CN108182696A - Image processing method, device and Multi-target position tracking system - Google Patents
Image processing method, device and Multi-target position tracking system Download PDFInfo
- Publication number
- CN108182696A CN108182696A CN201810066147.9A CN201810066147A CN108182696A CN 108182696 A CN108182696 A CN 108182696A CN 201810066147 A CN201810066147 A CN 201810066147A CN 108182696 A CN108182696 A CN 108182696A
- Authority
- CN
- China
- Prior art keywords
- frame image
- target
- image
- movement target
- data processing
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K17/00—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations
- G06K17/0022—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations arrangements or provisious for transferring data to distant stations, e.g. from a sensing device
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides a kind of image processing method, device and Multi-target position tracking systems, are related to technical field of image processing.Previous frame image and next frame image of the method including camera acquisition environment to be measured are simultaneously sent to data processing module.The corresponding second feature point of the second movement target in data processing module extraction previous frame image in the corresponding fisrt feature point of first movement target and next frame image, judge whether fisrt feature point and second feature point meet preset condition, if satisfied, determine that the corresponding first movement target of fisrt feature point the second movement target corresponding with second feature point is same mobile target;First position information and second movement target second position information in next frame image of the first movement target in previous frame image is obtained again;First position information and second position information are then based on, obtains the corresponding motion track of first movement target.The corresponding motion track of the mobile target of acquisition is realized, more accurately.
Description
Technical field
The present invention relates to technical field of image processing, in particular to a kind of image processing method, device and multiple target
Locating and tracking system.
Background technology
In recent years, it about the location technology of article, is greatly developed, especially wireless aware location technology and computer
Vision positioning technology.Traditional location technology such as GPS, radar, laser etc., but its equipment is expensive, and application range has very greatly
Limitation.In wireless aware field, can realize the technology of positioning and article trajectory tracking has the technologies such as WIFI, CSI, RFID,
WIFI, CSI can realize the tracing and positioning of article under simple scenario, but if target is not single, implement just quite tired
Difficulty, and the slightly complicated precision that will substantially reduce its positioning of environment.
Invention content
The purpose of the present invention is to provide a kind of image processing method, device and Multi-target position tracking system, to improve
The above problem.To achieve these goals, the technical solution that the present invention takes is as follows:
In a first aspect, an embodiment of the present invention provides a kind of image processing method, applied to image processing apparatus, the figure
Picture processing unit includes camera and data processing module, and the camera is connect with the data processing module.The camera shooting
The previous frame image and next frame image of head acquisition environment to be measured simultaneously send the previous frame image and the next frame image
To the data processing module.The data processing module extracts first movement target corresponding first in the previous frame image
The corresponding second feature point of the second movement target in characteristic point and the next frame image, judges the fisrt feature point and institute
State whether second feature point meets preset condition, if satisfied, determining the corresponding first movement target of the fisrt feature point and institute
It is same mobile target to state the corresponding second movement target of second feature point.The data processing module obtains described first and moves
First position information and the second movement target of the moving-target in the previous frame image are in the next frame image
Second position information.The data processing module is based on the first position information and the second position information, described in acquisition
The corresponding motion track of first movement target.
Second aspect, an embodiment of the present invention provides a kind of image processing apparatus, including camera and data processing module,
The camera is connect with the data processing module.The camera, for acquiring the previous frame image of environment to be measured under
The previous frame image and the next frame image are simultaneously sent to the data processing module by one frame image.The data processing
Module, for extracting in the corresponding fisrt feature point of first movement target in the previous frame image and the next frame image
The corresponding second feature point of second movement target, judges whether the fisrt feature point and second feature point meet default item
Part, if satisfied, determining the second movement corresponding with the second feature point of the corresponding first movement target of the fisrt feature point
Target is same mobile target.The data processing module, for obtaining the first movement target in the previous frame figure
The second position information of first position information and the second movement target in the next frame image as in.The data
Processing module for being based on the first position information and the second position information, obtains the first movement target and corresponds to
Motion track.
