first indicator in association with the area information.