CN114758464A - Storage battery anti-theft method, device and storage medium based on charging pile monitoring video - Google Patents

Storage battery anti-theft method, device and storage medium based on charging pile monitoring video Download PDF

Info

Publication number
CN114758464A
CN114758464A CN202210675753.7A CN202210675753A CN114758464A CN 114758464 A CN114758464 A CN 114758464A CN 202210675753 A CN202210675753 A CN 202210675753A CN 114758464 A CN114758464 A CN 114758464A
Authority
CN
China
Prior art keywords
detection
area
charging pile
acquiring
storage battery
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
Application number
CN202210675753.7A
Other languages
Chinese (zh)
Other versions
CN114758464B (en
Inventor
梁帆
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangdong Prophet Big Data Co ltd
Original Assignee
Dongguan Prophet Big Data Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Dongguan Prophet Big Data Co ltd filed Critical Dongguan Prophet Big Data Co ltd
Priority to CN202210675753.7A priority Critical patent/CN114758464B/en
Publication of CN114758464A publication Critical patent/CN114758464A/en
Application granted granted Critical
Publication of CN114758464B publication Critical patent/CN114758464B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B13/00—Burglar, theft or intruder alarms
    • G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
    • G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
    • G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
    • G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
    • G08B13/19602—Image analysis to detect motion of the intruder, e.g. by frame subtraction
    • G08B13/19613—Recognition of a predetermined image pattern or behaviour pattern indicating theft or intrusion

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Burglar Alarm Systems (AREA)
  • Closed-Circuit Television Systems (AREA)
  • Charge And Discharge Circuits For Batteries Or The Like (AREA)

Abstract

The invention belongs to the technical field of image recognition, and particularly discloses a storage battery anti-theft method, equipment and a storage medium based on a charging pile monitoring video. The method comprises the following steps: acquiring a monitoring video of a charging pile area in real time and acquiring a monitoring picture; when the fact that the person enters the charging pile area is judged, acquiring the limb coordinates of key parts of the person in each frame of image; setting a detection rectangular area, and acquiring information of the battery car in the detection rectangular area; acquiring the information of a tire frame of the battery car, and acquiring the action score of a person; and detecting the battery items in the continuous picture area based on the personnel action scores to obtain a battery detection result. The method effectively identifies the key characteristics of the video through a special algorithm, solves the problems of high cost and low efficiency of manual inspection, realizes the standardization, automation and high efficiency of the anti-theft monitoring of the storage battery in the storage battery car charging place, and realizes the real-time detection and early warning of the storage battery theft event.

