CN116136416B - Real-time track optimization method and device based on multi-feature fusion filtering - Google Patents
Real-time track optimization method and device based on multi-feature fusion filtering Download PDFInfo
- Publication number
- CN116136416B CN116136416B CN202310133212.6A CN202310133212A CN116136416B CN 116136416 B CN116136416 B CN 116136416B CN 202310133212 A CN202310133212 A CN 202310133212A CN 116136416 B CN116136416 B CN 116136416B
- Authority
- CN
- China
- Prior art keywords
- data
- point
- queue
- target
- time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000001914 filtration Methods 0.000 title claims abstract description 143
- 238000000034 method Methods 0.000 title claims abstract description 54
- 230000004927 fusion Effects 0.000 title claims abstract description 38
- 238000005457 optimization Methods 0.000 title claims abstract description 38
- 238000012216 screening Methods 0.000 claims abstract description 27
- 238000012163 sequencing technique Methods 0.000 claims abstract description 9
- 230000008859 change Effects 0.000 claims description 24
- 238000004590 computer program Methods 0.000 claims description 12
- 238000010276 construction Methods 0.000 claims description 6
- 238000013500 data storage Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 12
- 230000002159 abnormal effect Effects 0.000 description 10
- 238000004422 calculation algorithm Methods 0.000 description 10
- 230000005856 abnormality Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000005094 computer simulation Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3407—Route searching; Route guidance specially adapted for specific applications
- G01C21/343—Calculating itineraries, i.e. routes leading from a starting point to a series of categorical destinations using a global route restraint, round trips, touristic trips
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3446—Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags, using precalculated routes
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/36—Input/output arrangements for on-board computers
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/38—Electronic maps specially adapted for navigation; Updating thereof
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/38—Electronic maps specially adapted for navigation; Updating thereof
- G01C21/3804—Creation or updating of map data
- G01C21/3807—Creation or updating of map data characterised by the type of data
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
- G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/42—Determining position
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Computer Networks & Wireless Communication (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
Abstract
The embodiment of the invention discloses a real-time track optimization method and device based on multi-feature fusion filtering, wherein the method comprises the following steps: acquiring a plurality of point location data of a target person in a preset period, wherein the point location data at least comprises position data, acquisition time data and warehouse-in time data; screening the data of each point to obtain a target filtering queue, and in the target filtering queue, sequentially taking each point data as target point data, and screening the target point data according to a preset judging strategy; and if the target point position data is determined to be qualified data, storing the qualified data, and sequencing all stored qualified data according to the sequence of the acquisition time to obtain the optimized real-time track of the personnel. The technical problem of poor real-time track optimization effect in the prior art is solved.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a real-time track optimization method and device based on multi-feature fusion filtering.
Background
In the current information age, with the high-speed development of satellite navigation positioning technology, position-based services are widely applied to daily life and personnel management of people, and people are not only users of position data, but also collectors of position data. By utilizing the map to display the real-time track, people can check the real-time track of the people, and management staff can check the real-time behavior track of the staff, however, due to the influence of factors such as environmental interference and unstable hardware equipment, the data collected by the positioning equipment usually generate abnormality, so that the GPS real-time track drifts.
In order to correct track drift, to make the real-time track conform to the actual situation, in the prior art, track optimization is generally performed by adopting the following manner:
1. clustering and abnormality detection algorithms based on a large number of trajectory data; the algorithm is used for preprocessing track data by collecting a large amount of real-time track data and adopting data cleaning and track compression, detecting track abnormal data by using a clustering algorithm based on spatial features and time features, removing the abnormal data and carrying out track optimization. However, the method needs a large amount of track data, has a good detection effect on the historical track data, has a small data amount when the data acquisition is just started on the real-time track data, and cannot adopt a large data clustering method to judge the abnormality of the starting data, so that the real-time track optimization effect is poor.
2. Based on map matching and anomaly detection algorithms; the algorithm effectively acquires the track through a track acquisition point position and road data matching method, and performs abnormality detection by adopting a clustering algorithm based on multiple characteristics such as position, speed and direction. However, the realization of the method needs effective road data as reference, but the electronic map road data is difficult to acquire in practical application, and meanwhile, the algorithm has larger daily application limitation because the movement randomness of personnel is larger and people do not have to walk on a conventional road.
3. The GPS track big data self-adaptive filtering method based on the segmentation-filtering model; the method divides complete GPS track data through angle and distance constraint, takes track dividing sections as basic filtering units, and guides filtering according to quantized relation between similarity and GPS positioning precision by comparing similarity between GPS track vectors in the track dividing sections and reference base lines. However, the algorithm filters and selects a large amount of acquired track data, and a large amount of track data is required to be supported, so that the real-time track data cannot be better optimized.
4. Removing noise data in the track data based on filtering; according to the method, the spatial position predicted value of the next track point is obtained through calculation according to the movement characteristics such as the position, the course, the speed and the like of the previous track point, and compared with the real measured value of the next track point, so that the judgment of abnormal data is realized. The algorithm has high prediction difficulty, can only correct obvious track noise data, and has poor optimization accuracy.
Therefore, the real-time track optimization method and device based on multi-feature fusion filtering are provided, so that the technical problem that the real-time track optimization effect is poor in the prior art is solved, and the problem to be solved by the person skilled in the art is solved.
Disclosure of Invention
Therefore, the embodiment of the invention provides a real-time track optimization method and device based on multi-feature fusion filtering, aiming at solving the technical problem of poor real-time track optimization effect in the prior art.
