CN109272528A - A kind of pedestrian track acquisition methods and device - Google Patents
A kind of pedestrian track acquisition methods and device Download PDFInfo
- Publication number
- CN109272528A CN109272528A CN201811090203.9A CN201811090203A CN109272528A CN 109272528 A CN109272528 A CN 109272528A CN 201811090203 A CN201811090203 A CN 201811090203A CN 109272528 A CN109272528 A CN 109272528A
- Authority
- CN
- China
- Prior art keywords
- pedestrian
- track
- time period
- result data
- preset time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
Abstract
The embodiment of the present application provides a kind of pedestrian track acquisition methods and device; obtain track identification result data; wherein; track identification result data includes pedestrian ID, recognition time and pedestrian's coordinate point, and track identification result data is the multiple pictures for the corresponding pedestrian of pedestrian ID that same camera obtains in the first preset time period;Corresponding multiple pictures per second in the first preset time period are obtained, are averaged to the pedestrian's coordinate point of the pedestrian ID of corresponding multiple pictures per second, the pedestrian position average value of corresponding pedestrian ID per second in the first preset time period is obtained;Calculate the position difference of adjacent two seconds pedestrian position average value in the first preset time period;Judge whether position difference is greater than the first preset value;If so, determining in the corresponding pedestrian of above-mentioned adjacent two seconds one skilled in the art ID in movement.If pedestrian is mobile, the mobile track of pedestrian can be obtained according to pedestrian's moving direction that chronological order obtains.
Description
Technical field
This application involves field of image processings, in particular to a kind of pedestrian track acquisition methods and device.
Background technique
With increasingly developed, the optimization and iteration of the model algorithms such as deep learning, neural network of artificial intelligence, machine is known
Not Chu people accuracy it is very nearly the same with the recognition accuracy of the mankind.Meanwhile the application based on pedestrian track tracking
It is more and more.Under the scene of business intelligence, the time-space relationship for clearing people and object is particularly important.How the position of pedestrian is made good use of
Confidence breath, under big flow, the scene of big data, the motion track that the pedestrian how is obtained in market is particularly important.
Apply for content
In view of this, the embodiment of the present application provides a kind of pedestrian track acquisition methods and device.
In a first aspect, the embodiment of the present application provides a kind of pedestrian track acquisition methods, which comprises obtain tracking
Recognition result data, wherein the track identification result data includes pedestrian ID, recognition time and pedestrian's coordinate point, described
Track identification result data is the more of the corresponding pedestrian of the pedestrian ID that same camera obtains in the first preset time period
Open photo;Corresponding multiple pictures per second in first preset time period are obtained, to the corresponding multiple pictures per second
The pedestrian's coordinate point of pedestrian ID is averaged, and the pedestrian position of corresponding pedestrian ID per second in first preset time period is obtained
Average value;Calculate the position difference of adjacent two seconds pedestrian position average value in first preset time period;Judge institute's rheme
Set whether difference is greater than the first preset value;If so, determining that the corresponding pedestrian of the pedestrian ID is moving in above-mentioned adjacent two seconds
It is dynamic.
In a possible design, after judging whether the position difference is greater than the first preset value, the method
If further include: the position difference is less than first preset value, determines that the pedestrian ID is corresponding in above-mentioned adjacent two seconds
Pedestrian be stationary state.
In a possible design, the method also includes: it is right according to the time sequencing of first preset time period
The pedestrian position average value carries out line, obtains the corresponding pedestrian track of the pedestrian ID.
In a possible design, after obtaining the corresponding pedestrian track of the pedestrian ID, the method also includes:
According to GeoJSON standard, the pedestrian track is generated into corresponding data;The data are integrated and are stored to business number
According to library.
In a possible design, before the acquisition track identification result data, the method also includes: it obtains
The video flowing of camera acquisition;Control graphics processor handles the video flowing, obtains the track identification number of results
According to.