Description

Storage battery anti-theft method, device and storage medium based on charging pile monitoring video
Technical Field
The invention belongs to the technical field of image recognition, and particularly relates to a storage battery anti-theft method, equipment and a storage medium based on a charging pile monitoring video.
Background
When the storage battery car stops at the charging pile for charging, because no specially-assigned person is watched nearby the charging pile, the storage battery is easily stolen, and in the process of post reconnaissance, a large amount of monitoring videos need to be watched by a policeman to search for stolen people, so that a large amount of labor cost is consumed, and the efficiency is low, the storage battery anti-theft real-time detection method based on the charging pile monitoring videos is needed to realize real-time detection and early warning of the storage battery theft event.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention aims to provide a storage battery anti-theft method based on a charging pile monitoring video. This system passes through the theftproof detection score behind the calculation personnel entering charging pile, carries out real-time detection to storage battery theft event according to the score height, has solved the high cost of manual inspection, inefficient problem, has realized storage battery theftproof control's in storage battery car place of charging standardization, automation and high efficiency.
In order to achieve the above object, the embodiments of the present invention provide the following technical solutions.
A storage battery anti-theft method based on charging pile monitoring videos comprises the following steps:
step S1: deploying a monitoring camera in a charging pile area, acquiring a monitoring video of the monitoring camera in real time, and acquiring the width W and the height H of a monitoring picture;
step S2: setting a charging pile area in the monitoring picture;
step S3: judging whether personnel exist in the charging pile area or not;
step S4: when the person is judged to enter the charging pile area, acquiring the neck coordinate of the person in each frame of image
Figure 986247DEST_PATH_IMAGE001
Hip bone center point coordinates
Figure 382594DEST_PATH_IMAGE002
Arm coordinate
Figure 787030DEST_PATH_IMAGE003
，
Figure 636037DEST_PATH_IMAGE004
And wrist coordinates
Figure 541545DEST_PATH_IMAGE005
，
Figure 57977DEST_PATH_IMAGE006
Wherein i represents a frame number; initializing an item score for each frame
Figure 508681DEST_PATH_IMAGE007
；
Step S5: setting a detection rectangular area, acquiring the information of the storage battery car in the detection rectangular area, and acquiring the synchronous score of people and cars
Figure 844985DEST_PATH_IMAGE008
A value;
step S6: when the battery car exists in the detection rectangular area, acquiring the information of a tire frame of the battery car, and acquiring a person action score;
step S7: and detecting the battery items in the continuous picture area based on the personnel action scores to obtain a battery detection result.
Further, set up the electric pile area of filling in the control picture, include:
four boundary points are set in the monitoring picture
Figure 163971DEST_PATH_IMAGE009
The four points are sequentially connected clockwise to form a charging pile area; the charging pile area covers the parking lot range in the monitoring picture in a perspective relation.
Further, the judging whether personnel exist in the charging pile area comprises the following steps:
real-time acquisition of personnel coordinates in a monitoring screen
Figure 269330DEST_PATH_IMAGE010
When the personnel coordinate meets a first condition, judging that the personnel enters a charging pile area; the first condition is:
Figure 140203DEST_PATH_IMAGE011
Figure 698223DEST_PATH_IMAGE012
further, the setting of the detection rectangular area includes:
step S5.1: setting the detection rectangular area as
Figure 820900DEST_PATH_IMAGE013
Wherein
Figure 780766DEST_PATH_IMAGE014
Respectively representing the abscissa of the top left vertex of the detection rectangular region, the ordinate of the top left vertex, the width of the region and the height of the region; wherein, the first and the second end of the pipe are connected with each other,
Figure 573272DEST_PATH_IMAGE015
Figure 884168DEST_PATH_IMAGE016
Figure 544956DEST_PATH_IMAGE017
Figure 93749DEST_PATH_IMAGE018
in the formula (I), the compound is shown in the specification,
Figure 447370DEST_PATH_IMAGE019
a width correction constant obtained by training historical data;
Figure 104617DEST_PATH_IMAGE020
a height correction constant obtained by training historical data;
Figure 303517DEST_PATH_IMAGE021
forward panning derived for historical data training
Figure 237975DEST_PATH_IMAGE022
The constant of the correction is changed,
Figure 762497DEST_PATH_IMAGE023
；
Figure 392193DEST_PATH_IMAGE024
the inverse translation correction constants trained for historical data,
Figure 660363DEST_PATH_IMAGE025
；
Figure 449327DEST_PATH_IMAGE026
to identify the length of the diagonal of the portrait frame;
acquiring the information of the battery cars in the detection rectangular area and acquiring the synchronous scores of people and cars
Figure 879172DEST_PATH_IMAGE027
Values, including:
step S5.2: using a trained yolov4 model to detect the rectangular area
Figure 511010DEST_PATH_IMAGE013
Carrying out storage battery car detection; setting when there is a battery car in the area
Figure 317292DEST_PATH_IMAGE028
(ii) a When no battery car exists in the area, setting
Figure 960763DEST_PATH_IMAGE029
。
Further, acquire storage battery car tire square frame information, obtain personnel's action score, include:
step S6.1: when the storage battery car exists in the detection rectangular area, acquiring a complete image of the storage battery car in a monitoring picture and identifying information of two groups of tire square frames of the storage battery car; the two groups of tire square frame information are respectively
Figure 827088DEST_PATH_IMAGE030
,
Figure 431376DEST_PATH_IMAGE031
Wherein
Figure 41349DEST_PATH_IMAGE032
，
Figure 804905DEST_PATH_IMAGE033
The left vertex abscissa of the image box of the tire,
Figure 576552DEST_PATH_IMAGE034
，
Figure 182983DEST_PATH_IMAGE035
is the vertical coordinate of the top left corner of the tire image box,
Figure 331068DEST_PATH_IMAGE036
，
Figure 949131DEST_PATH_IMAGE037
is the width of the square frame of the tire image,
Figure 891679DEST_PATH_IMAGE038
，
Figure 329614DEST_PATH_IMAGE039
high for the tire image square;
step S6.2: then obtaining the action score of the person
Figure 156755DEST_PATH_IMAGE040
，
Figure 894904DEST_PATH_IMAGE041
(ii) a Personnel action scoring when there is no battery car in the area
Figure 8354DEST_PATH_IMAGE042
；
Wherein the content of the first and second substances,
Figure 199163DEST_PATH_IMAGE043
scoring for contact:
Figure 813684DEST_PATH_IMAGE044
Figure 406340DEST_PATH_IMAGE045
