CN107871019A - People's car association search method and device - Google Patents
People's car association search method and device Download PDFInfo
- Publication number
- CN107871019A CN107871019A CN201711247163.XA CN201711247163A CN107871019A CN 107871019 A CN107871019 A CN 107871019A CN 201711247163 A CN201711247163 A CN 201711247163A CN 107871019 A CN107871019 A CN 107871019A
- Authority
- CN
- China
- Prior art keywords
- image
- vehicle
- target person
- people
- behavior
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
Landscapes
- Engineering & Computer Science (AREA)
- Library & Information Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The embodiment of the present invention provides a kind of people's car association search method and device.People's car association search method includes：The first object image of the character features is included in the image gathered according to the character features query image collecting device of setting, realizes the image search to target person；When the target person is close to vehicle, judge whether the target person has the behavior into the vehicle；When the target person has into during the behavior of the vehicle, the vehicle characteristics of the vehicle are obtained；The second target image for including the vehicle characteristics in the image of described image collecting device collection is inquired about according to the vehicle characteristics, realizes the image search to vehicle.
Description
Technical field
The present invention relates to image processing field, in particular to a kind of people's car association search method and device.
Background technology
For video monitoring image system, such as day eye system, all installed in the diverse location of monitor area (e.g., road)
There is monitoring device (such as high-definition camera, night vision camera is first-class), for being monitored in real time to objects such as people, vehicles.Some when
Time can also be scanned for by the monitor video that the monitoring device is shot to particular persons, but due to the environment on road
Complexity, the particular person behavior such as get on the bus, get off can cause that the image of people can not be obtained again, cause to be difficult to continue target person
Search.
The content of the invention
In view of this, the purpose of the embodiment of the present invention is to provide a kind of people's car association search method and device.
A kind of people's car association search method provided in an embodiment of the present invention, applied to control terminal, it is described control terminal with
Multiple images collecting device communicates to connect, and people's car association search method includes：
The first of the character features are included in the image gathered according to the character features query image collecting device of setting
Target image is realized to be searched for the image of target person；
When the target person is close to vehicle, judge whether the target person has the behavior into the vehicle；
When the target person has into during the behavior of the vehicle, the vehicle characteristics of the vehicle are obtained；
The comprising the vehicle characteristics is inquired about in the image that described image collecting device gathers according to the vehicle characteristics
Two target images are realized to be searched for the image of vehicle.
Preferably, people's car association search method also includes：
Analysis is carried out to second target image and determines whether that the target person leaves the behavior of the vehicle；
When the target person has the behavior for leaving the vehicle, institute is included in the image of query image collecting device collection
State the first object image of character features, or in the image of query image collecting device collection comprising the character features the
One target image and the second target image comprising the vehicle characteristics.
The embodiment of the present invention also provides a kind of people's car association search device, applied to control terminal, it is described control terminal with
Multiple images collecting device communicates to connect, and people's car association identification device includes：
First enquiry module, for including institute in the image that is gathered according to the character features query image collecting device of setting
The first object image realization for stating character features is searched for the image of target person；
First judge module, for when the target person is close to vehicle, judging whether the target person has entrance
The behavior of the vehicle；
Acquisition module, for when the target person have it is special into the vehicle for during behavior of the vehicle, obtaining the vehicle
Sign；
Second enquiry module, for being included in the image according to vehicle characteristics inquiry described image collecting device collection
Second target image of the vehicle characteristics is realized to be searched for the image of vehicle.
Preferably, people's car association search device also includes：
Second judge module, determine whether that the target person leaves for carrying out analysis to second target image
The behavior of the vehicle；
When there is the behavior that the target person leaves the vehicle, first enquiry module, or triggering institute are triggered
State the first enquiry module and second enquiry module.
Compared with prior art, people's car association search method and device provided in an embodiment of the present invention, passes through character features
The first object image comprising the character features in the image that query image collecting device collects is gone to realize to target person
Image search.When the target person is got on the bus, then vehicle is scanned for, realize people's car associative search, can be more effective
The whereabouts of target person are searched on ground.
To enable the above objects, features and advantages of the present invention to become apparent, preferred embodiment cited below particularly, and coordinate
Appended accompanying drawing, is described in detail below.
Brief description of the drawings
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below by embodiment it is required use it is attached
Figure is briefly described, it will be appreciated that the following drawings illustrate only certain embodiments of the present invention, therefore be not construed as pair
The restriction of scope, for those of ordinary skill in the art, on the premise of not paying creative work, can also be according to this
A little accompanying drawings obtain other related accompanying drawings.
