2006 results about "Goal recognition" patented technology

A method for radiation therapy with target recognition has a first target identification system for obtaining first target characteristics within a patient's body. A second target identification system obtains second target characteristics within the body aided by the first target characteristics. A computation means for calculation of three-dimensional coordinates of the target region with respect to a three-dimensional radiotherapy system uses the second target characteristics. Irradiation means for radiotherapy mode adaptation is used in response to the second target characteristics and the calculation of three-dimensional coordinates of the target region.

The invention provides an early warning method for preventing vehicle collision and a device. The method includes steps of acquiring video image information of the front of a vehicle, and obtaining first characteristic information of an obstacle target of the front of the vehicle according to the video image information; acquiring radar measurement information of the front of the vehicle, and determining second characteristic information of the obstacle target of the front of the vehicle according to the radar measurement information; fusing characteristics of the first characteristic information and the second characteristic information so as to determine final characteristic information of the obstacle target of the front of the vehicle; estimating collision risks to the obstacle target according to the final characteristic information, and realizing early warning for a driver according to a collision risk estimation result. The obstacle target of the front of the vehicle and state information of the obstacle target are identified by means of fusing information, which are acquired by double cameras and a radar device, of the front of the vehicle, target identification precision is improved, and a collision preventive alarm function of the vehicle can be well realized.

A three dimensional shape correlation computer software program which uses laser radar data for target identification. The correlation program obtains a scan of laser radar data of a target from a Ladar sensor. The data includes a plurality of X,Y,Z coordinate detection points for the target. The software simulates the sensor scan using a 3D wire-frame model of the target. An X,Y,Z coordinate location is computed for every point in the computer model of the target. The software compares the X,Y,Z coordinate detection points for the target with the X,Y,Z coordinate points for the computer model to determine if the points match. When there is a match a target identification is declared.

The invention relates to a convolutional neural network-based unmanned air vehicle to-ground specific target recognition method. The method comprises the following steps of: (1) labeling to-ground specific target data sets acquired by an unmanned air vehicle according to categories, and dividing the to-ground specific target data sets into training sets, verification sets and test sets according to proportions; (2) setting convolutional neural network model training parameters, starting training and obtaining an optimal solution of a convolutional neural network model according to the trainingcondition; (3) changing a depth of the convolutional neural network model, restarting the training in the step (2) to obtain an optimal convolutional neural network model; (4) testing the test set soas to obtain recognition correctness; and (5) applying convolutional neural network model parameters, correctness of which satisfies requirements, to a practical scene of an unmanned air vehicle to-ground specific target, so as to recognize an image target acquired by the unmanned aerial vehicle.

The invention relates to a scene and target identification method and device based on multi-task learning. The method comprises the steps that pictures containing different scenes and targets are collected as image sample data; the image sample data is subjected to manual label marking, and target class labels and scene class labels are obtained; a multi-layer convolutional neural network model is built, and network initialization is conducted; the image sample data and the corresponding target class labels are adopted for pre-training the built model till convergence, and a target identification model is obtained; based on a multi-task learning technology, network branches are added into a specific layer of the target identification model, random initialization is conducted, and a multi-task network is obtained; the image sample data and the corresponding scene class labels and target class labels are adopted for e-training the multi-task network till convergence, and a multi-task learning model is obtained; new image data is input to the multi-task learning model, and classification results of scene and target identification of images are obtained. Accordingly, the single task identification precision is improved.

The invention discloses a binocular visible light camera and thermal infrared camera-based target identification method. The method comprises the steps of calibrating internal and external parametersof two cameras of a binocular visible light camera through a position relationship between an image collected by the binocular visible light camera and a pseudo-random array stereoscopic target in a world coordinate system, and obtaining a rotation and translation matrix position relationship, between world coordinate systems, of the two cameras; according to an image collected by a thermal infrared camera, calibrating internal and external parameters of the thermal infrared camera; calibrating a position relationship between the binocular visible light camera and the thermal infrared camera;performing binocular stereoscopic visual matching on the images collected by the two cameras of the binocular visible light camera by adopting a sift feature detection algorithm, and calculating a visible light binocular three-dimensional point cloud according to a matching result; performing information fusion on temperature information of the thermal infrared camera and the three-dimensional point cloud of the binocular visible light camera; and inputting an information fusion result to a trained deep neural network for performing target identification.

