119results about How to "Achieve goal tracking" patented technology

The invention discloses a probability hypothesis density multi-target tracking method based on a variational Bayesian approximation technology, and belongs to the technical field of guidance and intelligent information processing. The probability hypothesis density multi-target tracking method based on the variational Bayesian approximation technology mainly solves the problem that an existing random set filtering method can not achieved varied number multi-target tracking under an unknown quantity measurement noise environment. According to the method, the variational Bayesian approximation technology is introduced, posterior probability hypothesis density of target states and measurement noise covariance is estimated in a combination mode, a Gaussian mixture inverse gamma distribution recurrence closed solution is adopted, and thus the varied number multi-target tracking under the unknown quantity measurement noise environment is achieved. The probability hypothesis density multi-target tracking method based on the variational Bayesian has a good tracking effect and robustness, is capable of meeting the design demands on practical engineering systems and has good engineering application value.

The invention relates to the field of unmanned aerial vehicle target tracking and image processing, and discloses an unmanned aerial vehicle target tracking system based on machine vision and an ultra-wideband positioning technology. The target tracking system is composed of a ground control platform S1 and an unmanned aerial vehicle tracker S2. The ground control platform is composed of a piece of flight control software, a data transmission module, and a video display interface. The unmanned aerial vehicle tracker is composed of a microprocessor, an FPGA, a positioning module, an airborne sensor, an intelligent vision module, a flight control module, and a data transmission module. The ground control platform sends a target tracking command. After receiving the target tracking command, the unmanned aerial vehicle tracker performs algorithm processing on an image acquired by the intelligent vision module and automatically identifies the position of a target in the image, and meanwhile, the unmanned aerial vehicle tracker reads data of the positioning module and the airborne sensor, plans a flight route according to a gesture guiding and adjusting algorithm, and sends a target moving image to the ground control platform to realize automatic visual tracking of the moving target.

The invention discloses a vehicle detection method based on laser and vision fusion. The method comprises the following steps of 1) acquiring target detection information for an input image and laserpoint cloud; 2) performing optimal matching on the images of the front frame and the rear frame and the point cloud detection frame, and establishing a tracking sequence of an image and point cloud detection target; 3) fusing the tracking sequences of the image and the detection frame thereof and the tracking sequences of the point cloud and the detection frame thereof; 4) classifying all the target detection boxes, outputting a fusion list, and outputting a fusion result; and 5) obtaining the accurate position of the surrounding vehicle relative to the vehicle in the current frame, reading the next frame of image and the point cloud data, circulating the steps 1) to 5), and outputting a fusion detection result. According to the method, on the basis of point cloud and image target detection, the detection result is subjected to information tracking, the detection result is optimally matched, and the fusion result is preferentially input into the final fusion list, so that compared witha single sensor target detection method, the target detection precision is improved, and the false detection rate is reduced.

The invention relates to an online target tracking method and an online target tracking system based on multiple cameras, solves a synergy problem and a timeliness problem among the multiple cameras by combining a preset calibration synchronization scheme with a self-learning tracking method, and provides the corresponding method. The preset calibration synchronization scheme uses a target projection matrix calculation method matched with feature points, and synchronizes shared information of the multiple cameras of an overlapping region. The self-learning tracking method records a presentation model of a monitored target, performs detection tracking by synchronizing a center server to the neighbor camera, and thereby achieves conductive information synchronization effects.

The invention discloses a heterogeneous unmanned aerial vehicle cluster target tracking system and method based on biosocial force. The target tracking system includes a cluster hardware system architecture, a cluster software system architecture, a cluster communication system architecture and a cluster flight management and control system. The method comprises the following steps that 1, modeling of an unmanned aerial vehicle state is carried out; 2, a consistency protocol is designed; 3, unmanned aerial vehicle control instructions are designed based on a phase difference consistency algorithm; 4, trajectory tracking based on non-linear guidance is carried out; 5, a heterogeneous unmanned aerial vehicle cluster system based on the biosocial force is described; and 6, heterogeneous unmanned aerial vehicle cluster target tracking based on the biosocial force is carried out. The heterogeneous unmanned aerial vehicle cluster target tracking system and method based on the biosocial forcehas the advantages that the heterogeneous unmanned aerial vehicle cluster target tracking is realized, the speed of controlling an unmanned aerial vehicle to gradually converge to an expected path isincreased, and the system of the whole target tracking system is complete, the functions are perfect, and the verification of targets in different task scenes can be realized.