In order to achieve the above object, the embodiment of the present invention provides the following technical solutions:
the invention provides a real-time track optimization method based on multi-feature fusion filtering, which comprises the following steps:
acquiring a plurality of point location data of a target person in a preset period, wherein the point location data at least comprise position data, acquisition time data and warehousing time data;
screening the point location data to obtain a target filtering queue;
in the target filtering queue, sequentially taking each point location data as target point location data, and screening the target point location data according to a preset judging strategy;
if the target point location data are determined to be qualified data, storing the qualified data;
sequencing all stored qualified data according to the sequence of the acquisition time to obtain an optimized real-time personnel track;
the preset judgment strategy comprises fusion characteristics at least comprising a point location real-time position, a speed, an acquisition time, a warehouse-in time, a point location mean value, a point location variance and adjacent point location deflection angles.
In some embodiments, filtering each point location data to obtain a target filtering queue specifically includes:
acquiring effective duration of the target point location data, and adding the target point location data into a filtering queue under the condition that the effective duration is smaller than or equal to a duration threshold;
and determining the actual data length of the filtering queue, and ordering the position data of all the target point position data in the filtering queue according to the acquisition time under the condition that the actual data length is greater than or equal to a length threshold value so as to obtain the target filtering queue.
In some embodiments, in the target filtering queue, each point location data is sequentially used as target point location data, and the target point location data is screened according to a preset determination policy, which specifically includes:
calculating the point position speed of the target point position data in the target filtering queue;
under the condition that the point position speed is lower than a speed threshold, calculating an overall mean value meanttotal, an overall variance stdTotal of the target filtering queue, a local mean value meanPart after the target point position data is removed, and a local variance stdPart after the target point position data is removed;
Calculating the mean absolute difference meanDiffabs and the variance ratio stdRatio of each target point location data according to the overall mean value, the overall variance stdTital, the local mean value meanPart after the target point location data are removed and the local variance stdPart after the target point location data are removed of the target filter queue;
and determining the point with the maximum variance ratio stdRatio in all the target point bit data as a target point, and eliminating the corresponding target point bit data on the target point bit under the condition that the variance ratio stdRatio of the target point bit is larger than a preset variance ratio threshold and the mean absolute difference of the target point bit is smaller than a preset mean absolute difference threshold.
In some embodiments, determining the point with the largest variance ratio stdwatio among all the target point bit data as the target point further includes:
calculating the point-position adjacent time gpsTimeDiff of each target point-position data in the target filtering queue under the condition that the variance ratio stdRatio of the target point position is smaller than or equal to the variance ratio threshold and the mean absolute difference meanDiffabs of the target point position is larger than or equal to the mean absolute difference threshold;
And if the point position adjacent time of any point position in the target point position data is larger than a preset adjacent time threshold value, eliminating the target point position data corresponding to the point position, and resetting the target filtering queue.
In some embodiments, calculating a bit-adjacent time gpsTimeDiff for each of the target bit data in the target filter queue further includes:
calculating the angle change value of a target point group consisting of any three points in the target filtering queue when the point adjacent time of all the points in the target point data is smaller than or equal to the adjacent time threshold;
under the condition that the angle change value meets the angle change condition, eliminating point position data corresponding to the middle point position in the target filtering queue;
and outputting first data in the target filtering queue and marking the first data as the qualified data under the condition that the angle change value does not meet the angle change condition.
In some embodiments, filtering each of the point location data to obtain a target filtering queue further includes:
initializing a filtering queue and setting the length of the filtering queue.
In some embodiments, filtering each of the point location data to obtain a target filtering queue further includes:
initializing a point location, a speed and a status indication, wherein the point location is defined by a geodetic longitude and latitude coordinate (d 1 ，d 2 ) Converted into space rectangular coordinates (x, y, z).
The invention also provides a real-time track optimizing device based on multi-feature fusion filtering, which comprises:
the data acquisition unit is used for acquiring a plurality of point location data of a target person in a preset period, wherein the point location data at least comprise position data, acquisition time data and warehouse-in time data;
the queue construction unit is used for screening the point location data to obtain a target filtering queue;
the data screening unit is used for sequentially taking each point location data as target point location data in the target filtering queue and screening the target point location data according to a preset judging strategy;
the data storage unit is used for determining that the target point location data are qualified data and storing the qualified data;
the track construction unit is used for sequencing all stored qualified data according to the sequence of the acquisition time to obtain an optimized real-time track of the personnel;
The preset judgment strategy comprises fusion characteristics at least comprising a point location real-time position, a speed, an acquisition time, a warehouse-in time, a point location mean value, a point location variance and adjacent point location deflection angles.
The invention also provides a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the method as described above when executing the program.
The invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the method as described above.
According to the real-time track optimization method based on multi-feature fusion filtering, the point location data of a target person in a preset period are obtained, and the point location data at least comprise position data, acquisition time data and warehouse-in time data; screening the point location data to obtain a target filtering queue, and in the target filtering queue, sequentially taking each point location data as target point location data, and screening the target point location data according to a preset judging strategy; if the target point position data are determined to be qualified data, storing the qualified data, and sequencing all stored qualified data according to the sequence of the acquisition time to obtain an optimized real-time personnel track; the preset judgment strategy comprises fusion characteristics at least comprising a point location real-time position, a speed, an acquisition time, a warehouse-in time, a point location mean value, a point location variance and adjacent point location deflection angles.
In order to correct track drift and enable the real-time track to meet the actual situation, the method for fusing multi-feature filtering is adopted to judge and remove abnormal data in the track, the GPS real-time track is optimized, and the multi-feature filtering analysis method based on the fused point real-time position, speed, acquisition time, warehousing time, point mean value, point variance, adjacent point deflection angle and the like is adopted to remove abnormal track data, so that optimization of the personnel real-time track is achieved, and the technical problem of poor real-time track optimization effect in the prior art is solved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It will be apparent to those of ordinary skill in the art that the drawings in the following description are exemplary only and that other implementations can be obtained from the extensions of the drawings provided without inventive effort.