The third aspect, an embodiment of the present invention provides a kind of Multi-target position tracking system, including above-mentioned image procossing
Device, RFID module and electronic equipment.The electronic equipment is connect with described image processing unit, the RFID module.It is described
Electronic equipment, for obtaining the M mobile corresponding motion track of target and the RFID that image processing apparatus is got
The phase value sequence for the target labels that module is got;It is regular based on the phase value sequence and the distance conversion of preset phase,
Obtain the distance between the target labels and the RFID value sequence;By the described M mobile corresponding moving rail of target
Each motion track in mark is matched one by one with described apart from value sequence, obtains the corresponding matching of each motion track
Value;Based on the corresponding matching value of each motion track, obtain the maximum value in the matching value and export the maximum value
The corresponding mobile target of corresponding motion track.
The advantageous effect of the embodiment of the present invention is:The previous frame image and next frame image of camera acquisition environment to be measured are simultaneously
The previous frame image and the next frame image are sent to data processing module.On the data processing module extraction is described
The second movement target in one frame image in the corresponding fisrt feature point of first movement target and the next frame image is corresponding
Second feature point, judges whether the fisrt feature point and second feature point meet preset condition, if satisfied, determining described
The corresponding first movement target of fisrt feature point the second movement target corresponding with the second feature point is same mobile mesh
Mark.The data processing module obtains first position information of the first movement target in the previous frame image and described
Second position information of the second movement target in the next frame image.The data processing module is based on the first position
Information and the second position information, obtain the corresponding motion track of the first movement target.Realize the mobile target of acquisition
Corresponding motion track, more accurately, to further improve positioning accuracy.
Other features and advantages of the present invention will illustrate, also, partly become from specification in subsequent specification
It is clear that by implementing understanding of the embodiment of the present invention.The purpose of the present invention and other advantages can be by saying what is write
Specifically noted structure is realized and is obtained in bright book, claims and attached drawing.
Description of the drawings
It in order to illustrate the technical solution of the embodiments of the present invention more clearly, below will be to needed in the embodiment attached
Figure is briefly described, it should be understood that the following drawings illustrates only certain embodiments of the present invention, therefore is not construed as pair
The restriction of range, for those of ordinary skill in the art, without creative efforts, can also be according to this
A little attached drawings obtain other relevant attached drawings.
Fig. 1 is the structure diagram of Multi-target position tracking system provided in an embodiment of the present invention;
Fig. 2 is application scenarios schematic diagram provided in an embodiment of the present invention;
Fig. 3 is the flow chart of image processing method provided in an embodiment of the present invention;
Fig. 4 is the structure diagram of image processing apparatus provided in an embodiment of the present invention.
Specific embodiment
Purpose, technical scheme and advantage to make the embodiment of the present invention are clearer, below in conjunction with the embodiment of the present invention
In attached drawing, the technical solution in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is
Part of the embodiment of the present invention, instead of all the embodiments.The present invention being usually described and illustrated herein in the accompanying drawings is implemented
The component of example can be configured to arrange and design with a variety of different.Therefore, below to provide in the accompanying drawings the present invention reality
The detailed description for applying example is not intended to limit the range of claimed invention, but is merely representative of the selected implementation of the present invention
Example.Based on the embodiments of the present invention, those of ordinary skill in the art are obtained without creative efforts
Every other embodiment, shall fall within the protection scope of the present invention.
It should be noted that:Similar label and letter represents similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined in a attached drawing, does not then need to that it is further defined and explained in subsequent attached drawing.Meanwhile the present invention's
In description, term " first ", " second " etc. are only used for distinguishing description, and it is not intended that instruction or hint relative importance.
RFID, as the key technology of Internet of Things, has been applied to life as one of this century most promising technology
In many scenes, for example the management in warehouse, the classification of airdrome luggage, commodity are traced to the source, library book sorts.Computer regards
Feel the advantage with Multi-target position with tracking, but it is being blocked or the target feelings such as outside computer vision monitoring range
Under condition, it is difficult to play supervisory function bit.RFID can also work in the case where blocking grade complex environments, although environment is more complicated,
Positioning accuracy is affected, but still can track the general orientation of article.It is mutual that the two technological incorporation can complete multiple target
It blocks, the article location tracking under the environment such as other articles block.