A collaborative engagement system comprises: at least two unmanned vehicles comprising an unmanned air vehicle including sensors configured to locate a target and an unmanned ground vehicle including sensors configured to locate and track a target; and a controller facilitating control of, and communication and exchange of data to and among the unmanned vehicles, the controller facilitating data exchange via a common protocol. The collaborative engagement system controls the unmanned vehicles to maintain line-of-sight between a predetermined target and at least one of the unmanned vehicles.

The invention provides a ship intelligent identification tracking method. For the ship intelligent identification tracking method, based on a deep learning algorithm based on computer vision, a basicclassification network structure and a multi-scale target prediction method in traditional deep learning are improved, and a Darknet network and a YOLOv3 algorithm are combined to track a ship and detect and identify the type of the ship in real time. According to the ship intelligent identification tracking method, the idea of a residual error network is introduced; a full convolution structure is adopted; the network depth is increased; the data feature learning capability is improved; and local feature interaction between the feature maps is achieved in a convolution kernel mode through a YOLOv3 algorithm, and matching and positioning of targets are conducted, and target area prediction and category prediction are integrated into a single neural network model on the basis, so that global information of the images is recognized as the targets. Experimental results show that compared with a traditional method, the algorithm provided by the invention not only has better real-time performance and accuracy, but also has better robustness for various environmental changes.

The invention discloses a target identification model training method, a target identification model training device, a target identification method, a target identification device and computing equipment, which belong to the technical field of computer vision. The target identification model training method comprises the steps of: inputting a plurality of local candidate regions selected for a training image into a target identification model, so as to obtain a preliminary result of classification of the plurality of local candidate regions output by the target identification model; performing local candidate region integration according to weak supervisory information and the preliminary result of classification of the plurality of local candidate regions; correcting parameters of the target identification model according to the preliminary result of classification of the plurality of local candidate regions and a result of local candidate region integration; and iteratively executing the training steps till a training result of the target identification model satisfies a predetermined convergence condition. The target identification model training method, the target identification model training device, the target identification method, the target identification device and the computing equipment can perform direct supervision of pixel level, can optimize a semantic segmentation model in an end-to-end manner, and can improve the result of target identification according to judgment of the local candidate regions.

The invention discloses a moving target analyzing and tracking method and system based on video monitoring. The moving target analyzing and tracking method comprises the following steps of: monitoring video acquisition, acquiring video streaming recorded by a monitoring camera; performing image preprocessing: primarily processing an image of the video streaming, and acquiring a processed image; performing target recognition: performing target recognition classification on each foreground object of the processed image, wherein the classified type of targets comprises persons, vehicles and objects; performing motion track analysis: analyzing the motion track of each target according to the setting of an alarm rule, marking a target of which the motion track is matched with the alarm rule as a suspected target, and giving out an alarm; and tracking the target: tracking the suspected target, and recording the actual motion track and the actual motion direction of the suspected target. According to the method, the alarm is automatically given aiming at an abnormal event, the possibility of missing report and error report is reduced, and the workload of security monitoring personnel is lightened.

The invention discloses a method for identifying objects in 3D point cloud data. 2D SIFT features are extended to a 3D scene, SIFT key points and a surface normal vector histogram are combined to achieve scale-invariant local feature extraction of 3D depth data, and the features are stable and reliable. A provided language model overcomes the shortcoming that a traditional visual word bag model is not accurate and is easily influenced by noise when using local features to describe global features, and the accuracy of target global feature description based on the local features is greatly improved. By means of the method, the model is accurate, and identification effect is accurate and reliable. The method can be applied to target identification in all outdoor complicated or simple scenes.