Fig. 1 is the schematic diagram that the control terminal that present pre-ferred embodiments provide interacts with image capture device.
Fig. 2 is the block diagram for the control terminal that present pre-ferred embodiments provide.
Fig. 3 is the flow chart for people's car association search method that present pre-ferred embodiments provide.
Fig. 4 is the flow chart for people's car association search method that present pre-ferred embodiments provide.
Fig. 5 is the high-level schematic functional block diagram for people's car association search device that present pre-ferred embodiments provide.
Embodiment
Below in conjunction with accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Ground describes, it is clear that described embodiment is only part of the embodiment of the present invention, rather than whole embodiments.Generally exist
The component of the embodiment of the present invention described and illustrated in accompanying drawing can be configured to arrange and design with a variety of herein.Cause
This, the detailed description of the embodiments of the invention to providing in the accompanying drawings is not intended to limit claimed invention below
Scope, but it is merely representative of the selected embodiment of the present invention.Based on embodiments of the invention, those skilled in the art are not doing
The every other embodiment obtained on the premise of going out creative work, belongs to the scope of protection of the invention.
It should be noted that：Similar label and letter represents similar terms in following accompanying drawing, therefore, once a certain Xiang Yi
It is defined, then it further need not be defined and explained in subsequent accompanying drawing in individual accompanying 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.
As shown in figure 1, it is that the control terminal 100 that present pre-ferred embodiments provide is handed over image capture device 200
Mutual schematic diagram.The control terminal 100 is communicatively coupled by network and one or more image capture devices 200, with
Enter row data communication or interaction.The control terminal 100 can be the webserver, database server etc..The control is eventually
End 100 can also be PC (personal computer, PC), tablet personal computer, smart mobile phone, personal digital assistant
(personal digital assistant, PDA) etc..Described image collecting device 200 can be the individual containing camera
Computer (personal computer, PC), video monitoring apparatus on street etc..
As shown in Fig. 2 it is the block diagram of the control terminal 100 shown in Fig. 1.The control terminal 100 includes
People's car association search device 110, memory 111, storage control 112, processor 113, Peripheral Interface 114, input and output list
Member 115, display unit 116.It will appreciated by the skilled person that the structure shown in Fig. 2 is only to illustrate, it is not to control
The structure of terminal 100 processed causes to limit.For example, control terminal 100 may also include the group more or less than shown in Fig. 2
Part, or there is the configuration different from shown in Fig. 2.
The memory 111, storage control 112, processor 113, Peripheral Interface 114, input-output unit 115 and aobvious
Show that 116 each element of unit is directly or indirectly electrically connected between each other, to realize the transmission of data or interaction.For example, these
Element can be realized by one or more communication bus or signal wire be electrically connected between each other.People's car association search device
110 can be stored in the memory 111 or be solidificated in institute including at least one in the form of software or firmware (Firmware)
State the software function module in the operating system (Operating System, OS) of control terminal 100.The processor 113 is used
In performing the executable module that is stored in memory, such as the software function module that people's car association search device 110 includes
Or computer program.
Wherein, the memory 111 may be, but not limited to, random access memory (Random Access
Memory, RAM), read-only storage (Read Only Memory, ROM), programmable read only memory (Programmable
Read-Only Memory, PROM), erasable read-only memory (Erasable Programmable Read-Only
Memory, EPROM), electricallyerasable ROM (EEROM) (Electric Erasable Programmable Read-Only
Memory, EEPROM) etc..Wherein, memory 111 is used for storage program, the processor 113 after execute instruction is received,
Described program is performed, the method performed by control terminal 100 that the process that any embodiment of the embodiment of the present invention discloses defines can
To be realized applied in processor 113, or by processor 113.
The processor 113 is probably a kind of IC chip, has the disposal ability of signal.Above-mentioned processor
113 can be general processor, including central processing unit (Central Processing Unit, abbreviation CPU), network processes
Device (Network Processor, abbreviation NP) etc.；It can also be digital signal processor (DSP), application specific integrated circuit
(ASIC), field programmable gate array (FPGA) either other PLDs, discrete gate or transistor logic,
Discrete hardware components.It can realize or perform disclosed each method, step and the logic diagram in the embodiment of the present invention.It is general
Processor can be microprocessor or the processor can also be any conventional processor etc..
Various input/output devices are coupled to processor 113 and memory 111 by the Peripheral Interface 114.At some
In embodiment, Peripheral Interface 114, processor 113 and storage control 112 can be realized in one single chip.Other one
In a little examples, they can be realized by independent chip respectively.
