396results about How to "Real-time tracking" patented technology

The invention discloses a man-machine interactive system and a real-time gesture tracking processing method for the same. The method comprises the following steps of: obtaining image information of user side, executing gesture detection by a gesture detection unit to finish separation of a gesture and a background, and automatically determining a smaller rectangular frame which surrounds the hand as a region of interest in the image information through a vision algorithm; calculating the hand profile state of each frame in a video sequence by a gesture tracking unit; executing validity check on hand actions according to the calculated hand profile state, and determining the gesture action finished by the user; and generating a corresponding gesture action control instruction according to the determined gesture action, and making corresponding feedbacks by a three-dimensional user interface according to the gesture action control instruction. In the system and the method, all or part of gesture actions of the user are sensed so as to finish accurate tracking on the gesture, thus, a real-time robust solution is provided for an effective gesture man-machine interface port based on a common vision sensor.

The invention provides a logistics management method based on a cloud computing technology. After one or more logistics agencies and staff thereof register / login a logistics management server, the logistics management method is characterized by comprising the following steps of: registering logistics information; allocating a unique waybill number; based on the logistics information and the state of each logistics agency and the staff of the logistics agency, allocating a logistics task to an appropriate logistics agency and parties of the logistics agency; sending the logistics information and the waybill number to the terminal equipment of the parties; attaching a waybill having the waybill number or a radio frequency identification (RFID) tag, on which the waybill number is recorded, to corresponding goods; monitoring and recording the parties and position of the goods in the logistics process; providing logistics state information; and after the logistics process is finished, settling accounts. The invention also provides the logistics management server and a logistics management system. By adoption of the logistics management method, functions of tracking logistics state, sharing logistics resources and settling the accounts among a plurality of logistics companies can be realized.

The invention relates to a region-of-interest video encoding and transmitting method which realize multi-channel combination, and belongs to the technical field of the video encoding and transmission. The method adopts the following steps: step one, space down sampling is performed to the panoramic video with high resolution collected by a panoramic camera, and then encoding is performed after video with low resolution is obtained; step two, region-of-interest detection is performed to video with high definition collected by a visible-light camera, and self-adaptive switching is performed to the two channels of video, namely, downsized video and down-sampled video, according to the area and the position of the region-of-interest detection; step three, an an infrared thermal imager is used for performing detection and tracking to interest targets, encoding infrared region-of-interest video with primary low resolution, and adjusting quantization parameter to realize code rate control; step four, the priority of the three channels of video is set, protecting channel encoding for non-uniform channel is performed according to the priority, and the code is multiplexed into one channel of code stream to be sent to the channel for transmission, and code rate distribution of the channel bandwidth is performed according to the priority. The method guarantees precise detection and high quality encoding to the region of interest when ensuring global detection on the complete scene.

The invention relates to a multi-target tracking system based on deep learning and an implementation method. The method comprises the following steps: getting the target position of a first frame through target detection, and adding multiple to-be-tracked targets to a tracking queue; inputting a next frame of image and traversing the tracking queue to get the position of the target in the next frame; after getting the position of the target in the next frame, judging whether the target is off the screen based on thresholds; if the target is not off the screen, invoking target detection every other fixed frame, and calculating the IOU (intersection over union) of the target detection result and the tracking result; if IOU<0.1, judging that a new target is added to the screen, and adding the target to the tracking queue; if IOU>0.5, replacing the tracking box with the target detection box to correct the position; and continuing target tracking. By carefully designing the network structure and improving the training method, under the condition of high tracking precision, the tracking speed is increased significantly, network redundancy is reduced, and the size of the model is reduced.

