99 results about "Visual cognition" patented technology

The invention discloses a semantic image restoration method based on a DenseNet generative adversarial network. The method comprises the following steps of preprocessing collected images, and constructing a training and testing data set; constructing a DenseNet generative adversarial network; training a DenseNet generation adversarial network stage; and finally, realizing repair processing of thedefect image by using the trained network. Under the framework of the generative adversarial network, the DenseNet structure is introduced, a new loss function is constructed to optimize the network,the gradient disappearance is reduced, network parameters are reduced, meanwhile, transmission and utilization of features are improved, and the similarity and visual effect of large-area semantic information missing image restoration are improved and improved. Examples show that face image restoration with serious defect information can be achieved, and compared with other existing methods, the restoration results better conform to visual cognition.

The invention discloses a face image restoration method based on a generation antagonism network. The method comprises the following steps: a face data set is preprocessed, and a face image with a specific size is obtained by face recognition of the collected image; In the training phase, the collected face images are used as dataset to train the generating network and discriminant network, aimingat obtaining more realistic images through the generating network. In order to solve the problems of instability of training and mode collapse in the network, the least square loss is used as the loss function of discriminant network. In the repairing phase, a special mask is automatically added to the original image to simulate the real missing area, and the masked face image is input into the optimized depth convolution to generate an antagonistic network. The relevant random parameters are obtained through context loss and two antagonistic losses, and the repairing information is obtainedthrough the generated network. The invention can not only solve the face image repairing with serious defective information, but also generate a face repairing image which is more consistent with visual cognition.

The invention provides an image semantic retrieving method based on a visual attention mechanism model, which is driven by data completely, thus understanding the semantics of images from an angle of a user as far as possible under the condition of no need to increase the interactive burden of the user, and being close to the perception of the user so as to improve the retrieving performance. The image semantic retrieving method has the advantages that: (1) a visual attention mechanism theory in a visual cognition theory is introduced into image retrieve; (2) the method is a completely bottom-up retrieve mode, thus having no need of user burden brought by user feedback; and (3) obvious edge information and obvious regional information in images are simultaneously considered, the mode of retrieval integration is realized, and the performance of image retrieval is improved.

The invention discloses a visual computing-based optical field imaging device and method. The visual computing-based optical field imaging device comprises an optical imaging system, an integrated near-infrared light source, a data transmission module, a high-capacity cache unit, a human-machine interaction device, a logic control unit and a processing unit. The invention provides an optical field imaging device based on a computing and imaging interactive mutual-beneficial mode; and with optical field imaging as the leading and deep perception and high-dynamic range imaging as the assistance, visual perception intelligent and visual cognition precision are realized, novel visual information with characteristics of large depth-of-field, wide dynamic range, actual three dimension, high resolution and capability of collecting and editing is obtained, and accuracy and robustness of a visual computing task are improved through data innovation of a visual perception source; and the optical field imaging device is widely applied to the fields of internet of things, security monitoring and control, biological recognition, intelligent transportation system, aerial remote sensing, digital medical treatment, animation media and the like.

The invention discloses a transmission line malfunction visualized report method and system based on a Web and a GIS. The system comprises a web server side (1), a switch (2) and a client side (3). The web server side (1) is used for acquiring transmission line malfunction information, locating a malfunction to a specific tower, and providing Web services by combining a satellite map. The switch (2) is used for enabling the web server side (1) and the client side (3) to be connected. The client side (3) is used for visualized displaying of the transmission line malfunction. After electric transmission lines of a power grid break down, the system is triggered to work, the Web service side locates the malfunction tower position and generates an XML file after malfunction information computational analysis, and provides Web services to the client side (3) to carry out visualized displaying of the malfunction information. According to the transmission line malfunction visualized report method and system based on the Web and the GIS, the transmission line malfunction information is displayed visually in real time, the visual cognition degree of power transmission network malfunctions is improved, the capacities that power enterprise personnel display important information in a large amount of power system data and monitor the states of the power grid can be improved, and the reliability of the system is guaranteed.

