599 results about "Human behavior" patented technology

The invention discloses a human behavior recognition method integrating the space-time dual-network flow and an attention mechanism. The method includes the steps of extracting moving optical flow features and generating an optical flow feature image; constructing independent time flow and spatial flow networks to generate two segments of high-level semantic feature sequences with a significant structural property; decoding the high-level semantic feature sequence of the time flow, outputting a time flow visual feature descriptor, outputting an attention saliency feature sequence, and meanwhile outputting a spatial flow visual feature descriptor and the label probability distribution of each frame of a video window; calculating an attention confidence scoring coefficient per frame time dimension, weighting the label probability distribution of each frame of the video window of the spatial flow, and selecting a key frame of the video window; and using a softmax classifier decision to recognize the human behavior action category of the video window. Compared with the prior art, the method of the invention can effectively focus on the key frame of the appearance image in the originalvideo, and at the same time, can select and obtain the spatial saliency region features of the key frame with high recognition accuracy.

A communication robot control system displays a selection input screen for supporting input of actions of a communication robot. The selection input screen displays in a user-selectable manner a list of a plurality of behaviors including not only spontaneous actions but also reactive motions (reflex behaviors) in response to behavior of a person as a communication partner, and a list of emotional expressions to be added to the behaviors. According to a user's operation, the behavior and the emotional expression to be performed by the communication robot are selected and decided. Then, reproductive motion information for interactive actions including reactive motions and emotional interactive actions, is generated based on input history of the behavior and the emotional expression.

Disclosed are method and system for generating history of behavior that is capable of simplifying input of a behavior content of a human behavior pattern determined from data measured by a sensor. A computer obtains biological information measured by a sensor which is mounted to a person and accumulates the biological information, obtains motion frequencies from the accumulated biological information, obtains time-series change points of the motion frequencies, extracts a period between the change points as a scene which is a period of being in the state of an identical motion, compares the motion frequencies with a preset condition for each extracted scene and identifies the action contents in the scene, estimates the behavior content performed by the person in the scene on the basis of the appearance sequence of the action contents, and generates the history of the behaviors on the basis of the estimated behavior contents.

An improved method for analyzing computer network security has been developed. The method first establishes multiple nodes, where each node represents an actor, an event, a condition, or an attribute related to the network security. Next, an estimate is created for each node that reflects the ease of realizing the event, condition, or attribute of the node. Attack paths are identified that represent a linkage of nodes that reach a condition of compromise of network security. Next, edge probabilities are calculated for the attack paths. The edge probabilities are based on the estimates for each node along the attack path. Next, an attack graph is generated that identifies the easiest conditions of compromise of network security and the attack paths to achieving those conditions. Finally, attacks are detected with physical sensors on the network, that predict the events and conditions. When an attack is detected, security alerts are generated in response to the attacks.

A method for analyzing computer network security has been developed. The method first establishes multiple nodes, where each node represents an actor, an event, a condition, or an attribute related to the network security. Next, an estimate is created for each node that reflects the case of realizing the event, condition, or attribute of the node. Attack paths are identified that represent a linkage of nodes that reach a condition of compromise of network security. Next, edge probabilities are calculated for the attack paths. The edge probabilities are based on the estimates for each node along the attack path. Finally, an attack graph is generated that identifies the easiest conditions of compromise of network security and the attack paths to achieving those conditions.

The invention belongs to the field of computer vision video motion identification, and discloses a human behavior identification method based on a 3D deep convolutional network. The human behavior identification method comprises the steps of: firstly, dividing a video into a series of consecutive video segments; then, inputting the consecutive video segments into a 3D neural network formed by a convolutional computation layer and a space-time pyramid pooling layer to obtain features of the consecutive video segments; and then calculating global video features by means of a long and short memory model, and regarding the global video features as a behavior pattern. The human behavior identification method has obvious advantages, can perform feature extraction on video segments of arbitrary resolution and time length by improving a standard 3D convolutional network C3D and introducing multistage pooling, improves the great robustness of the model to behavior change, is conductive to increasing video training data scale while maintaining video quality, and improves the integrity of behavior information through carrying out correlation information embedding according to motion sub-states.

The invention provides a human behavior recognition method based on a depth neural network, comprising the following steps: acquiring original depth data stream of an actor; extracting human skeleton joint data from the original depth data stream of the actor; modeling the entire human body with three-dimensional coordinates corresponding to the extracted human skeleton joint data; extracting features by modeling the entire human body, sending feature data to a restricted Boltzmann machine network for preprocessing, training out a depth neural network model based on received weight initialization BP neural network parameters, and identifying a behavior from a feature extraction result; overlapping the extracted human skeleton joint data and the actual human body through multi-threaded parallel processing, and displaying the identified behavior in real time; and establishing an abnormal behavior template library and alarming for a detected abnormal behavior. The change of human behavior can be detected in real time, and alarm can be raised for abnormal behaviors (such as fall) of a human body.