The structures, proportions, sizes, etc. shown in the present specification are shown only for the purposes of illustration and description, and are not intended to limit the scope of the invention, which is defined by the claims, so that any structural modifications, changes in proportions, or adjustments of sizes, which do not affect the efficacy or the achievement of the present invention, should fall within the ambit of the technical disclosure.
FIG. 1 is a schematic flow chart of a real-time trajectory optimization method based on multi-feature fusion filtering according to the present invention;
FIG. 2 is a second flow chart of the real-time trajectory optimization method based on multi-feature fusion filtering according to the present invention;
FIG. 3 is a third flow chart of the real-time trajectory optimization method based on multi-feature fusion filtering according to the present invention;
FIG. 4 is a schematic structural diagram of a real-time trajectory optimization device based on multi-feature fusion filtering according to the present invention;
fig. 5 is a block diagram of a computer device according to the present invention.
Detailed Description
Other advantages and advantages of the present invention will become apparent to those skilled in the art from the following detailed description, which, by way of illustration, is to be read in connection with certain specific embodiments, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In order to solve the problem of poor real-time track optimization effect in the prior art, the method adopts a multi-feature filtering analysis method based on fusion point real-time position, speed, acquisition time, warehouse-in time, point mean value, point variance, adjacent point deflection angle and the like, eliminates abnormal track data, and optimizes the personnel real-time track.
In a specific embodiment, as shown in fig. 1, the real-time trajectory optimization method based on multi-feature fusion filtering provided by the invention comprises the following steps:
s110: acquiring a plurality of point location data of a target person in a preset period, wherein the point location data at least comprise position data, acquisition time data and warehousing time data;
s120: and screening the point location data to obtain a target filtering queue. Specifically, when constructing a target filtering queue, firstly, acquiring the effective duration of the target point location data, and adding the target point location data into the filtering queue under the condition that the effective duration is less than or equal to a duration threshold; and determining the actual data length of the filtering queue, and ordering the position data of all the target point position data in the filtering queue according to the acquisition time under the condition that the actual data length is greater than or equal to a length threshold value so as to obtain the target filtering queue. In this way, the point location data with the effective duration and the actual data duration not meeting the requirements are removed, so that the interference data of the constructed target filtering queue is less, and the workload of subsequent filtering is effectively reduced.
S130: in the target filtering queue, sequentially taking each point location data as target point location data, and screening the target point location data according to a preset judging strategy; the preset judgment strategy comprises fusion characteristics at least comprising a point location real-time position, a speed, an acquisition time, a warehouse-in time, a point location mean value, a point location variance and adjacent point location deflection angles.
S140: if the target point location data are determined to be qualified data, storing the qualified data; that is, after the data filtering in the above step S130, the obtained qualified data may be many groups, and the qualified data is stored so as to generate the track.
S150: and sequencing all stored qualified data according to the sequence of the acquisition time to obtain an optimized real-time personnel track.
In some embodiments, filtering each of the point location data to obtain a target filtering queue further includes:
initializing a filtering queue, setting the length of the filtering queue, and initializing point location, speed and state indication, wherein the point location is defined by the longitude and latitude coordinates (d 1 ，d 2 ) Converted into space rectangular coordinates (x, y, z).
In step S130, as shown in fig. 2, in the target filtering queue, each point location data is sequentially used as target point location data, and the target point location data is screened according to a preset determination policy, which specifically includes the following steps:
s210: calculating the point position speed of the target point position data in the target filtering queue;
s220: under the condition that the point position speed is lower than a speed threshold, calculating an overall mean value meanttotal, an overall variance stdTotal of the target filtering queue, a local mean value meanPart after the target point position data is removed, and a local variance stdPart after the target point position data is removed;
s230: calculating the mean absolute difference meanDiffabs and the variance ratio stdRatio of each target point location data according to the overall mean value, the overall variance stdTital, the local mean value meanPart after the target point location data are removed and the local variance stdPart after the target point location data are removed of the target filter queue;
s240: and determining the point with the maximum variance ratio stdRatio in all the target point bit data as a target point, and eliminating the corresponding target point bit data on the target point bit under the condition that the variance ratio stdRatio of the target point bit is larger than a preset variance ratio threshold and the mean absolute difference of the target point bit is smaller than a preset mean absolute difference threshold.
That is, when data screening is performed, the point location speed can be used as one of the judging conditions, when the point location speed meets the preset judging condition, the judgment is performed by using the mean absolute difference and the variance ratio, and the effect of track optimization is effectively improved by using the fusion characteristics of multiple dimensions as the judging basis.
Further, in the above step S240, after determining, as the target point, the point where the variance ratio stdwatio is the largest among all the target point bit data, the method may further include:
calculating the point-position adjacent time gpsTimeDiff of each target point-position data in the target filtering queue under the condition that the variance ratio stdRatio of the target point position is smaller than or equal to the variance ratio threshold and the mean absolute difference meanDiffabs of the target point position is larger than or equal to the mean absolute difference threshold;
and if the point position adjacent time of any point position in the target point position data is larger than a preset adjacent time threshold value, eliminating the target point position data corresponding to the point position, and resetting the target filtering queue.
That is, in some embodiments, after the determination is performed by the mean absolute difference and the variance ratio, in order to further improve the track optimization effect, the point location adjacent time may be further added as a determination condition, and the purposes of removing the corresponding point location and resetting the target filtering queue are achieved by determining the point location adjacent time.
Calculating the point neighboring time gpsTimeDiff of each target point data in the target filtering queue, and then further comprising:
calculating the angle change value of a target point group consisting of any three points in the target filtering queue when the point adjacent time of all the points in the target point data is smaller than or equal to the adjacent time threshold;
under the condition that the angle change value meets the angle change condition, eliminating point position data corresponding to the middle point position in the target filtering queue;
and outputting first data in the target filtering queue and marking the first data as the qualified data under the condition that the angle change value does not meet the angle change condition.