The input-output unit 115 is used to be supplied to user input data.The input-output unit 115 can be,
But it is not limited to, mouse and keyboard etc..
The display unit 116 provides interactive interface between the control terminal 100 and user, and (such as user grasps
Make interface) or for display image data give user reference.In the present embodiment, the display unit can be liquid crystal display
Or touch control display.If touch control display, it can be the capacitance type touch control screen or resistance for supporting single-point and multi-point touch operation
Formula touch screen etc..Single-point and multi-point touch operation is supported to refer to that touch control display can sense on the touch control display one
Or multiple opening positions touch control operation with caused by, and the touch control operation that this is sensed transfers to processor to be calculated and located
Reason.
Referring to Fig. 3, it is that the people's car association for being applied to the control terminal shown in Fig. 2 that present pre-ferred embodiments provide is searched
Suo Fangfa flow chart.The idiographic flow shown in Fig. 3 will be described in detail below.
Step S101, according to special comprising the personage in the image of the character features query image collecting device of setting collection
The first object image of sign is realized to be searched for the image of target person.
In one embodiment, the control terminal extracts the character features according to the photo of the target person,
Go to search the first object image further according to the character features.
In another embodiment, the control terminal can be according to the feature description simulation generation figure map that user inputs
Picture, then the character features of the character image are extracted, go to search the first object image further according to the character features.It is described
Feature description can be the features such as height, body weight, face shape, hair style, dress.
In the present embodiment, after searching the first object image, the mesh will be tracked in the first object image
Mark personage.
In one embodiment, the control terminal uses core correlation filtering (Kernelized Correlation
Filters, KCF) realize the first object image for including the character features in the image of described image collecting device collection
In target person be tracked.Present embodiment is described in detail below.
According to pedestrian detection result, the initial position p of target is determined0；
In current location p0Centered on, extract sample area HoG (Histogram of Oriented Gradient,
Histograms of oriented gradients) feature xo；
1. calculate kernel regression device parameter using below equation (1)
Wherein,It is sample xoThe Fourier transformation of corresponding label,For the Fourier transformation of antithesis factor alpha, K is nuclear phase
Close matrix；
2. in ItIn frame, in previous frame position pt-1Sampling nearby, extract the HoG features z of sample areat；
3. calculate previous cycle vector z using formula (2)tCorrelation filtering response diagram yt；
yt=αTK(zt,xt-1) (2)
Take ytMaximum correspondence position is current goal position p in elementt；
4. with current location ptCentered on, extract the HoG features x of sample areat；
5. it is based on current goal template xt, updated using formula (1) and return device parameter
6. if tracking does not terminate, t=t+1, turn to step 4；Otherwise, current goal tracking is terminated.
In the present embodiment, after the image tracking of image capture device collection terminates, inquired about according to the character features
The image of other image capture device collections, to continue to track the target person.
After the tracking carried out in image capture device terminates, the control terminal needs to set from multiple images collection again
The target person or vehicle are inquired about in the image of standby collection.In one embodiment, stored in the control terminal and every
The particular location of individual image capture device, and the position relationship between image capture device, it is described control terminal from it is previous
Inquired about in the image of the adjacent image capture device collection of the image capture device of time search, if inquiry is less than the target person
During thing, then gradually expand seeking scope.In another embodiment, the movement for controlling terminal according to the target person
Direction, the image that the corresponding image capture device for inquiring about the corresponding region entered in the direction is gathered.
Step S102, when the target person is close to vehicle, judge whether the target person has into the vehicle
Behavior.
It is described to judge whether the target person has the behavior into the vehicle real in the following manner in the present embodiment
It is existing：When the image gathered to described image collecting device, which carries out analysis, determines the target person close to vehicle, extraction is current
The continuous dense optical flow vector of scene inputs the people's car related network trained and is predicted, according to prediction result as feature
Judge whether the target person has the behavior into the vehicle.
In one embodiment, people's car related network include convolutional layer, LSTM (Long Short-Term Memory,
Shot and long term memory network) layer and classification layer.In an example, the convolutional layer has five, and LSTM layers have three, layer one of classifying
It is individual.The classification layer can be softmax classification layers.In this example, the structure of LSTM layers is as follows：
it=σ (wxixt+wyiyt-1+wcict-1+bi)；
ft=σ (wxfxt+wyfyt-1+wcfct-1+bf)；
ct=ftct-1+it·tanh(wxcxt+wycyt-1+bc)；
ot=σ (wxoxt+wyoyt-1+wcoct+bo)；
yt=ot·tanh(ct)；
Wherein, w is weight, xt、it、ft、ct、ot、ytRespectively t frames when the inputs of LSTM layers, input gate, forget door,
Remember primitive unit cell, out gate and the state of output.
