311 results about "Behavior recognition" patented technology

This invention provides a method for fish passage behavior recognition based on a multimodal large model. First, imaging sonar image sequences and underwater optical video sequences of fish passing through fish passages or facilities are simultaneously acquired, and the multimodal data are aligned through time stamp synchronization and spatial calibration. Then, fish target detection, segmentation, and feature extraction are performed on the sonar image sequences and optical video sequences respectively to obtain the fish's spatial location, body length, water depth, motion state, morphological structure, and posture features. The obtained acoustic and optical features are input into a multimodal coding and fusion model based on the Transformer architecture, and a unified fish behavior representation vector is constructed through a cross-modal attention mechanism. During the training phase, model parameters are adjusted through a multi-task learning approach using cross-entropy loss, mean squared error loss, and contrastive learning loss, ultimately achieving fish passage behavior category recognition and prediction of individual and group passage difficulty scores.

The application relates to the technical field of image recognition, in particular to a children autism spectrum disorder stereotyped behavior recognition system based on video images. The system screens target pixel points from pixel points; determines a motion intensity index according to a trajectory point sequence of the target pixel points; converts the trajectory point sequence of the target pixel points into a motion vector sequence; determines direction similarity according to direction similarity between vectors; clusters the vectors based on the direction similarity, and identifies a target cluster; determines a motion regularity index according to the number of vectors in the target cluster and the direction similarity; determines a saliency index in combination with the motion intensity index; clusters the target pixel points based on the saliency index, and sets a region of interest; determines an enhancement weight according to the density of the target pixel points in the region and the saliency index; and determines a total enhancement demand value in combination with the gray scale and gradient features of the pixel points in the region; and reversely maps the total enhancement demand value into a gamma correction parameter, so that the accuracy of recognition is improved.

This application discloses a method, apparatus, and computer program product for processing outbound call services. Relating to the field of artificial intelligence, the method includes: executing an outbound call task to a user; processing the target service according to a preset service processing procedure; collecting the user's voice signal during the target service processing; extracting voice features and voice content from the voice signal; determining the current service processing node corresponding to the voice content in the preset service processing procedure; determining the service path map corresponding to the preset service processing procedure; determining a path deviation index value based on the current service processing node and the service path map; inputting the voice features into a target model to obtain the user's behavior recognition result; determining a risk index value for the user interrupting the target service based on the behavior recognition result and the path deviation index value; and adjusting the preset service processing procedure according to the risk index value. This application solves the problem of poor accuracy in recognizing user intent in outbound call services in related technologies.

The application belongs to the technical field of computer vision, image processing, group behavior recognition and the like, and discloses a volleyball match group behavior recognition method fusing space-time information under a missing frame environment. The method uses a VGG16 network to process an input volleyball video frame sequence to obtain global features, then inputs the feature vectors and individual bounding boxes into a RoiAlign layer to obtain individual features, inputs the individual features into an inference network to obtain initial group features and individual space-time interaction features, obtains original features, inputs the original features into a space-time Transformer module to model space-time interaction information, and processes the effective inference network module to effectively improve the complexity of discontinuous feature transition. The application can complete overall modeling of space-time dependence, reduce the influence of missing frames, capture complex interaction relationships of individuals, and effectively improve the group behavior recognition capability of the volleyball match.

The present invention relates to a terminal for providing vibration feedback on the basis of user behavior recognition. The terminal possessed by a user comprises: a memory for storing at least one instruction; and a processor, wherein the at least one instruction is executed by the processor so that the terminal: acquires a classification result about a counterpart user behavior type obtained by providing, to a pre-trained behavior type classification model, data generated by detecting the movement of the counterpart user in one or more wearable patches attached to the body of the counterpart user; acquires a vibration pattern corresponding to the acquired classification result on the basis of a mapping table in which a predetermined vibration pattern is defined for respective behavior types; and controls that vibration is generated according to the acquired vibration pattern in the wearable patch attached to the body of the user.