Second aspect, the embodiment of the present application provide a kind of pedestrian track acquisition device, and described device includes: result data
Module is obtained, for obtaining track identification result data, wherein when the track identification result data includes pedestrian ID, identification
Between and pedestrian's coordinate point, the track identification result data be described in same camera obtains in the first preset time period
The multiple pictures of the corresponding pedestrian of pedestrian ID;Position mean obtains module, every in first preset time period for obtaining
Second corresponding multiple pictures, average to the pedestrian's coordinate point of the pedestrian ID of the corresponding multiple pictures per second, obtain institute
State the pedestrian position average value of corresponding pedestrian ID per second in the first preset time period;Position difference calculating module, for calculating
The position difference of adjacent two seconds pedestrian position average value in first preset time period;Difference judgment module, for judging
Whether the position difference is greater than the first preset value;Pedestrian moves determination module, described in above-mentioned adjacent two seconds for determining
The corresponding pedestrian of pedestrian ID is in movement.
In a possible design, described device further include: the static determination module of pedestrian, for determining above-mentioned adjacent
The corresponding pedestrian of the pedestrian ID is stationary state in two seconds.
In a possible design, described device further include: pedestrian track obtains module, for pre- according to described first
If the time sequencing of period, line is carried out to the pedestrian position average value, obtains the corresponding pedestrian track of the pedestrian ID.
In a possible design, described device further include: data generation module is used for according to GeoJSON standard, will
The pedestrian track generates corresponding data;Data memory module, for being integrated and being stored to business number by the data
According to library.
In a possible design, described device further include: video flowing acquisition module, for obtaining camera acquisition
Video flowing;Result data obtains module, handles for controlling graphics processor the video flowing, obtains the tracking and knows
Other result data.
In pedestrian track acquisition methods provided by the embodiments of the present application and device, track identification result data is obtained,
In, the track identification result data includes pedestrian ID, recognition time and pedestrian's coordinate point, the track identification result data
For the multiple pictures for the corresponding pedestrian of the pedestrian ID that same camera obtains in the first preset time period;Obtain described
Corresponding multiple pictures per second in one preset time period, to the pedestrian's coordinate point of the pedestrian ID of the corresponding multiple pictures per second
It averages, obtains the pedestrian position average value of corresponding pedestrian ID per second in first preset time period;Calculate described
The position difference of adjacent two seconds pedestrian position average value in one preset time period;Judge whether the position difference is greater than first
Preset value;If so, determining that the corresponding pedestrian of the pedestrian ID is in movement in above-mentioned adjacent two seconds.It can be according to adjacent two seconds
The position difference of pedestrian position average value be compared with the first preset value, then judged pedestrian at this according to comparison result
Whether move in adjacent two seconds, if pedestrian is mobile, can be obtained according to pedestrian's moving direction that chronological order obtains
The mobile track of pedestrian.
Above objects, features, and advantages to enable the embodiment of the present application to be realized are clearer and more comprehensible, be cited below particularly compared with
Good embodiment, and cooperate appended attached drawing, it is described in detail below.
Detailed description of the invention
Illustrate the technical solutions in the embodiments of the present application or in the prior art in order to clearer, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of application for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is the flow chart for the pedestrian track acquisition methods that the application first embodiment provides;
Fig. 2 is a kind of process of the specific embodiment for the pedestrian track acquisition methods that the application first embodiment provides
Figure;
Fig. 3 is the part steps flow chart for the pedestrian track acquisition methods that the application first embodiment provides;
Fig. 4 is the structural block diagram for the pedestrian track acquisition device that the application second embodiment provides.
Specific embodiment
First embodiment
Referring to Figure 1, Fig. 1 shows the process signal of the pedestrian track acquisition methods of the application first embodiment offer
Figure, specifically comprises the following steps:
Step S110 obtains track identification result data, wherein the track identification result data includes pedestrian ID, knows
Other time and pedestrian's coordinate point, the same camera of track identification result data obtain in the first preset time period
The multiple pictures of the corresponding pedestrian of the pedestrian ID.
