CN108830142A - The location tracking method and device identified again based on pedestrian - Google Patents
The location tracking method and device identified again based on pedestrian Download PDFInfo
- Publication number
- CN108830142A CN108830142A CN201810410845.6A CN201810410845A CN108830142A CN 108830142 A CN108830142 A CN 108830142A CN 201810410845 A CN201810410845 A CN 201810410845A CN 108830142 A CN108830142 A CN 108830142A
- Authority
- CN
- China
- Prior art keywords
- pedestrian
- picture
- target pedestrian
- target
- identified
- 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.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/53—Recognition of crowd images, e.g. recognition of crowd congestion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/103—Static body considered as a whole, e.g. static pedestrian or occupant recognition
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Abstract
The invention discloses the location tracking methods and device that are identified again based on pedestrian, the initial picture of acquisition target pedestrian and picture library to be identified, carry out unitized processing, pedestrian is carried out to target pedestrian in picture library later to identify again, find the N number of and most like pedestrian's picture of target pedestrian, if having target pedestrian in certain a group traveling together's picture found, then inquire place corresponding with certain a group traveling together's picture, transfer the monitor video in inquired place, target pedestrian is positioned and tracked, the walking data such as track route of target pedestrian can be obtained.The monitored results for the result combination fixing camera that the present invention is identified again using pedestrian realize the location tracking to target pedestrian, the track route of available target pedestrian.Further, the walking states of pedestrian at that time can also be judged according to the height, step-length, the speed of travel of pedestrian.Walking analysis to target pedestrian, including track route and walking states can be used for subsequent scouting analysis.
Description
Technical field
The present invention relates to the technical fields of criminal investigation and real-time video monitoring, more particularly to are determined based on what pedestrian identified again
Position method for tracing and device.
Background technique
Pedestrian identifies that (Person Re-identification) is also referred to as pedestrian and identifies again again, is to utilize computer vision skill
Art judges the technology that whether there is specific pedestrian in image or video sequence, is extensively considered as that the son of an image retrieval is asked
Topic gives a monitoring pedestrian image, retrieves the pedestrian image under striding equipment.It is intended to make up the view of camera fixed at present
Feel limitation, and can be combined with pedestrian detection/pedestrian tracking technology, can be widely applied to intelligent video monitoring, intelligent security etc.
Field.
After obtain the result that pedestrian identifies again, the monitoring for the result combination fixing camera how to be identified again using pedestrian
It is a direction of current research as a result, realizing the location tracking to target pedestrian.
Summary of the invention
For overcome the deficiencies in the prior art, the purpose of the present invention is to provide the location tracking sides identified again based on pedestrian
Method and device, it is intended to which, using the monitored results for the result combination fixing camera that pedestrian identifies again, target pedestrian is determined in realization
Position tracking.
The purpose of the present invention is implemented with the following technical solutions:
A kind of location tracking method identified again based on pedestrian, including:
Picture obtaining step, the initial picture of acquisition target pedestrian and picture library to be identified;In the picture library to be identified
Pedestrian's picture base area point classify;
Normalizing step, the picture in initial picture and picture library to be identified to target pedestrian carry out unitized processing;
Weight identification step carries out pedestrian to target pedestrian in picture library to be identified according to the initial picture of target pedestrian
It identifies again, finds the N number of and most like pedestrian's picture of target pedestrian;N is positive integer;
Query steps, if there is target pedestrian in certain a group traveling together's picture found, inquiry and certain a group traveling together's picture
Corresponding place;
Video acquisition step obtains the monitor video in inquired place;
Location tracking step is positioned and is tracked to target pedestrian in monitor video, obtains the walking of target pedestrian
Data;The walking data include track route.
On the basis of the above embodiments, it is preferred that the walking data further include the speed of travel;
The method also includes:
Analytical procedure obtains height, the step-length of target pedestrian;According to the height, step-length, the speed of travel of target pedestrian, estimate
Count the walking states of target pedestrian.
On the basis of the above embodiments, it is preferred that the walking states of the target pedestrian include:Relatively slow, slow, normal,
Fastly, comparatively fast.
On the basis of above-mentioned any embodiment, it is preferred that the unitized processing includes the unitized processing of size, gray scale
One of processing, filtering processing, black white binarization processing are a variety of.
On the basis of above-mentioned any embodiment, it is preferred that N=5.