Figure 956270DEST_PATH_IMAGE046
Figure 368797DEST_PATH_IMAGE047
Figure 537741DEST_PATH_IMAGE048
Figure 984903DEST_PATH_IMAGE049
Figure 705734DEST_PATH_IMAGE050
in the formula (I), the compound is shown in the specification,
Figure 871136DEST_PATH_IMAGE051
and
Figure 437247DEST_PATH_IMAGE052
a contact correction constant and a separation correction constant obtained by training historical data;
Figure 863549DEST_PATH_IMAGE053
correcting the threshold for the lower bound;
Figure 755282DEST_PATH_IMAGE054
scoring the contact distance;
Figure 142401DEST_PATH_IMAGE055
correcting the threshold value for the upper bound;
Figure 777781DEST_PATH_IMAGE056
scoring the junction;
Figure 74902DEST_PATH_IMAGE057
a first sub-score for the contact;
Figure 137535DEST_PATH_IMAGE058
a second sub-score for contact;
Figure 11951DEST_PATH_IMAGE059
scoring the limbs:
Figure 185443DEST_PATH_IMAGE060
Figure 586337DEST_PATH_IMAGE061
in the formula (I), the compound is shown in the specification,
Figure 819872DEST_PATH_IMAGE062
，
Figure 181584DEST_PATH_IMAGE063
setting a first judgment threshold value and a second judgment threshold value;
Figure 158767DEST_PATH_IMAGE064
scoring for trunk:
Figure 430479DEST_PATH_IMAGE065
in the formula (I), the compound is shown in the specification,
Figure 834916DEST_PATH_IMAGE066
the resulting correction constants are trained for historical data,
Figure 152765DEST_PATH_IMAGE067
in order to set the third determination threshold value,
Figure 933639DEST_PATH_IMAGE068
positive real numbers much smaller than 1.
Further, the step S7 includes:
step S7.1: scoring when detecting an in-frame person action
Figure 184492DEST_PATH_IMAGE069
For the frame before the picture
Figure 884463DEST_PATH_IMAGE070
Recording the action scores of the persons in the frame picture to obtain
Figure 955188DEST_PATH_IMAGE071
Scoring of human actions for successive frames, including
Figure 274173DEST_PATH_IMAGE072
(ii) a When in use
Figure 379533DEST_PATH_IMAGE073
When it is used, order
Figure 1138DEST_PATH_IMAGE074
；
Wherein the content of the first and second substances,
Figure 824738DEST_PATH_IMAGE075
a set fourth determination threshold;
Figure 681835DEST_PATH_IMAGE070
is a set positive integer;
step S7.2: meterIs obtained by calculation
Figure 907280DEST_PATH_IMAGE076
(ii) a When in use
Figure 949054DEST_PATH_IMAGE077
Judging the current detection frame as the initial detection frame; detecting the battery-like articles in the region O by a trained yolo model for any frame k from the initial detection frame; when battery-like articles exist in the region O, setting
Figure 994371DEST_PATH_IMAGE078
；
Wherein the content of the first and second substances,
Figure 655159DEST_PATH_IMAGE079
is a set fifth judgment threshold;
Figure 469531DEST_PATH_IMAGE080
scoring a continuous action; the definition of the region O is:
Figure 698519DEST_PATH_IMAGE081
satisfy the requirement of
Figure 965552DEST_PATH_IMAGE082
Then the
Figure 430031DEST_PATH_IMAGE083
；
Wherein, the point in the region O is a set of all points meeting the condition in the detection scene;
and adding the blurred battery images into a yolo training model to obtain a yolo model of the battery article detection model.
Further, the method further includes step S8:
recording the number N of monitoring video frames from entering a charging pile area to leaving the charging pile area0；
When the temperature is higher than the set temperature
Figure 364489DEST_PATH_IMAGE084
Then, the entry score is calculated
Figure 623432DEST_PATH_IMAGE085
；
Calculating to obtain leaving score
Figure 779693DEST_PATH_IMAGE086
；
Calculating to obtain action score
Figure 47864DEST_PATH_IMAGE087
；
Calculating to obtain the score of the article
Figure 836828DEST_PATH_IMAGE088
；
Calculating to obtain a theft detection score
Figure 266672DEST_PATH_IMAGE089
；
Figure 649243DEST_PATH_IMAGE090
Figure 455525DEST_PATH_IMAGE091
Wherein the content of the first and second substances,
Figure 98996DEST_PATH_IMAGE092
is a set sixth determination threshold;
Figure 965321DEST_PATH_IMAGE093
is a set first calculation constant;
Figure 818877DEST_PATH_IMAGE094
is a set second calculation constant;
Figure 428849DEST_PATH_IMAGE095
，
Figure 926827DEST_PATH_IMAGE096
respectively set as a seventh judgment threshold and an eighth judgment threshold;
Figure 964053DEST_PATH_IMAGE097
，
Figure 55637DEST_PATH_IMAGE098
the first judgment threshold and the second judgment threshold are respectively set;
Figure 203722DEST_PATH_IMAGE099
and (4) an access correction constant trained for historical data.
Further, the method further includes step S9: when theft detection scores
Figure 821785DEST_PATH_IMAGE100
And when the detection threshold TS is larger than the set detection threshold TS, the storage battery stealing behavior of the personnel is judged, and the personnel information is acquired and a real-time alarm is sent to the supervision personnel through the communication device.
Another object of the present invention is to provide a computer device/mobile terminal, comprising:
a memory for storing a computer program;
and the processor is used for executing the computer program in the memory so as to realize the operation steps of the battery anti-theft method based on the charging pile monitoring video.
Another object of the present invention is to provide a computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the operation steps of the charging pile monitoring video-based battery theft prevention method.
Compared with the prior art, the invention has the beneficial effects that:
the invention provides a storage battery anti-theft method based on a charging pile monitoring video, compared with the prior art, when a storage battery car stops at a charging pile for charging, because no special person is located near the charging pile, the storage battery is easy to be stolen, and in the process of reconnaissance after the event, a policeman needs to watch a large amount of monitoring videos to search for stolen persons, so that a large amount of labor cost is consumed, and the efficiency is low.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention.
FIG. 1 is a schematic flow chart of a method according to an alternative embodiment of the present invention;
FIG. 2 is a diagram of a simulation of a detection scenario in accordance with an alternative embodiment of the present invention;
FIG. 3 is a schematic diagram of charging pile areas and human body key points in accordance with an alternative embodiment of the present invention;
FIG. 4 is a schematic diagram of a rectangular area for detection according to an alternative embodiment of the present invention;
fig. 5 is a schematic diagram of information of a battery car according to an alternative embodiment of the invention.
Legend labels:
1-charging pile area; 2-arm; 3-wrist; 4-the crotch bone; 5-neck; 6-detecting a rectangular area; 7-tyre; 8-battery car.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