Track identification result data may include pedestrian ID, recognition time and pedestrian's coordinate point, and pedestrian ID can be mark
Know the pedestrian, be allowed to the identifier distinguished with other pedestrians, specifically, camera can according to the apparel characteristic of pedestrian come
Generate pedestrian ID.Recognition time can be the exact date of camera shooting, also may include that camera occurs from record pedestrian
The specific duration to disappear from the visual field of camera to the pedestrian.Pedestrian's coordinate point can be the corresponding pedestrian of pedestrian ID in image
In the coordinate at four angles that outlines of rectangle frame.
The track identification result data is specially the pedestrian that same camera obtains in the first preset time period
The multiple pictures of the corresponding pedestrian of ID.
Before step S110, the method also includes: obtain the video flowing of camera acquisition;Control graphics processor pair
The video flowing is handled, and the track identification result data is obtained.
Specifically, the video flowing in the camera coverage can be collected by camera, and by video stream
Graphics processor processing is given, to obtain track identification result data.Graphics processor can be pre-processed, including check number
According to correctness and compressed data, then pretreated data are bundled in message queue, data are read from message queue, together
When to the data decompression and arrangement taken out.
Graphics processor during processing, can generate pedestrian ID according to the garment feature of pedestrian, and by the row
The corresponding pedestrian of people ID is outlined in a manner of rectangle frame in the picture, then can also provide four angles of rectangle frame, the i.e. square
The coordinate points of shape frame.
Step S120 obtains corresponding multiple pictures per second in first preset time period, to described per second corresponding
The pedestrian's coordinate point of the pedestrian ID of multiple pictures is averaged, and corresponding pedestrian ID per second in first preset time period is obtained
Pedestrian position average value.
First preset time period is that the corresponding pedestrian of pedestrian ID occurs disappearing to the pedestrian from the picture that camera takes
The period in picture is lost, camera is per second can to shoot multiple pictures.
For the multiple pictures of acquisition per second, it can average, obtain to the corresponding pedestrian's coordinate point of pedestrian ID in photo
Obtain pedestrian position average value.Specifically, the interposition on rectangle frame bottom edge can be obtained according to the corresponding rectangle frame of pedestrian's coordinate point
It sets, as the location point of pedestrian, then specifically averages to pedestrian location point, obtain pedestrian position average value.
In a kind of specific embodiment, the first preset time period can be 10 seconds, and camera is per second can to obtain 5
Photo all obtains the average value of the location point of pedestrian in 5 photos then for each second in 10 seconds, to obtain in 10 seconds
The pedestrian position average value of corresponding pedestrian ID per second.
Step S130 calculates the position difference of adjacent two seconds pedestrian position average value in first preset time period.
After the pedestrian position average value for obtaining corresponding pedestrian ID per second, the phase in the first preset time period can be calculated
The position difference of adjacent two seconds pedestrian position average value.
Step S140, judges whether the position difference is greater than the first preset value, if so, executing step S150.
Then the position difference of adjacent two seconds pedestrian position average value is compared with the first preset value, if alternate position spike
Value is greater than the first preset value, then shows that pedestrian is in moving condition, therefore execute step S150.
Step S150 determines that the corresponding pedestrian of the pedestrian ID is in movement in above-mentioned adjacent two seconds.
Determine that the corresponding pedestrian of pedestrian ID in above-mentioned adjacent two seconds is in moving condition.
Fig. 2 is referred to, Fig. 2 shows a kind of specific realities for the pedestrian track acquisition methods that the application first embodiment provides
Mode is applied, is specifically comprised the following steps:
Step S110 obtains track identification result data, wherein the track identification result data includes pedestrian ID, knows
Other time and pedestrian's coordinate point, the same camera of track identification result data obtain in the first preset time period
The multiple pictures of the corresponding pedestrian of the pedestrian ID.