The invention discloses a moving object relay tracing algorithm of multiple PTZ (pan / tilt / zoom) cameras. The moving object relay tracing algorithm is characterized in that the moving object relay tracing algorithm is carried out according to the following steps: 1. estimating inner parameter matrixes of the PTZ cameras by adopting a camera self-calibration method; 2. setting a view cutting line between adjacent PTZ cameras; 3. using Logistics regression model as a classification function, and combining with a mean value drifting algorithm and realizing the target tracking; 4. continuously adjusting angles of the PTZ cameras in the course of tracking, so that the target is always located in the center zone of the PTZ camera view; 5. when the target exceeds the view cutting line of the PTZ camera at present and enters the monitoring view of the adjacent PTZ camera, calculating the coordinate of the target in the adjacent PTZ camera view, and transferring the adjacent PTZ cameras to track the target, and rotating the original PTZ camera to return the preset position. The moving object relay tracing algorithm can accurately control the camera rotation, and perform stable tracking for a long time on the target; and thereby, the complete historical movement information of the target can be obtained.

The invention relates to an unmanned aerial vehicle maneuvering target tracking method based on DDPG transfer learning, and the unmanned aerial vehicle maneuvering target tracking method carrying outtask decomposition, initializes an environment state, neural network parameters and other hyper-parameters, and carries out the training of a neural network. At the beginning of each round, the unmanned aerial vehicle executes an action to change the speed and the course angle, to obtain a new state, stores the experience of each round in an experience pool to serve as a learning sample, and continuously iterates and updates parameters of the neural network. And when the training is completed, the neural network parameters trained by the sub-tasks are stored, and are migrated to the unmanned aerial vehicle maneuvering target tracking network in the next task scene until the final task is completed.

The invention discloses an unmanned aerial vehicle target tracking method, which comprises the following steps: (1) obtaining a left-eye image and a right-eye image by using a binocular camera image acquisition device; (2) calculating the position coordinates of the output UAV in the world coordinate system by the visual SLAM algorithm; (3) detecting the target in the panoramic image composed of the left-eye and the right-eye images, and calculating the three-dimensional coordinates of the output tracking target in the camera coordinate system; (4) taking the real-time position of the UAV in the world coordinate system and the real-time position of the tracking target in the camera coordinate system as the input of the speed control algorithm, and calculating the desired speed as the inputof the flight controller of the UAV to control the flight parameters of the UAV and realizing the target tracking. The method performs autonomous tracking through visual positioning while detecting targets, and is particularly suitable for tracking tasks in weak GPS or GPS-free environments.

The invention discloses a target tracking method based on triple twin hash network learning, and relates to the technical field of computer vision, target tracking and deep learning. According to themethod, firstly, a triple twin hash network is constructed, and the network is composed of a data input layer, a convolution feature extraction layer and a hash coding layer. In the initial training process of the network, a training data set and a random gradient descent back propagation algorithm are used for training the triple twinning Hash network, and after training is completed, the initialcapacity of target positioning can be obtained through the network. In the tracking process, firstly, an input image passes through a triple twin region recommendation network to obtain correspondingcandidate frames, then the candidate frames are input into a triple twin Hash network to be subjected to forward processing, the similarity between each candidate frame and a query sample is calculated, the candidate frame with the highest similarity is selected as a tracking target object, and therefore target tracking is achieved.

The embodiment of the invention discloses a target tracking method, which comprises the steps of using a presetting algorithm to extract the corner feature of a reference image to obtain the first feature point set of the reference image, removing abnormal points which exceed the range of images to be matched from the first feature point set to obtain a second feature point set, matching the second feature point set with the images to be matched and finishing the target tracking of the images to be matched according to matching results. The embodiment of the invention additionally discloses a target tracking device. By using the target tracking method and the target tracking device, the extracted corner feature has good identifiability and stability, the matching speed is greatly improved, the feature point set of the reference image is optimized, the corners which exceed the range are removed, the problem that the matching cannot be realized due to a reason that the feature points exceed the range in the prior art is solved and the matching reliability is improved.

The invention relates to an object tracking method for an intensive scene based on multi-module sparse projection. The object characteristic is characterized by a sparse projection method; and for solving the serious mutual shield problem in an intensive scene, a reconstruction matrix based on a multi-module core color histogram is designed and further a corresponding object matching and updating algorithm is designed. According to the object tracking method, the automatic tracking of objects in the people stream intensive scene in a public place is realized; and meanwhile, the solution to the problem of serious mutual shield in the intensive scene is provided.