See the method flow diagram shown in fig. 1. In a preferred embodiment provided by the invention, the battery anti-theft method based on the monitoring video of the charging pile comprises the following steps:
step S1: and deploying a monitoring camera in a charging pile area, acquiring a monitoring video of the monitoring camera in real time, and acquiring the width W and the height H of a monitoring picture.
Fig. 2 is a simulation diagram of a detection scenario according to an alternative embodiment of the present invention.
Step S2: and setting a charging pile area in the monitoring picture. The method specifically comprises the following steps:
four boundary points are set in the monitoring picture
Figure 764333DEST_PATH_IMAGE009
And the four points are sequentially connected clockwise to form a charging pile area. The charging pile area covers the parking lot range in the monitoring picture in a perspective relation.
Fig. 3 is a schematic diagram of charging pile areas and human body key points according to an alternative embodiment of the invention.
Step S3: and judging whether personnel exist in the charging pile area or not. The method specifically comprises the following steps:
real-time acquisition of personnel coordinates in a monitoring screen
Figure 858060DEST_PATH_IMAGE010
And when the personnel coordinate meets a first condition, judging that the personnel enter a charging pile area. The first condition is:
Figure 809835DEST_PATH_IMAGE011
Figure 282405DEST_PATH_IMAGE012
step S4: when the person is judged to enter the charging pile area, acquiring the neck coordinate of the person in each frame of image
Figure 395854DEST_PATH_IMAGE001
Hip bone center point coordinates
Figure 586664DEST_PATH_IMAGE002
Arm coordinate
Figure 951918DEST_PATH_IMAGE003
，
Figure 544573DEST_PATH_IMAGE004
And wrist coordinates
Figure 828924DEST_PATH_IMAGE005
，
Figure 507030DEST_PATH_IMAGE006
Where i represents the number of frames. Initializing an item score for each frame
Figure 535029DEST_PATH_IMAGE007
。
Step S5: setting a detection rectangular area, acquiring the information of the storage battery car in the detection rectangular area, and acquiring the synchronous score of people and cars
Figure 106824DEST_PATH_IMAGE027
The value is obtained. The method comprises the following specific steps:
step S5.1: setting the detection rectangular area as
Figure 827656DEST_PATH_IMAGE013
Wherein
Figure 727479DEST_PATH_IMAGE014
Respectively representing the horizontal coordinates of the top left corner vertex of the detection rectangular area, the vertical coordinates of the top left corner vertex, the width of the area and the height of the area; wherein the content of the first and second substances,
Figure 559168DEST_PATH_IMAGE015
Figure 860837DEST_PATH_IMAGE016
Figure 627936DEST_PATH_IMAGE017
Figure 15055DEST_PATH_IMAGE018
in the formula (I), the compound is shown in the specification,
Figure 650435DEST_PATH_IMAGE022
a width correction constant obtained by training historical data;
Figure 72189DEST_PATH_IMAGE020
a height correction constant obtained by training historical data;
Figure 869244DEST_PATH_IMAGE021
forward panning derived for historical data training
Figure 868293DEST_PATH_IMAGE022
The constant of the correction is changed to be constant,
Figure 41785DEST_PATH_IMAGE023
；
Figure 318046DEST_PATH_IMAGE024
the inverse translation correction constants trained for historical data,
Figure 551581DEST_PATH_IMAGE025
；
Figure 647713DEST_PATH_IMAGE026
to identify the length of the diagonal of the portrait frame.
Step S5.2: using a trained yolov4 model to detect the rectangular area
Figure 500262DEST_PATH_IMAGE013
Carrying out storage battery car detection; when the storage battery car exists in the region, setting the man-car synchronous score
Figure 631030DEST_PATH_IMAGE028
(ii) a When no battery car exists in the region, setting man-car synchronous scoring
Figure 35466DEST_PATH_IMAGE029
。
Fig. 4 is a schematic diagram of a rectangular detection area according to an alternative embodiment of the present invention.
Step S6: when the detection rectangular area has the battery car, the information of the tire square frame of the battery car is obtained, and the action score of the person is obtained. The method specifically comprises the following steps:
step S6.1: when the storage battery car exists in the detection rectangular area, acquiring a complete image of the storage battery car in a monitoring picture and identifying the square frame information of two groups of tires of the storage battery car. The two groups of tire square frame information are respectively
Figure 884473DEST_PATH_IMAGE030
，
Figure 399768DEST_PATH_IMAGE031
Wherein
Figure 509676DEST_PATH_IMAGE032
，
Figure 85014DEST_PATH_IMAGE033
The left vertex abscissa of the image box of the tire,
Figure 421317DEST_PATH_IMAGE034
，
Figure 474724DEST_PATH_IMAGE035
the vertical coordinate of the left vertex angle of the tire image box,
Figure 580083DEST_PATH_IMAGE036
，
Figure 201688DEST_PATH_IMAGE037
for the width of the square frame of the tire image,
Figure 25288DEST_PATH_IMAGE038
，
Figure 882385DEST_PATH_IMAGE039
the height of the box of the tire image.
Step S6.2: then obtaining the action score of the person
Figure 576672DEST_PATH_IMAGE040
，
Figure 759391DEST_PATH_IMAGE041
(ii) a Personnel action scoring when there is no battery car in the area
Figure 929342DEST_PATH_IMAGE042
。
Wherein the content of the first and second substances,
Figure 590130DEST_PATH_IMAGE043
to the contact score:
Figure 670082DEST_PATH_IMAGE044
Figure 492544DEST_PATH_IMAGE045
Figure 25157DEST_PATH_IMAGE046
Figure 365002DEST_PATH_IMAGE047
Figure 299460DEST_PATH_IMAGE048
Figure 558403DEST_PATH_IMAGE049
Figure 312733DEST_PATH_IMAGE050
in the formula (I), the compound is shown in the specification,
Figure 315324DEST_PATH_IMAGE051
and
Figure 228922DEST_PATH_IMAGE052
a contact correction constant and a separation correction constant obtained by training historical data;
Figure 924345DEST_PATH_IMAGE053
correcting the threshold value for the lower bound;
Figure 431550DEST_PATH_IMAGE054
scoring the contact distance;
Figure 706674DEST_PATH_IMAGE055
correcting the threshold value for the upper bound;
Figure 615724DEST_PATH_IMAGE056
scoring a junction;
Figure 91836DEST_PATH_IMAGE057
a first sub-score for the contact;
Figure 86336DEST_PATH_IMAGE058
is the exposure to the second sub-score.
Figure 165151DEST_PATH_IMAGE059
Scoring the limbs:
Figure 928708DEST_PATH_IMAGE060
Figure 965934DEST_PATH_IMAGE061
in the formula (I), the compound is shown in the specification,
Figure 306785DEST_PATH_IMAGE062
，
Figure 454870DEST_PATH_IMAGE063
the first judgment threshold value and the second judgment threshold value are set.
Figure 807354DEST_PATH_IMAGE064
Scoring for trunk:
Figure 15481DEST_PATH_IMAGE065
in the formula (I), the compound is shown in the specification,
Figure 718995DEST_PATH_IMAGE066
the resulting correction constants are trained for historical data,
Figure 280557DEST_PATH_IMAGE067
in order to set the third determination threshold value,
Figure 753127DEST_PATH_IMAGE068