Step S120 obtains corresponding multiple pictures per second in first preset time period, to described per second corresponding
The pedestrian's coordinate point of the pedestrian ID of multiple pictures is averaged, and corresponding pedestrian ID per second in first preset time period is obtained
Pedestrian position average value.
Step S130 calculates the position difference of adjacent two seconds pedestrian position average value in first preset time period.
Step S140, judges whether the position difference is greater than the first preset value, if so, executing step S150;If it is not, holding
Row step S160.
Step S150 determines that the corresponding pedestrian of the pedestrian ID is in movement in above-mentioned adjacent two seconds.
Step S160 determines that the corresponding pedestrian of the pedestrian ID is stationary state in above-mentioned adjacent two seconds.
The position difference of adjacent two seconds pedestrian position average value is compared with the first preset value, if position difference is small
In the first preset value, then show that pedestrian almost without movement, then can be determined that the corresponding row of pedestrian ID in above-mentioned adjacent two seconds
Man-made static's state.
Fig. 3 is referred to, Fig. 3 shows the specific steps schematic diagram after step S160, specifically comprises the following steps:
Step S170 connects the pedestrian position average value according to the time sequencing of first preset time period
Line obtains the corresponding pedestrian track of the pedestrian ID.
Line can be carried out to the pedestrian position average value of acquisition according to the time sequencing of the first preset time period, thus
The corresponding pedestrian track of pedestrian ID is obtained, location point when wherein pedestrian is stationary state can also be averaged again, to obtain
Obtain the position of the corresponding pedestrian track of pedestrian ID.
The pedestrian track is generated corresponding data according to GeoJSON standard by step S180.
Specifically pedestrian track can be generated into corresponding data according to GeoJSON standard.
The data are integrated and are stored to service database by step S190.
Then it will store after these above-mentioned Data Integrations into service database.
Specifically, due to there is multiple brand quotient in market, each brand quotient has multiple shops, and there are multiple camera shootings in each shops
Head, thus can according to the sequence of brand quotient ID, shops ID, camera ID and pedestrian ID come to track identification result data into
Row classification.
Due to being classified to track identification result data, data analysis condition can be constructed to inquire after classification
Track identification result data constructs query statement according to data analysis condition, thus the track identification number of results completed to classification
According to being inquired.Inquiry operation request specifically can be to time series database initiation.According to the corresponding camera of inquiry request
ID and pedestrian ID, can obtain the movement track that the pedestrian ID is obtained under the shooting of camera ID, and according to
GeoJSON standard criterion generates corresponding data.It, can be by data according to certain after data are reintegrated and classified
Rule is saved in database, which can be service database.
Second embodiment
Fig. 4 is referred to, Fig. 4 shows the pedestrian track acquisition device of the application second embodiment offer, the device 300 packet
It includes:
Result data obtains module 310, for obtaining track identification result data, wherein the track identification number of results
According to including pedestrian ID, recognition time and pedestrian's coordinate point, the track identification result data is that same camera is pre- first
If the multiple pictures of the corresponding pedestrian of the pedestrian ID obtained in the period.
Position mean obtains module 320, for obtaining corresponding multiple pictures per second in first preset time period,
It averages, is obtained in first preset time period to the pedestrian's coordinate point of the pedestrian ID of the corresponding multiple pictures per second
The pedestrian position average value of corresponding pedestrian ID per second.
Position difference calculating module 330, it is flat for calculating adjacent two seconds pedestrian positions in first preset time period
The position difference of mean value.
Difference judgment module 340, for judging whether the position difference is greater than the first preset value.
Pedestrian moves determination module 350, for determining that the corresponding pedestrian of the pedestrian ID is moving in above-mentioned adjacent two seconds
It is dynamic.
Described device further include:
The static determination module of pedestrian, for determining the corresponding row man-made static shape of the pedestrian ID in above-mentioned adjacent two seconds
State.Pedestrian track obtains module, for the time sequencing according to first preset time period, to the pedestrian position average value
Line is carried out, the corresponding pedestrian track of the pedestrian ID is obtained.Data generation module is used for according to GeoJSON standard, will be described
Pedestrian track generates corresponding data.Data memory module, for being integrated and being stored to service database by the data.