The invention relates to a noninvasive radiotherapy system for a robot, and belongs to the medical equipment field. The noninvasive radiotherapy system for the robot consists of seven modules, i.e. a radiotherapy planning system, a three-dimensional numerical-control therapy bed, an automatic tracking system for a four-dimensional real-time image, a robot system, a radioactive source, an adjuvant therapy system and an integrated control system, wherein the automatic tracking system for the four-dimensional real-time image consists of a six-freedom-of-degree G-shaped arm real-time image system and an intelligent tracking system; the six-freedom-of-degree G-shaped arm real-time image system is formed by successively connecting a G-shaped arm, a G-shaped arm sliding rail, a G-shaped arm spindle, a G-shaped arm pitch shaft and a G-shaped arm sliding seat; an X ray source and an X ray dynamic flat panel detector are formed into one group, and two groups are correspondingly installed on the G-shaped arm; and the G-shaped arm sliding seat is installed in a rail (9). According to the noninvasive radiotherapy system for the robot, which is disclosed by the invention, the defects of unmatched projection time, time waste and low therapy precision in the prior art are overcome, the precise therapy of the whole body tumor can be carried out, and the cardiovascular disease therapy and the noninvasive regulation of the renal nerve disease can be carried out.

The invention relates to a portable personal health monitor and a method thereof for monitoring personal health. The portable personal health monitor comprises a hand-held shell structure which is internally provided with an input unit, a storage unit, a processing unit and an output unit, wherein the input unit is used for inputting user personal information and data information related to nutrition, at least one database for storing data information with different purposes is supported by the storage unit, the processing unit is used for processing the data information according to user commands and a plurality of preset function programs, and the output unit is used for outputting the information according to processed result data and an appointed output mode.

Embodiments of the invention disclose a human face key point tracking method and apparatus. The method comprises the steps of obtaining human face key point coordinates and a confidence degree of a previous frame of image to calculate human face key point coordinates of a current frame; and then, performing multi-human face identification on the current frame according to the human face key point coordinates of the current frame, calculating a corresponding confidence degree of the current frame for reference by a next frame of image, and circulating the process until all images in a video stream are identified, so that the purpose of tracking human face key points in the video stream in real time is achieved. According to the scheme, the detection time can be greatly shortened, the processing efficiency can be improved, the resource consumption can be reduced, and real-time calculation can be realized at a mobile terminal.

A system, method, and apparatus infrastructure provide real time wireless tracking of multiple initial data parameters transmitted from individual mobile receiving or system units installed in customer vehicles. A management network receives and decodes initial data parameters from respective receiving mobile units, matches and encodes the same according to stored predetermined customer specified format preferences, and transmits customer specified data streams to customers. An additional step correlates the received specified-data streams with additional public-supplied data or third-party contractually supplied data to provide an enhanced customer report enabling a number of reports; including a credibility determination between the public-supplied data and the received specified-data, a customer vehicle travel efficiency report, a safe operation vehicle report, and a vehicle operator effectiveness report. Each vehicle system unit is functionally enabled to secure transmission of a communication protocol over GSM, GPRS, CDMA, or other networks enabling seamless and secure functionality between wireless or wired data-links.

The invention discloses an automatic aiming laser bird scaring device based on mode recognition, which comprises a horizontal rotating table and a vertical rotating table. The vertical rotating table is arranged on the horizontal rotating table, the horizontal rotating table and the vertical rotating table are connected in movable mode, a camera is arranged in the vertical rotating table, and a laser device is arranged on the vertical rotating table. Besides, the invention further discloses a bird scaring method based on recognition pattern, firstly the camera is utilized to search targets and locate the targets, and then the laser device emits laser to achieve the aim of scaring birds. The bird scaring device and the bird scaring method not only avoid random irradiation of laser so as to avoid interference of the laser device on people and passing-by vehicles, but also is accurate in bird locating, adopts the low-power laser device to scare birds to lower cost, causes no serious damage to birds, avoids dropping of bird scaring effect caused by the fact that birds are adapted to the bird scaring device, can further update a controller database and application programs according to different application occasions, and increases adaptability of the device.

The invention discloses a portable target tracking method and system based on a four-axis air vehicle. The method includes the steps that (1) the four-axis air vehicle tracks and collects a target image in real time, and the image is output after being compressed; (2) video compression data are received, decompression is performed, target detecting and tracking are conducted through a TLD algorithm according to the decompressed image data, template matching is executed independently, and when a target is detected, the detected target location is output; (3) a control parameter is obtained through calculation by using a PID algorithm according to the target location, a PID coefficient in the PID algorithm is set according to the flight state, and the movement of the four-axis air vehicle is controlled. The device comprises the four-axis air vehicle, a target detecting and tracking module and a flight control unit, wherein the four-axis air vehicle is used for tracking and collecting the target image in real time, the target detecting and tracking module is used for conducting target detecting and tracking, and the flight control unit is used for calculating the control parameter. The device has the advantages of being high in execution speed, high in tracking accuracy and capable of achieving the purpose of automatic searching and tracking.

