204 results about "Perceptual information" patented technology

A real-time body status monitoring system (RBMS) is presented in this invention. A wearable monitoring apparatus (WMA) worn by users consists of one or a few sensor nodes and a computing module. Sensor nodes communicate with the computing module via either wired or wireless protocols. RBMS incorporates a monitoring center that connects and serves many WMAs. Together with the sensors and context-aware information fusion and analysis, the system in the invention goes beyond sampling rare events that may be of profound diagnostic, prognostic, or therapeutic importance. It measures the physiological responses to therapeutic interventions during daily activities, which constitute direct and practical health indicators for the patient.

A method for encoding a digital signal into a scalable bitstream comprising quantizing the digital signal, and encoding the quantized signal to form a core-layer bitstream, performing an error mapping based on the digital signal and the core-layer bitstream to remove information that has been encoded into the core-layer bitstream, resulting in an error signal, bit-plane coding the error signal based on perceptual information of the digital signal, resulting in an enhancement-layer bitstream, wherein the perceptual information of the digital signal is determined using a perceptual model, and multiplexing the core-layer bitstream and the enhancement-layer bitstream, thereby generating the scalable bitstream. A method for decoding a scalable bitstream into a digital signal comprising de-multiplexing the scalable bitstream into a core-layer bitstream and an enhancement-layer bitstream, decoding and de-quantizing the core-layer bitstream to generate a core-layer signal, bit-plane decoding the enhancement-layer bitstream based on perceptual information of the digital signal, and performing an error mapping based on the bit-plane decoded enhancement-layer bitstream and the de-quantized core-layer signal, resulting in an reconstructed transformed signal, wherein the reconstructed transformed signal is the digital signal.

A robot arm system for controlling a motion of a robot arm includes an order determining section for determining an order of teaching information based on at least one or more pieces of perceptual information about circumference environment of the robot arm used by a person to operate the robot arm and change the motion of the robot arm that is sensed by the person, reaction time information as time information from a time when the person receives the perceptual information to a time when the person operates robot arm, and dispersion information about a dispersion level between at least one or more pieces of the teaching information or the perceptual information, and creates motion information about the robot arm based on the teaching information and the order determined by the order determining section.

The invention provides a method and device for route programming in a dynamic unknown environment. In the moving process of a robot along a preset optimal route, a collision-free optimal route is obtained through calculation by using a linear programming gradient method and through environment information acquired by a preset rolling window, and then partial routes are obtained through calculation carried out on the obtained collision-free optimal route and acquired perceptual information in the rolling window. In the calculation process, the rolling window is used for reducing calculation amount and improving efficiency, and the linear programming gradient method is applied to ensure global convergence and to prevent from being caught in the problems of local minimum and oscillation.

The invention provides a meat product freshness detection method based on multisource perceptual information fusion. According to the method, a near infrared spectrometer, a computer vision system and an electronic nose are used for acquiring internal and external information of a sample simultaneously and respectively, the feature extraction and fusion treatment are performed on the acquired information, and the freshness grade of a meat product is evaluated according to a freshness grade evaluation standard of the meat product. The method comprises the steps of establishing the freshness grade evaluation standard of the meat product, establishing a freshness grade forecast model of the meat product, and performing freshness grade evaluation on the sample to be detected. The method comprehensively uses the spectrum, image and smell fingerprint information, comprehensively determines the internal and external quality of the meat product, and can realize quick, simple, convenient and objective grade evaluation of the freshness of the meat product.

An electronic device that allows data to be viewed intuitively using visual perception information (which is other than a graph) is described. In particular, the electronic device may be associated with a user of an environmental monitoring device that monitors an environmental condition in an external environment that includes the environmental monitoring device. When the environmental monitoring device provides environmental-summary information that specifies a time history of the environmental condition, the electronic device may represent the time history of the environmental condition as a sequence of images. A given image may include a numerical value of the environmental condition at a given time and associated visual perceptual information, such as a color associated with the numerical value and / or the environmental condition. The electronic device presents one of the sequence of images on a display. Moreover, the user can provide a user-interface command to view another of the sequence of images.