A kind of location tracking device identified again based on pedestrian, including:
Picture obtain module, for obtain target pedestrian initial picture and picture library to be identified;The picture to be identified
Pedestrian's picture base area point in library is classified;
Unitized module carries out unitized place for the picture in the initial picture and picture library to be identified to target pedestrian
Reason;
Weight identification module carries out target pedestrian in picture library to be identified for the initial picture according to target pedestrian
Pedestrian identifies again, finds the N number of and most like pedestrian's picture of target pedestrian;N is positive integer;
Enquiry module, if there is target pedestrian in certain a group traveling together's picture for being found, inquiry and certain a group traveling together
The corresponding place of picture;
Video acquiring module, for obtaining the monitor video in inquired place;
Location tracking module obtains target pedestrian's for target pedestrian to be positioned and tracked in monitor video
Walking data;The walking data include track route.
On the basis of the above embodiments, it is preferred that the walking data further include the speed of travel;
Described device further includes:
Analysis module, for obtaining height, the step-length of target pedestrian;According to the height of target pedestrian, step-length, walking speed
Degree estimates the walking states of target pedestrian.
On the basis of the above embodiments, it is preferred that the walking states of the target pedestrian include:Relatively slow, slow, normal,
Fastly, comparatively fast.
On the basis of above-mentioned any embodiment, it is preferred that the unitized processing includes the unitized processing of size, gray scale
One of processing, filtering processing, black white binarization processing are a variety of.
On the basis of above-mentioned any embodiment, it is preferred that N=5.
Compared with prior art, the beneficial effects of the present invention are:
The invention discloses the location tracking methods and device that are identified again based on pedestrian, obtain the initial picture of target pedestrian
With picture library to be identified, unitized processing is carried out to whole pictures, pedestrian is carried out to target pedestrian in picture library later and is known again
, do not find it is N number of with the most like pedestrian's picture of target pedestrian, i.e., with the highest top n pedestrian picture of target pedestrian's similarity, such as
There is target pedestrian in certain a group traveling together's picture that fruit is found, then inquires place corresponding with certain a group traveling together's picture, transfer and looked into
The monitor video in the place ask is positioned and is tracked to target pedestrian in monitor video, can obtain target pedestrian's
Walking data such as track route.The monitored results for the result combination fixing camera that the present invention is identified again using pedestrian are realized
To the location tracking of target pedestrian, the track route of available target pedestrian.Further, it can also obtain target pedestrian's
The speed of travel judges the walking states of pedestrian at that time according to the height, step-length, the speed of travel of pedestrian.Walking to target pedestrian
Analysis, including track route and walking states can be used for subsequent scouting analysis.
Detailed description of the invention
Present invention will be further explained below with reference to the attached drawings and examples.
Fig. 1 shows a kind of process signal of location tracking method identified again based on pedestrian provided in an embodiment of the present invention
Figure;
Fig. 2 shows a kind of structural representations of the location tracking device identified again based on pedestrian provided in an embodiment of the present invention
Figure.
Specific embodiment
In the following, being described further in conjunction with attached drawing and specific embodiment to the present invention, it should be noted that not
Under the premise of conflicting, new implementation can be formed between various embodiments described below or between each technical characteristic in any combination
Example.
Specific embodiment one
As shown in Figure 1, the embodiment of the invention provides a kind of location tracking methods identified again based on pedestrian, including:
Picture obtaining step S101, the initial picture of acquisition target pedestrian and picture library to be identified;The picture to be identified
Pedestrian's picture base area point in library is classified;
Normalizing step S102, the picture in initial picture and picture library to be identified to target pedestrian carry out unitized place
Reason;
Weight identification step S103 carries out target pedestrian in picture library to be identified according to the initial picture of target pedestrian
Pedestrian identifies again, finds the N number of and most like pedestrian's picture of target pedestrian;N is positive integer;
Query steps S104, if there is target pedestrian in certain a group traveling together's picture found, inquiry and certain a group traveling together
The corresponding place of picture;
Video acquisition step S105 obtains the monitor video in inquired place;
Location tracking step S106, positions and tracks to target pedestrian in monitor video, obtains target pedestrian's
Walking data;The walking data include track route.
The initial picture of acquisition target pedestrian of the embodiment of the present invention and picture library to be identified, unitize to whole pictures
Processing carries out pedestrian to target pedestrian in picture library later and identifies again, finds N number of pedestrian most like with target pedestrian and schemes
Piece, i.e., with the highest top n pedestrian picture of target pedestrian's similarity, if having target line in certain a group traveling together's picture found
People then inquires place corresponding with certain a group traveling together's picture, the monitor video in inquired place is transferred, in monitor video
Target pedestrian is positioned and tracked, the walking data such as track route of target pedestrian can be obtained.The embodiment of the present invention
Using the monitored results for the result combination fixing camera that pedestrian identifies again, realizes to the location tracking of target pedestrian, can obtain
Take the track route of target pedestrian.Walking analysis to target pedestrian, such as track route can be used for subsequent scout and divide
Analysis.
