93 results about "Trajectory database" patented technology

The invention relates to a GPS positioning-based road network grid digital map automatic generation method in the field of ground mapping. The invention is characterized in that vehicle-mounted GPS equipment is used for gathering data about the travelling track of a vehicle on a road network, that is, road information data; a computer is used for switching the travelling track data from geodetic coordinates to urban construction coordinates and then storing the travelling track data in a track database; the travelling track data in the track database is filtered and enhanced by the computer; the travelling track data after being subjected to processing, filtration and enhancement by the computer is then used for generating a sketch of a road network grid digital map; and finally, the computer is adopted to process the sketch and produce the road network grid digital map. The invention has the following advantages: the data source adopted by the invention is convenient and relatively cheap to acquire; and the road network grid digital map generated by the invention is complete and clear, has high precision, and changes in line with the actual road network, so that the map can better satisfy the application requirements for a road network map on timeliness and accuracy.

The invention discloses a human posture estimation method based on OpenPose and Kinect and a rehabilitation training system. The system comprises a human posture estimation module based on OpenPose and Kinect, a scene interactive rehabilitation training virtual scene module and a three-dimensional joint motion trajectory database. The human posture estimation module based on OpenPose and Kinect fuses the depth information of Kinect and 2D human joints obtained by OpenPose algorithm to obtain 3D human joints. The scene interactive rehabilitation virtual scene part builds the progressive rehabilitation virtual scene based on Unity3D platform, and realizes the virtual agent's motion control and other functions. The three-dimensional joint motion trajectory database is used to store and read the motion trajectory data of each joint in the process of rehabilitation training. The system can capture the spatial coordinates of three-dimensional human joints in real time, scene interactive rehabilitation training is lively and interesting, and can provide targeted rehabilitation training according to the patient's situation.

The invention relates to a vehicle locus prediction and MEC application migration method based on extreme learning, and belongs to the wireless communication network field; the method comprises the following steps: S1, using a MEC application to gather, store and process positioning information of a networked vehicle, and building a vehicle local driving locus database; S2, using a local MEC server as the center to reconstruct a vehicle local driving locus, combining an edge network to gather data and dates of adjacent MEC servers, and forming a sample set; S3, using an ELM prediction algorithm to predict a vehicle mobile direction, determining a network vehicle to access the MEC server, and migrating an internet of vehicles application into the server. The method can be applied to pre-migration of the internet of vehicles application deployed based on MEC servers under a mobile edge network scene.

A trajectory processing apparatus comprises a trajectory database configured to store a position coordinate of a movable body detected from a camera image in association with data that specifies the camera image from which the movable body is detected, and a camera image database configured to store the camera image. A control section fetches the position coordinate of the movable body and the specifying data for the camera image from which the movable body is detected from the trajectory database. Further, the position coordinate of the movable body fetched from the trajectory database is displayed in a display section as a trajectory of the movable body. Furthermore, the control section acquires from the camera image database the camera image specified by the specifying data fetched from the trajectory database. Moreover, this camera image is displayed in the display section.

In a digital video surveillance system, a number of processing stages are employed to identify foreground regions representing moving objects in a video sequence. An object tracking stage (5) is also provided in order to identify a correspondence between candidate objects in a current frame and those that have already been identified in one or more previous frames. In this way, it is possible to calculate the path taken by the or each foreground object and to record this path information in a trajectory database. In order to improve tracking performance, the object tracking stage (5) employs a state transitional object management scheme which determines whether or not a particular object is tracked. The path information generated by the object tracking stage (5) can be displayed on a video monitor (15) of the surveillance system and / or made available to high level applications (7).

The invention discloses a vehicle track prediction method based on the Internet of vehicles, which belongs to the field of track prediction, especially vehicle track prediction. A historical track database is built based on track records collected by a GPS device of a vehicle, comparative retrieval is performed in the historical track database according to the current known state information of a user to work out the probabilities of all possible states, and the state with biggest probability is a predicted next state, namely, a predicted location. The predicted location is substituted into the track database as a current state for iterative calculation, and finally, the continuous track of the vehicle in the future is acquired. The method is advantaged in that the regularity of vehicle movement can be analyzed accurately, and the possible destination at a future moment and the continuous movement track of a vehicle can be predicted accurately.