The invention discloses a multi-laser-radar-based pedestrian target tracking method. The multi-laser-radar-based pedestrian target tracking method comprises the following steps that: a sensor network consisting of a plurality of single-line laser radars monitors a whole scene; at every sampling moment, the radars output footstep point distance data of pedestrians, and the data among different radars are unified at a coordinate system through system calibration; a footstep movement model of the pedestrians is built and pedestrian movement states are tracked through Kalman filtering so as to finally acquire a stable target trace and relevant statistical information. In the method, the laser radars are used as sensors, so that the defects of influence of illumination variance on an image sensor in the tracking method can be overcome and reliability is enhanced greatly; furthermore, the tracking range is wide, the algorithm speed is high, the number of tracked pedestrians is large, all movement modes of the pedestrians are compatible, such as standing, walking and jogging, and positions of the pedestrians can be detected effectively and movement traces of the pedestrians can be tracked in real time. The multi-laser-radar-based pedestrian target tracking method is applicable to occasions in which main movement targets are pedestrians.

The invention discloses a method for supervising clothing production based on a radio frequency identification (RFID) technology. The method comprises the following steps of: 1, setting a clothing production line; 2, preparing RFID equipment; and 3, installing the RFID equipment. The invention also discloses a system for implementing the method. By the method provided by the invention, clothing production operating information can be supervised quickly and accurately in real time. The system provided by the invention is simple in structure and smart in design. By adoption of the RFID technology, the conventional paper work ticket is replaced by an electronic RFID tag, and the RFID tag is arranged on each clothing product; every time when the clothing product finishes a process, an RFID data acquisition terminal in the corresponding process automatically sends the operating information of the process to an information management server; the production data of clothing in a certain process is collected in real time; an effect of supervising the clothing production is achieved; and the production efficiency and decision management capacity of an enterprise are effectively improved.

The invention relates to a vehicle emission remote monitoring system based on OBD (on-board diagnostics) detection data. The system comprises a data processing unit, a network communicating unit and a remote monitoring client side. On the basis of a KWP 2000 protocol, data flow and a fault code communication algorithm of a data processing unit and an on-board ECU (electronic control unit) are completed, data flow and fault information, such as oxygen sensor signals, accelerated speed, engine loads, engine rotating speed, the fuel-injection quantity and the actual air-fuel ratio affecting an exhaust emission system are extracted, abnormality of the data flow and the system fault content are analyzed, related information is transmitted to the remote monitoring client side with a wireless communication technology, then the working state of a corresponding system part is recognized and diagnosed, and alarm information is sent to an on-board terminal according to the abnormal emission condition, so that vehicle traveling parameters are remotely monitored, and information is fed back.

The embodiment of the invention provides a visual multi-target tracking method and a device based on deep learning, and the method comprises the steps: sequentially obtaining the candidate detection frames of a tracking target in a current video frame through a target detection network model, recording the coordinate position information, and obtaining a corresponding template image; acquiring each frame of image in the video except the first frame as a to-be-searched area image; and inputting each template image and the to-be-searched region image into a target tracking network model constructed by a twin convolutional neural network, thereby obtaining a tracking result of a tracking target. According to the visual multi-target tracking method and the device based on deep learning, the template image corresponding to each tracking target and the to-be-searched area image which are acquired by using the target detection network model are respectively input into the target tracking network model constructed by the twin convolutional neural network, so that the tracking result of the tracking target corresponding to the template image is acquired, the calculation amount is low, and multi-target real-time and accurate tracking is realized.

The invention relates to a real-time tracking method of a nonspecific target based on partitioning, comprising three steps of classifier updating, target detection and weight updating. In the method, the target region is divided into multiple blocks; a classifier is used for maintaining each block, and updating is conducted frame by frame; the detection result of each classifier is comprehensively considered to determine the position of the target in the new video frame. In the method, an automatic weight updating mechanism is designed, so as to enable the blocks which are relatively stable to have greater decision-making power over the judgment of results, thus reducing the influence of various interferences; and the tracking performance is better than multiple international published algorithms recently. In the method, changes of appearances of objects caused by various interferences can be captured and accurate tracking can be conducted; the method has universality on target objects in various shapes and types; the calculation has low complexity and can be processed at real time. The invention has wide application prospect in various occasions needing tracking techniques, such as video monitoring, automatic driving, man-machine interaction, intelligent traffic, robot, airborne early warning and the like.