Preferably, the walking data can also include the speed of travel;The method can also include:Analytical procedure
S107 obtains height, the step-length of target pedestrian;According to the height, step-length, the speed of travel of target pedestrian, estimate target pedestrian's
Walking states.The advantage of doing so is that judging the walking states of pedestrian at that time, walking states can be used for subsequent scout and divide
Analysis.
The embodiment of the present invention to the walking states of target pedestrian without limitation, it is preferred that the walking shape of the target pedestrian
State may include:It is relatively slow, slow, normal, fast, very fast.It can also include loading conditions, state of hurrying up, state of running, disordered state
Deng.
The embodiment of the present invention to the unitized processing of picture without limitation, it is preferred that the unitized processing may include
Size unitize processing, gray proces, filtering processing, black white binarization processing one of or it is a variety of.The advantage of doing so is that
According to practical situations, suitable processing is carried out to picture in advance, improves accuracy and recognition efficiency that pedestrian identifies again.
The embodiment of the present invention to the numerical value of N without limitation, it is preferred that N=5.
In above-mentioned specific embodiment one, the location tracking method identified again based on pedestrian is provided, is corresponded
, the application also provides the location tracking device identified again based on pedestrian.Implement since Installation practice is substantially similar to method
Example, so describing fairly simple, the relevent part can refer to the partial explaination of embodiments of method.Device described below is implemented
Example is only schematical.
Specific embodiment two
As shown in Fig. 2, the embodiment of the invention provides a kind of location tracking devices identified again based on pedestrian, including:
Picture obtain module 201, for obtain target pedestrian initial picture and picture library to be identified;The figure to be identified
Pedestrian's picture base area point in valut is classified;
Unitized module 202 carries out unification for the picture in the initial picture and picture library to be identified to target pedestrian
Change processing;
Weight identification module 203, for the initial picture according to target pedestrian, in picture library to be identified to target pedestrian into
Every trade people identifies again, finds the N number of and most like pedestrian's picture of target pedestrian;N is positive integer;
Enquiry module 204, if there is target pedestrian in certain a group traveling together's picture for being found, inquiry and certain a line
The corresponding place of people's picture;
Video acquiring module 205, for obtaining the monitor video in inquired place;
Location tracking module 206 obtains target pedestrian for target pedestrian to be positioned and tracked in monitor video
Walking data;The walking data include track route.
The initial picture of acquisition target pedestrian of the embodiment of the present invention and picture library to be identified, unitize to whole pictures
Processing carries out pedestrian to target pedestrian in picture library later and identifies again, finds N number of pedestrian most like with target pedestrian and schemes
Piece, i.e., with the highest top n pedestrian picture of target pedestrian's similarity, if having target line in certain a group traveling together's picture found
People then inquires place corresponding with certain a group traveling together's picture, the monitor video in inquired place is transferred, in monitor video
Target pedestrian is positioned and tracked, the walking data such as track route of target pedestrian can be obtained.The embodiment of the present invention
Using the monitored results for the result combination fixing camera that pedestrian identifies again, realizes to the location tracking of target pedestrian, can obtain
Take the track route of target pedestrian.Walking analysis to target pedestrian, such as track route can be used for subsequent scout and divide
Analysis.
Preferably, the walking data can also include the speed of travel;Described device can also include:Analysis module 207,
For obtaining height, the step-length of target pedestrian;According to the height, step-length, the speed of travel of target pedestrian, the row of target pedestrian is estimated
Walk state.
The embodiment of the present invention to the walking states of target pedestrian without limitation, it is preferred that the walking shape of the target pedestrian
State may include:It is relatively slow, slow, normal, fast, very fast.
The embodiment of the present invention to the unitized processing of picture without limitation, it is preferred that the unitized processing may include
Size unitize processing, gray proces, filtering processing, black white binarization processing one of or it is a variety of.
The embodiment of the present invention to the numerical value of N without limitation, it is preferred that N=5.
The present invention is from using in purpose, and in efficiency, the viewpoints such as progressive and novelty are illustrated, the practical progress having
Property, oneself meets the function that Patent Law is emphasized and promotes and use important document, and more than the present invention explanation and attached drawing are only of the invention
Preferred embodiment and oneself, the present invention is not limited to this, therefore, it is all constructed with the present invention, device, wait the approximations, thunder such as levy
With, i.e., all according to equivalent replacement made by present patent application range or modification etc., the patent application that should all belong to of the invention is protected
Within the scope of shield.