This invention belongs to the field of laboratory safety monitoring technology, and particularly relates to a method and system for real-time intervention of experimental operation violations based on multimodal behavior recognition. It includes collecting multimodal operation data during the experiment; constructing a database of standard operating procedures (SOPs); identifying the currently executed action; comparing the currently executed action with data in the SOP database in multiple dimensions; calculating a deviation score based on the comparison results; and, combined with preset hazard coefficients, environmental coefficients, and personnel coefficients, using a fuzzy logic algorithm to determine the risk level of the experimental violation, thus achieving real-time intervention for experimental operation violations. This invention is based on the deployment and data acquisition of a multimodal sensor network, performing multidimensional modeling of standard operating procedures, and then using a real-time behavior recognition algorithm for multidimensional comparison and violation determination, thereby initiating corresponding intervention measures to promptly eliminate safety hazards, resulting in significant social and economic benefits.

This invention relates to the field of intelligent driving vehicle technology, specifically disclosing a method for recognizing "dragging" behavior in assisted driving vehicles based on multimodal temporal feature analysis. First, vehicle driving data is collected and processed to calculate the temporal signal of the vehicle's lateral distance relative to the lane centerline. Second, the active state of the assisted driving system is verified. Then, the peaks and troughs of the lateral distance signal are detected collaboratively, and the extreme points are intelligently paired and optimized using temporal alternation constraints and extreme value competition rules to generate an extreme point sequence that conforms to the laws of physical motion. Finally, a joint judgment is made using multi-dimensional criteria: when the optimized extreme point sequence simultaneously satisfies the conditions of periodicity, amplitude validity, and persistence, "dragging" behavior is determined to have occurred, and quantitative parameters and severity levels can be output. This invention achieves high-precision, quantifiable detection of "dragging" behavior, providing data support for the performance evaluation and optimization of assisted driving systems.

This application provides a behavior recognition method, apparatus, electronic device, and storage medium based on exponential fitting, comprising: determining the corresponding power delay spectrum for the channel frequency response of a Wi-Fi signal at each observation time; fitting an exponential probability density function based on the power distribution of each sampling point in the power delay spectrum; performing a Fourier transform on the probability density function to obtain a frequency domain correlation function; determining filter coefficients based on the frequency domain correlation function and a preset frequency domain signal-to-noise ratio; filtering the channel frequency response based on the filter coefficients to obtain a denoised channel frequency response; and performing behavior recognition of passive targets based on the denoised channel frequency response at multiple observation times. This application's solution effectively denoises the channel frequency response of a Wi-Fi signal using exponential fitting, thereby enabling accurate behavior recognition based on the denoised channel frequency response.

This invention relates to a system for identifying and managing abnormal behavior in the elderly based on smart elderly care terminal devices, specifically in the field of abnormal behavior recognition. By effectively fusing visual and radar information through cross-modal attention alignment, it overcomes the limitations of single sensors in complex home environments such as obstruction and low light, thereby improving the robustness of data acquisition. The adopted joint training paradigm of mask reconstruction and contrastive learning drives the model to learn general behavioral representations invariant to environmental disturbances, enhancing the model's generalization ability. Utilizing spatiotemporal graph modeling and prototype contrastive quantitative learning, it can accurately capture and distinguish subtle differences in movements, achieving high-precision, fine-grained abnormal behavior recognition. Through a teacher-student framework and a personalized adaptive update mechanism, the model can continuously adapt to the user's unique behavioral patterns and mitigate concept drift, ultimately significantly reducing false alarms and false negatives, providing reliable, long-term, and personalized safety monitoring for the elderly.

The application discloses an abnormal driving behavior recognition method and system based on multi-modal data fusion, and particularly relates to the technical field of multi-vehicle cooperative driving safety control, and is used for solving the problem that the existing cooperative driving system cannot convert the abnormal behavior risk of a driver into a cooperative control instruction at the vehicle fleet level; the abnormal state of the driver is recognized by collecting and fusing multi-modal sensor data of the vehicle; when the vehicle is a lead vehicle of a vehicle fleet, the comprehensive risk of the abnormal state to the safety of the vehicle fleet is evaluated based on the abnormal state through probabilistic evolution simulation; the expected effect of different vehicle fleet control strategies is simulated according to the risk evaluation result, and the best strategy is selected; vehicle fleet risk information containing the strategy is generated and sent to all following vehicles through vehicle-to-vehicle communication; the whole process from single-vehicle driver state monitoring to vehicle fleet level cooperative risk prevention and control is realized, and the overall safety of the vehicle fleet system is improved.