Therefore, when the data left after the judgment is carried out through the mean absolute difference and the variance ratio, the dimension of the angle change value is further utilized for screening, so that the screening accuracy of qualified data is further improved, and the effect of subsequent track optimization is further ensured.
For easy understanding, a specific algorithm process of the real-time trajectory optimization method based on multi-feature fusion filtering provided by the invention is described below by taking a specific usage scenario as an example.
As shown in fig. 3, in one specific usage scenario, it is assumed that the single target point location data is d= [ d ] 1 ，d 2 ，d 3 ，d 4 ]D comprises longitude d 1 Latitude d 2 GPS acquisition time d 3 GPS warehouse-in time d 4 The method comprises the steps of carrying out a first treatment on the surface of the Filter queue q= { Q i |i∈[1，L]' L is the queue length, q i For single point data d, where q i，j ＝d j ，i∈[1，L]，j∈[1，4]The data screening method comprises the following steps:
(1) Initializing a filtering queue Q to be empty, and setting the length L of the queue to be 5;
(2) Initializing a point location, a speed and a state indicating initstate=1, the point location being defined by geodetic longitude and latitude coordinates (d 1 ，d 2 ) Converting into space rectangular coordinates (x, y, z), wherein the speed unit is m/s;
(3) Reading individual position data d of a person in real time according to a certain frequency, and calculating effective duration t of the data d, wherein t=d 4 -d 3 ；
(4) Judging the effective duration T, if T is greater than a threshold value T (assuming T=3600s), discarding, and acquiring the next point position data d; if T < = threshold T, adding the position data to the filter queue Q;
(5) Judging the actual data length size (Q) of the queue Q, and returning to the step (3) if the size (Q) is less than L; if size (Q) > =l, ordering the position data in the queue Q by acquisition time;
(6) And calculating the speeds V of all adjacent positions in the queue Q according to the personnel position data and the acquisition time. If the newly added point speed V is more than 50m/s and initState=0, discarding the newly added point, and returning to the step (3); otherwise, calculating the Q overall mean value meanttotal and the variance stdTital, and the local mean value meanPart and the variance stdPart after each point bit is removed;
(7) Calculating the mean absolute difference meansdiffabs and the variance ratio stdRatio of each point, wherein meansdiffabs= |meanstotal-meanspart|, stdRatio=stdTital/stdPart
(8) Judging stdRatio and meanDiffabs, and eliminating the position data if the maximum stdRatio in each point position is more than 5 and the point position corresponds to meanDiffabs < 20; otherwise, calculate the phase adjacent time gpsTimeDiff, gpsTimeDiff =q of each point Q i+1，3 -q i，3 ，i∈[1，L-1]；
(9) Judging gpsTimeDiff, if gpsTimeDiff of a certain point in the queue Q is more than 100, clearing all data before the certain point in the queue Q, resetting the state initState=1, and then returning to the step (3); if gpsTimeDiff < = 100 at a certain point in the queue Q, calculating the angle change a among multiple groups of adjacent 3 points in the queue Q 123 、a 124 、a 234 ；
(10) Determination of angle a 123 、a 124 、a 234 If (a) 234 ＞100°||a 123 ＞100°)&&a 124 Eliminating the data of the middle point position of the Q queue and returning to the step 3; otherwise, outputting the first data of the Q queue and marking the first data as qualified data;
all qualified data obtained through the steps constitute an optimized real-time track of the personnel.
In the specific embodiment, the real-time track optimization method based on multi-feature fusion filtering provided by the invention is characterized in that a plurality of point location data of a target person in a preset period are obtained, wherein the point location data at least comprise position data, acquisition time data and warehouse-in time data; screening the point location data to obtain a target filtering queue, and in the target filtering queue, sequentially taking each point location data as target point location data, and screening the target point location data according to a preset judging strategy; if the target point position data are determined to be qualified data, storing the qualified data, and sequencing all stored qualified data according to the sequence of the acquisition time to obtain an optimized real-time personnel track; the preset judgment strategy comprises fusion characteristics at least comprising a point location real-time position, a speed, an acquisition time, a warehouse-in time, a point location mean value, a point location variance and adjacent point location deflection angles.
In order to correct track drift and enable the real-time track to meet the actual situation, the method for fusing multi-feature filtering is adopted to judge and remove abnormal data in the track, the GPS real-time track is optimized, and the multi-feature filtering analysis method based on the fused point real-time position, speed, acquisition time, warehousing time, point mean value, point variance, adjacent point deflection angle and the like is adopted to remove abnormal track data, so that optimization of the personnel real-time track is achieved, and the technical problem of poor real-time track optimization effect in the prior art is solved.
In addition to the above method, the present invention also provides a real-time trajectory optimization device based on multi-feature fusion filtering, as shown in fig. 4, where the device includes:
the data acquisition unit 401 is configured to acquire a plurality of point location data of a target person within a preset period, where the point location data at least includes position data, acquisition time data, and warehouse entry time data;
a queue construction unit 402, configured to screen each point location data to obtain a target filtering queue;
a data screening unit 403, configured to sequentially take each point location data as target point location data in the target filtering queue, and screen the target point location data according to a preset decision policy;
A data storage unit 404, configured to determine that the target point location data is qualified data, and store the qualified data;
the track construction unit 405 is configured to sort all stored qualified data according to the sequence of the acquisition time, so as to obtain an optimized real-time track of the person;
the preset judgment strategy comprises fusion characteristics at least comprising a point location real-time position, a speed, an acquisition time, a warehouse-in time, a point location mean value, a point location variance and adjacent point location deflection angles.