a positive real number much less than 1, such as 0.0001.
Fig. 5 is a schematic diagram of information of a battery car according to an alternative embodiment of the present invention.
Step S7: and detecting the battery items in the continuous picture area based on the personnel action scores to obtain a battery detection result. The method specifically comprises the following steps:
step S7.1: scoring when detecting an in-frame person action
Figure 132156DEST_PATH_IMAGE069
For the frame before the picture
Figure 322966DEST_PATH_IMAGE070
Recording the action scores of the persons in the frame picture to obtain
Figure 812853DEST_PATH_IMAGE071
Scoring of human actions for successive frames, including
Figure 264563DEST_PATH_IMAGE072
(ii) a When in use
Figure 814493DEST_PATH_IMAGE073
When it is used, order
Figure 227020DEST_PATH_IMAGE074
。
Wherein the content of the first and second substances,
Figure 520598DEST_PATH_IMAGE075
is a set fourth determination threshold;
Figure 967760DEST_PATH_IMAGE070
is a set positive integer, such as 10.
Step S7.2: is obtained by calculation
Figure 298378DEST_PATH_IMAGE076
(ii) a When in use
Figure 198201DEST_PATH_IMAGE077
Judging the current detection frame as the initial detection frame; detecting the battery-like articles in the region O by a trained yolo model for any frame k from the initial detection frame; when battery-like articles exist in the region O, setting
Figure 29891DEST_PATH_IMAGE078
。
Wherein the content of the first and second substances,
Figure 597138DEST_PATH_IMAGE079
is a set fifth judgment threshold;
Figure 613505DEST_PATH_IMAGE080
scoring a continuous motion; the definition of the region O is:
Figure 266203DEST_PATH_IMAGE081
satisfy the requirement of
Figure 636004DEST_PATH_IMAGE082
Then
Figure 792179DEST_PATH_IMAGE083
Where the points in region O are the set of all points within the detection scene that satisfy the condition.
Preferably, because standard storage battery detection error is great, so add some blurred storage battery images into training yolo model, obtain the yolo model of class storage battery article detection model, reduce and miss the judgement.
Based on the embodiment, based on the personnel action score and the storage battery detection result, the technical effect of the storage battery anti-theft method based on the charging pile monitoring video can be obtained.
Preferably, the embodiment may add the following steps.
Step S8: recording the number N of monitoring video frames from entering a charging pile area to leaving the charging pile area0。
When in use
Figure 854813DEST_PATH_IMAGE084
Then, the entry score is calculated
Figure 604594DEST_PATH_IMAGE085
；
Calculating to obtain leaving score
Figure 43666DEST_PATH_IMAGE086
；
Calculating to obtain action score
Figure 319926DEST_PATH_IMAGE087
；
Is obtained by calculationItem scoring
Figure 553462DEST_PATH_IMAGE088
；
Calculating to obtain a theft detection score
Figure 649594DEST_PATH_IMAGE089
；
Figure 751411DEST_PATH_IMAGE090
Figure 882178DEST_PATH_IMAGE091
Wherein, the first and the second end of the pipe are connected with each other,
Figure 286614DEST_PATH_IMAGE092
is a set sixth determination threshold;
Figure 870042DEST_PATH_IMAGE093
is a set first calculation constant;
Figure 385337DEST_PATH_IMAGE094
is a set second calculation constant;
Figure 511556DEST_PATH_IMAGE095
，
Figure 86894DEST_PATH_IMAGE096
respectively set as a seventh judgment threshold and an eighth judgment threshold;
Figure 423198DEST_PATH_IMAGE097
，
Figure 476604DEST_PATH_IMAGE098
respectively set as a ninth judgment threshold and a tenth judgment threshold;
Figure 581963DEST_PATH_IMAGE099
and (4) an access correction constant trained for historical data.
Preferably, the embodiment may add the following steps.
Step S9: score g when theft is detectedfWhen the TS is larger than the set detection threshold TS, the battery stealing behavior of the personnel is judged, and the personnel information is acquired to send a real-time alarm to the supervision personnel through the communication device.
Another embodiment of the present invention provides a computer device/mobile terminal based on the foregoing battery anti-theft method based on charging pile monitoring video, including:
a memory for storing a computer program;
and the processor is used for executing the computer program in the memory so as to realize the operation steps of the battery anti-theft method based on the charging pile monitoring video.
In order to load the above system and method for operation, the system may include more or less components than those described above, or combine some components, or different components, in addition to the various modules described above, for example, a monitoring camera, an input/output device, a network access device, a bus, a processor, a memory, and the like.
The Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. The general purpose processor may be a microprocessor or the processor may be any conventional processor or the like which is the control center for the client or associated system and which connects the various parts of the overall user terminal using various interfaces and lines.
The memory can be used for storing computer and mobile phone programs and/or modules, and the processor can realize various functions of the client by running or executing the computer, the mobile phone programs and/or modules stored in the memory and calling data stored in the memory. The memory mainly comprises a storage program area and a storage data area, wherein the storage program area can store an operating system, application programs (such as an information acquisition template display function, a product information publishing function and the like) required by at least one function and the like; the storage data area may store data created according to the use of the berth-state display system (e.g., product information acquisition templates corresponding to different product types, product information that needs to be issued by different product providers, etc.), and the like. In addition, the memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
In another embodiment of the present invention, on the basis of the foregoing battery anti-theft method based on charging pile monitoring video, a computer-readable storage medium is provided, on which a computer program is stored, and the computer program, when being executed by a processor, implements the foregoing operating steps of the battery anti-theft method based on charging pile monitoring video.
It will be understood by those of ordinary skill in the art that all or part of the processes and modules in the above embodiments may be implemented by computer and mobile phone programs, hardware, and combinations thereof. The program may be stored in a non-volatile computer readable storage medium, and when executed, may implement processes including embodiments of the modules and methods described above.
The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (10)