The invention discloses a system and a method for recognizing a remote sensing image target based on migration network learning, mainly solving the problems that the correct recognition rate for a remote sensing image with a label is relatively low when the number of data is less and the obtaining of the image label is difficult and needs high cost in the conventional methods. The whole system comprises an image characteristic extracting module, a migration network classifier learning system generating module and a migration network classifier learning system learning module, wherein the image characteristic extracting module is used for completing the characteristic extraction of the image; the migration network classifier learning system generating module is used for training input sample data by a network integrated learning algorithm introduced into migration learning to obtain a migration network classifier learning system; and the migration network classifier learning system learning module is used for completing the classification and the recognition of the characteristics of a new sample image. The invention has the advantage of the capability of utilizing other existing resources to improve the correct recognition rate of the remote sensing image target without collecting data again and can be used for the target recognition of the remote sensing image.

The invention discloses a ground-air heterogeneous multi-robot search and rescue system, which comprises air flying robots, a plurality of ground rescue robots, an image processing computer, an image acquisition card, a monitoring computer, search and rescue command personnel, a wireless data transmission radio, a wireless image transmission radio, obstacles, and objects to be rescued. The air flying robots are responsible for carrying out rapid and systematic large-area reconnaissance on the rescue site so as to more accurately judge the rescue site conditions, find out the positions of the obstacles or objects to be rescued, and help the search and rescue command personnel formulate detailed rescue plan. The ground rescue robot group, according to control instructions issued by the search and rescue command personnel, cooperatively executes the search and rescue work of the objects to be rescued at the rescue site. The robots in the system all adopt the control mode combining the autonomous intelligent control with remote control of the search and rescue command personnel; by the coordination of a plurality of ground-air robots with different structures, the system improves the reliability and accuracy of rescue site environmental perception and object recognition, reduces the search spread time and improves the rescue efficiency.

The invention discloses a radar one-dimensional range profile target recognition method based on a depth convolution neural network, includes the following steps: a data set is collected, the collected data is preprocessed, features are extracted from the preprocessed data, the HRRP signal is divided into two parts: low SNR and high SNR, A feature enhancement algorithm based on robust Boltzmann isconstructed, and a HRRP target recognition model based on convolution neural network and bidirectional loop neural network based on LSTM is constructed. The parameters of the network model are fine-tuned by using gradient descent algorithm, and an effective target recognition model is obtained. A radar HRRP automatic target recognition technology with small sample robustness and noise robustnessconstructed by the invention has strong engineering practicability, and a radar one-dimensional range profile target recognition model based on a convolution neural network and a cyclic neural networkis proposed from the aspects of feature extraction and the design of a classifier.

The invention discloses a vehicle front trafficability analyzing method based on a convolution nerve network. The method comprises the following steps: first, a vidicon arranged in the front of a vehicle is used for collecting a large number of actual vehicle traveling environment images; a Gamma rectification function is used for pre-processing the images; training of the convolution nerve network is conducted. According to the method, a nonlinear function superimposed Gamma rectification method is used for pre-processing the images, so that influence of light illumination of strong changes on identification of objects is avoided, and the image resolution ratio is improved. According to the method, a geometry normalization method is used, so that the resolution ratio difference caused by identifying the distance of an object distance vidicon is reduced. The convolution nerve network LeNet-5 adopted in the method can extract implicit expression characteristics with class distinguishing capacity and is simple in extracting process. The LeNet-5 is combined with a local receptive field, weight share and secondary sampling to ensure robustness of simple geometry deformation, reduce training parameters of the network, and simplify the structure of the network.

An object recognition ingestion system is presented. The object ingestion system captures image data of objects, possibly in an uncontrolled setting. The image data is analyzed to determine if one or more a priori know canonical shape objects match the object represented in the image data. The canonical shape object also includes one or more reference PoVs indicating perspectives from which to analyze objects having the corresponding shape. An object ingestion engine combines the canonical shape object along with the image data to create a model of the object. The engine generates a desirable set of model PoVs from the reference PoVs, and then generates recognition descriptors from each of the model PoVs. The descriptors, image data, model PoVs, or other contextually relevant information are combined into key frame bundles having sufficient information to allow other computing devices to recognize the object at a later time.