In some embodiments, filtering each point location data to obtain a target filtering queue specifically includes:
acquiring effective duration of the target point location data, and adding the target point location data into a filtering queue under the condition that the effective duration is smaller than or equal to a duration threshold;
and determining the actual data length of the filtering queue, and ordering the position data of all the target point position data in the filtering queue according to the acquisition time under the condition that the actual data length is greater than or equal to a length threshold value so as to obtain the target filtering queue.
In some embodiments, in the target filtering queue, each point location data is sequentially used as target point location data, and the target point location data is screened according to a preset determination policy, which specifically includes:
Calculating the point position speed of the target point position data in the target filtering queue;
under the condition that the point position speed is lower than a speed threshold, calculating an overall mean value meanttotal, an overall variance stdTotal of the target filtering queue, a local mean value meanPart after the target point position data is removed, and a local variance stdPart after the target point position data is removed;
calculating the mean absolute difference meanDiffabs and the variance ratio stdRatio of each target point location data according to the overall mean value, the overall variance stdTital, the local mean value meanPart after the target point location data are removed and the local variance stdPart after the target point location data are removed of the target filter queue;
and determining the point with the maximum variance ratio stdRatio in all the target point bit data as a target point, and eliminating the corresponding target point bit data on the target point bit under the condition that the variance ratio stdRatio of the target point bit is larger than a preset variance ratio threshold and the mean absolute difference of the target point bit is smaller than a preset mean absolute difference threshold.
In some embodiments, determining the point with the largest variance ratio stdwatio among all the target point bit data as the target point further includes:
Calculating the point-position adjacent time gpsTimeDiff of each target point-position data in the target filtering queue under the condition that the variance ratio stdRatio of the target point position is smaller than or equal to the variance ratio threshold and the mean absolute difference meanDiffabs of the target point position is larger than or equal to the mean absolute difference threshold;
and if the point position adjacent time of any point position in the target point position data is larger than a preset adjacent time threshold value, eliminating the target point position data corresponding to the point position, and resetting the target filtering queue.
In some embodiments, calculating a bit-adjacent time gpsTimeDiff for each of the target bit data in the target filter queue further includes:
calculating the angle change value of a target point group consisting of any three points in the target filtering queue when the point adjacent time of all the points in the target point data is smaller than or equal to the adjacent time threshold;
under the condition that the angle change value meets the angle change condition, eliminating point position data corresponding to the middle point position in the target filtering queue;
and outputting first data in the target filtering queue and marking the first data as the qualified data under the condition that the angle change value does not meet the angle change condition.
In some embodiments, filtering each of the point location data to obtain a target filtering queue further includes:
initializing a filtering queue and setting the length of the filtering queue.
In some embodiments, filtering each of the point location data to obtain a target filtering queue further includes:
initializing a point location, a speed and a status indication, wherein the point location is defined by a geodetic longitude and latitude coordinate (d 1 ，d 2 ) Converted into space rectangular coordinates (x, y, z).
In the specific embodiment, the real-time track optimizing device based on multi-feature fusion filtering provided by the invention is characterized in that the point location data at least comprises position data, acquisition time data and warehouse-in time data by acquiring a plurality of point location data of a target person in a preset period; screening the point location data to obtain a target filtering queue, and in the target filtering queue, sequentially taking each point location data as target point location data, and screening the target point location data according to a preset judging strategy; if the target point position data are determined to be qualified data, storing the qualified data, and sequencing all stored qualified data according to the sequence of the acquisition time to obtain an optimized real-time personnel track; the preset judgment strategy comprises fusion characteristics at least comprising a point location real-time position, a speed, an acquisition time, a warehouse-in time, a point location mean value, a point location variance and adjacent point location deflection angles.
In order to correct track drift and enable the real-time track to meet the actual situation, the method adopts a method of fusing multi-feature filtering to judge and remove abnormal data in the track, optimizes the GPS real-time track, and removes abnormal track data by adopting a multi-feature filtering analysis method based on fusion point real-time position, speed, acquisition time, warehouse-in time, point mean value, point variance, adjacent point deflection angle and the like, so that optimization of the personnel real-time track is realized, and the technical problem of poor real-time track optimization effect in the prior art is solved.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 5. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and model predictions. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The model predictions of the computer device are used to store static information and dynamic information data. The network interface of the computer device is used for communicating with an external terminal through a network connection. Which computer program, when being executed by a processor, carries out the steps of the above-mentioned method embodiments.
It will be appreciated by those skilled in the art that the structure shown in FIG. 5 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
Corresponding to the above embodiments, the present invention further provides a computer storage medium, which contains one or more program instructions. Wherein the one or more program instructions are for being executed with the method as described above.
The present invention also provides a computer program product comprising a computer program storable on a non-transitory computer readable storage medium, the computer program being capable of performing the above method when being executed by a processor.
In the embodiment of the invention, the processor may be an integrated circuit chip with signal processing capability. The processor may be a general purpose processor, a digital signal processor (Digital Signal Processor, DSP for short), an application specific integrated circuit (Application Specific f ntegrated Circuit ASIC for short), a field programmable gate array (FieldProgrammable Gate Array FPGA for short), or other programmable logic device, discrete gate or transistor logic device, discrete hardware components.
The disclosed methods, steps, and logic blocks in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be embodied directly in the execution of a hardware decoding processor, or in the execution of a combination of hardware and software modules in a decoding processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The processor reads the information in the storage medium and, in combination with its hardware, performs the steps of the above method.
The storage medium may be memory, for example, may be volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory.
The nonvolatile Memory may be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an electrically Erasable ROM (Electrically EPROM, EEPROM), or a flash Memory.