The invention discloses a radar detection system and method for low-altitude multi-target classification and identification. The radar detection system for low-altitude multi-target classification andidentification includes a waveform generator, an antenna unit, a reception unit and a signal processing unit, wherein the waveform generator is used for generating detection wave beams in which the energy is concentrated below the specified threshold according to the low-altitude area to be detected; the antenna unit is used for transmitting the detection wave beams output from the waveform generator and receiving a target echo signal; the reception unit is used for performing down-conversion on the target echo signal received by the antenna unit to become an intermediate frequency signal andoutput the intermediate frequency signal; and the signal processing unit is used for acquiring the positional information of the target according to the intermediate frequency signal output from thereception unit and outputting the identified target type. The radar detection method for low-altitude multi-target classification and identification is to realize low-altitude multi-target classification and identification. The radar detection system and method low-altitude multi-target classification and identification can realize real-time detection and classification and identification of low-altitude multiple targets, and have the advantages of high identification efficiency, high accuracy and high flexibility.

The invention provides an anti-unmanned aerial vehicle detection tracking interference system and a photoelectric tracking system working method. The anti-unmanned aerial vehicle detection tracking interference system comprises a radar, a photoelectric tracking system, an unmanned aerial vehicle interference unit and a holder; the photoelectric tracking system comprises a motion detection module,a correlation filtering target tracking module, a deep learning target detection module and a deep learning target tracking module; the radar is in communication connection with the photoelectric tracking system; and the photoelectric tracking system is in communication connection with the holder. According to the anti-unmanned aerial vehicle detection tracking interference system, when target distance is farther, the deep learning target detection module cannot extract target characteristics, and target detection is carried out by using the motion detection module; when the target distance isfarther, under the condition that the deep learning target tracking module cannot extract target characteristics, target tracking is carried out by using the correlation filtering target tracking module; and the problem that the deep learning target tracking module cannot provide degree of confidence is solved by using data of the correlation filtering target tracking module.

The invention discloses a target tracking system based on the cooperation of an UAV and an unmanned vehicle. The target tracking system includes an UAV, a workstation and an unmanned vehicle, whereinthe UAV includes a camera, an image transmission module and a control signal receiver. The camera transmits a captured image with position and feature information to a ground signal receiver via the image transmission module. After receiving an image captured by the camera on the UAV, the workstation searches and accurately positions a target object and an obstacle. A signal transmission module transmits the position information of the target object and the obstacle to the onboard computer of the unmanned vehicle. The onboard computer designs the driving route of the unmanned vehicle accordingto the position information of the target object and obstacle, and controls the vehicle to advance to the target object to complete the target tracking. By means of the cooperation of the UAV and theunmanned vehicle, the target tracking system improves the reliability, the accuracy, and the work efficiency of target tracking.

The invention discloses a land electronic fence monitoring system. An object throwing detector (1) and a vibration optical fiber detector (2) send signals to a CAN (Controller Area Network) converter (5) and a sensing cable system processing main machine (7), video streams of a common video monitoring device (3) and an intelligent video monitoring device (4) are uploaded to a video forwarding module (14) and a video storing module (15) through a video coder (6) and an intelligent video processor (8); a communication control module (11) receives the signals sent by an object throwing detection management server (9), the sensing cable system processing main machine (7) and an intelligent video server (10), and forwards the signals to a central management module (12); a resource request module (13) feeds back information and sending the fed back information to the video forwarding module (14) after receiving a command of a comprehensive display control module (16); and the video streams are decoded by a decoder (17) and then sent to an analog video matrix (18). The land electronic fence monitoring system has a perfect function and stable performance.

The invention discloses a method for realizing multi-target tracking by using video segmentation and particle filter. The method comprises the steps of establishment of a system model, establishment of a target motion model and a color model, video segmentation and the like. The method realizes the multi-target tracking and greatly increases the tracking speed and precision by combining the respective advantages of the video segmentation and the particle filter and realizes the multi-target motion tracking under a shielding condition by fully utilizing the correlation degree between the measurement and the target.

The invention relates to a target tracking method. The target tracking method comprises the steps of performing target detection at a static state of equipment; when a target is detected to appear in a monitoring picture, performing positioning on the target; predicting a moving direction of the target according to a movement track generated by the target; controlling the equipment to rotate according to the moving direction of the target when the target is detected to have a trend of leaving the field of view of a camera; and tracking the target by adopting a dynamic background modeling mode at a rotating state of the equipment. According to the invention, the amount of calculation is reduced, thus the hardware cost can be saved, and continuous tracking for the target under rotation of the monitoring equipment is realized.