The following each embodiments of the present invention can be applied to Multi-target position tracking system as shown in Figure 1 unless otherwise instructed
In, as shown in Figure 1, system includes electronic equipment 100, image processing apparatus 200, RFID module 300.Electronic equipment 100 with
Image processing apparatus 200, RFID module 300 connect.As a kind of embodiment, electronic equipment 100 can be filled with image procossing
200, RFID module 300 is put to be electrically connected.Alternatively, electronic equipment 100 can pass through network and image processing apparatus
200th, RFID module 300 connects.The network can be wired or wireless network.In the embodiment of the present invention, electronic equipment 100,
Image processing apparatus 200, RFID module 300 can be directly connected to by communication network.Electronic equipment 100, image processing apparatus
200th, RFID module 300 can establish communication connection in Wi-Fi (Wireless Fidelity) network, 2G/3G/4G networks or LAN.
The electronic equipment, for obtaining the M mobile corresponding moving rail of target that image processing apparatus is got
The phase value sequence for the target labels that mark and the RFID module are got;Based on the phase value sequence and preset phase distance
From conversion rule, the distance between the target labels and the RFID value sequence are obtained;Described M mobile target is respectively right
Each motion track in the motion track answered is matched one by one with described apart from value sequence, obtains each motion track
Corresponding matching value;Based on the corresponding matching value of each motion track, the maximum value in the matching value and output are obtained
The corresponding mobile target of the corresponding motion track of the maximum value.
Further, the preset phase distance conversion rule can beInstitute
Electronic equipment is stated, for being based onObtain the target labels and the RFID
The distance between module value sequence, wherein, item numbers of the K for the phase value sequence, θ (ti) for i-th of phase value, D (ti) for institute
State i-th of distance value between target labels and the RFID module.
As shown in Fig. 2, C1 represents camera, C2 represents the antenna of RFID module, Bi, i=1, and 2 ..., M represents M shifting
Moving-target.If it was found that there is object loss, article is provided with target labels, and while transferring camera head monitor finds, article is lost
When, there are the M mobile i.e. multiple people of target to appear within field range simultaneously, and block mutually, only there are one mobile for the inside
Target carries target labels, but it is which movement target has taken away article on earth that cannot be differentiated with camera merely, at this moment
It tracks the motion track of each mobile target within sweep of the eye simultaneously using camera, while article rail is tracked using RFID technique
Mark, when be provided with the track of article of target labels with wherein some movement target movement track it is consistent when, band can be confirmed
Walk the mobile target of article which, complete the tracking and matching of target trajectory, can also be using only even if target is blocked
RFID determines target location.There are multiple mobile targets in the scene of Fig. 2, adhere to target labels, mesh in some movement target
Mark label is RFID label tag.Field range is continuously monitored using a monocular cam, the antenna of RFID reader is received simultaneously
Collect the phase value sequence of information, that is, target labels of target labels.
In the embodiment of the present invention, electronic equipment 100 can be used as user terminal or as server.Electronic equipment
Can be PC (personal computer) computer, tablet computer, mobile phone, laptop, smart television, set-top box, vehicle-mounted
The terminal devices such as terminal.The RFID module can include RFID reader.RFID, that is, Radio Frequency
Identification。
Referring to Fig. 3, an embodiment of the present invention provides a kind of image processing method, it is described applied to image processing apparatus
Image processing apparatus includes camera and data processing module, and the camera is connect with the data processing module.The side
Method includes step S200, step S210, step S220 and step S230.
Step S200:The camera acquires the previous frame image of environment to be measured and next frame image and by the previous frame
Image and the next frame image are sent to the data processing module.
Step S210:The data processing module extracts corresponding first spy of first movement target in the previous frame image
Sign point and second the corresponding second feature point of target is moved in the next frame image, judge the fisrt feature point and described
Whether second feature point meets preset condition, if satisfied, determine the corresponding first movement target of the fisrt feature point with it is described
The corresponding second movement target of second feature point is same mobile target.
Further, the data processing module is filtered the previous frame image and the next frame image respectively
After processing, the previous frame image after filtering process and the next frame image are obtained;To described upper one after filtering process
Frame image and the next frame image are detected connected region processing, extract the in the previous frame image after filtering process
Second movement target corresponding the in the next frame image after the 1 corresponding fisrt feature point of movement target and filtering process
Two characteristic points.
Further, the preset condition can be no more than preset difference value, judge the fisrt feature point and described the
Whether two characteristic points are no more than preset difference value, if so, determining the corresponding first movement target of the fisrt feature point and described the
The corresponding second movement target of two characteristic points is same mobile target.Preset difference value can be the positive number of a very little, such as
Preset difference value can be 0.