1. A storage battery anti-theft method based on charging pile monitoring video is characterized by comprising the following steps:
step S1: deploying a monitoring camera in a charging pile area, acquiring a monitoring video of the monitoring camera in real time, and acquiring the width W and the height H of a monitoring picture;
step S2: setting a charging pile area in the monitoring picture;
step S3: judging whether personnel exist in the charging pile area or not;
step S4: when the person is judged to enter the charging pile area, acquiring the neck coordinate of the person in each frame of image
Figure 668974DEST_PATH_IMAGE001
Hip bone center point coordinates
Figure 176179DEST_PATH_IMAGE002
Arm coordinate
Figure 451303DEST_PATH_IMAGE003
,
Figure 360353DEST_PATH_IMAGE004
And wrist coordinates
Figure 836465DEST_PATH_IMAGE005
,
Figure 830965DEST_PATH_IMAGE006
Wherein i represents the number of frames; initializing the items of each frameIs divided into
Figure 175359DEST_PATH_IMAGE007
；
Step S5: setting a detection rectangular area, acquiring the information of the storage battery car in the detection rectangular area, and acquiring the synchronous score of people and cars
Figure 673336DEST_PATH_IMAGE008
A value;
step S6: when the battery car exists in the detection rectangular area, acquiring the information of a tire frame of the battery car, and acquiring a person action score;
step S7: and detecting the storage battery articles in the continuous picture area based on the personnel action score to obtain a storage battery detection result.
2. The method according to claim 1, wherein the setting of the charging pile area in the monitoring screen comprises:
four boundary points are set in the monitoring picture
Figure 710563DEST_PATH_IMAGE009
The four points are sequentially connected clockwise to form a charging pile area; the charging pile area covers the parking lot range in the monitoring picture in a perspective relation.
3. The method of claim 2, wherein the determining whether personnel are present in the charging post area comprises:
real-time acquisition of personnel coordinates in a monitoring screen
Figure 51414DEST_PATH_IMAGE010
When the personnel coordinate meets a first condition, judging that the personnel enters a charging pile area; the first condition is:
Figure 199499DEST_PATH_IMAGE011
,
Figure 817562DEST_PATH_IMAGE012
。
4. the method of claim 3, wherein:
the setting of the detection rectangular area includes:
step S5.1: setting the detection rectangular area as
Figure 760110DEST_PATH_IMAGE013
Wherein
Figure 463624DEST_PATH_IMAGE014
Respectively representing the abscissa of the top left vertex of the detection rectangular region, the ordinate of the top left vertex, the width of the region and the height of the region; wherein the content of the first and second substances,
Figure 25186DEST_PATH_IMAGE015
Figure 763335DEST_PATH_IMAGE016
Figure 142364DEST_PATH_IMAGE017
Figure 67595DEST_PATH_IMAGE018
in the formula (I), the compound is shown in the specification,
Figure 557482DEST_PATH_IMAGE019
a width correction constant obtained by training historical data;
Figure 9192DEST_PATH_IMAGE020
a height correction constant obtained by training historical data;
Figure 559122DEST_PATH_IMAGE021
forward panning derived for historical data training
Figure 971649DEST_PATH_IMAGE022
The constant of the correction is changed to be constant,
Figure 265227DEST_PATH_IMAGE023
；
Figure 712388DEST_PATH_IMAGE024
the inverse translation correction constants trained for historical data,
Figure 43007DEST_PATH_IMAGE025
；
Figure 208409DEST_PATH_IMAGE026
to identify the length of the diagonal of the portrait frame;
the battery car information in the detection rectangular region is obtained, and the man-car synchronous score is obtained
Figure 774519DEST_PATH_IMAGE008
Values, including:
step S5.2: using a trained yolov4 model to detect the rectangular area
Figure 341767DEST_PATH_IMAGE013
Carrying out storage battery car detection; when the battery car exists in the area, the device is arranged
Figure 967920DEST_PATH_IMAGE027
(ii) a When no battery car exists in the area, setting
Figure 745252DEST_PATH_IMAGE028
。
5. The method as claimed in claim 4, wherein the obtaining of the battery car tire square information and the obtaining of the personnel action score comprises:
step S6.1: when the storage battery car exists in the detection rectangular area, acquiring a complete image of the storage battery car in a monitoring picture and identifying information of two groups of tire square frames of the storage battery car; the two groups of tire square frame information are respectively
Figure 380633DEST_PATH_IMAGE029
，
Figure 271229DEST_PATH_IMAGE030
Wherein
Figure 333863DEST_PATH_IMAGE031
，
Figure 208278DEST_PATH_IMAGE032
The left vertex abscissa of the image box of the tire,
Figure 522716DEST_PATH_IMAGE033
，
Figure 798976DEST_PATH_IMAGE034
the vertical coordinate of the left vertex angle of the tire image box,
Figure 32511DEST_PATH_IMAGE035
，
Figure 394223DEST_PATH_IMAGE036
for the width of the square frame of the tire image,
Figure 105827DEST_PATH_IMAGE037
，
Figure 361227DEST_PATH_IMAGE038
high for the tire image square;
step S6.2: then obtaining the action score of the person
Figure 765664DEST_PATH_IMAGE039
，
Figure 614671DEST_PATH_IMAGE040
(ii) a Personnel action scoring when there is no battery car in the area
Figure 129966DEST_PATH_IMAGE041
；
Wherein the content of the first and second substances,
Figure 256185DEST_PATH_IMAGE042
scoring for contact:
Figure 565944DEST_PATH_IMAGE043
Figure 902247DEST_PATH_IMAGE044
Figure 221233DEST_PATH_IMAGE045