This application discloses a driver behavior recognition method applied to vehicles. The method includes: acquiring a hyperspectral image containing the driver; extracting multiple three-dimensional cubes from the dimensionality-reduced hyperspectral data, where the label of each three-dimensional cube is determined by the category label of its central pixel; inputting the multiple three-dimensional cubes into an attention mechanism model for inference to obtain the semantic category of each three-dimensional cube; determining whether the driver is currently in a preset dangerous behavior state based on the semantic category, and activating an onboard warning mechanism when the dangerous behavior state meets preset triggering conditions. Thus, by using an attention mechanism model to infer the three-dimensional cubes extracted from hyperspectral data to capture global semantics of behavior, and combining the semantic categories of the cubes for dangerous state judgment and warning, high-precision and reliable behavior discrimination of high-dimensional driving data is achieved, effectively balancing global semantic modeling with practical safety application needs.

This invention provides an AI behavior analysis method and system for routers, gateways, and cameras in the field of video surveillance technology. The method includes: Step S1, acquiring surveillance video streams through cameras; Step S2, calling a multi-task deep learning model to infer from the surveillance video streams to obtain behavior recognition results carrying abnormal behaviors; Step S3, generating structured behavior event logs based on the behavior recognition results and sending them to the router or gateway; Step S4, the router or gateway receiving behavior event logs from one or more cameras and performing cross-device correlation analysis to obtain correlation analysis results; Step S5, generating alarm commands at the router or gateway based on preset rules and correlation analysis results, distributing the alarm commands to trigger the target device to execute alarm response actions. The advantages of this invention are: greatly improving the accuracy, real-time performance, multi-behavior collaboration capabilities, and resource efficiency of edge AI behavior analysis.

The application discloses a zero-shot station behavior recognition method based on dynamic and static cooperative support set optimization, and aims to solve the problems of low sample quality and insufficient support set information mining in a video behavior recognition task. The method realizes zero-shot behavior recognition in a station scene through a key frame cascaded support set construction module and a dynamic and static cooperative weighted prediction module. The key frame cascaded support set construction module and the dynamic and static cooperative weighted prediction module constitute a zero-shot learning framework. In the key frame cascaded support set construction module, a text-to-image and image-to-video generation model is used to generate static key frame images and dynamic video support set samples for each behavior category. In the dynamic and static cooperative weighted prediction module, rich semantic information in the above samples is fully utilized, and dynamic fusion is performed on the static key frame and the dynamic video through a dynamic and static cooperative strategy, so that high-precision identification of key actions in the station scene is realized.

The application discloses a camera monitoring system based on behavior feature recognition and concretely relates to the field of intelligent security monitoring, and comprises five modules of multi-source data acquisition, multi-dimensional feature analysis, intelligent feature fusion, case base matching determination, application output and closed-loop management and control; through the deployment of visual acquisition, environmental sensing, positioning tracking and equipment linkage units, multi-dimensional original data are collected and cleaning and standardized preprocessing are completed; four-dimensional features are extracted from visual behavior, environmental correlation, space-time trajectory and equipment interaction, and adaptive weights are generated in combination with data quality; comprehensive behavior features are generated through feature quality evaluation, weighted fusion and dimensionality reduction operation; coarse and fine matching is executed relying on a hierarchical case base to realize accurate behavior recognition; hierarchical alarm is pushed based on the recognition result, visual data and system logs are generated, and hierarchical closed-loop management and control is executed; the system improves the accuracy and generalization ability of behavior recognition in complex scenes and guarantees efficient landing of security management and control.