The invention discloses a tumor-targeting living body multimodality imaging and analyzing method based on gold nano-clusters. According to the invention, through an in-vitro cell (including various tumor cells and normal cells) experiment, related cells and chlorauric acid with a certain concentration and a salt solution thereof are incubated under a physiological condition, such that gold nano-clusters are produced; and real-time non-invasive high-resolution tumor cell fluorescence imaging, Raman imaging and ultrasound imaging can be realized. On the basis, a local subcutaneous injection method is adopted, and real-time in-situ living body tumor-targeting fluorescence imaging, Raman imaging and ultrasound imaging are realized on tumor-transplantation nude mice models. With the functional nano-grade probes, multiple functions of tumor targeting, fluorescence imaging, Raman imaging and ultrasound imaging are combined, such that multimodality synchronic monitoring can be realized. Also, with the gold nano-cluster in-situ living body imaging method, accurate positioning and tumor-targeting imaging and analysis can be realized.

The invention discloses a compressive sensing-based real-time multi-scale target tracking method. A sample is modeled by extracting the normalized rectangle features of sampled image, and the normalized rectangle features have higher robustness for the multi-scale target tracking. The normalized rectangle features are very high in dimensionality, so that the method can be used for compressing high-dimensional features based on compressive sensing, the feature vector is compressed under the condition that the extraction scale is not changed, the computation complexity is greatly reduced by integrogram, and the demand of real-time tracking can be met. The compressed feature vector of the sample is classified by a Naive Bayes classifier, so that the most probable position of a target can be determined; the classifier is used for responding and estimating the particle weight and resampling particles so as to prevent the degeneration of particle tracking capability; furthermore, a second-order model is used for estimating and predicting the particle state under the condition that the target movement speed factor is considered. The target in video image can be tracked in real time by the compressive sensing-based real-time multi-scale target tracking method; the method is high in accuracy and low in computation complexity; a tracking frame changes in real time along with the change of target scale, so that the demand of actual tracking application can be met.

The invention discloses a high-resolution intelligent network camera array system with global synchronization function. The system adopts global synchronization signals to realize the synchronous acquisition of a camera array, comprises at least two intelligent network cameras used for image acquisition, wherein the working mode of one camera is configured as a main mode, while the other cameras are configured to be in a slave mode; the main-mode camera produces and provides global horizontal synchronization signals and vertical synchronization signals for the slave-mode cameras; and every intelligent network camera is connected with a central computer through a network and is used for receiving control commands in real time and transmitting image data so as to realize distributed computing function. The system has the advantages of satisfying the real-time high-performance processing for acquired data, realizing the global synchronous shooting of the camera array, supporting large-scale array expansion, realizing the control of the central computer over a plurality of working modes of the intelligent cameras and realizing high-resolution video-image data shooting.

The invention discloses a construction site builder intra-site positioning system based on UWB. The system comprises an application layer, a resolving layer, a transmission layer and an equipment layer; the application layer acquires a positioning label location through the resolving layer; the resolving layer performs wireless signal propagation between itself and a positioning base station of the located region through the positioning label; the transmission layer downwards transmits an application layer related instruction to the positioning base station, an upwards transmits the wireless signal propagation data between the positioning label and the positioning base station to the resolving layer; the equipment layer comprises multiple positioning base stations and the positioning labeltransmitted through a UWB wireless channel; the positioning is performed by adopting a downlink positioning way; the positioning baes stations are distributed at various floors of the construction site so as to accomplish the related setting according to the received instruction issued by the application layer. By adopting the UWB technology, the accurate location positioning and state supervision are performed on the builders, the working efficiency is greatly improved, the supervision mode is improved, and the site management cost is reduced.

