21 results about "Person recognition" patented technology

The present invention aims to provide a program that allows each user to easily identify candidates who meet their desired referral criteria (candidate criteria). [Solution] The program of the present invention causes a referral system comprising at least a memory unit and a processing unit to execute a personnel memory function that stores user information, candidate information, and referrer information in the memory unit; a condition memory function that stores candidate conditions desired by one user, which are included in the user information of each user, in the memory unit; and a specification function that, if a candidate who meets the candidate conditions exists and a referrer who can introduce that candidate has a connection with the one user, identifies one or more such candidates as one or more suitable candidates to introduce to the one user.

This disclosure relates to the field of pedestrian recognition technology, and provides a method and apparatus for identifying people traveling together. The method includes: constructing an encoder using multiple fully connected layers; constructing a self-optimizing clustering module based on a clustering algorithm; constructing a people traveling together recognition model using a graph attention network, the encoder, and the self-optimizing clustering module; training the people traveling together recognition model using a reconstruction loss function, a mapping loss function, and a clustering loss; acquiring pedestrian images; extracting pedestrian relationship features and pedestrian attribute features from the pedestrian images; inputting the pedestrian relationship features and pedestrian attribute features into the trained people traveling together recognition model; and outputting the recognition result of whether the pedestrian in the pedestrian image is a person traveling together. By employing the above technical means, the problem of high computational load and low efficiency in existing people traveling together recognition methods is solved.

The application provides an image and voice recognition management method and system for trapped person identification, and belongs to the technical field of voice recognition, and specifically comprises the following steps: determining an intervention processing strategy of a voice recognition device of an elevator in a stop state based on a recognition risk type of the voice recognition device and voice recognition data of the voice recognition device in a recent preset time period; determining a voice recognition processing result of the voice recognition device based on the intervention processing strategy; and determining an intervention management method of the voice recognition device in the stop state in a current time period by using the voice recognition processing result and idle running data of the elevator in different time periods, so that the reliability of trapped person identification processing is improved.

A pedestrian detection device for blind spots on buses with risk avoidance function includes a powered telescopic frame, a pedestrian recognition module, an audible and visual alarm, an environmental recognition module, a geographic location recognition module, an emergency avoidance module, and an embedded microcontroller. The powered telescopic frame is installed on the front roof of the bus. The pedestrian recognition module, environmental recognition module, and emergency avoidance module are all mounted on the powered telescopic frame. The audible and visual alarm and the embedded microcontroller are both installed on the interior ceiling of the bus, directly below the powered telescopic frame. The geographic location recognition module is mounted on the embedded microcontroller. The embedded microcontroller is connected to the powered telescopic frame, pedestrian recognition module, audible and visual alarm, environmental recognition module, geographic location recognition module, and emergency avoidance module via signals. This invention can effectively identify pedestrians in the blind spots of buses, alert the driver to driving safety through the audible and visual alarm to avoid traffic accidents, and also has risk avoidance and emergency avoidance functions.

This application discloses an image recognition method, a server, and a display device. The display device sends an image recognition request to the server. The server receives the image recognition request, which includes the target image, video identifier, and playback time point. It obtains the feature matching confidence level of the facial data corresponding to the person in the target image and the target person's name. If the feature matching confidence level of the target person's name is greater than a first preset threshold, the person information corresponding to the target person's name is directly output as the recognition result. If the feature matching confidence level of the target person's name is not greater than the first preset threshold, the method outputs the person information corresponding to the target person's name as the recognition result based on the video identifier, playback time point, and a list of people determined by the media asset database, and if the target person's name is in the list. Otherwise, an unrecognized identifier is output. Voiceprint-assisted recognition improves the accuracy and recall rate of person recognition, enhancing the user experience.

To provide a person recognition device that can more reliably determine the intrusion of a person into the area near the garbage collecting vehicle.SOLUTION: A person recognition device comprises an image processor for recognizing a person in the vicinity of a garbage inlet 4. The image processor includes person determination means capable of performing: an upper body determination process of comparing an object image in an image with feature data of a head portion to determine whether or not the object image represents the head portion; and a lower body determination process of comparing the object image in the image with feature data of a leg portion to determine whether or not the object image represents the leg portion. The person determination means also includes intrusion determination means that determines whether or not the object image determined by the person determination means as representing the head portion or leg portion is in a predetermined area near the garbage inlet 4. The person determination mean is configured to: when the upper body determination process is executed to result in that the object image is determined not to represent the head portion, execute the lower body determination process; or otherwise, when the lower body determination process is executed to result in that the object image is determined not to represent the leg portion, execute the upper body determination process.SELECTED DRAWING: Figure 1