A system collaboratively and autonomously plans and controls a team of vehicles having subsystems within an environment. The system includes a mission management component, a communication component, a payload controller component, and an automatic target recognition component. The mission management component plans and executes a mission plan of the team and plans and executes tasks of the vehicles. The communication component plans communication and networking for the team. The communication component manages quality of service for the team. The communication component directs communication subsystems for the team and for the vehicles. The payload controller component directs and executes sensor subsystems for the team and for the vehicles. The automatic target recognition component processes and fuses information from the sensor subsystems and from the vehicles for use by the mission management component.

The invention discloses a target automatically recognizing and tracking method based on affine invariant points and optical flow calculation, which comprises the following steps: firstly, carrying out image pretreatment on a target image and video frames and extracting affine invariant feature points; then, carrying out feature point matching, eliminating mismatching points; determining the target recognition success when the feature point matching pairs reach certain number and affine conversion matrixes can be generated; then, utilizing the affine invariant points collected in the former step for feature optical flow calculation to realize the real-time target tracking; and immediately returning to the first step for carrying out the target recognition again if the tracking of middle targets fails. The feature point operator used by the invention belongs to an image local feature description operator which is based on the metric space and maintains the unchanged image zooming and rotation or even affine conversion. In addition, the adopted optical flow calculation method has the advantages of small calculation amount and high accuracy, and can realize the real-time tracking. The invention is widely applied to the fields of video monitoring, image searching, computer aided driving systems, robots and the like.

The invention relates to a target detection system and method based on self-adaption combined wave filtering and multilevel detection. The system includes a target detection module combing a moving target detection unit with an obvious target detection unit, a target identification module based on a convolutional neural network and a target tracking module based on combination decision and multi-channel image features; the target detection module, the target identification module and the target tracking module tightly cooperate with one another to constitute the stable and reliable target detection system together. System output includes detected candidate target position information, target classification information and position information of selected targets obtained by target tracking. The target detection system is achieved on a high-performance multi-core DSP chip and used for carrying out targeted optimization on the multi-core DSP chip, real-time target detection and target tracking are achieved, and a function of quickly identifying a target is achieved. The target detection system and method have the advantages of being high in practicability and feasibility and convenient to integrate into various solution schemes with target detection demands, and can achieve intelligent target detection, identification and tracking.

The invention relates to a target detection and positioning method based on a lightweight convolutional neural network, which belongs to the technical field of deep learning, and solves the problem that an existing method cannot meet the requirement of the real-time processing of an unmanned vehicle. The method comprises the steps of collecting the image data and the point cloud data in front of avehicle in real time; transmitting the image data to a target detection model, carrying out target identification, and obtaining the target information, wherein the target detection model adopts thelightweight convolutional neural network; and inputting the obtained target information and the point cloud data into the trained target positioning model, and carrying out target positioning to obtain the position information of the target relative to the vehicle. According to the method, the real-time detection and positioning of the static and dynamic targets are realized, so that the vehicle can sense the target information in real time, the obstacle avoidance processing is conducted on the target in time, the detection and recognition result has the higher accuracy, the method can be usedfor the complex scenes with a plurality of static and dynamic targets, and the real-time detection and positioning requirement of the automatic driving vehicle is met.

The invention discloses a suspicious target detection tracking and recognition method based on dual-camera cooperation, and belongs to the technical field of video image processing. The method comprises the steps that a panoramic surveillance camera is utilized for collecting a panoramic image, the improved Gaussian mixture modeling method is adopted for carrying out foreground detection, basic parameters of moving targets are extracted, a Kalman filter is utilized for estimating a movement locus of a specific target, the specific target is recognized according to velocity analysis, the dual-camera cooperation strategy is adopted, a feature tracking camera is controlled to carry out feature tracking on the moving targets, a suspicious target is locked, the face of the suspicious target is detected, face recognition is carried out, face data are compared with a database, and an alarm is given if abnormities exist. According to the suspicious target detection tracking and recognition method, the dual-camera cooperation tracking surveillance strategy is adopted, defects of a single surveillance camera on a specific scene are overcome, and the added face recognition function can assist workers in identifying the specific target to a greater degree; in addition, the tracking algorithm adopted in the method is good in real-time performance, target recognition and judgment standards are simple and reliable, and the operation process is fast and accurate.