The present invention relates to the real-time measurement method of the 3D profile and deformation of object in high speed motion based on stroboscopic light source projecting structure in Fourier transformation contour process in 3D sensing technology. Equilateral grating structure modulating template is imaged on the moving object surface instantaneously with stroboscopic light source, serial deformation stripe patterns in different times are recorded with video camera, the deformation stripe patterns are then processed via Fourier transformation process to restore the 3D profiles of the moving object in different times precisely, and digital information, such as object deformation, etc. may be obtained through further data analysis. The real-time measurement method may be used in measurement and research of various periodic motion and non-periodic motion, and has the advantages of being precise, fast and timely.

The invention discloses a linearly polarized light-based polarization real-time tracking method, which relate to a polarization tracking system and a polarization tracking method. The invention solves the poor real-time tracking problem of the conventional polarization tracking method. In the system, a polarization analyzer is fixed on an output shaft of a step motor, a detection face of a charge coupled device (CCD) detector acquires incident light transmitted in the polarization analyzer and outputs an image to the computer through an image acquisition card, and the control signal output end of the computer is connected with the control signal input end of the step motor. In the method, the detection face of the CCD detector detects the incident light and generates an image, the image acquisition card detects the gray scale of the image, the computer calculates according to a detected value to obtain the polarization direction change information of the incident light and drive the step motor to drive the polarization analyzer to rotate to a direction consistent with the polarization direction of incident light, and thus, the polarization tracking of the incident light is realized. The system and the method are applicable to the polarization tracking of linearly polarized light.

The invention is applicable to the technical field of electric variable sampling measurement, and provides an industrial frequency interference resistant signal sampling method and a system. The method comprises the following steps: step A. extracting industrial signals from input commercial power alternating-current signals, synchronously tracking industrial interference signals superposed on detection signals through industrial frequency signals, and generating an industrial frequency synchronous signal; and step B. locking a zero crossing phase of the industrial frequency interference signals according to the industrial frequency synchronous signals, and synchronously sampling the input detection signals at the zero crossing phase. The invention realizes the synchronous sampling of thedetection signals at the zero crossing phase by synchronously tracking the industrial frequency interference signals; and compared with the wave traps or filter technique, the embodiment of the invention can furthest reserve effective components in the detection signals while eliminating the industrial frequency interference, has simple algorithm realization, and little source and time consumption, and can real-time track the industrial frequency interference.

The invention discloses a method for eliminating null shift of a micro-electromechanical system (MEMS) gyroscope. The method comprises the following steps of: (1) acquiring a zero-point value zero of an initial gyroscope; (2) arranging a tolerance range plus or minus allowance nearby the zero-point value zero of the initial gyroscope, and determining whether a difference value diff between a current output value of the gyroscope and the zero-point value zero of the initial gyroscope exceeds the minus or plus allowance or not; judging that the gyroscope is at a standstill if the difference value diff between the current output value of the gyroscope and the zero-point value zero of the initial gyroscope does not exceed the tolerance range, and enabling the current output value of the gyroscope to participate in the calculation of a zero point of the gyroscope; and judging that input is available outside if diff exceeds the tolerance range, and adopting the difference value as a magnitude of angular velocity of the gyroscope to be outputted normally and not to participate in the calculation of the zero point. Due to the adoption of the method, the null shift and temperature drift of the MEMS gyroscope can be effectively overcome, a precise and complex error compensation algorithm is not needed, and the zero point variation of the gyroscope can be tracked in real time.

The invention relates to a handheld pan-tilt with a tracking function. A pan-tilt controller and a communication module which is connected with an external mobile phone in a Bluetooth manner so as to receive signals transmitted from the external mobile phone are arranged in a rod body, a first motor is arranged in a first rotating mechanism, a second motor is arranged in a second rotating mechanism, a third motor is arranged in a third rotating mechanism, the first motor, the second motor, the third motor and the communication module are electrically connected with the pan-tilt controller, the pan-tilt controller is used for controlling operations of the first motor, the second motor and the third motor according to the received signals transmitted from the external mobile phone, and the handheld pan-tilt has the tracking function during shooting.