In the present embodiment, the pedestrian marked is got on the bus, get off and the video datas such as people's car is uncorrelated extracted it is thick
Close light stream vector inputs people's car related network and is trained, to determine the ginseng to be determined in people's car related network
Number, so as to obtain the people's car related network trained.
In the present embodiment, the first object of the character features is included in the image of the query image collecting device collection
The second target image comprising the vehicle characteristics passes through following in image or the image of inquiry described image collecting device collection
Mode is realized：After the target person or vehicle leave the region that one of image capture device can gather, institute is inquired about
It is described to inquire about to state the image that the image capture device in the corresponding region entered of mobile trend of target person or vehicle is gathered
First object image and the second target image.
After the search carried out in image capture device terminates, the control terminal needs to set from multiple images collection again
The target person or vehicle are inquired about in the image of standby collection.In one embodiment, stored in the control terminal and every
The particular location of individual image capture device, and the position relationship between image capture device, it is described control terminal from it is previous
Inquired about in the image of the adjacent image capture device collection of the image capture device of time search, if inquiry is less than the target person
When thing or vehicle, then gradually expand seeking scope.In another embodiment, the control terminal is according to the target person
Or the moving direction of vehicle, the image that the corresponding image capture device for inquiring about the corresponding region entered in the direction is gathered.
In the present embodiment, when the target person is close to vehicle, the continuous dense optical flow vector of current scene is as special
The people's car related network trained described in sign input is trained, and the classification results obtained according to the grader can determine whether described
Whether target person enters vehicle.
When the target person has into during the behavior of the vehicle, step S103 is performed；Otherwise step S101 is continued executing with.
Step S103, obtain the vehicle characteristics of the vehicle.
In one embodiment, after step S103, methods described also includes：Inquired about again according to the character features
Whether the character features are included in the image of image capture device collection；If comprising the character features, continue query image
The first object image of the character features is included in the image of collecting device collection.
Step S104, inquired about according to the vehicle characteristics in the image of described image collecting device collection and include the vehicle
Second target image of feature is realized to be searched for the image of vehicle.
In one embodiment, the control terminal uses core correlation filtering (Kernelized Correlation
Filters, KCF) realize in the image of described image collecting device collection in the second target image comprising vehicle characteristics
Vehicle is tracked.The target person in first object image on the tracking for vehicle and foregoing description is tracked
Mode it is similar, specifically may be referred to the description of the tracking of above-mentioned target person, will not be repeated here.
In the present embodiment, the second target of the vehicle characteristics is included in the image of the query image collecting device collection
Image is accomplished by the following way：After the vehicle leaves the region that one of image capture device can gather, inquiry
The image that the image capture device in the corresponding region entered of the mobile trend of the vehicle is gathered is to inquire about second target
Image.
After the search carried out in image capture device terminates, the control terminal needs to set from multiple images collection again
The vehicle is inquired about in the image of standby collection.In one embodiment, storage and each IMAQ in the control terminal
The particular location of equipment, and the position relationship between image capture device, it is described control terminal from previous time search
Inquired about in the image of the adjacent image capture device collection of image capture device, if inquiry is less than the target person or vehicle
When, then gradually expand seeking scope.In another embodiment, the control terminal is according to the target person or vehicle
Moving direction, the image that the corresponding image capture device for inquiring about the corresponding region entered in the direction is gathered.
In the present embodiment, the first object of the character features is included in the image of the query image collecting device collection
The second target image comprising the vehicle characteristics passes through following in image or the image of inquiry described image collecting device collection
Mode is realized：After the target person or vehicle leave the region that one of image capture device can gather, institute is inquired about
It is described to inquire about to state the image that the image capture device in the corresponding region entered of mobile trend of target person or vehicle is gathered
First object image and the second target image.
After the search carried out in image capture device terminates, the control terminal needs to set from multiple images collection again
The target person or vehicle are inquired about in the image of standby collection.In one embodiment, stored in the control terminal and every
The particular location of individual image capture device, and the position relationship between image capture device, it is described control terminal from it is previous
Inquired about in the image of the adjacent image capture device collection of the image capture device of time search, if inquiry is less than the vehicle
When, then gradually expand seeking scope.In another embodiment, the moving direction for controlling terminal according to the vehicle,
The image that the corresponding image capture device for inquiring about the corresponding region entered in the direction is gathered.