Video flowing acquisition module, for obtaining the video flowing of camera acquisition.Result data obtains module, for controlling graphics processor
The video flowing is handled, the track identification result data is obtained.
It is apparent to those skilled in the art that for convenience and simplicity of description, the device of foregoing description
Specific work process, no longer can excessively be repeated herein with reference to the corresponding process in preceding method.
The application also provides a kind of electronic equipment, comprising: processor, memory and bus, the memory storage is
The executable machine readable instructions of processor are stated, when electronic equipment operation, between the processor and the memory
By bus communication, method described in first embodiment is executed when the machine readable instructions are executed by the processor.
The application also provides a kind of computer readable storage medium, is stored with computer on the computer readable storage medium
Program executes method described in first embodiment when the computer program is run by processor.
The application also provides a kind of computer program product to be made when the computer program product is run on computers
It obtains computer and executes method described in first embodiment.
In pedestrian track acquisition methods provided by the embodiments of the present application and device, track identification result data is obtained,
In, the track identification result data includes pedestrian ID, recognition time and pedestrian's coordinate point, the track identification result data
For the multiple pictures for the corresponding pedestrian of the pedestrian ID that same camera obtains in the first preset time period;Obtain described
Corresponding multiple pictures per second in one preset time period, to the pedestrian's coordinate point of the pedestrian ID of the corresponding multiple pictures per second
It averages, obtains the pedestrian position average value of corresponding pedestrian ID per second in first preset time period;Calculate described
The position difference of adjacent two seconds pedestrian position average value in one preset time period;Judge whether the position difference is greater than first
Preset value;If so, determining that the corresponding pedestrian of the pedestrian ID is in movement in above-mentioned adjacent two seconds.It can be according to adjacent two seconds
The position difference of pedestrian position average value be compared with the first preset value, then judged pedestrian at this according to comparison result
Whether move in adjacent two seconds, if pedestrian is mobile, can be obtained according to pedestrian's moving direction that chronological order obtains
The mobile track of pedestrian.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description
Specific work process, no longer can excessively be repeated herein with reference to the corresponding process in preceding method.
It virtually can be a switching equipment by multiple switch in the embodiment of the present application, which receives target
Address functional instruction, and corresponding operation is executed according to corresponding operation instruction.However since switching equipment can not be complete in real time
At the processing of all operational orders, therefore, there is partial target address functional instruction to be buffered.When switching equipment receives one newly
Target address operation instruction when, it can be determined that in the address functional instruction of caching, if there are address functional instruction carry
Destination address is consistent with the destination address of the new received target address operation instruction, and if it exists, then gives up destination address behaviour
It instructs, because can be with the address functional instruction of the new received target address operation instruction execution same operation
Caching, therefore do not need to cache target address operation instruction again, preferably reduce the redundancy in buffer queue.
It should be noted that all the embodiments in this specification are described in a progressive manner, each embodiment weight
Point explanation is the difference from other embodiments, and the same or similar parts between the embodiments can be referred to each other.
For device class embodiment, since it is basically similar to the method embodiment, so being described relatively simple, related place ginseng
See the part explanation of embodiment of the method.
In several embodiments provided herein, it should be understood that disclosed device and method can also pass through it
Its mode is realized.The apparatus embodiments described above are merely exemplary, for example, the flow chart and block diagram in attached drawing are aobvious
The device of multiple embodiments according to the application, architectural framework in the cards, the function of method and computer program product are shown
It can and operate.In this regard, each box in flowchart or block diagram can represent one of a module, section or code
Point, a part of the module, section or code includes one or more for implementing the specified logical function executable
Instruction.It should also be noted that function marked in the box can also be attached to be different from some implementations as replacement
The sequence marked in figure occurs.For example, two continuous boxes can actually be basically executed in parallel, they sometimes may be used
To execute in the opposite order, this depends on the function involved.It is also noted that each of block diagram and or flow chart
The combination of box in box and block diagram and or flow chart can be based on the defined function of execution or the dedicated of movement
The system of hardware is realized, or can be realized using a combination of dedicated hardware and computer instructions.