The present invention belongs to the computer vision field and proposes a convolutional neural network regression model-based visual tracking method and device. The invention aims to solve the problem that a target tracking process is divided into two independent steps of component matching and target positioning and cannot infer the location of a target directly through components. The method comprises the following steps that: S1, an image block is sampled according to a given target to be tracked at the initial frame of visual tracking, the image block is divided into a plurality of components; S2, a pre-constructed convolutional neural network regression model is trained through using a random gradient descent method; and S3, at the follow-up frames of visual tracking, a search area is constructed based on the position of the target to be tracked in the last frame, and the position of the target to be tracked in a current frame is obtained through the trained convolutional neural network regression model. According to the method and device of the invention, the components are fully combined with the positioning of the target, and therefore, better robustness can be realized.

The embodiment of the invention provides a video monitoring method and a video monitoring server. The video monitoring method and the video monitoring server are used for achieving target tracking among multiple monitoring devices, and the matching accuracy during target tracking is improved. The method in the embodiment includes the steps that when a first target leaves the scope of a first monitoring device, the video monitoring server obtains a preset motion track of the first target according to first target data transmitted by the first monitoring device; the video monitoring server obtains a smooth motion track of a second target according to received second target data transmitted by the second monitoring device; the video monitoring server judges whether any one of the smooth motion track of the second target and the preset motion track of the first target is matched or not; if any one of the smooth motion track of the second target and the preset motion track of the first target is matched, the video monitoring server determines the second target as the first target. The embodiment of the invention further provides the video monitoring server.

The invention discloses a small low-flight target visual detection tracking system and a method thereof. The system comprises a video data input unit, a video preprocessing unit, a training data construction unit, a detection model training unit, a target comparison screening unit, a detection correction unit, a reference frame initialization unit, a sample library dynamic construction unit, an online learning unit, a position refinement unit, a decision control unit and a tracking result output unit. The method comprises the following steps: constructing a target detection network, and comparing and screening targets; carrying out target tracking online learning; and dynamically constructing a classifier training sample library, and performing target tracking position refinement. The system and the method have the following advantages: the tracking drift condition of the tracking target caused by factors such as shielding, scale change and illumination can be effectively relieved, androbust target tracking can be realized; the capability of updating reference frame features in time according to target changes is achieved; and meanwhile, error tracking caused by updating the reference frame features can be avoided by introducing a feature point matching algorithm.

The present invention discloses a real-time target tracking method based on multi-feature discriminative learning. The method comprises the steps of: 1) acquiring a gray-scale video frame in a video,and describing a brightness attribute of a tracking target by using a Cross-bin distribution field feature; 2) using the enhanced gradient histogram feature EHOG to carry out modeling on texture diversity of the tracking target; 3) extracting the color feature CN to maintain color consistency through a color video frame in the video; 4) projecting dimensional features obtained in the steps 1), 2),and 3) into the high dimensional feature space through the Hilbert space mapping to obtain the inner product mapping; and 5) placing an obtained confidence map in the CSK framework to track, findingout a tracking target location, and then updating the template to carry out target tracking. The method disclosed by the present invention can effectively solve the problems such as light change, background interference, occlusion, low real-time performance and the like existing in target tracking.

The invention discloses an extended target tracking method based on variational Bayesian expectation maximization (VBEM) and mainly solves the problem that tracking performance of a target is weakened dramatically under the condition that measurement noise covariance is unknown in the conventional extended target tracking field. The extended target tracking method includes firstly predicting relevant parameters of Gaussian inverse gamma components in joint probability hypothesis density of a target state and the measurement noise covariance; updating the parameters of the Gaussian inverse gamma components; finally acquiring the extended target state and the number by construction and combination. It is proved by simulation experiment that multiple extended targets can be well tracked under the unknown number and the unknown measurement noise covariance, and the extended target tracking method is high in tracking accuracy and can be used for tracking aircrafts and submarine targets.

The invention relates to a visual identification system applied to an unmanned aerial vehicle for target tracking and locking. The system comprises a ground control platform and an unmanned aerial vehicle tracker, wherein the ground control platform comprises flight control software, a data transmission module and a video display interface; and the unmanned aerial vehicle tracker comprises a microprocessor, an FPGA, a positioning module, an airborne sensor, an intelligent vision module, a flight control module and a data transmission module. According to the system, a target tracking instruction is sent through the ground control platform, the unmanned aerial vehicle tracker automatically identifies the position of a target in an image coordinate system of images collected by the intelligent vision module by the adoption of an HOG characteristic and SVM combined rapid target detection algorithm after receiving the target tracking instruction, data of the positioning module and the airborne sensor is read, target moving images are issued to the ground control platform, and therefore automatic visual tracking of the moving target is realized. The system is high in automatic degree, easy to operate, high in precision and excellent in real-time tracking performance, and spatial coordinates are digitalized.