The people's car association search method provided according to embodiments of the present invention, query image collecting device is removed by character features
The first object image comprising the character features is realized in the image collected searches for the image of target person, judging
State target person to get on the bus, then vehicle is scanned for, realize people's car associative search, can more effectively search for the row of target person
Track.
Example is applied other, after step S104, methods described also includes step S105-S106.As shown in figure 4, this reality
The method applied in example is further comprising the steps of.
Step S105, analysis is carried out to second target image and determines whether that the target person leaves the vehicle
Behavior.
Whether the behavior of leaving the vehicle of the target person is had in the second whereabouts image for judging the vehicle
It is accomplished by the following way：When the image gathered to described image collecting device, which carries out analysis, determines the vehicle parking, carry
The continuous dense optical flow vector of current scene is taken to input the people's car related network trained and be trained as feature, root
Judge whether the target person has the behavior for leaving the vehicle according to training result.
When the target person has the behavior for leaving the vehicle, step S106 is performed；Otherwise the shadow to vehicle is continued to
As search.
Step S106, the first object images of the character features is included in the image of query image collecting device collection.
In another embodiment, methods described also includes, step S107, the shadow of query image collecting device collection
The first object image comprising the character features and the second target image comprising the vehicle characteristics as in.
By judge target person whether have leave vehicle behavior can with the behavior being likely to occur of monitoring objective personage,
Further to track the target person, the mobile route of target person is obtained, more accurately to obtain the position of target person
Put, improve the accuracy rate of target person search.
Referring to Fig. 5, it is the function of people's car association search device 110 shown in Fig. 2 of present pre-ferred embodiments offer
Module diagram.Modules in the car association search device 110 of the present embodiment are used to perform in above method embodiment
Each step.People's car association search device 110 includes：First enquiry module 1101, the first judge module 1102, obtain mould
The enquiry module 1104 of block 1103 and second.
First enquiry module 1101, for the image gathered according to the character features query image collecting device of setting
In the first object image comprising the character features realize the image of target person searched for.
First judge module 1102, for when the target person is close to vehicle, judging that the target person is
The no behavior having into the vehicle.
The acquisition module 1103, for having into during the behavior of the vehicle when the target person, obtain the vehicle
Vehicle characteristics.
Second enquiry module 1104, for inquiring about the shadow of described image collecting device collection according to the vehicle characteristics
The second target image comprising the vehicle characteristics is realized as in searches for the image of vehicle.
In the present embodiment, the first enquiry module 1101 of people's car association search device 110, it is additionally operable to when first judges
Module judges that target person has into during the behavior of the vehicle, and according to the character features, query image collecting device gathers again
Image in whether include the character features, if including the character features, continue the shadow of query image collecting device collection
The first object image of the character features is included as in.
In the present embodiment, people's car association search device 110 also includes：
Second judge module 1105, the target person is determined whether for carrying out analysis to second target image
Leave the behavior of the vehicle；When the target person has the behavior for leaving the vehicle, first enquiry module is triggered
1101, or the first enquiry module 1101 of triggering and the second enquiry module inquiry 1104.
In the present embodiment, first judge module 1102 is accomplished by the following way：When to described image collecting device
When the image of collection carries out the analysis determination target person close to vehicle, the continuous dense optical flow vector for extracting current scene is made
Be characterized, input the people's car related network trained and be trained, according to training result judge the target person whether have into
Enter the behavior of the vehicle.
Second judge module 1105 is accomplished by the following way：When the image gathered to described image collecting device enters
When row analysis determines the vehicle parking, the continuous dense optical flow vector of current scene is extracted as feature, inputs what is trained
People's car related network is trained, and judges whether the target person has the behavior for leaving the vehicle according to training result.
In the present embodiment, first enquiry module 1101 is additionally operable to adopt when the target person leaves one of image
Behind the region that collection equipment can gather, the image for inquiring about the corresponding region entered of mobile trend of the target person or vehicle is adopted
The image that is gathered of collection equipment is to inquire about the first object image.
Second enquiry module 1104 is additionally operable to gather when the vehicle leaves one of image capture device
Region after, inquire about image that the image capture device in the corresponding region entered of mobile trend of the vehicle gathered to inquire about
Second target image.
Other details on the present embodiment can also further refer to the description in above method embodiment, herein not
Repeat again.
The people's car association search device provided according to embodiments of the present invention, query image collecting device is removed by character features
The first object image comprising the character features is realized in the image collected searches for the image of target person, judging
State target person to get on the bus, then vehicle is scanned for, realize people's car associative search, can more effectively search for the row of target person
Track.