In addition, each functional module in each embodiment of the application can integrate one independent portion of formation together
Point, it is also possible to modules individualism, an independent part can also be integrated to form with two or more modules.
It, can be with if the function is realized and when sold or used as an independent product in the form of software function module
It is stored in a computer readable storage medium.Based on this understanding, the technical solution of the application is substantially in other words
The part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be a
People's computer, server or network equipment etc.) execute each embodiment the method for the application all or part of the steps.
And storage medium above-mentioned includes: that USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
The various media that can store program code such as reservoir (RAM, Random Access Memory), magnetic or disk.It needs
Illustrate, herein, relational terms such as first and second and the like be used merely to by an entity or operation with
Another entity or operation distinguish, and without necessarily requiring or implying between these entities or operation, there are any this realities
The relationship or sequence on border.Moreover, the terms "include", "comprise" or its any other variant are intended to the packet of nonexcludability
Contain, so that the process, method, article or equipment for including a series of elements not only includes those elements, but also including
Other elements that are not explicitly listed, or further include for elements inherent to such a process, method, article, or device.
In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including the element
Process, method, article or equipment in there is also other identical elements.
The foregoing is merely preferred embodiment of the present application, are not intended to limit this application, for the skill of this field
For art personnel, various changes and changes are possible in this application.Within the spirit and principles of this application, made any to repair
Change, equivalent replacement, improvement etc., should be included within the scope of protection of this application.It should also be noted that similar label and letter exist
Similar terms are indicated in following attached drawing, therefore, once being defined in a certain Xiang Yi attached drawing, are then not required in subsequent attached drawing
It is further defined and explained.
The above, the only specific embodiment of the application, but the protection scope of the application is not limited thereto, it is any
Those familiar with the art within the technical scope of the present application, can easily think of the change or the replacement, and should all contain
Lid is within the scope of protection of this application.Therefore, the protection scope of the application shall be subject to the protection scope of the claim.
Claims (10)
1. a kind of pedestrian track acquisition methods, which is characterized in that the described method includes:
Obtain track identification result data, wherein the track identification result data includes pedestrian ID, recognition time and pedestrian
Coordinate points, the track identification result data are that the pedestrian ID that same camera obtains in the first preset time period is corresponding
Pedestrian multiple pictures;
Corresponding multiple pictures per second in first preset time period are obtained, to the pedestrian of the corresponding multiple pictures per second
The pedestrian's coordinate point of ID is averaged, and the pedestrian position for obtaining corresponding pedestrian ID per second in first preset time period is average
Value;
Calculate the position difference of adjacent two seconds pedestrian position average value in first preset time period;
Judge whether the position difference is greater than the first preset value;
If so, determining that the corresponding pedestrian of the pedestrian ID is in movement in above-mentioned adjacent two seconds.
2. the method according to claim 1, wherein judging whether the position difference is greater than the first preset value
Later, the method also includes:
If the position difference is less than first preset value, the corresponding row of the pedestrian ID in above-mentioned adjacent two seconds is determined
Man-made static's state.
3. according to the method described in claim 2, it is characterized in that, the method also includes:
According to the time sequencing of first preset time period, line is carried out to the pedestrian position average value, obtains the row
The corresponding pedestrian track of people ID.
4. according to the method described in claim 3, it is characterized in that, after obtaining the corresponding pedestrian track of the pedestrian ID,
The method also includes:
According to GeoJSON standard, the pedestrian track is generated into corresponding data;
The data are integrated and are stored to service database.
5. described the method according to claim 1, wherein before the acquisition track identification result data
Method further include:
Obtain the video flowing of camera acquisition;
Control graphics processor handles the video flowing, obtains the track identification result data.