Figure 326592DEST_PATH_IMAGE046
Figure 807252DEST_PATH_IMAGE047
Figure 501625DEST_PATH_IMAGE048
Figure 624302DEST_PATH_IMAGE049
in the formula (I), the compound is shown in the specification,
Figure 584168DEST_PATH_IMAGE050
and
Figure 501308DEST_PATH_IMAGE051
a contact correction constant and a separation correction constant obtained by training historical data;
Figure 546624DEST_PATH_IMAGE052
correcting the threshold for the lower bound;
Figure 82779DEST_PATH_IMAGE053
scoring the contact distance;
Figure 897151DEST_PATH_IMAGE054
correcting the threshold value for the upper bound;
Figure 250772DEST_PATH_IMAGE055
scoring the junction;
Figure 783385DEST_PATH_IMAGE056
a first sub-score for the contact;
Figure 982285DEST_PATH_IMAGE057
a second sub-score for exposure;
Figure 775798DEST_PATH_IMAGE058
scoring the limbs:
Figure 300320DEST_PATH_IMAGE059
Figure 320228DEST_PATH_IMAGE060
in the formula (I), the compound is shown in the specification,
Figure 322819DEST_PATH_IMAGE061
，
Figure 987150DEST_PATH_IMAGE062
setting a first judgment threshold value and a second judgment threshold value;
Figure 416994DEST_PATH_IMAGE063
scoring for trunk:
Figure 658620DEST_PATH_IMAGE064
in the formula (I), the compound is shown in the specification,
Figure 464902DEST_PATH_IMAGE065
the resulting correction constants are trained for historical data,
Figure 373952DEST_PATH_IMAGE066
in order to set the third determination threshold value,
Figure 709118DEST_PATH_IMAGE067
positive real numbers much smaller than 1.
6. The method according to claim 5, wherein the step S7 includes:
step S7.1: scoring when detecting an in-frame person action
Figure 828253DEST_PATH_IMAGE068
When, toBefore the frame
Figure 172647DEST_PATH_IMAGE069
Recording the action scores of the persons in the frame picture to obtain
Figure 936203DEST_PATH_IMAGE070
Scoring of human actions for successive frames, including
Figure 707850DEST_PATH_IMAGE071
(ii) a When in use
Figure 924068DEST_PATH_IMAGE072
When it is used, make
Figure 947519DEST_PATH_IMAGE073
；
Wherein the content of the first and second substances,
Figure 565582DEST_PATH_IMAGE074
a set fourth determination threshold;
Figure 773709DEST_PATH_IMAGE069
is a set positive integer;
step S7.2: is obtained by calculation
Figure 477223DEST_PATH_IMAGE075
(ii) a When in use
Figure 897840DEST_PATH_IMAGE076
Judging the current detection frame as the initial detection frame; detecting the battery goods in the region O for any subsequent frame k from the initial detection frame through a trained yolo model; when battery-like articles exist in the region O, setting
Figure 760623DEST_PATH_IMAGE077
；
Wherein the content of the first and second substances,
Figure 874072DEST_PATH_IMAGE078
is a set fifth judgment threshold;
Figure 64882DEST_PATH_IMAGE079
scoring a continuous motion; the definition of the region O is:
Figure 289190DEST_PATH_IMAGE080
satisfy the requirement of
Figure 881846DEST_PATH_IMAGE081
Then
Figure 307142DEST_PATH_IMAGE082
(ii) a Wherein, the point in the region O is a set of all points meeting the condition in the detection scene;
and adding the blurred battery images into a yolo training model to obtain a yolo model of the battery article detection model.
7. The method according to claim 6, further comprising step S8:
recording the number N of monitoring video frames from entering a charging pile area to leaving the charging pile area0；
When in use
Figure 985248DEST_PATH_IMAGE083
Then, the entry score is calculated
Figure 13247DEST_PATH_IMAGE084
；
Calculating to obtain leaving score
Figure 194829DEST_PATH_IMAGE085
；
Calculating to obtain action score
Figure 915661DEST_PATH_IMAGE086
；
Calculating to obtain the score of the article
Figure 205697DEST_PATH_IMAGE087
；
Calculating to obtain a theft detection score
Figure 37386DEST_PATH_IMAGE088
；
Figure 73476DEST_PATH_IMAGE089
Figure 965208DEST_PATH_IMAGE090
Wherein the content of the first and second substances,
Figure 617906DEST_PATH_IMAGE091
is a set sixth determination threshold;
Figure 863074DEST_PATH_IMAGE092
is a set first calculation constant;
Figure 19249DEST_PATH_IMAGE093
is a set second calculation constant;
Figure 81883DEST_PATH_IMAGE094
，
Figure 956298DEST_PATH_IMAGE095
respectively set as a seventh judgment threshold and an eighth judgment threshold;
Figure 395370DEST_PATH_IMAGE096
，
Figure 796264DEST_PATH_IMAGE097
respectively set as a ninth judgment threshold and a tenth judgment threshold;
Figure 764220DEST_PATH_IMAGE098
and (4) an access correction constant trained for historical data.
8. The method according to claim 7, further comprising step S9: when theft detection scores
Figure 125931DEST_PATH_IMAGE099
And when the detection threshold TS is larger than the set detection threshold TS, the storage battery stealing behavior of the personnel is judged, and the personnel information is acquired and a real-time alarm is sent to the supervision personnel through the communication device.
9. A computer device/mobile terminal, comprising:
a memory for storing a computer program;
a processor for executing the computer program in the memory to carry out the operational steps of the method of any one of claims 1 to 8.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the operating steps of the method according to any one of claims 1 to 8.
CN202210675753.7A 2022-06-15 2022-06-15 Storage battery anti-theft method, device and storage medium based on charging pile monitoring video Active CN114758464B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210675753.7A CN114758464B (en) 2022-06-15 2022-06-15 Storage battery anti-theft method, device and storage medium based on charging pile monitoring video