It should be noted that in the absence of conflict, the feature in embodiment and embodiment in the present invention can phase
Mutually combination.Although present invention has been a degree of descriptions, it will be apparent that, in the item for not departing from the spirit and scope of the present invention
Under part, the appropriate variation of each condition can be carried out.It is appreciated that the present invention is not limited to the embodiments, and it is attributed to right and wants
The range asked comprising the equivalent replacement of each factor.It will be apparent to those skilled in the art that can as described above
Various other corresponding changes and deformation are made in technical solution and design, and all these change and deformation is all answered
Within this is belonged to the protection scope of the claims of the invention.
Claims (10)
1. a kind of location tracking method identified based on pedestrian again, which is characterized in that including:
Picture obtaining step, the initial picture of acquisition target pedestrian and picture library to be identified;Row in the picture library to be identified
People's picture base area point is classified;
Normalizing step, the picture in initial picture and picture library to be identified to target pedestrian carry out unitized processing;
Weight identification step carries out pedestrian to target pedestrian in picture library to be identified and knows again according to the initial picture of target pedestrian
Not, the N number of and most like pedestrian's picture of target pedestrian is found;N is positive integer;
Query steps are inquired corresponding to certain a group traveling together's picture if there is target pedestrian in certain a group traveling together's picture found
Place;
Video acquisition step obtains the monitor video in inquired place;
Location tracking step is positioned and is tracked to target pedestrian in monitor video, obtains the walking data of target pedestrian;
The walking data include track route.
2. the location tracking method according to claim 1 identified based on pedestrian again, which is characterized in that the walking data
It further include the speed of travel;
The method also includes:
Analytical procedure obtains height, the step-length of target pedestrian;According to the height, step-length, the speed of travel of target pedestrian, mesh is estimated
Mark the walking states of pedestrian.
3. the location tracking method according to claim 2 identified based on pedestrian again, which is characterized in that the target pedestrian
Walking states include:It is relatively slow, slow, normal, fast, very fast.
4. the location tracking method according to claim 1 or 2 identified based on pedestrian again, which is characterized in that the unification
Changing processing includes one of the unitized processing of size, gray proces, filtering processing, black white binarization processing or a variety of.
5. the location tracking method according to claim 1 or 2 identified based on pedestrian again, which is characterized in that N=5.
6. a kind of location tracking device identified based on pedestrian again, which is characterized in that including:
Picture obtain module, for obtain target pedestrian initial picture and picture library to be identified;In the picture library to be identified
Pedestrian's picture base area point classify;
Unitized module carries out unitized processing for the picture in the initial picture and picture library to be identified to target pedestrian;
Weight identification module carries out pedestrian to target pedestrian in picture library to be identified for the initial picture according to target pedestrian
It identifies again, finds the N number of and most like pedestrian's picture of target pedestrian;N is positive integer;
Enquiry module, if there is target pedestrian in certain a group traveling together's picture for being found, inquiry and certain a group traveling together's picture
Corresponding place;
Video acquiring module, for obtaining the monitor video in inquired place;
Location tracking module obtains the walking of target pedestrian for target pedestrian to be positioned and tracked in monitor video
Data;The walking data include track route.
7. the location tracking device according to claim 6 identified based on pedestrian again, which is characterized in that the walking data
It further include the speed of travel;
Described device further includes:
Analysis module, for obtaining height, the step-length of target pedestrian;According to the height, step-length, the speed of travel of target pedestrian, estimate
Count the walking states of target pedestrian.
8. the location tracking device according to claim 7 identified based on pedestrian again, which is characterized in that the target pedestrian
Walking states include:It is relatively slow, slow, normal, fast, very fast.
9. the location tracking device according to claim 6 or 7 identified based on pedestrian again, which is characterized in that the unification
Changing processing includes one of the unitized processing of size, gray proces, filtering processing, black white binarization processing or a variety of.