The invention provides a method for evaluating experience quality of a video stream media service. The method comprises the steps of acquiring a time complexity parameter temporal perceptual information (TI) of an original video stream and an image display quality parameter of the compressed video stream; acquiring a bit rate adopted in compressing of the video stream; acquiring packet loss rate of the video stream that is transmitted through network and then is decompressed; and building an experience quality evaluation model by use of a neutral network, using the time complexity parameter TI, the image display quality parameter, the bit rate and the packet loss rate as input of the model, and outputting a mean opinion score (MOS) of the experience quality. According to the method, impact of compressed coding and network transmission on display quality of the video stream are taken into account comprehensively, the evaluation accuracy of the service experience quality evaluation model is improved, and the evaluation result is more approximate to practical experience results of users.

The invention discloses a mobile robot positioning method based on a laser scanner and strong reflective signs. The method comprises that steps that a mobile robot environment monitoring system composed of the multi-line laser scanner and the strong reflective signs is established, and the strong reflective signs are recognized and relatively positioned through environment light intensity data and distance data obtained by the multi-line laser scanner. When the initial position of the robot is not known, distance and gradient information of pairs of connected lines of the reflective signs is calculated, therefore global positioning of the reflective signs is achieved through data matching, and finally position information acquisition of the robot under the global environment is achieved through the relative position relation between the robot and the reflective signs. The mobile robot positioning method has the beneficial effects that the defects that perceptual information is excessively simple when only distance or direction data are adopted, and less target characteristics are obtained are overcome, and recognition stability is improved.

The invention discloses a positioning perception information acquiring method, device and system. The method comprises the steps of acquiring an information transmission range; detecting road participants positioned within the information transmission range, wherein the road participants comprise a target participant and peripheral participants; acquiring first estimated positioning perception information and second estimated positioning perception information of the target participant, wherein the first estimated positioning perception information is the own positioning perception informationof the target participant, and the second estimated positioning perception information is the estimated positioning perception information of the peripheral participants to the target participant; and fusing the own positioning perception information with the estimated positioning perception information, and thus acquiring target positioning perception information. According to the method, deviceand system provided by the invention, the more accurate and reliable target positioning perception information can be acquired, and thus a path plan with stronger cooperativity can be made for the target participant based on the target positioning perception information.

The invention relates to an object material classification method based on multimodal fusion deep learning and belongs to the technical field of computer vision, artificial intelligence and material classification. The object material classification method based on multimodal fusion deep learning is a multimodal fusion method of an extreme learning machine based on multi-scale local reception fields. The method achieves accurate classification of object materials through fusion of perceptual information (including visual images, tactile acceleration signals and tactile sound signals) of different modes of object materials. The method not only can perform high-representativeness feature extraction on complex materials by using multi-scale local reception fields but also can fuse information of all modes effectively to achieve information complementation between modes. The method can improve the robustness and accuracy of complex material classification, thereby having greater applicability and universality.

The invention provides a cross-perception information interaction sensing fusion method in intelligent bionic evaluation for food quality. A huge matrix, comprising sensing information with different physical significances and different dimensions / magnitudes, is obtained by different bionic sensors. According to principal component analysis, all original characteristic variables are recombined to obtain a plurality of orthogonal principal components (PCi), so that the interaction sensing fusion of different types of sensing information is realized. The visual, olfactory and gustatory scores of manual organoleptic inspection are regressed according to the plurality of principal components so as to respectively obtain corresponding visual, olfactory and gustatory dummy variables. The dummy variables serve as the input of a decision making system, the nonlinear decision making system is constructed according to a genetic neural network method, the cross-perception sensor information interaction sensing fusion of visual, olfactory, gustatory and other sensations is truly realized, and a final comprehensive evaluation result approaches to human perception behaviors to the greatest extent.

A space is set substantially in a tropical rain forest type environment to activate a human's essential brain region and realize an environment suitable for the human's brain by arranging a device for setting the tropical rain forest type environment based on characteristics of activating human's essential brain region responsive to tropical rain forest type environment information, in a space such as an urban space, a housing space or other living space. The tropical rain forest type environmental information has higher density and higher complexity than those of urban space type environmental information, and includes at least one of auditory information, visual information, and super perceptual information of aerial vibration. The tropical rain forest type environmental information is comfortable for the human with no excessive stress, and is environmental information for effecting prevention and treatment of diseases due to stress by realizing the environment comfortable for the human's brain.