An automatic speech recognition (ASR) system that includes a speech-response application and a speech recognition engine. The ASR system generates user prompts to elicit certain spoken input, and when the spoken input is recognized, the voice-response application performs an action. The recognition engine compares sounds in the input audio signal to phonemes in the acoustic model to identify candidate matching phonemes. A recognition confidence score is calculated for each candidate matching phoneme, and the confidence score is used to aid in the recognition of one or more possible matching phoneme sequences that appear to match the word in the speech-response application's grammar. A confidence score for each phoneme is evaluated against predefined confidence score criteria (eg, a discrimination score below a "low confidence" threshold), and the results of the evaluation are used to influence the selection of subsequent user prompts. One such system uses confidence scores to select cues for object recognition training - encouraging input to be recognized as phonemes with low confidence recognition scores. Another system selects prompts to block input of sounds that are not easily recognizable.

The invention discloses a significant object detection method based on sparse subspace clustering and low-order expression. The method comprises the steps of: 1, carrying out super pixel segmentation and clustering on an input image; 2, extracting the color, texture and edge characteristics of each super pixel in clusters, and constructing cluster characteristic matrixes; 3, ranking all super pixel characteristics according to the magnitude of color contrast, and constructing a dictionary; according to the dictionary, constructing a combined low-order expression model, solving the model and decomposing the characteristic matrixes of the clusters so as to obtain low-order expression coefficients, and calculating significant factors of the clusters; and 5, mapping the significant value of each cluster into the input image according the spatial position, and obtaining a significant map of the input image. According to the invention, the significant objects relatively large in size in the image can be completely and consistently detected, the noise in a background is inhibited, and the robustness of significant object detection of the image with the complex background is improved. The significant object detection method is applicable to image segmentation, object identification, image restoration and self-adaptive image compression.

The invention provides a visual support and match analysis system for a ping-pong match. The system comprises the following modules: an image acquiring and ping-pong ball target recognizing and positioning module, a KALMAN filter module, a track data fitter module, a characteristic analyzing module, a kinematic parameter learning machine module, a single path judging module, a three-dimensional virtual scene reappearing module, a match characteristic data storing module and a user interaction module. A set of system with friendly and complete information extraction and storage, user interaction support and capability of performing track recording well and extracting characteristic information on ball hit of an athlete is developed through real-time visual acquisition. The system can process data in real time and filter and record the processed data in ping-pong trainings and matches, automatically extracts ping-pong ball path characteristic, bring convenience to a judge to replay, is applied to automatic judging and television relaying in the ping-pong match, has a complete, effective and overall analyzing function after the match and can automatically extract and store the characteristic information in a match process and intuitively counts and displays ball throwing and ball winning path characteristics of the ping-pong athlete.

The invention discloses a method for countering a deception false target by utilizing a netted radar system, which mainly solves the problem that deception probability is high in the event of countering the deception false target only by utilizing target position information fusion. The method comprises the following steps of: (1), carrying out coordinate transformation on measurements of node radars, namely, taking various node radars as a polar coordinate system of a reference original point, and transforming to a uniform rectangular coordinate system of the netted radar system; (2), matching measurements through a nearest neighbour association method so as to obtain an association measurement sequence; (3), identifying true and false targets by utilizing target position information, and reserving the association measurement sequence passing fusion testing; (4), obtaining a practical speed vector set corresponding to the reserved association measurement sequence; and (5), carrying out identification of true and false targets by utilizing target speed information, and further reducing the deception probability of netted radar. The method disclosed by the invention effectively reduces the deception probability of the netted radar and can be used for the netted radar to effectively resist deception interference.