This invention discloses a noise-robust method and apparatus for identifying the behavior of communication radiation sources, relating to the fields of wireless communication and signal processing technology. The method includes: acquiring the original signal of the communication radiation source to be identified, and preprocessing the original signal to obtain a standard communication radiation source signal; inputting the standard communication radiation source signal into a pre-trained behavior recognition model, and outputting the behavior category identification result of the communication radiation source; wherein the behavior recognition model includes at least: a multi-scale convolution module for extracting features of the input signal from different scales and outputting multi-scale fused features; and a contraction attention module coupled to the multi-scale convolution module for adaptive redundancy suppression and feature purification of the multi-scale fused features, outputting redundancy-suppressed features. This invention significantly improves the noise robustness of communication radiation source behavior recognition in complex electromagnetic scenarios.

The method comprises the steps of: obtaining target low-resolution video data; preprocessing the target low-resolution video data to obtain a face video image sequence; processing the face video image sequence by using a preset fatigue driving behavior recognition model to obtain a fatigue driving behavior recognition result in the target low-resolution video data; and wherein the fatigue driving behavior recognition model is obtained by updating parameters of a preset model according to a label type and a prediction type of to-be-trained low-resolution video data. The present application can train a fatigue driving behavior recognition model according to a dynamic video, and utilize the time sequence relationship of face features between multiple frames of images in the dynamic video, so as to improve the recognition accuracy of the dynamic video scene to a certain extent.

This application discloses a behavior recognition method, apparatus, device, storage medium, and computer program product, relating to the field of computer technology. The method includes: acquiring business behavior records of cloud services within a historical time period; labeling cloud interface call records with stage tags; constructing an interface call behavior chain based on the stage tags; and performing behavior recognition on a target account based on the interface call behavior chain to obtain the behavior recognition result of the target account. For cloud interface call records, stage tags are labeled according to the risk event stage to determine the corresponding risk stage of the interface call. The behavior chain formed by the stage tags represents the characteristics of the interfaces continuously called by the target account, thereby analyzing the risk situation of the target account based on the behavior chain and improving the accuracy of behavior recognition. This application can be applied to various scenarios such as cloud technology, map-based vehicle networking, and intelligent transportation, including trip sharing and parking space allocation.

The present application relates to solid waste intelligent management technical field, especially in kind based on the whole process closed loop monitoring system of solid waste garbage classification processing of Internet of Things, including resident end monitoring subsystem, cleaner end monitoring subsystem, property company end monitoring subsystem, transportation party end monitoring subsystem, maintenance and maintenance end monitoring subsystem, AI behavior recognition module and data synchronization submodule;Resident end monitoring subsystem, cleaner end monitoring subsystem, property company end monitoring subsystem, transportation party end monitoring subsystem, maintenance and maintenance end monitoring subsystem, AI behavior recognition module, data synchronization submodule are connected with intelligent management system communication through cloud, and form the control system of data real-time flow, link closely connected;Property company end monitoring subsystem undertakes the responsibility of area overall planning and process supervision, is used for visual monitoring and examination to key link.The present application improves the accuracy of garbage classification and collection and transportation efficiency, realizes whole process traceability and responsibility traceability.

The application provides a fish school behavior recognition method, device and equipment and medium, and relates to the field of aquaculture, which comprises the following steps: all image frames in an initial image data set are segmented according to an encoder gradient to obtain first gradient features of a preset gradient; the remaining gradient features in each preset gradient are connected to a decoder to decode second gradient features of the preset gradient in each image frame; the first gradient features and the second gradient features in each image frame are fused to obtain fish school segmentation images of each image frame, and the initial image data set is traversed until a fish school segmentation image set is obtained; and fish school dispersion indexes and fish school activity indexes are calculated according to the fish school segmentation image set to obtain fish school behavior according to a long short-term memory network model. The application solves the problem that a target fish school region is similar to the background of an image region and cannot be distinguished, realizes accurate segmentation of the boundary of the fish school target, increases the recognition accuracy, reduces the parameter quantity and the calculation amount, and improves the efficiency of fish breeding.

The present application relates to the technical field of artificial intelligence, and more particularly to an AI interaction system for ornithological scientific research, which comprises a collection unit, a trigger determination unit, a path determination unit, a dominant determination unit, a prompt generation unit and an adjustment unit. The present application constructs a multi-level behavior determination process through joint analysis of bird song spectrum, image motion characteristics, flight trajectory and environmental factors, and through statistical analysis of the time distribution and spatial distribution of these behavior indicators within a preset period, and correlation analysis with environmental factors such as temperature, humidity, wind speed and illumination, the influence of environmental changes on bird activity frequency and spatial aggregation degree can be identified, so that the acoustic trigger threshold can be dynamically adjusted, so that the system can continuously maintain the sensitive recognition ability of bird activity with the change of the habitat environment, and then realize high-reliable behavior recognition and interaction prompt for ornithological scientific research.

This invention discloses a machine vision-based system for detecting and recognizing abnormal intrusion targets along pipelines, relating to the field of intelligent security. It includes a pipeline scene modeling module, a target enhancement and detection module, a spatiotemporal tracking module, and a risk warning module. This invention solves problems such as missed detection of small targets at long distances in pipeline scenes, lack of spatial constraints, inaccurate behavior recognition, high false alarm rates, and unreasonable risk classification. It is suitable for real-time safety monitoring of long-distance pipelines such as oil and gas, water conservancy, and natural gas pipelines, and has the advantages of low missed detection, low false alarms, high robustness, and easy deployment.

This invention discloses a multimodal behavior recognition method based on modal credibility scheduling and conflict reconstruction, comprising the following steps: acquiring video and skeletal modal data of behavior samples, completing time alignment and standardization preprocessing to obtain time-synchronized bimodal input tensors; feature encoding the bimodal input tensors respectively to obtain global semantic features and behavior category prediction probability distributions for each modality; calculating the credibility weights of video and skeletal modalities based on the uncertainty of the prediction probability distributions; calculating the comprehensive conflict intensity of the bimodal prediction distributions to generate continuous conflict adjustment factors; modulating the credibility weights using the conflict adjustment factors to complete the adaptive fusion of bimodal probabilities, and outputting the final behavior recognition result. This method solves the technical problems in existing multimodal behavior recognition technologies, such as the lack of explicit quantitative modeling of modal reliability and the lack of active intervention mechanisms for cross-modal prediction conflicts, leading to insufficient recognition accuracy and system stability in complex scenarios.

The application is suitable for the technical field of device management, and provides a behavior recognition method based on space-time relationship and an electronic device. The method comprises the following steps: receiving target video data to be recognized; introducing the target video data into a preset inter-frame action extraction network to obtain inter-frame action feature data; introducing the inter-frame action feature data into a feature extraction network to output sparse feature data corresponding to the target video data; the feature extraction network is generated by performing sparse constraint processing on each convolution kernel in a pooling fusion network through selected weights; introducing the target video data into a context attention network to determine gait behavior data of a target object in the target video data; and obtaining a behavior category of the target object according to the gait behavior data and the sparse feature data. The above method can greatly reduce the calculation cost of video data in the behavior recognition process, thereby improving the operation efficiency.

The application provides an infant education intelligent bracelet and a data processing method, and belongs to the technical field of wearable devices. The infant education intelligent bracelet comprises a main control processing module, a multi-source sensing module, a 4G communication module and a low-power control module. The multi-source sensing module comprises at least a three-axis acceleration sensor and a three-axis gyroscope, and is used for continuously collecting motion data and posture data of the infant. The 4G communication module is used for establishing a direct data communication connection between the intelligent bracelet and a cloud server, so that the data is directly transmitted to the cloud server. The main control processing module is used for data collection scheduling, data preprocessing and communication control logic. The low-power control module is used for dynamically adjusting the sampling frequency of the multi-source sensing module and the data upload period of the 4G communication module according to the behavior state of the infant. The application can solve the problems of low behavior recognition accuracy, high positioning error rate, insufficient data continuity and weak data fusion capability in the prior art.