The embodiment of the invention provides a navigation route generation method and device and equipment. The method comprises the steps that a user driving trajectory database is inquired to obtain a driving trajectory matched with current time; position information, matched with the current time, in the driving trajectory is obtained according to the driving trajectory; matching is conducted on current position information according to the matched position information; if matching succeeds, it is determined that the driving trajectory is a driving trajectory needed by a user currently, and a corresponding navigation route is generated. Even if the user does not input a destination address, a destination where the user may go can be judged automatically and intelligently, and a corresponding navigation route can be generated.

Embodiments of the invention disclose a prediction method and apparatus for positioning trajectories. According to a technical scheme in the invention, a road is expressed by a network formed by road sections among intersections, a map model is established, and a database of historical trajectories of a user is established; when the user enters a place, positioning terminal information and positional information of the user sent by a positioning terminal of the user are received, historical trajectory data of the user is acquired according to the positioning terminal information and includes the walking frequency of the user on each road section and path choices of the user at each intersection, and a path probability model is established according to the historical trajectory data so as to characterize the probability that the user selects an adjacent road section at each intersection; and a predicted trajectory of the user is obtained according to the current positional information of the user and the path probability model. The technical scheme provided by embodiments in the invention overcomes the problem that related positioning technology cannot predict the movement trajectory of the user.

The invention relates to an operating device among optional functions on an electronic device through image selection, which is characterized in that an image selection device, an image track identification module, a hand track database, a control option program and an option function execution module are arranged in a target electronic device; wherein, at least one hand track data is arranged in the hand track database, and at least one control option program is arranged in the control option program. When the hand track of the user complies with any preset hand track data, the control option corresponding to the preset hand track data and the control instruction is executed, so as to control the specified function of the target electronic device.

The invention relates to a spatial-temporal trajectory big data storage method for a database. The method comprises the steps that information collection is conducted on state information of an object with a position information sampling function through an information collection terminal; after information collection, collected information is transmitted to a data processing system through transmission equipment; noise filtering preprocessing and data cleaning preprocessing are conducted on the received original data information in the data processing system, the preprocessed data information is stored in a trajectory database by serving as source spatial data, and then a data storage layer is obtained, wherein the source spatial data is stored in a dispersion-type sampling storage mode; the source spatial data is modeled and processed, after interception, projection, measurement and built-in function fitting operations, track data is obtained, and then a trajectory layer is constructed; a complex query function of spatial-temporal trajectory data analysis is provided. The method has the advanced technical advantages of large-scale source data concurrency loading, lightweight trajectory data representing, flexible query processing and the like.

The invention discloses a method for identifying illegally-operated vehicles. The method comprises the following steps of S1, collecting vehicle data to establish a vehicle number plate database, a vehicle running track database and a bayonet longitude and latitude database; S2, cleaning the collected vehicle data; S3, conducting deep learning based on the cleaned vehicle data and establishing anintelligent identification model; S4, identifying all vehicles by the intelligent recognition model. By means of the method and system for identifying the illegally-operated vehicles and a computer readable storage medium, the illegally-operated vehicles can be efficiently and accurately identified.

The invention provides a database-assisted satellite system and ground cellular network spectrum sharing method. The method comprises the steps that firstly, a satellite broadcasts the beam coverage range and the overhead time of the satellite to a ground station through a downlink, and beam coverage range information and overhead time information form a satellite trajectory database; then the ground station and the ground cellular network share a satellite trajectory database; and finally, when the cellular base station needs to access the millimeter wave frequency band for spectrum sharing,the cellular base station sends own position information to the satellite trajectory database, and the satellite trajectory database feeds back the maximum available transmitting power to the cellularbase station. The method is simple, the time delay is controllable, the outage probability of the satellite link is reduced, the utilization rate of the frequency spectrum opportunity is improved, and the throughput of the ground cellular network is improved.

The invention discloses a robot spray gun trajectory setting method in copper plate spraying operation. The method comprises the steps that a spray gun spraying area is set, wherein the geometric model of the area is a spraying cone; spraying mediums and related parameters of a spray gun are set; the area and the radius of the spraying area and the thickness of a coating are acquired; the stacking range of the spraying area is calculated; according to a spraying angle of the spray gun and the distance between the spray guns of all spraying areas, the stacking distance between adjacent spraying areas is acquired; for a copper plate corner angle, the spray gun is always vertical to an arc face of the copper plate corner angle; in adjacent spraying areas, the spray gun rotates an angle of beta by taking the axis of the corner angle arc face as the circle center; a robot spray gun trajectory database is established and related parameters of the spray gun trajectories of the database are programmed into a spray gun trajectory subprogram; and the trajectory of the spray gun runs according to the setting of the subprogram. According to the method, through the acquired robot spray gun trajectory, an optimization target of the robot spraying operation is realized; the uniformity and the quality of the coating are effectively improved; the spraying cost is reduced; and the spraying efficiency is improved.