This invention discloses a method and system for real-time accompaniment and structured memory generation based on scene perception, relating to the fields of artificial intelligence, augmented reality, and mobile computing. The system includes core modules such as an audio and video acquisition module, a scene intent recognition and scheduling module, a sensor parameter dynamic configuration module, a real-time dialogue perception engine, and a structured information extraction module. This invention achieves dynamic optimization of hardware parameters driven by scene semantics, balancing perception accuracy and device power consumption. It realizes speaker recognition without training through a large language model, and adopts a local priority architecture to protect data privacy. It can achieve seamless continuous accompaniment after a single trigger, completing real-time understanding of dialogue content, multi-dimensional structured information extraction, and local memory generation. At the same time, through a voice activity adaptive acquisition mechanism and a runtime voice command reconfiguration mechanism, it achieves low-power acquisition and touchless parameter adjustment, making it suitable for various scenarios such as medical consultation, business negotiation, and daily social interaction.

To improve the accuracy of identifying the same person. [Solution] The information processing device includes an audio processing unit that acquires audio direction information indicating the direction of the sound of speech uttered by a plurality of persons engaging in a dialogue from sound collection devices positioned for the persons said by

An automated test platform configured for use in testing and validating point of sale (POS) software and hardware. The platform is designed for mounting within shelf or drawer of a conventional server rack to enhance the safety and security of using the automated test platform, and a test system may include a plurality of server racks filled with dozens of the automated test platforms to concurrently test numerous terminals. The platform includes robotic or mechanical systems to perform EMV (Europay, Mastercard, and Visa) card inserts, swipes, and tap transactions on a payment or transaction terminal undergoing testing. The platform utilizes a robotic system that performs PIN (personal identification number) entry and button pressing on the touch screen of the payment or transaction terminal. The platform has capabilities of automating tests that require use of barcode scans and simulated network and / or device outages.

This invention discloses a method, apparatus, and device for identifying skin regions of people in images. The method includes: acquiring different images containing people and skin; labeling each image with an original image, a first person feature region, and a first skin feature region, and generating a training sample set; constructing a person recognition model and a skin recognition model based on the first person feature region and the first skin feature region, respectively; jointly training the person recognition model and the skin recognition model using the training sample set; and extracting the skin region of the image to be recognized based on the trained person recognition model and skin recognition model. This invention splits the original single-skin-model process into two sequential steps: person recognition and skin recognition. The two steps first identify the person and then identify the skin. It can be understood that the person recognition model is used for initial screening of the image, and then the skin recognition model is used to precisely select the skin region.

This application relates to a method, apparatus, device, and storage medium for short-time audio speaker recognition. The method includes: acquiring speech features of all speech frames in a short-time audio stream, filtering all speech features to generate an effective speech feature map; sequentially fusing the effective speech feature map with local features from different frequency bands several times to obtain local fused features for different frequency bands; performing staged global fusion based on the local fused features of each frequency band except for the low-frequency band to obtain a global fused feature; inferring a speech vector based on the global fused feature, and comparing the speech vector with a registered vector in a registered sound database to identify the speaker's identity. This method improves the accuracy of short-time audio speaker recognition without compromising the core architecture of the model, while maintaining lightweight design and deployment compatibility.

The present document describes systems and methods for on-device person recognition and provision of intelligent alerts. The system includes a decentralized multi-camera system for on-device facial recognition. A device (e.g., security camera, video doorbell) captures images / video of a person, processes input image frames, detects face images, filters static faces, and aligns a rotation of the face to be upright and frontal. The device then filters low-quality face images and / or images having a large portion of the face occluded. The device computes a face embedding, compares it against a set of locally stored reference embeddings, and sends matching results to cloud services, which, based on the matching result, notifies the device owner whether the observed person is a known person or a stranger. Face detection and recognition computations are performed on device, not at the cloud. No sensitive information is transmitted off device and privacy is thus preserved.

This application discloses a speaker recognition method, apparatus, device, and storage medium, relating to the field of speech recognition technology. The method includes: acquiring several target speech segments; clustering each target speech segment to obtain pseudo-labels corresponding to each target speech segment; and obtaining predicted probability distributions corresponding to each target speech segment; determining the target confidence level corresponding to each target speech segment based on the pseudo-labels and predicted probability distributions; and determining the corresponding target weights based on the target confidence levels; training an initial speaker recognition model based on the target weights and predicted probability distributions; and using the trained target speaker model for speaker recognition. By determining the target confidence level based on pseudo-labels and predicted probability distributions, the method avoids treating all pseudo-labels as equal cases, thereby improving the accuracy of model recognition.