The invention provides an ultrasonic gesture recognition method. The method includes the steps that ultrasonic signals and situation information related to a current situation are collected at the same time, gesture features are obtained from the collected ultrasonic signals, and the probability that the gesture features belong to various preset gestures is obtained by means of a gesture classification model trained in advance; the probability that the gestures happen in the current situation is determined on the basis of the collected situation information; according to the two probabilities, the probability that the gesture features belong to various preset gestures in the current situation is calculated, and the gesture corresponding to the largest probability is recognized as the gesture corresponding to the collected ultrasonic signals. By means of the method, gesture signals and the situation information are fused, by means of the situation information, misoperation gestures of users are filtered, wrong gestures are corrected and recognized, invalid even wrong responses are reduced, accordingly accuracy and robustness of gesture recognition are improved, and man-machine interaction experiences are improved.

The invention discloses an interactive system combining the Internet and traditional media, including: a production module, which is based on Html5 technology to produce Html5 scene content; a function module, which is inserted into an interactive component based on the Html5 scene, and sets the functions in the interactive component; publishes module, which associates the Html5 scene inserted into the interactive component with the two-dimensional code information or perceptual information, and embeds the two-dimensional code information or perceptual information into the traditional media content; the interactive module, the user scans the traditional media content through the mobile Internet device QR code information or sensory information, open the Html5 scene and interact with the content of the interactive component. Thus breaking through the barriers between new media and traditional media, reshaping the advertising model of existing traditional media, completely overturning the public's stereotypes of traditional media in the past, and encouraging the public to actively participate and interact through various interactive activities such as red envelopes, so that advertisers The publicity is more effective, and the public can obtain "compensation rights" by watching advertisements, forming a virtuous circle.

The invention relates to a visual perception based interactive mammography image search method, comprising the following steps of: firstly reading a mammography image to be processed; marking a suspected lesion by an image segmentation algorithm; extracting the characteristics (including area, eccentricity ratio, compactness, invariant moment, Gabor characteristic and fractal dimension) of a suspected lesion area; automatically searching a lesion sample which is relative to the characteristics (including area, eccentricity ratio, compactness, invariant moment, Gabor characteristic and fractal dimension) of the suspected lesion area and confirmed by a biopsy in a lesion database; recording visual perception information, and learning and sorting the visual perception information by using a fuzzy neural network; and repeating the steps till a lesion most similar to the suspected lesion is searched. The invention can effectively enhance the diagnosis precision.

The invention discloses a cooperation segmentation method fusing perception information, which is used for performing joint segmentation on a group of image data set containing a common object, and each image can contain a plurality of common objects. The cooperation segmentation method comprises steps of using perception information like the significance, the repeatability, the space position, etc, which are based on the area as a global bound term to introduce an energy model to define the foreground likelihood, fully playing the important role of the perception information, converting the segmentation problem to the combination optimization problem to solve and using the object structural constraint based on the perception to perform iterative solution. Compared with the similar algorithm, the cooperation segmentation method fusing perception information and the solving method can be applicable to various complex occasions and can effectively segment the object.

The invention belongs to the technical field of digital image intelligent processing, and particularly relates to a multi-scale face image deblurring algorithm based on separation of low frequency andhigh frequency. The algorithm comprises the steps that a preprocessing network is used, and low-frequency information and semantic segmentation of a face image are recovered at the same time; Then the generated low-frequency information, semantic segmentation and fuzzy picture splicing are input into a subsequent multi-scale network to recover a clear picture; And finally, the deblurring network(a pre-processing network and a multi-scale network) and a high-level task are jointly trained, so that a clear picture generated by deblurring can be better expressed on the recognition of equal-level tasks. Experimental results show that the restored clear picture is very complete in structure and details, and meanwhile, the restored clear picture contains richer perceptual information through combination with a high-level task, so that the effect of the high-level task is greatly improved.