In several embodiments provided herein, it should be understood that disclosed apparatus and method, can also pass through
Other modes are realized.Device embodiment described above is only schematical, for example, flow chart and block diagram in accompanying drawing
Show the device of multiple embodiments according to the present invention, method and computer program product architectural framework in the cards,
Function and operation.At this point, each square frame in flow chart or block diagram can represent the one of a module, program segment or code
Part, a part for the module, program segment or code include one or more and are used to realize holding for defined logic function
Row instruction.It should also be noted that at some as in the implementation replaced, the function that is marked in square frame can also with different from
The order marked in accompanying drawing occurs.For example, two continuous square frames can essentially perform substantially in parallel, they are sometimes
It can perform in the opposite order, this is depending on involved function.It is it is also noted that every in block diagram and/or flow chart
The combination of individual square frame and block diagram and/or the square frame in flow chart, function or the special base of action as defined in performing can be used
Realize, or can be realized with the combination of specialized hardware and computer instruction in the system of hardware.
In addition, each functional module in each embodiment of the present invention can integrate to form an independent portion
Point or modules individualism, can also two or more modules be integrated to form an independent part.
If the function is realized in the form of software function module and is used as independent production marketing or in use, can be with
It is stored in a computer read/write memory medium.Based on such understanding, technical scheme is substantially in other words
The part to be contributed to prior art or the part of the technical scheme can be embodied in the form of software product, the meter
Calculation machine software product is stored in a storage medium, including some instructions are causing a computer equipment (can be
People's computer, server, or network equipment etc.) perform all or part of step of each embodiment methods described of the present invention.
And foregoing storage medium includes：USB flash disk, mobile hard disk, read-only storage (ROM, Read-Only Memory), arbitrary access are deposited
Reservoir (RAM, Random Access Memory), magnetic disc or CD etc. are various can be with the medium of store program codes.Need
Illustrate, herein, such as first and second or the like relational terms be used merely to by an entity or operation with
Another entity or operation make a distinction, and not necessarily require or imply between these entities or operation any this reality be present
The relation or order on border.Moreover, term " comprising ", "comprising" or its any other variant are intended to the bag of nonexcludability
Contain, so that process, method, article or equipment including a series of elements not only include those key elements, but also including
The other element being not expressly set out, or also include for this process, method, article or the intrinsic key element of equipment.
In the absence of more restrictions, the key element limited by sentence "including a ...", it is not excluded that including the key element
Process, method, other identical element also be present in article or equipment.
The preferred embodiments of the present invention are the foregoing is only, are not intended to limit the invention, for the skill of this area
For art personnel, the present invention can have various modifications and variations.Within the spirit and principles of the invention, that is made any repaiies
Change, equivalent substitution, improvement etc., should be included in the scope of the protection.It should be noted that：Similar label and letter exists
Similar terms is represented in following accompanying drawing, therefore, once being defined in a certain Xiang Yi accompanying drawing, is then not required in subsequent accompanying drawing
It is further defined and explained.
The foregoing is only a specific embodiment of the invention, but protection scope of the present invention is not limited thereto, any
Those familiar with the art the invention discloses technical scope in, change or replacement can be readily occurred in, should all be contained
Cover within protection scope of the present invention.Therefore, protection scope of the present invention described should be defined by scope of the claims.
Claims (10)
- A kind of 1. people's car association search method, it is characterised in that applied to control terminal, the control terminal is adopted with multiple images Collect equipment communication connection, people's car association recognition methods includes：The first object of the character features is included in the image gathered according to the character features query image collecting device of setting Image is realized to be searched for the image of target person；When the target person is close to vehicle, judge whether the target person has the behavior into the vehicle；When the target person has into during the behavior of the vehicle, the vehicle characteristics of the vehicle are obtained；The second mesh for including the vehicle characteristics in the image of described image collecting device collection is inquired about according to the vehicle characteristics Image realization is marked to search for the image of vehicle.
- 2. people's car association search method as claimed in claim 1, it is characterised in that when the target person has into the vehicle Behavior, after the vehicle characteristics for obtaining the vehicle, methods described also includes：Whether the character features are included according in the character features image that query image collecting device gathers again；If comprising the character features, continue to include the first of the character features in the image of query image collecting device collection Target image.
- 3. people's car association search method as claimed in claim 1, it is characterised in that according to the vehicle characteristics to described image In the image of collecting device collection after the second target image comprising the vehicle characteristics, methods described also includes：Analysis is carried out to second target image and determines whether that the target person leaves the behavior of the vehicle；When the target person has the behavior for leaving the vehicle, the people is included in the image of query image collecting device collection The first mesh of the character features is included in the first object image of thing feature, or the image of query image collecting device collection Mark image and the second target image comprising the vehicle characteristics.