The volatile memory may be a random access memory (Random Access Memory, RAM for short) which acts as an external cache. By way of example, and not limitation, many forms of RAM are available, such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (Double Data RateSDRAM), enhanced SDRAM (ESDRAM), synchronous DRAM (SLDRAM), and direct memory bus RAM (directracram, DRRAM).
The storage media described in embodiments of the present invention are intended to comprise, without being limited to, these and any other suitable types of memory.
Those skilled in the art will appreciate that in one or more of the examples described above, the functions described in the present invention may be implemented in a combination of hardware and software. When the software is applied, the corresponding functions may be stored in a computer-readable medium or transmitted as one or more instructions or code on the computer-readable medium. Computer-readable media includes both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A storage media may be any available media that can be accessed by a general purpose or special purpose computer.
The foregoing detailed description of the invention has been presented for purposes of illustration and description, and it should be understood that the foregoing is by way of illustration and description only, and is not intended to limit the scope of the invention.
Claims (10)
1. A real-time trajectory optimization method based on multi-feature fusion filtering, the method comprising:
acquiring a plurality of point location data of a target person in a preset period, wherein the point location data at least comprise position data, acquisition time data and warehousing time data;
screening the point location data to obtain a target filtering queue;
in the target filtering queue, sequentially taking each point location data as target point location data, and screening the target point location data according to a preset judging strategy;
if the target point location data are determined to be qualified data, storing the qualified data;
sequencing all stored qualified data according to the sequence of the acquisition time to obtain an optimized real-time personnel track;
The preset judging strategy comprises fusion characteristics at least comprising a point location real-time position, a speed, an acquisition time, a warehousing time, a point location mean value, a point location variance and adjacent point location deflection angles;
in determining the qualified data, it is assumed that the single target point location data is d= [ d ] 1 ，d 2 ，d 3 ，d 4 ]D comprises longitude d 1 Latitude d 2 GPS acquisition time d 3 GPS warehouse-in time d 4 The method comprises the steps of carrying out a first treatment on the surface of the Filter queue q= { Q i |i∈[1，L]' L is the queue length, q i For single point data d, where q i，j ＝d j ，i∈[1，L]，j∈[1，4]The data screening method comprises the following steps:
(1) Initializing a filtering queue Q to be empty, and setting the length L of the queue to be 5;
(2) Initializing a point location, a speed and a state indicating initstate=1, the point location being defined by geodetic longitude and latitude coordinates (d 1 ，d 2 ) Is converted into a space rectangular coordinate (x,y, z), the speed unit is m/s;
(3) Reading individual position data d of a person in real time according to a certain frequency, and calculating effective duration t of the data d, wherein t=d 4 -d 3 ；
(4) Judging the effective duration T, if T is greater than a threshold value T, discarding if T=3600s, and acquiring the next point position data d; if T < = threshold T, adding the position data to the filter queue Q;
(5) Judging the actual data length size (Q) of the queue Q, and returning to the step (3) if the size (Q) is less than L; if size (Q) > =l, ordering the position data in the queue Q by acquisition time;
(6) Calculating the speeds V of all adjacent positions in the queue Q according to the personnel position data and the acquisition time, discarding the newly added point position if the newly added point position speed V is more than 50m/s and initState=0, and returning to the step (3); otherwise, calculating the Q overall mean value meanttotal and the variance stdTital, and the local mean value meanPart and the variance stdPart after each point bit is removed;
(7) Calculating the mean absolute difference meanddiffabs and the variance ratio stdRatio of each point, wherein meanddiffabs= |meandtotal-meanpart|, stdRatio=stdTital/stdPart;
(8) Judging stdRatio and meanDiffabs, and eliminating the position data if the maximum stdRatio in each point position is more than 5 and the point position corresponds to meanDiffabs < 20; otherwise, calculate the phase adjacent time gpsTimeDiff, gpsTimeDiff =q of each point Q i+1，3 -q i，3 ，i∈[1，L-1]；
(9) Judging gpsTimeDiff, if gpsTimeDiff of a certain point in the queue Q is more than 100, clearing all data before the certain point in the queue Q, resetting the state initState=1, and then returning to the step (3); if gpsTimeDiff < = 100 at a certain point in the queue Q, calculating the angle change a among multiple groups of adjacent 3 points in the queue Q 123 、a 124 、a 234 ；
(10) Determination of angle a 123 、a 124 、a 234 If (a) 234 ＞100°||a 123 ＞100°)&&a 124 Eliminating the data of the middle point position of the Q queue and returning to the step 3; Otherwise, the first data of the Q queue is output and marked as qualified data.
2. The real-time trajectory optimization method based on multi-feature fusion filtering according to claim 1, wherein the filtering of each point location data to obtain a target filtering queue specifically comprises:
acquiring effective duration of the target point location data, and adding the target point location data into a filtering queue under the condition that the effective duration is smaller than or equal to a duration threshold;
and determining the actual data length of the filtering queue, and ordering the position data of all the target point position data in the filtering queue according to the acquisition time under the condition that the actual data length is greater than or equal to a length threshold value so as to obtain the target filtering queue.
3. The real-time track optimization method based on multi-feature fusion filtering according to claim 2, wherein in the target filtering queue, each point location data is sequentially used as target point location data, and the target point location data is screened according to a preset judgment strategy, which specifically comprises:
calculating the point position speed of the target point position data in the target filtering queue;
under the condition that the point position speed is lower than a speed threshold, calculating an overall mean value meanttotal, an overall variance stdTotal of the target filtering queue, a local mean value meanPart after the target point position data is removed, and a local variance stdPart after the target point position data is removed;
Calculating the mean absolute difference meanDiffabs and the variance ratio stdRatio of each target point location data according to the overall mean value, the overall variance stdTital, the local mean value meanPart after the target point location data are removed and the local variance stdPart after the target point location data are removed of the target filter queue;
and determining the point with the maximum variance ratio stdRatio in all the target point bit data as a target point, and eliminating the corresponding target point bit data on the target point bit under the condition that the variance ratio stdRatio of the target point bit is larger than a preset variance ratio threshold and the mean absolute difference of the target point bit is smaller than a preset mean absolute difference threshold.