The filtering process can include mean filter, medium filtering, low-pass filtering, middle pass filter or high-pass filtering.
Before filtering process, the method can also include calibration camera, to improve positioning accuracy, determine camera
Inside and outside parameter eliminates the influence brought due to camera distortion.
Feature point extraction is to extract the obvious characteristic in mobile target, such as the edge contour of object, the face of people
The color character etc. of feature, object, some dotted, the linear or planar features that object can be distinguished from ambient background.
Can image coordinate be converted into according to the image coordinate of camera and the relationship of world coordinate system by the world after extraction characteristic point
Coordinate, so as to fulfill the positioning of target.Feature point extraction is by detecting connected region moving target from the back of the body in the present embodiment
Scape static object is split.With the method for center coordination, the position of characteristic point in space at this time is determined.
Step S220:The data processing module obtains first of the first movement target in the previous frame image
The second position information of location information and the second movement target in the next frame image.
Further, the data processing module obtains first of the first movement target in the previous frame image
The second image coordinate of image coordinate and the second movement target in the next frame image;The data processing module will
Described first image coordinate is converted to first world's coordinate and second image coordinate is converted to second world coordinate.
Step S230:The data processing module is based on the first position information and the second position information, obtains
The corresponding motion track of the first movement target.
Further, the data processing module is based on first world's coordinate and the second world coordinate, obtains
The corresponding motion track of the first movement target.
If include multiple mobile targets in the previous frame image of environment to be measured and next frame image, based on step
S210- steps S230, similar, the corresponding motion track of each movement target of acquisition.If presetting for environment to be measured is got
During multiple image in the time, based on step S200- step S230, each mobile target corresponding shifting in preset time is obtained
Dynamic rail mark.
An embodiment of the present invention provides a kind of image processing methods, and the method includes cameras to acquire the upper of environment to be measured
The previous frame image and the next frame image are simultaneously sent to data processing module by one frame image and next frame image.It is described
Data processing module extracts the corresponding fisrt feature point of first movement target and the next frame image in the previous frame image
In the second corresponding second feature point of movement target, judge the fisrt feature point and second feature point whether meet it is pre-
If condition, if satisfied, determining the corresponding first movement target of the fisrt feature point and the second feature point corresponding second
Mobile target is same mobile target.The data processing module obtains the first movement target in the previous frame image
In first position information and the second position information of the second movement target in the next frame image.At the data
It manages module and is based on the first position information and the second position information, obtain the corresponding moving rail of the first movement target
Mark.The corresponding motion track of the mobile target of acquisition is realized, more accurately, to further improve positioning accuracy.It can be applied to supervise
Control article etc..
Referring to Fig. 4, described image processing unit 200 can include camera 210 and data processing module 220.It is described
Camera 210 is connect with the data processing module 220.
The camera 210, for acquiring the previous frame image of environment to be measured and next frame image and by the previous frame
Image and the next frame image are sent to the data processing module.
The data processing module 220, for extracting corresponding first spy of first movement target in the previous frame image
Sign point and second the corresponding second feature point of target is moved in the next frame image, judge the fisrt feature point and described
Whether second feature point meets preset condition, if satisfied, determine the corresponding first movement target of the fisrt feature point with it is described
The corresponding second movement target of second feature point is same mobile target;
The data processing module 220, for obtaining the first movement target first in the previous frame image
The second position information of location information and the second movement target in the next frame image;
The data processing module 220 for being based on the first position information and the second position information, obtains institute
State the corresponding motion track of first movement target.
Further, the data processing module 220, for the previous frame image and next frame image difference
After being filtered, the previous frame image after filtering process and the next frame image are obtained;After filtering process
The previous frame image and the next frame image are detected connected region processing, extract the previous frame after filtering process
Second movement target in the next frame image in image after the corresponding fisrt feature point of first movement target and filtering process
Corresponding second feature point.
Further, the data processing module 220, for obtaining the first movement target in the previous frame image
In the first image coordinate and second image coordinate of the second movement target in the next frame image;At the data
Described first image coordinate is converted to first world's coordinate and second image coordinate is converted to the second world by reason module
Coordinate.