The invention describes a lighting system apparatus intended to increase safety during operation of mainly large or lengthy vehicles and combination vehicles in darkness and poor visibility. The lighting system is comprised of a single or plurality of light sources designed for vehicular use and housed in a durable thermally conductive material having a lens through which light is projected. Said light source housings are attached to the vehicle whereby, when actuated by a controller, sufficient illumination is directed onto the specific areas on the vehicle(s) and ground surface peripheral to said vehicle or combination of vehicles at one or more areas along the sides and rear or trailing portions to the extent that the driver can more safely control said vehicle(s) because of increased visual cognition of the aforementioned areas via the rear-view mirrors. Persons proximate are also more aware of said vehicle(s) position and pathway by means of said illumination and can more readily avoid dangerous contact.

The invention provides a computerized assessment system, as well as a method, that can be used for diagnosing driving skills in a driver of the class of vehicle drivers having impaired abilities. The system utilizes a) at least one prerecorded audio/visual training session capable of diagnosing the visual cognition, visual memory and visual recall abilities of a motor vehicle driver, where the training session comprises interactive driving simulations presented through four active visual zones; b) computerized means for digitally assessing driver actions in response to simulated driving situations presented by the interactive driving simulations; c) a database that records the driver actions; and d) a computer program capable of developing a diagnostic assessment of the visual cognition, visual memory and visual recall abilities of the driver.

The invention discloses a bird vision cognition learning and training system which comprises a host computer control system, a slavery computer control system and a training box, wherein the host computer control system consists of a PC (personal computer), a camera and a liquid crystal display screen; the video signal output end of the camera is connected with the video signal input end of the PC; the video signal output end of the PC is connected with the video signal input end of the liquid crystal display screen; the slavery computer control system consists of a single chip microcomputer, an awarding unit, a punishment unit and a behavior feedback unit; the output control interface of the single chip computer is connected with input control interfaces of the awarding unit and the punishment unit separately; a first communication interface of the single chip microcomputer is in communication connection with the PC; a second communication interface of the single chip microcomputer is in communication connection with the feedback unit. On the basis of physiological needs of birds on food after food control, the birds are fed through the awarding unit after the birds have correct behaviors, and the feeding quantity can be adjusted through opening and closing time of an electromagnet, thus being easy to control.

The invention discloses a rolling bearing variable-work-condition fault diagnosis method based on visual cognition, and relates to a rolling bearing variable-work-condition fault diagnosis technology. The method comprises the following steps of converting rolling bearing vibration signals under the variable work conditions into a two-dimensional image by using a recurrence plot technology; performing feature extraction on the two-dimensional image by utilizing an SURF (speed up robust features) algorithm to obtain the vision invariability high-dimension fault feature vector; performing dimension reduction processing on the high-dimension feature vector by using an equal-distance mapping Isomap algorithm to obtain the low-dimension stable feature vector; using an SVD (singular value decomposition) algorithm for extracting the feature matrix singular value built by the low-dimension stable feature vector to form the final feature vector; performing fault classification on the final feature vector by using the trained classifier; performing fault diagnosis on the rolling bearing under the variable work conditions. The invention provides a novel solution for the rolling bearing fault diagnosis.

The invention belongs to the technical field of image processing, and particularly relates to a method for extracting primary colors of a painting work image. The method comprises the following steps: 1, color clustering, to be specific, inputting the painting work image, and selecting 15 colors; 2, factor quantification, to be specific, analyzing area factors, purity factors and comparison factors of the 15 colors; 3, color sequencing, to be specific, grading the three types of factors in the step 2 to obtain grades of the 15 colors; 4, color selection, to be specific, selecting 5 colors according to the grade sequence and the selection rule in the step 3. The method disclosed by the invention has the benefits that the primary accurate colors of the painting work image can be obtained, so that the primary colors instruct image coloring and image color transmission to achieve a better effect. By the adoption of the method, a painting process of a person is fully considered, and quantification is realized, so that the primary colors of the painting work image conforming to human visual cognition are obtained. The method is qualitatively improved in the result quality aspect.

The invention provides an overall image information synthetic method driven by a visual cognition model, which comprises the following steps: creating a image significance visual cognition model, and defining a column width selection driving energy function for the overall image information synthesis; structuring an overall image information composite image model, defining a node and computing the connecting side weight of the node; adopting the Dijkstra algorithm to search in the overall image information composite image model to enable the overall composite image significance visual cognition difference to reach the minimum clipping path; and selecting certain pixel column width in each frame of image in intensive video sequence images according to the minimum clipping path order, arranging the selected pixel column width according to sequence code, and synthesizing the pixel column width into overall composite image. According to the method, the function of visual cognition model of people on the overall scene picture synthesis can be fully expressed, synthesis flaw caused by multi-dimension mobile interference can be reasonably avoided, and key contents of wide large-scale scene can be effectively repeated.