The invention discloses a spherical amphibious robot. An upper spherical shell has a buoyancy compensating function, and the autonomous suspension of the robot can be achieved; the bearing capacity ofa horizontal steering gear is reduced by a sliding rail structure. The spherical amphibious robot comprises the upper spherical shell, an intermediate partition plate, a leg structure and a sliding rail mechanism, the upper spherical shell has the buoyancy compensating function, which can achieve the independent suspension of the robot, and water inlet holes designed and evenly distributed at different heights of a water inlet compartment adjust the buoyancy of the robot. The leg structure is connected to a horizontal steering gear rotating shaft for powering the movement of the leg structurethrough the sliding rail mechanism, one end of a horizontal rotation rod in the sliding rail mechanism is fixed to a robot leg mechanism, the other end is connected with the bearing and placed on a sliding rail, thereby reducing the load of the horizontal steering gear and a horizontal bracket, and a detachable independent battery compartment is arranged on the lower end surface of the intermediate partition plate.

The invention relates to a target tracking method under arbitrary linear constraints, comprising: acquiring target position measurement information from an observation radar to construct a measurementvector, wherein the measurement vector comprises distance measurement and azimuth measurement of a target relative to the original of an observation radar coordinate system; performing state augmentation of the state vector of the target at the current time point using the state vector of the target at previous time points to obtain an augmented state vector and its corresponding state equation,wherein the augmented state includes states of the k time point and the previous d consecutive time points, and d represents the time span of the augmented part; constructing pseudo-measurement according to the linear trajectory shape of the target motion to describe the arbitrary linear constraint relationship, and augmenting the pseudo-measurement into the measurement vector to obtain an augmented measurement equation; and using a nonlinear filtering method, and performing filtering by using the augmented state equation and the augmented measurement equation. The method constructs the pseudo-measurement, uses the linear trajectory shape information to improve the filtering precision, and provides a new solution for the target tracking problem under any linear constraints.

The invention discloses an aerial photographing method, device and an unmanned aerial vehicle. The method comprises the following steps: acquiring images through two cameras; splicing the two images acquired by the two cameras into one 3D image; and sending the 3D image out. Thus, the unmanned aerial vehicle can provide the 3D image in the process of aerial photographing, and users are allowed to view the 3D image with the lifelike picture in real time, thereby bringing the immersive experience to the users, and greatly enhancing the aerial photographing experience of the users. Further, when the 3D image is transmitted to the users for viewing in real time, depth detection is carried out through the 3D image, so that the unmanned aerial vehicle can realize multiple functions, such as 3D aerial photographing, obstacle avoidance, tracking, ranging and so on by using a group of binocular cameras (that is two cameras), thus 3D photographing and depth detection can be respectively realized without respectively using the two groups of binocular cameras (that is four cameras), and multiple functions can be achieved at a lower cost.

The invention discloses an object tracking method based on simplex method, comprising the following steps of: selecting an object from an obtained image to carry out tracking processing; through the steps of target selection, image imputing, simplex peak selection, calculation of distance between the peak and the target, peak sequencing, simplex operation, target predication, and the like, finding out the node with the minimum distance to the target after certain times of iteration, that is, the target is at the position of the current image, so that the tracking for the target object is realized. The method can realize real-time and quick tracking of moving objects, and can automatically recover after the tracking is failed.

The invention provides a real-time target tracking system and method in an airborne photoelectric platform, and belongs to the technical field of intelligent video processing. The system comprises animage collecting module, an image decoding module, a data communication module and a target tracking module. The image collecting module is responsible for collecting visible light image data and infrared image data and inputting the infrared image data and the visible light image data into an image caching module after collection is completed. The data communication module is responsible for transmission of instruction information and image information between the data communication module and a DSP chip and the communication between an upper computer and a rear end servo control system. Thetarget tracking module receives instructions from the upper computer, reads the cached infrared image data and visible light image data, outputs a corresponding processing result (target direction information), and finally transmitting the target position information to the rear end servo control system. The system is easy to obtain, can instantly conduct real-time target tracking processing in the airborne photoelectric platform after images are collected, is high in precision and stability and low in output delay, and can replace manual work for implementing the intelligent control over a servo system.