Aspects provide methods and sound processor for encoding stimulation signals to convey pitch perception information to a recipient. The method may comprise identifying a first stimulation site based on a selected frequency component of the sound signal that contains pitch perception information, wherein a stimulation signal is generated based on the selected frequency component; determining a second stimulation site adjacent to the first stimulation site; and determining a time delay between when the second stimulation site is independently stimulated with the stimulation signal and when the first stimulation site is independently stimulated with the stimulation signal.

The invention relates to the technical field of cognitive radio safety and discloses a method and a device for resisting spectrum sensing data falsification through a distributed cognitive radio network, wherein the method comprises the following steps: a secondary user perceives signal energy of a primary user; the secondary user interacts local perceptual information with a neighbor node and calculates comprehensive credibility of the neighbor node according to a cognitive state value of the neighbor node; the secondary user performs iteration on the cognitive state value according to a comprehensive credibility weighting consistence scheme of the neighbor node until state values of all nodes are converged; the secondary user compares the converged state value with a detection threshold and judges whether an existing channel is occupied or not by the primary user. The method can be used for resisting spectrum sensing data falsification launched by a malicious user, improving spectrum sensing safety in the cognitive network and resisting SSDFs of various forms very well on the condition of not having priority knowledge of number of intruders, a falsification strategy, and the like.

According to the embodiment of the invention, a method, device, a medium and a system for assisting in controlling automatic driving of a vehicle are provided. The method comprises the following stepsof acquiring perceptual information related to an environment acquired by a sensor, with the sensor being disposed in the environment and independent of the vehicle; determining an environmental perception result related to the environment by processing the acquired perception information, wherein the environmental perception result indicates related information of a plurality of objects including the vehicle in the environment; and providing the environmental perception result to a vehicle-side control device associated with the vehicle for assisting in controlling the driving behavior of the vehicle. The sensor outside the vehicle is used for sensing the environment, so that the requirement on the sensing capability of the vehicle can be reduced, and the automatic driving capability ofa non-automatic driving vehicle or a vehicle with weaker automatic driving capability can be simply improved at low cost.

A system and method for securing media content are provided. A method for distributing security media content includes embedding a marking payload into media content, thereby producing embedded media content, applying a transform to the embedded media content, thereby producing secured media content, and distributing the secured media content. The marking payload is embedded based on perceptual information regarding the media content.

The embodiment of the invention discloses a perceptual information fusion processing method and device, an apparatus and a storage medium. The method comprises: a set of perceptual information in a target area is received, wherein the set of perceptual information includes perceptual sub-information transmitted by different roadside apparatuses and the perceptual sub-information has a same timestamp based on time calibration among the different roadside apparatuses; and the set of perceptual information is subjected to fusion processing by using a fusion algorithm. The embodiment of the invention solves the problems that vehicle-mounted sensing devices have a small sensing range during a driving process and the cost is high for deploying more sensing devices on a vehicle, expands the sensing detection range in the driving process, reduces the deployment cost of sensing devices in a single vehicle, ensures the accuracy of fusion processing results and helps to promote the popularizationof the intelligent transportation technology.

A context-aware information obtaining method and apparatus uses local service information. A communication apparatus may receive local service information associated with a location of the communication apparatus. The communication apparatus may interpret the local service information to generate context-aware information of the communication apparatus.

The embodiment of the invention discloses a group unmanned vehicle cooperative perception method based on a block chain. The method comprises the following steps: an information exchange step: constructing a decentralized group unmanned vehicle information exchange and sharing network to realize the information safe exchange and sharing mechanism among unmanned vehicles; an environmental consensusstep: constructing a distributed perceptual information synthesis model based on dynamic Bayesian network to synthesize the distributed multi-source heterogeneous perceptual information of group unmanned vehicles and eliminate the inconsistency of environmental perception; an active collaborative perception step: modeling the active collaborative perception task as a multi-objective optimizationtask, and carrying out the multi-objective optimization solution of the active collaborative task to gradually complete the perception of a specific environment and a specific target. The embodiment of the invention improves the reliable and accurate information basis for the optimal planning and decision-making of the group unmanned vehicle by establishing a perfect block chain-based high-level cooperative perception method and mechanism of the group unmanned vehicle.