4. The real-time trajectory optimization method based on multi-feature fusion filtering of claim 3, wherein determining a point with the largest variance ratio stdRatio among all the target point bit data as a target point, further comprises:
calculating the point-position adjacent time gpsTimeDiff of each target point-position data in the target filtering queue under the condition that the variance ratio stdRatio of the target point position is smaller than or equal to the variance ratio threshold and the mean absolute difference meanDiffabs of the target point position is larger than or equal to the mean absolute difference threshold;
And if the point position adjacent time of any point position in the target point position data is larger than a preset adjacent time threshold value, eliminating the target point position data corresponding to the point position, and resetting the target filtering queue.
5. The method for optimizing real-time trajectories based on multi-feature fusion filtering of claim 4, wherein calculating a point-to-point adjacency time gpstimul f for each of the target point data in the target filter queue further comprises:
calculating the angle change value of a target point group consisting of any three points in the target filtering queue when the point adjacent time of all the points in the target point data is smaller than or equal to the adjacent time threshold;
under the condition that the angle change value meets the angle change condition, eliminating point position data corresponding to the middle point position in the target filtering queue;
and outputting first data in the target filtering queue and marking the first data as the qualified data under the condition that the angle change value does not meet the angle change condition.
6. The method for optimizing real-time trajectories based on multi-feature fusion filtering according to claim 2, wherein filtering each point location data to obtain a target filtering queue further comprises:
Initializing a filtering queue and setting the length of the filtering queue.
7. The method for optimizing real-time trajectories based on multi-feature fusion filtering according to claim 2, wherein filtering each point location data to obtain a target filtering queue further comprises:
initializing a point location, a speed and a status indication, wherein the point location is defined by a geodetic longitude and latitude coordinate (d 1 ，d 2 ) Converted into space rectangular coordinates (x, y, z).
8. A real-time trajectory optimization device based on multi-feature fusion filtering, the device comprising:
the data acquisition unit is used for acquiring a plurality of point location data of a target person in a preset period, wherein the point location data at least comprise position data, acquisition time data and warehouse-in time data;
the queue construction unit is used for screening the point location data to obtain a target filtering queue;
the data screening unit is used for sequentially taking each point location data as target point location data in the target filtering queue and screening the target point location data according to a preset judging strategy;
the data storage unit is used for determining that the target point location data are qualified data and storing the qualified data;
The track construction unit is used for sequencing all stored qualified data according to the sequence of the acquisition time to obtain an optimized real-time track of the personnel;
the preset judging strategy comprises fusion characteristics at least comprising a point location real-time position, a speed, an acquisition time, a warehousing time, a point location mean value, a point location variance and adjacent point location deflection angles;
in determining the qualified data, it is assumed that the single target point location data is d= [ d ] 1 ，d 2 ，d 3 ，d 4 ]D comprises longitude d 1 Latitude d 2 GPS acquisition time d 3 GPS warehouse-in time d 4 The method comprises the steps of carrying out a first treatment on the surface of the Filter queue q= { Q i |i∈[1，L]' L is the queue length, q i For single point data d, where q i，j ＝d j ，i∈[1，L]，j∈[1，4]The data screening method comprises the following steps:
(1) Initializing a filtering queue Q to be empty, and setting the length L of the queue to be 5;
(2) Initializing a point location, a speed and a state indicating initstate=1, the point location being defined by geodetic longitude and latitude coordinates (d 1 ，d 2 ) Converting into space rectangular coordinates (x, y, z), wherein the speed unit is m/s;
(3) Reading individual position data d of a person in real time according to a certain frequency, and calculating effective duration t of the data d, wherein t=d 4 -d 3 ；
(4) Judging the effective duration T, if T is greater than a threshold value T, discarding if T=3600s, and acquiring the next point position data d; if T < = threshold T, adding the position data to the filter queue Q;
(5) Judging the actual data length size (Q) of the queue Q, and returning to the step (3) if the size (Q) is less than L; if size (Q) > =l, ordering the position data in the queue Q by acquisition time;
(6) Calculating the speeds V of all adjacent positions in the queue Q according to the personnel position data and the acquisition time, discarding the newly added point position if the newly added point position speed V is more than 50m/s and initState=0, and returning to the step (3); otherwise, calculating the Q overall mean value meanttotal and the variance stdTital, and the local mean value meanPart and the variance stdPart after each point bit is removed;
(7) Calculating the mean absolute difference meanddiffabs and the variance ratio stdRatio of each point, wherein meanddiffabs= |meandtotal-meanpart|, stdRatio=stdTital/stdPart;
(8) Judging stdRatio and meanDiffAbs if the maximum in each point positionThe stdRatio of (2) is more than 5, and the point position corresponds to meanDiffabs < 20, and the position data is rejected; otherwise, calculate the phase adjacent time gpsTimeDiff, gpsTimeDiff =q of each point Q i+1，3 -q i，3 ，i∈[1，L-1]；
(9) Judging gpsTimeDiff, if gpsTimeDiff of a certain point in the queue Q is more than 100, clearing all data before the certain point in the queue Q, resetting the state initState=1, and then returning to the step (3); if gpsTimeDiff < = 100 at a certain point in the queue Q, calculating the angle change a among multiple groups of adjacent 3 points in the queue Q 123 、a 124 、a 234 ；
(10) Determination of angle a 123 、a 124 、a 234 If (a) 234 ＞100°||a 123 ＞100°)&&a 124 Eliminating the data of the middle point position of the Q queue and returning to the step 3; otherwise, the first data of the Q queue is output and marked as qualified data.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any one of claims 1 to 7 when the program is executed.