This invention discloses a posture monitoring method for smart AI glasses based on multimodal fusion, relating to the field of smart wearable technology. The method includes: collecting head motion data, denoising and standardizing it to generate processed head motion data; using a complementary filter algorithm to fuse the processed head motion data with angular velocity variance, and parsing pitch and roll attitude data to generate posture angle data; analyzing the changing trends of the posture angle data through a multi-stage abnormal behavior recognition algorithm, comparing it with historical behavior patterns to obtain abnormal behavior types, and adjusting the recognition criteria to determine whether the user has an undesirable posture; triggering an alarm signal when an abnormal posture is detected; and analyzing the user's behavior patterns and environmental changes when a corresponding feedback signal is triggered to generate a posture monitoring report. This invention improves the monitoring accuracy of smart glasses, provides an efficient feedback mechanism, and enhances user safety.

The application relates to a target object action recognition method and device, computer equipment and a storage medium. The target object action recognition method comprises the following steps: acquiring a motion sequence of a target object by using a motion sensor; and performing action recognition processing on the motion sequence by using a trained deep neural network based on the motion sequence, to obtain an action recognition result of the target object. The application can directly collect motion data of a target object, and can automatically learn nonlinear features and time sequence dependencies in a motion sequence by introducing a trained deep neural network, so that accurate recognition of fine-grained action categories is achieved, the accuracy of behavior recognition is improved, and the misjudgment rate is effectively reduced.

This invention discloses a lightweight human pose estimation and abnormal behavior recognition method for UAV aerial photography scenarios. First, a YOLOv11 multi-scale detection network is used for human target detection to obtain bounding boxes and multi-scale feature maps. Then, a semantically aware RoI feature extraction module is used to extract semantically consistent region features using dynamic sampling and learnable semantic masks. Next, a keypoint adaptive multi-scale fusion module is employed to dynamically adjust the scale fusion weights based on prior knowledge of human anatomy. The fused features are then input into a lightweight high-resolution network equipped with a one-dimensional spatial attention mechanism for heatmap regression and keypoint coordinate decoding. Finally, the continuous frame keypoint sequence is input into a lightweight manifold dynamics graph network, combining quaternion skeleton representation, single-step Eulerian dynamics, and sparse grouped graph convolution for abnormal behavior recognition. This invention can improve the accuracy of pose estimation from the UAV's perspective and achieve real-time detection of abnormal behaviors such as falls and fights.

This invention relates to the field of digital twin technology, specifically to a 3D digital twin equipment operation and maintenance and AR early warning system and method for wastewater treatment plants. The system includes an equipment status mapping module, an abnormal behavior identification module, a dynamic path planning module, a fault suppression and control module, and a global optimization and adaptation module. In this invention, by dynamically correlating load distribution curves with operating states, the system accurately analyzes the coupling characteristics between equipment operating patterns and the environment. It can identify operational deviations and response lag changes under complex operating conditions, strengthen real-time perception and trend prediction, and promote the transformation of equipment from static monitoring to dynamic evaluation, improving the accuracy of anomaly identification and the timeliness of response. Through multi-layer weight matching and priority ranking of fluctuating nodes, the system optimizes resource scheduling and operating sequence, reduces energy waste and equipment fatigue caused by uneven load, improves the system's adaptability and stability under changing operating conditions, achieves global coordination and continuous optimization, and improves operation and maintenance efficiency and system reliability.

The application provides a method and device for identifying river and lake behaviors, computer equipment and a storage medium, and relates to the field of data processing. The method comprises: acquiring first satellite remote sensing data and ground road network structure data, and determining a shoreline area of a river and lake based on the first satellite remote sensing data and the ground road network structure data; acquiring signaling data of an electronic device in a first analysis period, and determining a first trajectory feature of a target person carrying the electronic device in the shoreline area based on the signaling data; determining a behavior occurrence position of a river and lake violation behavior of the target person according to the first trajectory feature, and matching the first trajectory feature with pre-stored trajectory features in a trajectory feature library, determining a target trajectory feature matched with the first trajectory feature, and determining a behavior type of the river and lake violation behavior of the target person according to a behavior type corresponding to the target trajectory feature.