- 4. people's car association search method as claimed in claim 3, it is characterised in that described to judge whether the target person has Behavior into the vehicle is accomplished by the following way：When the image gathered to described image collecting device, which carries out analysis, determines the target person close to vehicle, extraction is current The continuous dense optical flow vector of scene inputs the people's car related network trained and is predicted, exported according to network as feature As a result judge whether the target person has the behavior into the vehicle；The behavior for leaving the vehicle for whether having the target person in the second whereabouts image for judging the vehicle passes through In the following manner is realized：When the image gathered to described image collecting device, which carries out analysis, determines the vehicle parking, the company of current scene is extracted Continuous dense optical flow vector inputs the people's car related network trained and is predicted, according to network output result as feature Judge whether the target person has the behavior for leaving the vehicle.
- 5. people's car association search method as described in claim 1-4 any one, it is characterised in that the query image collection First object image comprising the character features or the shadow of inquiry described image collecting device collection in the image of equipment collection The second target image comprising the vehicle characteristics is accomplished by the following way as in：After the target person or vehicle leave image acquisition region corresponding to one of image capture device, described in inquiry The mobile trend of target person or vehicle, the image that the image capture device in the corresponding region entered is gathered is to inquire about described the One target image and the second target image.
- 6. a kind of people's car association search device, it is characterised in that applied to control terminal, the control terminal is adopted with multiple images Collect equipment communication connection, people's car association identification device includes：First enquiry module, for including the people in the image that is gathered according to the character features query image collecting device of setting The first object image of thing feature is realized to be searched for the image of target person；First judge module, for when the target person is close to vehicle, judging whether the target person has into the car Behavior；Acquisition module, for having into during the behavior of the vehicle when the target person, obtain the vehicle characteristics of the vehicle；Second enquiry module, it is described for being included in the image according to vehicle characteristics inquiry described image collecting device collection Second target image of vehicle characteristics is realized to be searched for the image of vehicle.
- 7. people's car association search device as claimed in claim 6, it is characterised in that described device also includes：First enquiry module, it is additionally operable to when the first judge module judges that target person has into during the behavior of the vehicle, according to institute State in the character features image that query image collecting device gathers again and whether include the character features, if including the personage Feature, continue the first object image for including the character features in the image of query image collecting device collection.
- 8. people's car association search device as claimed in claim 6, it is characterised in that described device also includes：Second judge module, for carrying out analysis to second target image, to determine whether that the target person leaves described The behavior of vehicle；When there is the behavior that the target person leaves the vehicle, first enquiry module is triggered, or triggering described the One enquiry module and second enquiry module.
- 9. people's car association search device as claimed in claim 8, it is characterised in that first judge module passes through with lower section Formula is realized：When the image gathered to described image collecting device, which carries out analysis, determines the target person close to vehicle, extraction is current The continuous dense optical flow vector of scene inputs the people's car related network trained and is predicted, according to prediction result as feature Judge whether the target person has the behavior into the vehicle；Second judge module is accomplished by the following way：When the image gathered to described image collecting device, which carries out analysis, determines the vehicle parking, the company of current scene is extracted Continuous dense optical flow vector inputs the people's car related network trained and is trained, judged according to training result as feature Whether the target person has the behavior for leaving the vehicle.