The application provides an airport luggage check-in intelligent joint control method and system based on multi-person identification, relates to the technical field of airport intelligent service, and comprises the following steps: acquiring monitoring images of operation areas of multiple self-service devices; identifying and tracking multiple users in the operation areas according to the monitoring images, generating user identifiers of the users, and establishing an association relationship between the user identifiers and the luggage of the users; in combination with the positional relationship of the users with respect to the self-service devices and the state information of the self-service devices, distributing corresponding target self-service devices to the users, and establishing a binding relationship between the user identifiers and the corresponding target self-service devices; and generating control strategies of the target self-service devices according to the binding relationship. The application has the technical effect of reducing security risk problems such as user operation of incorrect devices and non-matching of luggage and user identity.

This application discloses a pedestrian recognition method, belonging to the field of computer vision technology, which helps to improve the accuracy of pedestrian recognition. The method includes: acquiring the contour information of pedestrians included in a target image; generating a mask image based on the contour information and the target image, wherein the mask image includes the image of the pedestrian in the target image, and the image area of ​​the pedestrian in the mask image, excluding the human head, is masked; extracting head features from the mask image, and extracting human morphological features from the mask image, and fusing the features obtained from the head feature extraction and the human morphological feature extraction respectively; and recognizing the pedestrian based on the fused features. This method reduces interference from invalid information introduced by the background and pedestrian clothing by masking the target image, and improves the accuracy of pedestrian recognition by extracting the head features and human morphological features of the pedestrian from the mask image.

A vehicle control method and related apparatus are disclosed, applicable to the field of intelligent vehicles. In this application, first configuration information is defined to configure the execution conditions and execution content of a first vehicle control operation. The execution conditions of the first vehicle control operation include detecting a target user. The vehicle control device can access the vehicle's cabin information, including perception information of the target user within the cabin. Based on the first configuration information and the cabin information, the vehicle control device executes the first vehicle control operation. This application can automatically execute pre-configured vehicle control operations, and these operations are user-specific, i.e., "person recognition," eliminating the cumbersome manual control operations required by the user. This allows the target user to immediately enjoy various intelligent in-vehicle functions, greatly improving the user's driving experience and contributing to enhanced vehicle usability and safety.

This application discloses a method, apparatus, electronic device, and storage medium for pedestrian recognition, relating to the field of image processing technology. The method includes: determining an image to be recognized; obtaining a segmentation result image of the image to be recognized and category labels corresponding to the segmentation result image; extracting a human face mask and an object mask from the image to be recognized based on the segmentation result image and category labels; performing saliency detection on the image to be recognized; identifying the main subject and pedestrians from the image to be recognized; extracting the human face mask corresponding to the pedestrian from the human face mask; extracting the object mask corresponding to the pedestrian from the object mask; and combining the human face mask and the object mask corresponding to the pedestrian to obtain a pedestrian image. This application, for the image to be recognized, uses a segmentation algorithm as a preprocessing step to identify all targets in the image, and the subsequent combination with saliency detection can achieve the purpose of intelligent pedestrian recognition, thereby improving the accuracy of pedestrian recognition.

To improve convenience for debt collectors. [Solution] An information processing device comprising: an acquisition unit that acquires debtor identification information for identifying a debtor and status information including debtor status, which is the state of the debtor; and a processing unit that, when the debtor status associated with the debtor identification information is changed, refers to subsequent processing information which is a pre-stored association between the debtor status and subsequent processing related to the claim to be executed according to the debtor status, and executes subsequent processing for the debtor according to the debtor status.

A system on chip (SoC) for performing partial highlighting with the aid of auxiliary information detection includes a person recognition circuit, a sound detection circuit, an auxiliary information detection circuit and a processing circuit. The person recognition circuit obtains image data from an image capturing device, and performs person recognition on the image data to generate a recognition result. The sound detection circuit receives a plurality of sound signals from a plurality of microphones, and determines a voice characteristic value of a main sound. The auxiliary information detection circuit generates auxiliary information for calibrating the voice characteristic value of the main sound. The processing circuit determines a specific region in the image data according to the recognition result, the auxiliary information, and the voice characteristic value, and processes the image data to highlight the specific region.

Embodiments relate to secure multi-user biometric template authentication (MBTA) for mobile computing devices. In an embodiment, a request to generate a biometric template (BT) associated with an end user is generated via a first mobile computing device associated with an MBTA system. In response to the request, biometric data associated with the end user is collected and a BT associated with the end user is generated based on the biometric data. In embodiments, a personal identification number (PIN) is generated and associated with the BT related to the end user. The BT and / or the PIN associated with the end user are stored in an active BT database and / or an active PIN database respectively. MBTA data associated with the active BT database and / or the active PIN database is transmitted for storage on a plurality of mobile computing devices that are different than the first mobile computing device.