The invention relates to a GPS positioning-based road network grid digital map automatic generation method in the field of ground mapping. The invention is characterized in that vehicle-mounted GPS equipment is used for gathering data about the travelling track of a vehicle on a road network, that is, road information data; a computer is used for switching the travelling track data from geodetic coordinates to urban construction coordinates and then storing the travelling track data in a track database; the travelling track data in the track database is filtered and enhanced by the computer; the travelling track data after being subjected to processing, filtration and enhancement by the computer is then used for generating a sketch of a road network grid digital map; and finally, the computer is adopted to process the sketch and produce the road network grid digital map. The invention has the following advantages: the data source adopted by the invention is convenient and relatively cheap to acquire; and the road network grid digital map generated by the invention is complete and clear, has high precision, and changes in line with the actual road network, so that the map can better satisfy the application requirements for a road network map on timeliness and accuracy.

The invention discloses a method of identifying a converse riding behavior of a shared bicycle based on a historical GPS trajectory. A riding behavior converse to a standard motor vehicle driving direction in the direction is defined as a converse riding behavior; through identifying each trip of the shared bicycle and matching the trajectory on a road, abnormal trajectory points are eliminated, converse riding behavior identifying method training is carried out, a trajectory clustering result is used to build a standard trajectory database, a candidate trajectory is subjected to parameter matching, and the converse riding behavior of a shared bicycle is identified. The shared bicycle converse riding behavior identifying reliability and the accuracy are improved, the abnormal trajectory points during the riding process can be quickly identified, a standard trip database can also be used to judge the category of a riding behavior, intervention of the shared bicycle converse riding behavior is thus facilitated, the traffic safety level of shared bicycle riding and motor vehicle driving is improved, and practical application value is reflected.

The invention provides a cargo transportation route planning method and system based on history data and a server. The method comprises the steps of receiving a departure point, a destination and departure time input by a user; searching tracks matching the departure point, the destination and the departure time from a pre-established history track database; carrying out clustering analysis on the obtained tracks matching the departure point, the destination and the departure time, thereby obtaining different kinds of tracks; obtaining the average time overhead of each kind of tracks after the clustering according to duration of each track in each kind of tracks after clustering; and planning cargo transportation routes for selection of a user, according to each kind of tracks after clustering and the average time overhead of each kind of tracks. According to the method, the system and the server, the cargo transportation routes are planned based on true history data, the time overhead corresponding to each kind of planned routes is obtained, and the user can carry out relatively accurate selection on the routes according to own specific demands.

The invention discloses a track data playing method and apparatus, which is used for shortening transmission time of track data and improving query and playing efficiency of the track data. The track data playing method comprises the steps of obtaining an identifier of a to-be-queried device and a query time period; querying the track data of the to-be-queried device in the query time period according to the identifier of the to-be-queried device and the query time period in a track database, performing redundancy elimination processing on the queried track data, and drawing a track line according to the track data subjected to the redundancy elimination processing, wherein the track database stores a corresponding relationships between an identifier of each device and the track data of the device at any moment; and sending the track line to a specified device for performing playing.

The invention discloses a novel online fault diagnosis method for a 110kV XLPE cross interconnection cable, namely a trajectory method. According to the method disclosed by the invention, cable metal sheath grounding wire loop current and operating voltage parameters are acquired through an online monitoring system, the parameters are transmitted to a computer, and a trajectory diagram integrating the two types of parameters in the same time period is constructed. Any fault corresponds to a different trajectory diagram, and differences between the trajectory diagram and normal conditions are analyzed and compared by using digital image processing technologies so as to carry out fault diagnosis accurately. The fault diagnosis method disclosed by the invention can overcome deficiencies of a traditional online monitoring and fault diagnosis method, is higher in accuracy and lower in cost, can realize real-time diagnosis, and can form a historical fault trajectory database.