6. a kind of pedestrian track acquisition device, which is characterized in that described device includes:
Result data obtains module, for obtaining track identification result data, wherein the track identification result data includes row
People ID, recognition time and pedestrian's coordinate point, the track identification result data are same camera in the first preset time period
The multiple pictures of the corresponding pedestrian of the pedestrian ID of interior acquisition;
Position mean obtains module, for obtaining corresponding multiple pictures per second in first preset time period, to described
The pedestrian's coordinate point of the pedestrian ID of corresponding multiple pictures per second is averaged, and it is per second right in first preset time period to obtain
The pedestrian position average value of the pedestrian ID answered;
Position difference calculating module, for calculating the position of adjacent two seconds pedestrian position average value in first preset time period
Set difference;
Difference judgment module, for judging whether the position difference is greater than the first preset value;
Pedestrian moves determination module, for determining that the corresponding pedestrian of the pedestrian ID is in movement in above-mentioned adjacent two seconds.
7. device according to claim 6, which is characterized in that described device further include:
The static determination module of pedestrian, for determining that the corresponding pedestrian of the pedestrian ID is stationary state in above-mentioned adjacent two seconds.
8. device according to claim 7, which is characterized in that described device further include:
Pedestrian track obtains module, average to the pedestrian position for the time sequencing according to first preset time period
Value carries out line, obtains the corresponding pedestrian track of the pedestrian ID.
9. device according to claim 8, which is characterized in that described device further include:
Data generation module, for according to GeoJSON standard, the pedestrian track to be generated corresponding data;
Data memory module, for being integrated and being stored to service database by the data.
10. device according to claim 6, which is characterized in that described device further include:
Video flowing acquisition module, for obtaining the video flowing of camera acquisition;
Result data obtains module, handles for controlling graphics processor the video flowing, obtains the track identification
Result data.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811090203.9A CN109272528A (en) | 2018-09-18 | 2018-09-18 | A kind of pedestrian track acquisition methods and device |
PCT/CN2018/117284 WO2020056913A1 (en) | 2018-09-18 | 2018-11-23 | Pedestrian trajectory acquisition method and apparatus, electronic device, and readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811090203.9A CN109272528A (en) | 2018-09-18 | 2018-09-18 | A kind of pedestrian track acquisition methods and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109272528A true CN109272528A (en) | 2019-01-25 |
Family
ID=65197938
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811090203.9A Pending CN109272528A (en) | 2018-09-18 | 2018-09-18 | A kind of pedestrian track acquisition methods and device |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN109272528A (en) |
WO (1) | WO2020056913A1 (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20060222205A1 (en) * | 2005-04-01 | 2006-10-05 | Porikli Fatih M | Tracking objects in low frame rate videos |
CN103425967A (en) * | 2013-07-21 | 2013-12-04 | 浙江大学 | Pedestrian flow monitoring method based on pedestrian detection and tracking |
CN103471720A (en) * | 2013-08-20 | 2013-12-25 | 中钢集团邢台机械轧辊有限公司 | Infrared real-time temperature measurement system and method for spray heat treatment |
CN103562822A (en) * | 2011-04-28 | 2014-02-05 | Nec软件系统科技有限公司 | Information processing device, information processing method, and recording medium |
CN103745485A (en) * | 2013-12-31 | 2014-04-23 | 深圳泰山在线科技有限公司 | Method and system for judging object stillness or movement |
CN104008367A (en) * | 2014-05-08 | 2014-08-27 | 中国农业大学 | Automatic fattening pig behavior analyzing system and method based on computer vision |