In the present embodiment, data processing module 220 can include processor, storage control and memory.Processor
It is electrically connected by storage control with the memory.
Memory can store various software programs and module, such as image processing method pair provided by the embodiments of the present application
Program instruction/the module answered.Processor is various so as to perform by running software program and module stored in memory
The image processing method in the embodiment of the present application is realized in application of function and data processing.
Memory can include but is not limited to random access memory (Random Access Memory, RAM), read-only to deposit
Reservoir (Read Only Memory, ROM), programmable read only memory (Programmable Read-Only Memory,
PROM), erasable read-only memory (Erasable Programmable Read-Only Memory, EPROM), electric erasable
Read-only memory (Electric Erasable Programmable Read-Only Memory, EEPROM) etc..
Processor can be a kind of IC chip, have signal handling capacity.Above-mentioned processor can be general place
Device is managed, including central processing unit (Central Processing Unit, abbreviation CPU), network processing unit (Network
Processor, abbreviation NP) etc.;It can also be digital signal processor (DSP), application-specific integrated circuit (ASIC), ready-made programmable
Gate array (FPGA) either other programmable logic device, discrete gate or transistor logic, discrete hardware components.It can
To realize or perform disclosed each method, step and the logic diagram in the embodiment of the present application.General processor can be micro-
Processor or the processor can also be any conventional processors etc..
The technique effect of image processing apparatus 200 provided in an embodiment of the present invention, realization principle and generation and aforementioned side
Method embodiment is identical, and to briefly describe, device embodiment part does not refer to part, can refer in corresponding in preceding method embodiment
Hold.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, that is made any repaiies
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (10)
1. a kind of image processing method, which is characterized in that applied to image processing apparatus, described image processing unit includes camera shooting
Head and data processing module, the camera are connect with the data processing module;The method includes:
The camera acquire environment to be measured previous frame image and next frame image and by the previous frame image and it is described under
One frame image is sent to the data processing module;
The data processing module extract in the previous frame image the corresponding fisrt feature point of first movement target and it is described under
The corresponding second feature point of the second movement target in one frame image, judges that the fisrt feature point and second feature point are
It is no to meet preset condition, if satisfied, determining the corresponding first movement target of the fisrt feature point and the second feature point pair
The the second movement target answered is same mobile target;
The data processing module obtains first position information and institute of the first movement target in the previous frame image
State second position information of the second movement target in the next frame image;
The data processing module is based on the first position information and the second position information, obtains the first movement mesh
Mark corresponding motion track.
2. according to the method described in claim 1, it is characterized in that, the data processing module is extracted in the previous frame image
The corresponding second feature point of the second movement target in the corresponding fisrt feature point of first movement target and the next frame image,
Including:
After the data processing module is filtered the previous frame image and the next frame image respectively, filtered
Wave treated the previous frame image and the next frame image;
Connected region processing, extraction filtering are detected to the previous frame image after filtering process and the next frame image
The next frame in treated the previous frame image after the corresponding fisrt feature point of first movement target and filtering process
The corresponding second feature point of second movement target in image.
3. according to the method described in claim 2, it is characterized in that, the filtering process includes mean filter, medium filtering, low
Pass filter, middle pass filter or high-pass filtering.
4. according to the method described in claim 2, it is characterized in that, the data processing module obtains the first movement target
The second of first position information and the second movement target in the next frame image in the previous frame image
Confidence ceases, including:
The data processing module obtains first image coordinate and institute of the first movement target in the previous frame image
State second image coordinate of the second movement target in the next frame image;
Described first image coordinate is converted to first world's coordinate and by second image coordinate by the data processing module
Be converted to second world coordinate.
5. according to the method described in claim 4, it is characterized in that, the data processing module is based on the first position information
With the second position information, the corresponding motion track of the first movement target is obtained, including:
The data processing module is based on first world's coordinate and the second world coordinate, obtains the first movement mesh
Mark corresponding motion track.