A trajectory processing apparatus comprises a trajectory database configured to store a position coordinate of a movable body detected from a camera image in association with data that specifies the camera image from which the movable body is detected, and a camera image database configured to store the camera image. A control section fetches the position coordinate of the movable body and the specifying data for the camera image from which the movable body is detected from the trajectory database. Further, the position coordinate of the movable body fetched from the trajectory database is displayed in a display section as a trajectory of the movable body. Furthermore, the control section acquires from the camera image database the camera image specified by the specifying data fetched from the trajectory database. Moreover, this camera image is displayed in the display section.

The invention discloses an underwater production facility virtual assembly method. The underwater production facility virtual assembly method includes the following steps: (1) building a relational data base and a track data base based on the Pro / E secondary development technology; (2) leading in a to-be-assembled sub-assembly body and part model, and conducting position and pose transformation on parts to be assembled through the cooperative relationship between to-be-assembled sub-assembly bodies and the parts in the built relational data base and attributes and identification of the parts until the parts can reach the sub-assembly bodies only through transverse movement; (3) visiting the track data base, selecting to determine the shortest assembly track in multiple assembly paths through the track data base, and outputting track files between the sub-assembly bodies and the parts; (4) assembling the to-be-assembled sub-assembly bodies and the parts according to the output track files; (5) repeatedly executing the step (2), the step (3) and the step (4) until assembling of the assembly bodies is completed. By means of the method, the assembly validity and the assembly accuracy are improved.

The embodiment of the invention provides a reversing trajectory display method and device. The method comprises the following steps: when a reversing process of a vehicle is started, acquiring a current turning angle of the vehicle; acquiring a corresponding reversing trajectory from a trajectory database according to the turning angle, wherein the trajectory database is a database which is acquired in an offline manner and has reversing trajectories corresponding to all turning angles within a preset turning angle range; displaying the acquired reversing trajectory on a reversing video picture. According to the reversing trajectory display method and device, the trajectory database which is acquired in the offline manner and has the reversing trajectories corresponding to all the turning angles within the preset turning angle range is adopted, and when the reversing process is started, the corresponding reversing trajectory is acquired from the trajectory database according to the current turning angle of the vehicle, and is displayed on the reversing video picture, so that a process of calculating the reversing trajectory in hardware in real time in an online manner in the prior art is eliminated, and the processing pressure of the hardware is reduced.

In a digital video surveillance system, a number of processing stages are employed to identify foreground regions representing moving objects in a video sequence. An object tracking stage 5 is also provided in order to identify a correspondence between candidate objects in a current frame and those that have already been identified in one or more previous frames. In this way, it is possible to calculate the path taken by the or each foreground object and to record this path information in a trajectory database. In order to improve tracking performance, the object tracking stage 5 employs a state transitional object management scheme which determines whether or not a particular object is to be tracked. As part of the object management scheme, spurious objects, which are identified on the basis of their motion characteristics, are deleted from the system. This ensures that valuable processing resources are not wasted tracking unwanted artifacts which may represent, for example, noise or random motion.

The invention discloses an automatic stall parking method and device. An angle adjusting variable is calculated, the direction and angle of a target vehicle are adjusted in real time according to theangle adjusting variable, with stall parking, the angle adjusting variable tends to be zero, and when the angle adjusting variable is zero, the direction and angle of the target car do not need to beadjusted, and whether the center point of a target parking spot and a coordinate origin coordinate or not is detected in real time. When the center point of the target parking spot coordinates with the coordinate origin, the target car is precisely parked in the parking spot. The method does not need to depend on a track database, the variety of ideal parking tracks of the track database is limited, and when the ideal parking tracks and the actual parking path deviate, the technical problem that the car cannot be precisely parked in the parking spot through an automatic parking device is caused.

A data improvement system, including an initial database, a verification database, and a processing device in communication with the initial database and the verification database. The processing device receives data from the initial database and the verification database, and determines verification data based thereon. A track data improvement system and a track database improvement system are also disclosed.

The invention discloses an on-line fault diagnosis method for a 110kV cross-linked polyethylene cross-connected cable based on a trajectory method, namely, a trajectory method formed by induction voltage and metal sheath grounding loop current measurement parameters. The on-line fault diagnosis method comprises the steps of collecting metal sheath grounding loop current and induction voltage parameters of the cable through an on-line monitoring system, transmitting the parameters to the MATLAB through a serial port, constructing a trajectory diagram integrating the two types of parameters within the same time period by using a fitting code, solving the parameters such as the long axis, the short axis, the area and the inclination angle, analytically comparing the difference between the trajectory diagram and a normal condition, and analyzing the change rate of the long axis, the short axis, the inclination angle and the eccentricity so as to accurately perform fault diagnosis. The method disclosed by the invention can overcome defects of the traditional on-line monitoring and fault diagnosis method, is higher in accuracy, can realize real-time diagnosis and can form a historical fault trajectory database. According to an online detection method for the induction voltage, the line adopts a cross-connected grounding mode, and measurement is performed at two ends of a sheath protector of a line cross-connected grounding box.