The invention discloses an ocean distributed target detection method based on collective evolution of agents, relating to the ocean target detection technology. The method comprises the steps of utilizing a synthetic aperture radar image, selecting an ocean background image in advance according to the ocean conditions of the ocean areas and computing the average gray distribution curve and dissimilarity degree distribution as the templates to establish a database according to the radar parameters. For the image areas to be detected, the radar parameters are used for retrieving the corresponding templates and the false-alarm probability is given to obtain the dissimilarity degree threshold of the gray distribution curve. If the dissimilarity degree is more than the threshold, the point is the target, and if the dissimilarity degree is less than the threshold, the point is the background. Upper and lower agents are designed according to the visual cognition process of human eyes. The lower agent carries out preliminary sensing and the upper agent computes the basic characteristic parameters of the distributed targets based on sensing, extracts information and carries out tendency association and combination. The upper and lower agents complete final target detection through collective cooperation. The method is fast and accurate in target detection.

The invention discloses a visual target active attention training system for sober rats/mice. The visual target active attention training system comprises a master control unit, a behavior restricting high table, a visual stimulation display unit, an infrared eye movement monitoring unit, a basic controller, a water feeding rewarding unit and a video monitoring unit. The visual target active attention training system has the advantages that active attention of the tested animals to visual targets can be effectively improved, the conditioned reflex time of the tested rats/mice from generating the attention to the visual targets to behavior feedback is shortened, and the duration of the active attention of the tested rats/mice to the visual targets is prolonged in experimental procedures; the visual target active attention training system supports various visual cognition experimental paradigms, and is easy to extent and high in universality; the visual target active attention training system has important application value and high experimental demands in research fields of coding of neurons of vision systems, brain cognition functions, drug evaluation, plasticity of neural networks and the like.

The invention provides a vehicle-mounted head rising display system and a user interface projection display method thereof in order to solve the problem that due to the fact that an image of an existing vehicle-mounted head rising display system is too dark, display content of a projected user interface can be hardly distinguished, or due to the fact that the image is too bright, discomfort is generated. The user interface projection display method comprises the steps that environment brightness is detected, wherein a photoreceptor is adopted for detecting the environment brightness of a car and transmits the environment brightness to a microcontrol unit in the vehicle-mounted head rising display system; user interface projection is displayed, wherein after the microcontrol unit acquires the environment brightness, the environment brightness is compared with preset brightness, when the environment brightness is larger than or equal to the preset brightness, the high-visual-cognition user interface projection is selected to be displayed, and when the environment brightness is smaller than the preset brightness, the mild and comfortable user interface projection is selected to be displayed. According to the method, the clear degree of a user interface and the comfort of human eyes can be comprehensively considered according to different environment brightnesses, and the high-visual-cognition comfortable user interface is automatically switched.

A visual cognition system immersed in a medium with object and the system is also an object. The system includes means for conveying energy, which include one or more dispersive elements. The system includes means for sensing energy. The means for sensing include a plurality of detectors. The system includes means for modeling sensed energy, thereby creating a sensed energy model. The sensed energy model represents the sensed energy at a plurality of frequency bands, a plurality of polarization states, a plurality of positions and a plurality of times, using the sensed data. The system includes means for modeling a scene, thereby creating a scene model. The scene model represents the scene in three-dimensional space. The means for modeling a scene uses the sensed energy model from a plurality of directions at a plurality of times.

The invention discloses a product preference image recognition system and method of under a visual cognition neural mechanism. The product preference image recognition system comprises a remote measuring type eye tracker, a computer B, a computer A, a computer C and an electroencephalograph, wherein the remote measuring type eye tracker and the electroencephalograph are connected to the computer Band the computer C respectively; the computer B and the computer C are connected to the computer A respectively; the computer A is used for storing an observation stimulation material of a product tobe detected and analyzing a collected material; the remote measuring type eye tracker and the electroencephalograph are used for collecting eye movement data and collecting electroencephalographic data respectively. According to the product preference image recognition system and method, disclosed by the invention, comprehensive analysis and match of the eye movement data and the electroencephalographic data can be carried out, a product preference image recognition is realized and the recognition method is more scientific and more accurate.