The present invention relates to a human behavior identification method based on a three-dimensional convolutional neural network and a transfer learning model. The method comprises: performing sampling frame by frame of video, stacking obtained continuous single-frame images on a time dimension to form an image cube with a certain size, and taking the image cube as the input of the three-dimensional convolutional neural network; performing training of a basic multi-classification three-dimensional convolutional neural network model when implementation is performed, selecting part of classes of input samples from a test result to construct a sub-data set, training a plurality of dichotomy models on the basis of the sub-data set, and selecting a plurality of models with the best dichotomy result; and finally, employing the transfer learning to transfer the knowledge learned by the models to an original multi-classification model to perform retraining of the transferred multi-classification model. Therefore, the multi-classification identification accuracy is improved and human behavior identification with high accuracy is realized.

In the present invention, an apparatus for behavior analysis and method thereof is provided. In this apparatus, each behavior is analyzed and has its corresponding posture sequence through a triangulation-based method of triangulating the different triangle meshes. The two important posture features, the skeleton feature and the centroid context, are extracted and complementary to each other. The outstanding ability of posture classification can generate a set of key postures for coding a behavior sequence to a set of symbols. Then, based on the string representation, a novel string matching scheme is proposed to analyze different human behaviors even though they have different scaling changes. The proposed method of the present invention has been proved robust, accurate, and powerful especially in human behavior analysis.

The invention provides distributed cognitive technology for an intelligent emotional robot, which can be applied in the field of multi-channel human-computer interaction in service robots, household robots, and the like. In a human-computer interaction process, the multi-channel cognition for the environment and people is distributed so that the interaction is more harmonious and natural. The distributed cognitive technology comprises four parts, namely 1) a language comprehension module which endows a robot with an ability of understanding human language after the steps of word division, word gender labeling, key word acquisition, and the like; 2) a vision comprehension module which comprises related vision functions such as face detection, feature extraction, feature identification, human behavior comprehension, and the like; 3) an emotion cognition module which extracts related information in language, expression and touch, analyzes user emotion contained in the information, synthesizes a comparatively accurate emotion state, and makes the intelligent emotional robot cognize the current emotion of a user; and 4) a physical quantity cognition module which makes the robot understand the environment and self state as the basis of self adjustment.

The present invention is a method and system for optimizing the observation and annotation of complex human behavior from video sources by automatically detecting predefined events based on the behavior of people in a first video stream from a first means for capturing images in a physical space, accessing a synchronized second video stream from a second means for capturing images that are positioned to observe the people more closely using the timestamps associated with the detected events from the first video stream, and enabling an annotator to annotate each of the events with more labels using a tool. The present invention captures a plurality of input images of the persons by a plurality of means for capturing images and processes the plurality of input images in order to detect the predefined events based on the behavior in an exemplary embodiment. The processes are based on a novel usage of a plurality of computer vision technologies to analyze the human behavior from the plurality of input images. The physical space may be a retail space, and the people may be customers in the retail space.

According to the invention, techniques for profiling of human behavior based upon analyzing data contained in databases, data marts and data warehouses. In an exemplary embodiment, the invention provides for creating a dynamic customer profile by analyzing relationships in data from one or more data sources of an enterprise. The method can be used with many popular visualization tools, such as On Line Analytical Processing (OLAP) tools and the like. The method is especially useful in conjunction with a meta-model based technique for modeling the enterprise data. The enterprise is typically a business activity, but can also be other loci of human activity. The human behavior profiled is typically that of a customer, but can be any other type of human behavior. Embodiments according to the invention can display data from a variety of sources in order to provide visual representations of data in a data warehousing environment.

The invention discloses a human behavior recognition method based on an attention mechanism and a 3D convolutional neural network. According to the human behavior recognition method, a 3D convolutional neural network is constructed; and the input layer of the 3D convolutional neural network includes two channels: an original grayscale image and an attention matrix. A 3D CNN model for recognizing ahuman behavior in a video is constructed; an attention mechanism is introduced; a distance between two frames is calculated to form an attention matrix; the attention matrix and an original human behavior video sequence form double channels inputted into the constructed 3D CNN and convolution operation is carried out to carry out vital feature extraction on a visual focus area. Meanwhile, the 3DCNN structure is optimized; a Dropout layer is randomly added to the network to freeze some connection weights of the network; the ReLU activation function is employed, so that the network sparsity isimproved; problems that computing load leap and gradient disappearing due to the dimension increasing and the layer number increasing are solved; overfitting under a small data set is prevented; and the network recognition accuracy is improved and the time losses are reduced.

A system and apparatus are disclosed for modeling patterns of behavior of humans or other animate objects and detecting a violation of a repetitive pattern of behavior. The behavior of one or more persons is observed over time and features of the behavior are recorded in a multi-dimensional space. Over time, the multi-dimensional data provides an indication of patterns of human behavior. Activities that are repetitive in terms of time, location and activity, such as sleeping and eating, would appear as a Gaussian distribution or cluster in the multi-dimensional data. Probability distribution functions can be analyzed using known Gaussian or clustering techniques to identify repetitive patterns of behavior and characteristics thereof, such as a mean and variance. Deviations from repetitive patterns of behavior can be detected and an alarm can be triggered, if appropriate.