The present invention discloses a multiple human-targets location and tracking method based on multichannel phase comparison location. The method comprises: based on a linear frequency modulation continuous wave radar system of single input multiple output, employing the moving target indication and de-mean method to perform preprocessing of experiment data and perform diploid interpolation refinement distance dimension windowing Fourier transform of each period of the echo data so as to obtain object distance information according to the distance spectrum of an object; obtaining the object distance information according to the object distance; extracting the phase information corresponding to the target from the peak value where a frequency spectrum object is located; fusing the phase information of different receiving channels, calculating the phase differences among different receiving channels, calculating the azimuth or the pitch angle of the object, and combining the object distance information to calculate the location result of the object at a two-dimensional plane or a three-dimensional plane; and finally, employing the Kalman filtering method to realize the tracking of the target. The multiple human-targets location and tracking method based on the multichannel phase comparison location can perform detection, location and tracking of a plurality of human body objects indoors and outdoors so as to effectively reject multiple paths while keeping the target and perform accurate location of the object.

The invention discloses a space positioning system comprising at least three beacons and at least one positioning terminal. The beacons are distributed in to-be-localized space and are used for generating low-frequency electromagnetic fields. Each positioning terminal receives low-frequency electromagnetic fields generated by the multiple beacons and calculates a spatial position of the positioning terminal according to the received low-frequency electromagnetic fields generated by the at least three beacons. Meanwhile, the invention also discloses a space positioning method. Therefore, defects of high implementation complexity, high deployment cost, large positioning error, and delayed positioning information updating of the existing positioning scheme can be overcome effectively. On the basis of the low-cost scheme, the indoor large-range precise real-time tracking can be realized; the environment requirement is loose and no metal and magnetic interference exists; and applicability of the space positioning scheme in different environment scenes can be improved obviously.

The invention discloses a puncture treatment robot system with a sleeved flexible needle. The puncture treatment robot system comprises an outer sleeve servo motor, lead screw linear guides, an outer sleeve servo motor base, a belt pulley, a belt, a roller bearing, a force sensor connecting shaft, a pressure sensor, a sleeve chuck, a chuck and shaft connecting mechanism, a sleeve supporting base, a flexible needle servo motor base, the other belt pulley, the other belt, the other roller bearing, the other force sensor connecting shaft, the other pressure sensor, a flexible needle chuck, the other chuck and shaft connecting mechanism, a flexible needle supporting base, a camera, and a movement control circuit. The puncture treatment robot system with the sleeved flexible needle has four degrees of freedom, and the arched puncture track of the flexible needle can be changed so that the flexible needle can avoids some obstacles and important organs to reach the focus accurately and flexibly. Besides, the puncture treatment robot system with the sleeved flexible needle can track the puncture path of the flexible needle in real time and acquire biological resistance in real time.

The invention relates to a binocular-vision-based real-time extraction method and system for three-dimensional hand information. The method comprises: obtaining image information collected by a left camera and a right camera of a binocular camera system in real time; detecting hands in the images collected by the left camera and the right camera in real time; detecting a hand at a first frame by using a histogram of oriented gradient (HOG) and a support vector machine (SVM) linear classifier and detecting hands at follow-up frames by using a target tracking algorithm; extracting information of centers of palms and fingertips of the detected hands in real time and using the information as feature points of the hands; and according to the binocular-vision principle, calculating three-dimension coordinates of the feature points based on the extracted feature points so as to obtain real-time three-dimensional hand information. In addition, the system is composed of a binocular camera system and an information processing device; and the information processing device includes a hand detection module, a feature point extraction module, and a three-dimensional reconstruction module. According to the invention, real-time reliable detection and tracking of hands under a complex background can be realized; and thus reliable reconstruction of the three-dimensional hand information can be realized based on the detection and tracking.

The invention provides a spilled oil tracing and positioning buoy device, which mainly comprises a shell, an integrated plate and built-in equipment, wherein the shell consists of an upper shell, a lower shell, an O-shaped ring, a bolt and a gasket; the built-in equipment consists of an equipment component and a magnetic control switch; the appearance of the device is similar to a hollow ball formed by two straw hat-shaped articles buckled with each other, and the inner part of the device is provided with an advanced communication control positioning module and remote control system. The spilled oil tracing and positioning buoy device has the advantages of novel conception, unique structure and advanced technique, and can really show the displacement and diffusion of the spilled oil at sea and provide a reliable decision-making basis for an emergency rescue department.