6. a kind of image processing apparatus, which is characterized in that including camera and data processing module, the camera and the number
It is connected according to processing module;
The camera, for acquiring the previous frame image of environment to be measured and next frame image and by the previous frame image and institute
It states next frame image and is sent to the data processing module;
The data processing module, for extracting the corresponding fisrt feature point of first movement target in the previous frame image and institute
The corresponding second feature point of the second movement target in next frame image is stated, judges the fisrt feature point and the second feature
Whether point meets preset condition, if satisfied, determining the corresponding first movement target of the fisrt feature point and the second feature
The corresponding second movement target of point is same mobile target;
The data processing module, for obtaining first position information of the first movement target in the previous frame image
And second position information of the second movement target in the next frame image;
The data processing module for being based on the first position information and the second position information, obtains described first
The corresponding motion track of movement target.
7. image processing apparatus according to claim 6, which is characterized in that the data processing module, for described
After previous frame image and the next frame image are filtered respectively, obtain filtering process after the previous frame image and
The next frame image;The previous frame image after filtering process and the next frame image are detected at connected region
Reason is extracted in the previous frame image after filtering process after the corresponding fisrt feature point of first movement target and filtering process
The corresponding second feature point of second movement target in the next frame image.
8. image processing apparatus according to claim 7, which is characterized in that the data processing module, for obtaining
First image coordinate and the second movement target of the first movement target in the previous frame image are stated in the next frame
The second image coordinate in image;Described first image coordinate is converted to first world's coordinate and will by the data processing module
Second image coordinate is converted to second world coordinate.
9. a kind of Multi-target position tracking system, which is characterized in that including such as claim 6-8 any one of them image procossing
Device, RFID module and electronic equipment, the electronic equipment are connect with described image processing unit, the RFID module;It is described
Electronic equipment, for obtaining the M mobile corresponding motion track of target and the RFID that image processing apparatus is got
The phase value sequence for the target labels that module is got;It is regular based on the phase value sequence and the distance conversion of preset phase,
Obtain the distance between the target labels and the RFID value sequence;By the described M mobile corresponding moving rail of target
Each motion track in mark is matched one by one with described apart from value sequence, obtains the corresponding matching of each motion track
Value;Based on the corresponding matching value of each motion track, obtain the maximum value in the matching value and export the maximum value
The corresponding mobile target of corresponding motion track.
10. system according to claim 9, which is characterized in that the preset phase distance conversion rule isThe electronic equipment, for being based onIt obtains
The distance between the target labels and the RFID module value sequence are obtained, wherein, item numbers of the K for the phase value sequence, θ
(ti) for i-th of phase value, D (ti) i-th of distance value between the target labels and the RFID module.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810066147.9A CN108182696A (en) | 2018-01-23 | 2018-01-23 | Image processing method, device and Multi-target position tracking system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810066147.9A CN108182696A (en) | 2018-01-23 | 2018-01-23 | Image processing method, device and Multi-target position tracking system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108182696A true CN108182696A (en) | 2018-06-19 |
Family
ID=62551295
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810066147.9A Pending CN108182696A (en) | 2018-01-23 | 2018-01-23 | Image processing method, device and Multi-target position tracking system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108182696A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113781519A (en) * | 2020-06-09 | 2021-12-10 | 华为技术有限公司 | Target tracking method and target tracking device |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1852428A (en) * | 2006-05-25 | 2006-10-25 | 浙江工业大学 | Intelligent tunnel safety monitoring apparatus based on omnibearing computer vision |
CN101840507A (en) * | 2010-04-09 | 2010-09-22 | 江苏东大金智建筑智能化***工程有限公司 | Target tracking method based on character feature invariant and graph theory clustering |