Heating is a significant factor in residential gas-energy usage. Saving energy on heating is receiving increasing attention with rising energy prices and the Kyoto Protocol on reducing greenhouse gas emissions. Energy awareness and energy efficiency hereby become important qualifications for human behavior and residential building codes, and become a factor in the evolution of the global climate. Here, we describe a novel measurement and validation system for domestic gas-energy usage in combination with primary weather data. We disclose a gas-energy observatory which visualizes human behavior in gas-energy consumption associated with domestic facilities, and measures home energy efficiency by calorimetry. Weather-sensitivity analysis quantifies energy-usage as a function of small variations in room temperature and home energy efficiency. Weather-sensitivity data can be used to calculate changes in room-temperature settings or improvements in home insulation for a desired reduction in CO₂-output. By public dissemination of its primary weather data, it creates in dual-use at no additional cost a novel in-situ climate observational systems with unprecedented wide-area coverage and spatial resolution.

A system and methodology/processes for non-kinematic/behavioral mapping to a local area abstraction (LAA) includes a technique for populating an LAA wherein human behavior or other non-strictly-kinematic motion may be present.

Human behavior is determined by sequential event detection by constructing a temporal-event graph with vertices representing adjacent first and second primitive images of a plurality of individual primitive images parsed from a video stream, and also of first and second idle states associated with the respective first and second primitive images. Constructing the graph is a function of an edge set between the adjacent first and second primitive images, and an edge weight set as a function of a discrepancy between computed visual features within regions of interest common to the adjacent first and second primitive images. A human activity event is determined as a function of a shortest distance path of the temporal-event graph vertices.

Human behavior alerts are determined from a video stream through application of video analytics that parse a video stream into a plurality of segments, wherein each of the segments are either temporally related to at least one of a plurality of temporally distinct transactions in an event data log; or they are each associated with a pseudo transaction marker if not temporally related to at least one of the temporally distinct transactions and an image analysis indicates a temporal correlation with at least one of the distinct transactions is expected. Visual image features are extracted from the segments and one-SVM classification is performed on the extracted features to categorize segments into inliers or outliers relative to a threshold boundary. Event of concern alerts are issued with respect to the inlier segments associated with the associated pseudo transaction marker.

The invention discloses an on-line sequential extreme learning machine-based incremental human behavior recognition method. According to the method, a human body can be captured by a video camera on the basis of an activity range of everyone. The method comprises the following steps of: (1) extracting a spatio-temporal interest point in a video by adopting a third-dimensional (3D) Harris corner point detector; (2) calculating a descriptor of the detected spatio-temporal interest point by utilizing a 3D SIFT descriptor; (3) generating a video dictionary by adopting a K-means clustering algorithm, and establishing a bag-of-words model of a video image; (4) training an on-line sequential extreme learning machine classifier by using the obtained bag-of-words model of the video image; and (5) performing human behavior recognition by utilizing the on-line sequential extreme learning machine classifier, and performing on-line learning. According to the method, an accurate human behavior recognition result can be obtained within a short training time under the condition of a few training samples, and the method is insensitive to environmental scenario changes, environmental lighting changes, detection object changes and human form changes to a certain extent.

An embodiment of an apparatus, or corresponding method, for developing a person's behavior according to the principles of the present invention comprises at least one visual behavior indicator that represents a behavior desired of a person viewing the at least one visual behavior indicator. The apparatus, or corresponding method, further includes at least two visual choice indicators viewable with the at least one visual behavior indicator that represent choices available to the person, the choices assisting in developing the behavior in the person by assisting the person in choosing an appropriately adaptive response supporting the desired behavior or as an alternative to behavior contrary to the desired behavior.

An artificially intelligent entity can emulate human behavior in video games. An AI model can be made by receiving gameplay logs of a video gameplay session, generating, based on the gameplay data, first situational data indicating first states of the video game, generating first control inputs provided by a human, the first control inputs corresponding to the first states of the video game, training a first machine learning system using the first situational data and corresponding first control inputs, and generating, using the first machine learning system, a first artificial intelligence model. The machine learning system can include a convolutional neural network. Inputs to the machine learning system can include a retina image and/or a matrix image.

A method and apparatus are disclosed for modeling patterns of behavior of humans or other animate objects and detecting a violation of a repetitive pattern of behavior. The behavior of one or more persons is observed over time and features of the behavior are recorded in a multi-dimensional space. Over time, the multi-dimensional data provides an indication of patterns of human behavior. Activities that are repetitive in terms of time, location and activity, such as sleeping and eating, would appear as a Gaussian distribution or cluster in the multi-dimensional data. Probability distribution functions can be analyzed using known Gaussian or clustering techniques to identify repetitive patterns of behavior and characteristics thereof, such as a mean and variance. Deviations from repetitive patterns of behavior can be detected and an alarm can be triggered, if appropriate.