10. the location tracking device according to claim 6 or 7 identified based on pedestrian again, which is characterized in that N=5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810410845.6A CN108830142A (en) | 2018-05-02 | 2018-05-02 | The location tracking method and device identified again based on pedestrian |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810410845.6A CN108830142A (en) | 2018-05-02 | 2018-05-02 | The location tracking method and device identified again based on pedestrian |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108830142A true CN108830142A (en) | 2018-11-16 |
Family
ID=64147940
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810410845.6A Withdrawn CN108830142A (en) | 2018-05-02 | 2018-05-02 | The location tracking method and device identified again based on pedestrian |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108830142A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110796074A (en) * | 2019-10-28 | 2020-02-14 | 桂林电子科技大学 | Pedestrian re-identification method based on space-time data fusion |
CN111897993A (en) * | 2020-07-20 | 2020-11-06 | 杭州叙简科技股份有限公司 | Efficient target person track generation method based on pedestrian re-recognition |
CN112131919A (en) * | 2020-04-24 | 2020-12-25 | 民航成都电子技术有限责任公司 | Security inspection method, device, equipment and medium |
CN112699745A (en) * | 2020-12-16 | 2021-04-23 | 安徽建筑大学 | Method for positioning trapped people on fire scene |
CN112784630A (en) * | 2019-11-06 | 2021-05-11 | 广东毓秀科技有限公司 | Method for re-identifying pedestrians based on local features of physical segmentation |
CN112949539A (en) * | 2021-03-16 | 2021-06-11 | 安徽领云物联科技有限公司 | Pedestrian re-identification interactive retrieval method and system based on camera position |
-
2018
- 2018-05-02 CN CN201810410845.6A patent/CN108830142A/en not_active Withdrawn
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110796074A (en) * | 2019-10-28 | 2020-02-14 | 桂林电子科技大学 | Pedestrian re-identification method based on space-time data fusion |
CN112784630A (en) * | 2019-11-06 | 2021-05-11 | 广东毓秀科技有限公司 | Method for re-identifying pedestrians based on local features of physical segmentation |
CN112131919A (en) * | 2020-04-24 | 2020-12-25 | 民航成都电子技术有限责任公司 | Security inspection method, device, equipment and medium |
CN111897993A (en) * | 2020-07-20 | 2020-11-06 | 杭州叙简科技股份有限公司 | Efficient target person track generation method based on pedestrian re-recognition |
CN112699745A (en) * | 2020-12-16 | 2021-04-23 | 安徽建筑大学 | Method for positioning trapped people on fire scene |
CN112949539A (en) * | 2021-03-16 | 2021-06-11 | 安徽领云物联科技有限公司 | Pedestrian re-identification interactive retrieval method and system based on camera position |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108830142A (en) | The location tracking method and device identified again based on pedestrian | |
US11670086B2 (en) | System and process for detecting, tracking and counting human objects of interest | |
CN107123131B (en) | Moving target detection method based on deep learning | |
US20210406550A1 (en) | Information processing apparatus, information processing method, and program | |
US20240071086A1 (en) | Information processing apparatus, information processing method, and program | |
CN110070155B (en) | Comprehensive behavior recognition method and system for prisoner based on wearable equipment | |
Everding et al. | Low-latency line tracking using event-based dynamic vision sensors | |
CN111445442B (en) | Crowd counting method and device based on neural network, server and storage medium | |
Ghodgaonkar et al. | Analyzing worldwide social distancing through large-scale computer vision | |
Lumentut et al. | Evaluation of recursive background subtraction algorithms for real-time passenger counting at bus rapid transit system | |
WO2019088333A1 (en) | Method for recognizing human body activity on basis of depth map information and apparatus therefor | |
CN109886100A (en) | A kind of pedestrian detecting system based on Area generation network | |
Valencia et al. | Overhead view bus passenger detection and counter using deepsort and tiny-yolo v4 | |
CN104361087A (en) | Image-based motor vehicle retrieval method and device | |
CN116366806A (en) | Intelligent monitoring system based on Internet of things | |
Changalasetty et al. | Classification of moving vehicles using k-means clustering | |
Syahidi et al. | Computer Vision in Smart City Application: A Mapping Review | |
Raman et al. | Towards optimized placement of cameras for gait pattern recognition | |
Mao et al. | CVRRSS‐CHD: Computer vision‐related roadside surveillance system using compound hierarchical‐deep models | |
JPWO2019138537A1 (en) | Information processing equipment, control methods, and programs | |
Malbog et al. | PED-AI: Pedestrian Detection for Autonomous Vehicles using YOLOv5 | |
Zhang et al. | Self-detection of optical contamination or occlusion in vehicle vision systems | |
Rama Santosh Naidu et al. | A Novel Hybrid Tracking Algorithm for Client–Server Connection Using a Machine Learning Technique | |
Sato et al. | User's Height Estimation based on Acceleration from Smartphone Sensors | |
Cutino et al. | Event-based human intrusion detection in UAS using Deep Learning |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20181116 |