CN106156745A (en) * | 2016-07-06 | 2016-11-23 | 宁波大学 | Pedestrian crossing traffic feature extraction method and device based on space-time track |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP5547144B2 (en) * | 2011-09-08 | 2014-07-09 | 株式会社東芝 | Monitoring device, method thereof, and program thereof |
CN104036246B (en) * | 2014-06-10 | 2017-02-15 | 电子科技大学 | Lane line positioning method based on multi-feature fusion and polymorphism mean value |
CN104156987B (en) * | 2014-09-10 | 2017-05-10 | 成都金盘电子科大多媒体技术有限公司 | Multi-target tracking method for video contents |
-
2018
- 2018-09-18 CN CN201811090203.9A patent/CN109272528A/en active Pending
- 2018-11-23 WO PCT/CN2018/117284 patent/WO2020056913A1/en active Application Filing
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20060222205A1 (en) * | 2005-04-01 | 2006-10-05 | Porikli Fatih M | Tracking objects in low frame rate videos |
CN103562822A (en) * | 2011-04-28 | 2014-02-05 | Nec软件系统科技有限公司 | Information processing device, information processing method, and recording medium |
CN103425967A (en) * | 2013-07-21 | 2013-12-04 | 浙江大学 | Pedestrian flow monitoring method based on pedestrian detection and tracking |
CN103471720A (en) * | 2013-08-20 | 2013-12-25 | 中钢集团邢台机械轧辊有限公司 | Infrared real-time temperature measurement system and method for spray heat treatment |
CN103745485A (en) * | 2013-12-31 | 2014-04-23 | 深圳泰山在线科技有限公司 | Method and system for judging object stillness or movement |
CN104008367A (en) * | 2014-05-08 | 2014-08-27 | 中国农业大学 | Automatic fattening pig behavior analyzing system and method based on computer vision |
CN106156745A (en) * | 2016-07-06 | 2016-11-23 | 宁波大学 | Pedestrian crossing traffic feature extraction method and device based on space-time track |
Also Published As
Publication number | Publication date |
---|---|
WO2020056913A1 (en) | 2020-03-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20210294326A1 (en) | Method and system for closed loop perception in autonomous driving vehicles | |
US10002309B2 (en) | Real-time object analysis with occlusion handling | |
CN102663722B (en) | Split using the moving object of depth image | |
US10970559B2 (en) | People flow estimation device, people flow estimation method, and recording medium | |
EP2858008B1 (en) | Target detecting method and system | |
US20180348785A1 (en) | Method and system for integrated global and distributed learning in autonomous driving vehicles | |
US11188739B2 (en) | Processing uncertain content in a computer graphics system | |
CN105405150B (en) | Anomaly detection method and device based on fusion feature | |
WO2020069525A1 (en) | Method for detecting objects and localizing a mobile computing device within an augmented reality experience | |
CN109189878B (en) | A kind of crowd's thermodynamic chart preparation method and device | |
JP2020061146A (en) | System and method for detecting poi change using convolutional neural network | |
CN106295598A (en) | A kind of across photographic head method for tracking target and device | |
WO2018161037A1 (en) | Systems and methods for quantitatively assessing collision risk and severity | |
US20120281873A1 (en) | Incorporating video meta-data in 3d models | |
CN108700946A (en) | System and method for parallel ranging and fault detect and the recovery of building figure | |
CN103477352A (en) | Gesture recognition using depth images | |
CN108229456A (en) | Method for tracking target and device, electronic equipment, computer storage media | |
CN111626201A (en) | Commodity detection method and device and readable storage medium | |
CN110991261A (en) | Interactive behavior recognition method and device, computer equipment and storage medium | |
CN111382637A (en) | Pedestrian detection tracking method, device, terminal equipment and medium | |
KR20190088087A (en) | method of providing categorized video processing for moving objects based on AI learning using moving information of objects | |
CN109272528A (en) | A kind of pedestrian track acquisition methods and device | |
Rutinowski et al. | Semi-automated computer vision-based tracking of multiple industrial entities: a framework and dataset creation approach | |
Leistner et al. | Visual on-line learning in distributed camera networks | |
Xiong et al. | Crowd density estimation based on image potential energy model |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190125 |
|
RJ01 | Rejection of invention patent application after publication |