- 10. people's car association search device as described in claim 6-9 any one, it is characterised in that the first inquiry mould Block is additionally operable to after the target person leaves image acquisition region corresponding to one of image capture device, inquire about the mesh The image that the image capture device in the corresponding region entered of the mobile trend of mark personage or vehicle is gathered is to inquire about described first Target image；Second enquiry module is additionally operable to when the vehicle leaves image acquisition areas corresponding to one of image capture device Behind domain, it is described to inquire about to inquire about the image that the image capture device in the corresponding region entered of mobile trend of the vehicle is gathered Second target image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711247163.XA CN107871019B (en) | 2017-12-01 | 2017-12-01 | Man-vehicle association search method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711247163.XA CN107871019B (en) | 2017-12-01 | 2017-12-01 | Man-vehicle association search method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107871019A true CN107871019A (en) | 2018-04-03 |
| CN107871019B CN107871019B (en) | 2020-09-15 |
Family
ID=61755000
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711247163.XA Active CN107871019B (en) | 2017-12-01 | 2017-12-01 | Man-vehicle association search method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107871019B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109214320A (en) * | 2018-08-23 | 2019-01-15 | 中国电子科技集团公司电子科学研究院 | People's vehicle correlating method and device based on video analysis |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101848377A (en) * | 2010-05-26 | 2010-09-29 | 苏州安杰瑞电子科技发展有限公司 | Device and method for intelligent linkage of multi-video recording device based on cloud computing and mass video searching |
| CN103530366A (en) * | 2013-10-12 | 2014-01-22 | 湖北微模式科技发展有限公司 | Vehicle searching method and system based on user-defined features |
| US20160239982A1 (en) * | 2014-08-22 | 2016-08-18 | Zhejiang Shenghui Lighting Co., Ltd | High-speed automatic multi-object tracking method and system with kernelized correlation filters |
| CN107256386A (en) * | 2017-05-23 | 2017-10-17 | 东南大学 | Human behavior analysis method based on deep learning |
-
2017
- 2017-12-01 CN CN201711247163.XA patent/CN107871019B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101848377A (en) * | 2010-05-26 | 2010-09-29 | 苏州安杰瑞电子科技发展有限公司 | Device and method for intelligent linkage of multi-video recording device based on cloud computing and mass video searching |
| CN103530366A (en) * | 2013-10-12 | 2014-01-22 | 湖北微模式科技发展有限公司 | Vehicle searching method and system based on user-defined features |
| US20160239982A1 (en) * | 2014-08-22 | 2016-08-18 | Zhejiang Shenghui Lighting Co., Ltd | High-speed automatic multi-object tracking method and system with kernelized correlation filters |
| CN107256386A (en) * | 2017-05-23 | 2017-10-17 | 东南大学 | Human behavior analysis method based on deep learning |
Non-Patent Citations (1)
| Title |
|---|
| 李天宇: "视频中行人和车辆的检测及跟踪技术研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109214320A (en) * | 2018-08-23 | 2019-01-15 | 中国电子科技集团公司电子科学研究院 | People's vehicle correlating method and device based on video analysis |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107871019B (en) | 2020-09-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | Towards more flexible and accurate object tracking with natural language: Algorithms and benchmark | |
| CN110807385B (en) | Target detection method, target detection device, electronic equipment and storage medium | |
| CN108537117B (en) | Passenger detection method and system based on deep learning | |
| CN108549846B (en) | Pedestrian detection and statistics method combining motion characteristics and head-shoulder structure | |
| CN109146921B (en) | Pedestrian target tracking method based on deep learning | |
| CN109800682B (en) | Driver attribute identification method and related product | |
| CN109859245A (en) | Multi-object tracking method, device and the storage medium of video object | |
| CN107145862A (en) | A kind of multiple features matching multi-object tracking method based on Hough forest | |
| CN110765954A (en) | Vehicle weight recognition method, equipment and storage device | |
| Jain et al. | Performance analysis of object detection and tracking algorithms for traffic surveillance applications using neural networks | |
| CN109960988A (en) | Image analysis method, device, electronic equipment and readable storage medium storing program for executing | |
| CN110991397A (en) | Traveling direction determining method and related equipment | |
| CN108986137A (en) | Human body tracing method, device and equipment | |
| Zhu et al. | Object reidentification via joint quadruple decorrelation directional deep networks in smart transportation | |
| CN106778731A (en) | A kind of license plate locating method and terminal | |
| CN110163264B (en) | Walking pattern recognition method based on machine learning | |
| Wang et al. | Urbanpose: A new benchmark for vru pose estimation in urban traffic scenes | |
| Ziaeefard et al. | Hierarchical human action recognition by normalized-polar histogram | |
| CN108257148B (en) | Target suggestion window generation method of specific object and application of target suggestion window generation method in target tracking | |
| CN107871019A (en) | People's car association search method and device | |
| CN113177439A (en) | Method for detecting pedestrian crossing road guardrail | |
| Paidi et al. | Tracking vehicle cruising in an open parking lot using deep learning and kalman filter | |
| CN111798356B (en) | Rail transit passenger flow abnormal pattern recognition method based on big data | |
| CN111832475B (en) | Face false detection screening method based on semantic features | |
| CN109359544B (en) | Portrait retrieval method and device |
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 | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: Person-vehicle association search method and device Effective date of registration: 20220823 Granted publication date: 20200915 Pledgee: Bank of China Limited Wuhan Economic and Technological Development Zone sub branch Pledgor: HUBEI MICROPATTERN TECHNOLOGY DEVELOPMENT CO.,LTD. Registration number: Y2022420000271 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right |