The invention discloses a force-directed segmented bone parallel coordinates plot clustering data bundling method. By adopting the innovative design of the bundling method, a linear layout after the bundling is improved, and a problem of a conventional parallel coordinates plot clustering data bundling method of visual cognition deviation of data distribution characteristics is solved.

The invention provides an experimental system for measuring brain load in multi-task visual cognition and a method. The system consists of an adjustable seat, a virtual vision interface display device and electroencephalogram signal acquiring and processing equipment, the adjustable seat and the virtual vision interface display device are used for simulating visual cognition tasks under various work conditions, the electroencephalogram signal acquiring and processing equipment is used for synchronously acquiring human electroencephalogram signals in a simulated visual cognition process, and acquisition and extraction of the electroencephalogram signals in a visual cognition scheme under the multiple tasks can be realized by the experimental system. The electroencephalogram signals of visual cognition under the different tasks are compared by means of analysis of electroencephalogram complexity, and the corresponding relationship between brain waves and brain activities is obtained, and accordingly brain load conditions in a visual cognition process can be judged.

A method and system for cooperative diversity visual cognition in a wireless sensor network is disclosed. The method and system are capable of solving distributed visual cognition tasks (for example, online simultaneous reconstruction of 3D models of a large area) by using multiple video streams and exploiting cooperative diversity video sensing information while ensuring an optimal tradeoff between energy consumption and video quality of images received from said multiple video streams.

The invention discloses a metaphorical map structure generation method considering hierarchical characteristics of semantic data. The method comprises a data preparation stage and a map construction stage, wherein the map construction stage comprises the steps of 1, constructing a metaphorical map framework; and 2, performing map finishing on the metaphorical map framework. Through the method, mapdisplay expression can be performed on the semantic data with the hierarchical relational characteristics, structural characteristics of the data are highlighted, data content is visually expressed,and data property characteristics are displayed; the visual cognition talent and familiarity on maps of a human are fully utilized to promote understanding and cognition of abstract data; and a new data visualization mode is provided, and by using the metaphorical map as a carrier, it is convenient to introduce map relevant technologies and methods to assist analysis of the abstract data without positioning characteristics.

The invention provides a traffic sign classification method and device. The traffic sign classification method comprises the steps of obtaining the visual cognition understanding time data of multipleexperimenters on each block of traffic signs to be classified; categorizing the traffic signs to be classified based on the visual cognition understanding time data. The traffic sign classification device is used for executing the above method. The invention is advantageous in that the features of the traffic sign layout and the visual cognition understanding time of drivers to the traffic signsare comprehensively taken into consideration, and the traffic signs are reasonably classified; the accuracy of the research of the traffic sign information threshold can be enhanced; accurate theory base is provided for traffic signs in road setting.

The invention belongs to the technical field of digital imaging, particularly relates to a ship intelligent navigation digital sand table system based on an electronic chart, and aims to solve the problem that a ship navigation environment of a specified sea area cannot be visually displayed in a three-dimensional space in the prior art. According to the invention, the digital sand table interaction interface and the three-dimensional digital sand table model are generated according to the electronic chart data and the target ship information data; instruction information sent by a user is received based on the digital sand table interaction interface, the digital sand table model is dynamically adjusted in real time according to the instruction information, and the three-dimensional digital sand table model is dynamically displayed through the virtual scene display unit. Visual cognition display is performed on the ship navigation environment of the designated sea area in the three-dimensional space so that the system has the characteristics of digitization and intellectualization; the digital sand table model is dynamically adjusted according to the instruction information data,the ship operation state is visually displayed from all directions, and interestingness and interactivity are improved.

The invention discloses a pattern design method based on shape grammar and a neural network. The pattern design method comprises the following steps: step 1, carrying out pattern parameterization based on shape grammar: 1) feature analysis and extraction; 2) rule definition and coding method construction; 3) rule reuse and parameter evolution generation design; 4) detecting and visualizing of a rule reuse result; step 2, constructing a user visual cognition image space through acquisition of a pattern composition sample and quantification of a visual cognition image; and step 3, constructing aneural network-based design parameter and style imagination relationship model, optimizing the neural network relationship model by using a genetic algorithm to obtain an optimal pattern design parameter, and completing pattern design. The method has the advantages that the optimal design parameter solution meeting the imagination value can be provided, and the style imagination requirements of consumers are met.