The invention provides a city perceptual information system based on a bus. The system comprises a plurality of sensors, a data collecting unit, an image collecting unit, a global positioning system (GPS) unit, a gateway unit, a transmission unit and a cloud server. The data collecting unit is used for collecting environmental data collected by the sensors. The image collecting unit is used for collecting an internal image and an external image of the city bus. The GPS unit is used for collecting position information and running speed of the city bus. The cloud server is used for receiving and storing the environmental data, the internal image and the external image of the city bus, and the position information and the running speed of the city bus, receiving an inquiry instruction sent by a user terminal, and transmitting information corresponding to the inquiry instruction to the user terminal. By means of the city perceptual information system based on the bus, a unified platform is formed between pieces of perceptual information, and the good fault-tolerant ability between networks can be ensured.

A method for encoding a digital signal into a scalable bitstream comprising quantizing the digital signal, and encoding the quantized signal to form a core-layer bitstream, performing an error mapping based on the digital signal and the core-layer bitstream to remove information that has been encoded into the core-layer bitstream, resulting in an error signal, bit-plane coding the error signal based on perceptual information of the digital signal, resulting in an enhancement-layer bitstream, wherein the perceptual information of the digital signal is determined using a perceptual model, and multiplexing the core-layer bitstream and the enhancement-layer bitstream, thereby generating the scalable bitstream. A method for decoding a scalable bitstream into a digital signal comprising de-multiplexing the scalable bitstream into a core-layer bitstream and an enhancement-layer bitstream, decoding and de-quantizing the core-layer bitstream to generate a core-layer signal, bit-plane decoding the enhancement-layer bitstream based on perceptual information of the digital signal, and performing an error mapping based on the bit-plane decoded enhancement-layer bitstream and the de-quantized core-layer signal, resulting in an reconstructed transformed signal, wherein the reconstructed transformed signal is the digital signal.

The invention belongs to the technical field of water resource management, and particularly relates to a method for process adjustment and risk identification of operation of a water resource system of Internet of water. The method is characterized in that irrigation water demand information is provided for a regional multi-water-resource optimization allocation model based on real-time perceptual information, and real-time water demand is determined by a real-time water distribution decision-making model; a medium and long term runoff forecasting model is used for forecasting the runoff volume of a drainage basin in the future month by month; a downscaling climate model is used for providing input for a short and medium term hydrologic forecasting model; an underground water simulation forecasting model is used for regulating the level of underground water; a coupled forecasting multi-water-resource optimal dispatching model is combined with all the information to achieve combined dispatching of multiple water resources; a multi-water-resource dispatching model provides a day-by-day runoff water distribution decision, and water flow transportation is achieved through a water resource transportation automatic control unit so that precise distribution can be achieved. The method can be widely applied to drainage basin (region) water resource management, especially efficient utilization of water resources in irrigated areas. Implementation steps are clear, and projects are easy to realize.

The invention discloses a power distribution network measurement data missing reconstruction method based on generative adversarial and double semantic perception, and belongs to the technical field of electric power big data processing. According to the method, a novel double semantic perception missing reconstruction constraint is formed by combination of the contextual information, the generateperceptual information and the reconstruct perceptual information by means of actively extracting data characteristics and the spatio-temporal distribution characteristics by a model based on the concept of game countermeasure of a generative adversarial network, and the data with highest similarity to the to-be-reconstructed data is found to realize the measurement data missing reconstruction. The method disclosed by the invention is completely based on data driving, and overcomes the limitation in multiple aspects of adaptively, algorithm efficiency and accuracy in establishing a mathematical reconstruction model based on a service mechanism; by adoption of the method, distribution hypothesis and characteristic explicit modeling of data can be carried out by needing a large amount of prior knowledge in a traditional missing reconstruction process are avoided; and the defects of low convergence speed, unstable training and the like of the traditional GAN are overcome, and the methodhas relatively high data missing reconstruction precision.