The invention discloses an automatic driving local path planning method, which comprises the following steps of: (1) receiving map data and vehicle positioning data of an area to be driven by a vehicle so as to generate a local map of a drivable area of the vehicle; (2) performing time sampling, speed sampling and angle sampling from the local map; (3) generating a plurality of predicted driving tracks based on time sampling, speed sampling and angle sampling; (4) traversing all the predicted driving tracks, carrying out collision detection on each predicted driving track, if a detection result shows that collision occurs, rejecting the predicted driving track, and if the detection result shows that collision does not occur, putting the predicted driving track into a predicted driving track database; and (5) selecting an optimal track from the predicted driving track database, and outputting the optimal track to the vehicle. Correspondingly, the invention further discloses an automaticdriving local path planning system.

The invention provides a high risk vehicle real-time alarm releasing system, and belongs to the technical field of vehicle comprehensive management and control systems. The high risk vehicle real-time alarm releasing system comprises a vehicle information collection unit, an alarm center and a mobile alarm terminal; the alarm center comprises a vehicle track database, a high risk vehicle database, a comparison alarm service module, a GIS service platform and an alarm subscription releasing module; an APP alarm client is arranged on the mobile alarm terminal, alarm services are subscribed through the APP alarm client, the alarm subscription releasing module receives the alarm services subscribed by all the mobile alarm terminals and pushes high risk vehicle alarm information to all the mobile alarm terminals in real time. The high risk vehicle real-time alarm releasing system has the advantages that the high risk vehicle alarm information can be pushed in a targeted mode according to the alarm service subscribed by the mobile alarm terminals, alarm releasing and vehicle intercepting can be quickly achieved, and therefore the vehicle management efficiency is improved; the mobile alarm terminal adopts the additionally loaded APP alarm client, therefore, the alarm means are diverse, and the improvement of the alarm timeliness is facilitated.

The invention belongs to the field of unmanned vehicle simulation testing, and particularly relates to a vehicle hardware-in-the-loop simulation training system and method based on deep reinforcement learning. The system comprises a virtual simulation unit and a real vehicle controller, wherein the virtual simulation unit comprises a simulation vehicle module, a simulation control module, a real vehicle track database, a simulation sensor module, a reset interface and a start-stop interface. The real vehicle controller and the virtual simulation scene are subjected to joint simulation training, effective operation of the deep reinforcement learning movementplanning model in a real vehicle unmanned driving system is achieved, and therefore the problem that the deep reinforcement learning model cannot be effectively transplanted from a virtual simulation vehicle to an unmanned real vehicle is solved.

Embodiments of the invention provide method and apparatus for prediction the propagation of infectious disease, computer equipment, and storage medium. The method includes: determining one or more to-be-predicted object; matching each to-be-predicted object with a corresponding prediction trace from a historical trace database; according to the prediction trace, determining the propagation trend of the infectious disease among the to-be-predicted objects. In the invention, the prediction trace of the to-be-predicted object is matched from the historical trace database, thus reducing the calculation load of acquiring the prediction trace.

The invention discloses a light weapon test identification method based on a simulation technology, which comprises a database module, a calculation module, a comprehensive analysis module and a faultanalysis and reproduction module; the database module comprises an inner trajectory database, a model database, a material database and an environment database; the calculation module comprises an inner ballistic trajectory calculation module, a mechanism action simulation analysis module, a structure field temperature field coupling calculation module, an outer ballistic trajectory calculation module and a damage efficiency calculation module. The identification steps are as follows: firstly, researching the characteristics of inner ballistic trajectory data, model library data, material data and environmental data; the light weapon test identification system composed of the database module, the calculation module, the comprehensive analysis module and the fault analysis and reproductionmodule is used for carrying out simulation identification tests on light weapons, multi-sample data simulation tests can be achieved, a large amount of identification data can be obtained through comprehensive identification and evaluation, the cost is saved, and the test period is short.