A small arms training target system including a portable, battery powered, rail guided, motor driven carriage, with stationary and moving targets connected thereto. A target-rotate control device operatively connects an electric motor and rotational arm assembly to rotate and position the target into and out of a field of view. The position is selectable by a remote control, pre-selected program, or when a sensor attached to the target is struck by a sensor. Additionally an obscuring medium is attached to the rotational arm, with a target, having on it an image of a weapon mounted behind the obscuring medium. The position of the obscuring medium is selectable to be in front of the image of a weapon, making the target a no-threat, or not in front of the target, making it a threat.

The invention discloses a multispectral remote sensing image terrain classification method based on deep and semi-supervised transfer learning. A training data set and kNN data are extracted according to ground truth; the training data set is divided into two parts to be trained respectively; a multispectral image to be classified is inputted, and two classification result images are obtained from two CNN models; two kNN nearest neighbor algorithm images are constructed according to the training samples; the tested data are extracted by using the two classification result images, and the data are classified by using the kNN nearest neighbor algorithm; the classification result images are updated; the training samples and the kNN training samples of cooperative training are updated; and two cooperative training CNN networks are trained again, and the points having the class label of the test data set are classified by using the trained model so that the class of partial pixel points in the test data set is obtained and compared with the real class label. The k nearest neighbor algorithm and the sample similarity are introduced so that deviation of cooperative training can be prevented, the classification accuracy in case of insufficient training samples can be enhanced and thus the method can be used for target recognition.

The invention discloses an image classification method based on hierarchical SIFT (scale-invariant feature transform) features and sparse coding. The method includes the implementation steps: (1) extracting 512-dimension scale unchanged SIFT features from each image in a data set according to 8-pixel step length and 32X32 pixel blocks; (2) applying a space maximization pool method to the SIFT features of each image block so that a 168-dimension vector y is obtained; (3) selecting several blocks from all 32X32 image blocks in the data set randomly and training a dictionary D by the aid of a K-singular value decomposition method; (4) as for the vectors y of all blocks in each image, performing sparse representation for the dictionary D; (5) applying the method in the step (2) for all sparse representations of each image so that feature representations of the whole image are obtained; and (6) inputting the feature representations of the images into a linear SVM (support vector machine) classifier so that classification results of the images are obtained. The image classification method has the advantages of capabilities of capturing local image structured information and removing image low-level feature redundancy and can be used for target identification.

The invention belongs to the technical field of network security, and particularly relates to a network attack target identification method and a network attack target identification system based on an attack graph, wherein the method comprises the following steps: modeling for a state migration process of an attacker in a network, acquiring a network attack graph model and all possible attack paths, and generating a network attack graph; mapping the network attack graph to a Markov chain, and constructing a state transition probability matrix which absorbs the Markov chain; and in combinationwith the state transition probability matrix, acquiring an expectancy for success probability matrix of attack intention of the attacker; through the expectancy for success probability matrix, finding out a state node corresponding to the maximum probability value, and completing attack target identification. With the method and the system provided by the invention, an average probability value of realizing different intentions of the attacker can be evaluated more objectively and accurately, a problem that the conventional method is limited by ideal cumulative probability when evaluating probability of occurrence of attacks is solved, computation complexity is low, operations are simple and convention to execute, and more reliable guidance is provided for assisting a security administrator to make a decision and improving network security performance.

Disclosed are image resource loading system and method, the system comprising a basic recording space for partitioning a game map into at least one cell and maintaining an object by unit of the cell, a loading target identification unit identifying a cell becoming a target for loading and an object associated with the cell in the basic recording space, in case that a loading event occurs, an order determination unit giving a loading order to the object associated with the cell in accordance with a predetermined determination criterion, and a processor unit loading the object by referring to the given loading order, wherein the order determination unit determines the loading order by considering the size of the object or whether the object is positioned within a predetermined range of the visual field.