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210675753.7A CN114758464B (en) 2022-06-15 2022-06-15 Storage battery anti-theft method, device and storage medium based on charging pile monitoring video

Publications (2)

Publication Number Publication Date
CN114758464A true CN114758464A (en) 2022-07-15
CN114758464B CN114758464B (en) 2022-09-13

Family

ID=82336841

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210675753.7A Active CN114758464B (en) 2022-06-15 2022-06-15 Storage battery anti-theft method, device and storage medium based on charging pile monitoring video

Country Status (1)

Country Link
CN (1) CN114758464B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115009074A (en) * 2022-07-21 2022-09-06 东莞先知大数据有限公司 Charging pile electricity stealing behavior detection method, electronic equipment and storage medium
CN115471787A (en) * 2022-08-09 2022-12-13 东莞先知大数据有限公司 Construction site object stacking detection method and device and storage medium
CN115862241A (en) * 2023-03-03 2023-03-28 江苏安能科技有限公司 Charging pile region theft monitoring method

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2002264874A (en) * 2001-03-12 2002-09-18 Toshiba Corp Communication device for motorcycle, and helmet and antitheft device using the same
CN106184490A (en) * 2016-08-18 2016-12-07 南京九致信息科技有限公司 The anti-theft device for battery of electrically assisted bicycle and electrically assisted bicycle
CN207503392U (en) * 2017-09-25 2018-06-15 河南英开电气股份有限公司 A kind of electric automobile charging pile anti-theft monitoring system
CN208233219U (en) * 2017-12-25 2018-12-14 常州金葵智能技术有限公司 A kind of warning device of public electric vehicle charging device
CN109522938A (en) * 2018-10-26 2019-03-26 华南理工大学 The recognition methods of target in a kind of image based on deep learning
CN112434666A (en) * 2020-12-11 2021-03-02 东莞先知大数据有限公司 Repetitive motion recognition method, device, medium, and apparatus

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2002264874A (en) * 2001-03-12 2002-09-18 Toshiba Corp Communication device for motorcycle, and helmet and antitheft device using the same
CN106184490A (en) * 2016-08-18 2016-12-07 南京九致信息科技有限公司 The anti-theft device for battery of electrically assisted bicycle and electrically assisted bicycle
CN207503392U (en) * 2017-09-25 2018-06-15 河南英开电气股份有限公司 A kind of electric automobile charging pile anti-theft monitoring system
CN208233219U (en) * 2017-12-25 2018-12-14 常州金葵智能技术有限公司 A kind of warning device of public electric vehicle charging device
CN109522938A (en) * 2018-10-26 2019-03-26 华南理工大学 The recognition methods of target in a kind of image based on deep learning
CN112434666A (en) * 2020-12-11 2021-03-02 东莞先知大数据有限公司 Repetitive motion recognition method, device, medium, and apparatus

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115009074A (en) * 2022-07-21 2022-09-06 东莞先知大数据有限公司 Charging pile electricity stealing behavior detection method, electronic equipment and storage medium
CN115009074B (en) * 2022-07-21 2023-03-31 东莞先知大数据有限公司 Charging pile electricity stealing behavior detection method, electronic equipment and storage medium
CN115471787A (en) * 2022-08-09 2022-12-13 东莞先知大数据有限公司 Construction site object stacking detection method and device and storage medium
CN115862241A (en) * 2023-03-03 2023-03-28 江苏安能科技有限公司 Charging pile region theft monitoring method

Also Published As

Publication number Publication date
CN114758464B (en) 2022-09-13

Similar Documents

Publication Publication Date Title
CN114758464B (en) Storage battery anti-theft method, device and storage medium based on charging pile monitoring video
CN111160379B (en) Training method and device of image detection model, and target detection method and device
Choudhury et al. Vehicle detection and counting using haar feature-based classifier
US20190347486A1 (en) Method and apparatus for detecting a garbage dumping action in real time on video surveillance system
US20140003710A1 (en) Unsupervised learning of feature anomalies for a video surveillance system
US20120027263A1 (en) Hand gesture detection
CN111723773B (en) Method and device for detecting carryover, electronic equipment and readable storage medium
CN111597879A (en) Gesture detection method, device and system based on monitoring video
CN110427810A (en) Video damage identification method, device, shooting end and machine readable storage medium
CN104794446A (en) Human body action recognition method and system based on synthetic descriptors
CN108924627A (en) Position distribution display methods, device, equipment and the storage medium of Moving Objects
CN111652111A (en) Target detection method and related device
CN106339684A (en) Pedestrian detection method, device and vehicle
CN108921147A (en) A kind of black smoke vehicle recognition methods based on dynamic texture and transform domain space-time characteristic
CN112883783A (en) Video concentration method and device, terminal equipment and storage medium
CN111813995A (en) Pedestrian article extraction behavior detection method and system based on space-time relationship
CN113283273A (en) Front obstacle real-time detection method and system based on vision technology
Sridevi et al. Automatic generation of traffic signal based on traffic volume
Balcilar et al. Extracting vehicle density from background estimation using Kalman filter
CN113792671A (en) Method and device for detecting face synthetic image, electronic equipment and medium
CN111539267A (en) Human body geometric feature extraction method, device, equipment and system
CN112580633A (en) Public transport passenger flow statistical device and method
CN117115856B (en) Target detection method based on image fusion, human body security inspection equipment and storage medium
CN115861316B (en) Training method and device for pedestrian detection model and pedestrian detection method
Saponara et al. Real-Time imaging acquisition and processing system to improve fire protection in indoor scenarios

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
CP03 Change of name, title or address
CP03 Change of name, title or address

Address after: Building 7, No. 124 Dongbao Road, Dongcheng Street, Dongguan City, Guangdong Province, 523128

Patentee after: Guangdong Prophet Big Data Co.,Ltd.

Country or region after: China

Address before: 523128 Room 401, building 6, No.5 Weifeng Road, Dongcheng Street, Dongguan City, Guangdong Province

Patentee before: Dongguan prophet big data Co.,Ltd.

Country or region before: China