CN102222341A (en) * | 2010-04-16 | 2011-10-19 | 东软集团股份有限公司 | Method and device for detecting motion characteristic point and method and device for detecting motion target |
US20150071489A1 (en) * | 2013-09-12 | 2015-03-12 | The Boeing Company | Isotropic Feature Matching |
CN104915618A (en) * | 2015-07-03 | 2015-09-16 | 南京大学 | Ultrahigh-frequency-RFID-technology-based book reservation method of library |
CN105512700A (en) * | 2015-12-01 | 2016-04-20 | 杨春光 | RFID and video technology-based analysis method and analysis system thereof |
CN107066931A (en) * | 2017-01-12 | 2017-08-18 | 张家港全智电子科技有限公司 | A kind of target trajectory tracking based on monitor video |
-
2018
- 2018-01-23 CN CN201810066147.9A patent/CN108182696A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1852428A (en) * | 2006-05-25 | 2006-10-25 | 浙江工业大学 | Intelligent tunnel safety monitoring apparatus based on omnibearing computer vision |
CN101840507A (en) * | 2010-04-09 | 2010-09-22 | 江苏东大金智建筑智能化***工程有限公司 | Target tracking method based on character feature invariant and graph theory clustering |
CN102222341A (en) * | 2010-04-16 | 2011-10-19 | 东软集团股份有限公司 | Method and device for detecting motion characteristic point and method and device for detecting motion target |
US20150071489A1 (en) * | 2013-09-12 | 2015-03-12 | The Boeing Company | Isotropic Feature Matching |
CN104915618A (en) * | 2015-07-03 | 2015-09-16 | 南京大学 | Ultrahigh-frequency-RFID-technology-based book reservation method of library |
CN105512700A (en) * | 2015-12-01 | 2016-04-20 | 杨春光 | RFID and video technology-based analysis method and analysis system thereof |
CN107066931A (en) * | 2017-01-12 | 2017-08-18 | 张家港全智电子科技有限公司 | A kind of target trajectory tracking based on monitor video |
Non-Patent Citations (1)
Title |
---|
徐晶 等: "《计算机视觉中的运动检测与跟踪》", 30 September 2012, 国防工业出版社 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113781519A (en) * | 2020-06-09 | 2021-12-10 | 华为技术有限公司 | Target tracking method and target tracking device |
WO2021249114A1 (en) * | 2020-06-09 | 2021-12-16 | 华为技术有限公司 | Target tracking method and target tracking device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111046752B (en) | Indoor positioning method, computer equipment and storage medium | |
Li et al. | Capturing human pose using mmWave radar | |
CN108805900B (en) | Method and device for determining tracking target | |
CN108376273A (en) | Multi-target position tracking, device, computer-readable medium and electronic equipment | |
CN108875542B (en) | Face recognition method, device and system and computer storage medium | |
CN109357679B (en) | Indoor positioning method based on significance characteristic recognition | |
CN114641809B (en) | Motion timing based on camera system | |
Nie et al. | Single/cross-camera multiple-person tracking by graph matching | |
CN106470478B (en) | Positioning data processing method, device and system | |
KR102572986B1 (en) | Object Tracking Based on Custom Initialization Points | |
CN109509233B (en) | PTZ camera target tracking method, system and device based on RFID label position information | |
Wang et al. | Computer vision-assisted 3D object localization via COTS RFID devices and a monocular camera | |
CN109635797A (en) | Coil of strip sequence precise positioning method based on multichip carrier identification technology | |
Yang et al. | Intelligent video analysis: A Pedestrian trajectory extraction method for the whole indoor space without blind areas | |
Fan et al. | Long-term visual tracking algorithm for UAVs based on kernel correlation filtering and SURF features | |
CN111047622A (en) | Method and device for matching objects in video, storage medium and electronic device | |
Duan et al. | Enabling RFID-based tracking for multi-objects with visual aids: A calibration-free solution | |
CN108280496A (en) | Method for synchronizing time, device, medium based on RFID and electronic equipment | |
CN109523573A (en) | The tracking and device of target object | |
CN114500873A (en) | Tracking shooting system | |
CN108182696A (en) | Image processing method, device and Multi-target position tracking system | |
Shi et al. | TagAttention: Mobile object tracing without object appearance information by vision-RFID fusion | |
CN113409358A (en) | Image tracking method, image tracking device, storage medium and electronic equipment | |
Ma et al. | Spatial perception of tagged cargo using fused RFID and CV data in intelligent storage | |
Tsai et al. | Design of vision‐based indoor positioning based on embedded system |
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 | ||
CB02 | Change of applicant information |
Address after: 610000 Floor 23, No. 11, Tianfu Software Park, 219 Tianhua Second Road, China (Sichuan) Free Trade Experimental Zone, Chengdu, Sichuan Province Applicant after: Sichuan science and technology Limited by Share Ltd Address before: 610000 floor 23, 11 building C, Tianfu Software Park, 219 Tianhua two road, Chengdu High-tech Zone, Sichuan. Applicant before: SICHUAN JINGGONG WEIDA INTELLIGENT TECHNOLOGY CO., LTD. |
|
CB02 | Change of applicant information | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180619 |
|
RJ01 | Rejection of invention patent application after publication |