10. A non-transitory computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310133212.6A CN116136416B (en) | 2023-02-07 | 2023-02-07 | Real-time track optimization method and device based on multi-feature fusion filtering |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310133212.6A CN116136416B (en) | 2023-02-07 | 2023-02-07 | Real-time track optimization method and device based on multi-feature fusion filtering |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116136416A CN116136416A (en) | 2023-05-19 |
| CN116136416B true CN116136416B (en) | 2023-11-17 |
Family
ID=86333448
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310133212.6A Active CN116136416B (en) | 2023-02-07 | 2023-02-07 | Real-time track optimization method and device based on multi-feature fusion filtering |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116136416B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113963399A (en) * | 2021-09-09 | 2022-01-21 | 武汉众智数字技术有限公司 | Personnel trajectory retrieval method and device based on multi-algorithm fusion application |
| CN114492590A (en) * | 2021-12-29 | 2022-05-13 | 中科大数据研究院 | Boundary channel generation method and device based on track clustering |
| CN114743165A (en) * | 2022-03-22 | 2022-07-12 | 浙江大华技术股份有限公司 | Method and device for determining vehicle trajectory, storage medium and electronic device |
| CN114739391A (en) * | 2022-04-06 | 2022-07-12 | 重庆工商大学 | Positioning optimization method of tracking target |
| CN115203340A (en) * | 2022-07-05 | 2022-10-18 | 北京锐安科技有限公司 | Method, device, equipment and storage medium for determining companion relationship |
| CN115290071A (en) * | 2022-08-08 | 2022-11-04 | 爱驰汽车有限公司 | Relative positioning fusion method, device, equipment and storage medium |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10203214B2 (en) * | 2017-02-06 | 2019-02-12 | Here Global B.V. | Method and apparatus for filtering device location points in a sampled trajectory while maintaining path reconstructability |
| US11550827B2 (en) * | 2020-09-22 | 2023-01-10 | International Business Machines Corporation | Graph enabled location optimization |
-
2023
- 2023-02-07 CN CN202310133212.6A patent/CN116136416B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113963399A (en) * | 2021-09-09 | 2022-01-21 | 武汉众智数字技术有限公司 | Personnel trajectory retrieval method and device based on multi-algorithm fusion application |
| CN114492590A (en) * | 2021-12-29 | 2022-05-13 | 中科大数据研究院 | Boundary channel generation method and device based on track clustering |
| CN114743165A (en) * | 2022-03-22 | 2022-07-12 | 浙江大华技术股份有限公司 | Method and device for determining vehicle trajectory, storage medium and electronic device |
| CN114739391A (en) * | 2022-04-06 | 2022-07-12 | 重庆工商大学 | Positioning optimization method of tracking target |
| CN115203340A (en) * | 2022-07-05 | 2022-10-18 | 北京锐安科技有限公司 | Method, device, equipment and storage medium for determining companion relationship |
| CN115290071A (en) * | 2022-08-08 | 2022-11-04 | 爱驰汽车有限公司 | Relative positioning fusion method, device, equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| 增强型目标轨迹预测与目标筛选研究及实现;卢雄;客车技术与研究(第5期);第5-9页 * |
| 轨迹数据的特征融合及异常检测;饶元淇;中国优秀硕士学位论文全文数据库 信息科技辑(第5期);I138-525 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116136416A (en) | 2023-05-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110210604B (en) | Method and device for predicting movement track of terminal equipment | |
| US20180300549A1 (en) | Road detecting method and apparatus | |
| CN110969854A (en) | Traffic flow prediction method, system and terminal equipment | |
| CN110781756A (en) | Urban road extraction method and device based on remote sensing image | |
| JP2021174496A (en) | Trajectory prediction method and system | |
| CN110221600B (en) | Path planning method and device, computer equipment and storage medium | |
| CN112700479B (en) | Registration method based on CNN point cloud target detection | |
| EP3349126B1 (en) | Method, device, storage medium, and apparatus for automatically discovering fuel station poi | |
| CN109886477B (en) | Water pollution prediction method and device and electronic equipment | |
| CN112215273A (en) | Intelligent building information monitoring method based on cloud platform and intelligent building system | |
| CN112434260A (en) | Road traffic state detection method and device, storage medium and terminal | |
| CN111402293A (en) | Vehicle tracking method and device for intelligent traffic | |
| CN113514843A (en) | Multi-subgraph laser radar positioning method and system and terminal | |
| CN113111580A (en) | Method for constructing battery SOH evaluation model and method for evaluating battery SOH value | |
| CN110673146A (en) | Weather prediction image detection method and device, computer equipment and readable storage medium | |
| CN111538918B (en) | Recommendation method and device, electronic equipment and storage medium | |
| CN116136416B (en) | Real-time track optimization method and device based on multi-feature fusion filtering | |
| CN111258968B (en) | Enterprise redundant data cleaning method and device and big data platform | |
| CN110275895B (en) | Filling equipment, device and method for missing traffic data | |
| CN116703004A (en) | Water system river basin intelligent patrol method and device based on pre-training model | |
| Chandio et al. | Towards adaptable and tunable cloud-based map-matching strategy for GPS trajectories | |
| CN114664104B (en) | Road network matching method and device | |
| CN116260970A (en) | Network communication method and system based on data mass transmission | |
| Du et al. | Comparison between CBR and CA methods for estimating land use change in Dongguan, China | |
| CN113721240A (en) | Target association method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |