CN110033430A - A kind of pedestrian's quantity statistics method and device - Google Patents
A kind of pedestrian's quantity statistics method and device Download PDFInfo
- Publication number
- CN110033430A CN110033430A CN201910125702.5A CN201910125702A CN110033430A CN 110033430 A CN110033430 A CN 110033430A CN 201910125702 A CN201910125702 A CN 201910125702A CN 110033430 A CN110033430 A CN 110033430A
- Authority
- CN
- China
- Prior art keywords
- pedestrian
- pixel
- leaves
- enters
- probability
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- 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
- 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
-
- 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
- G06T2207/30242—Counting objects in image
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
- Traffic Control Systems (AREA)
Abstract
The present invention provides a kind of pedestrian's quantity statistics method and devices, wherein this method comprises: obtaining several frames of video flowing；Determine the characteristic information of the pedestrian in several frames；According to the characteristic information, the probability that pedestrian's track route and pedestrian enter or leave in pixel is determined；The probability that the pedestrian enters or leaves in pixel is corrected according to pedestrian's track route, obtains the final probability that pedestrian enters or leaves in pixel；According to the final probability that the pedestrian enters or leaves in pixel, the interior pedestrian's quantity for entering or leaving of the statistics preset monitoring area of future time section.
Description
Technical field
The present invention relates to field of computer technology, in particular to a kind of pedestrian's quantity statistics method and device.
Background technique
Pedestrian's quantity statistics can play different effects in different applications.For example, different inside statistics market
Pedestrian's quantity outside pedestrian's quantity of period and market on pavement.Quotient can be assessed by counting obtained pedestrian's quantity
Whether field addressing is appropriate.
In practical application scene, the Statistics Bar people quantity generally by way of artificial picture frame is that is, artificial to draw a detection
Frame, statistics enter or leave pedestrian's quantity of detection block.
But this method cost of labor is higher.Also, due to detection block position difference, obtained statistical result there is also
Difference, and then reduce the reliability of statistical result.
Summary of the invention
In consideration of it, can reduce cost of labor the embodiment of the invention provides a kind of pedestrian's quantity statistics method and device
With the reliability for improving statistical result.
In a first aspect, the embodiment of the invention provides a kind of determining pedestrians in the side for the probability that pixel enters or leaves
Method, comprising:
Obtain several frames of video flowing；
Determine the characteristic information of the pedestrian in several frames；
According to the characteristic information, the probability that pedestrian's track route and pedestrian enter or leave in pixel is determined；
The probability that the pedestrian enters or leaves in pixel is corrected according to pedestrian's track route, obtains pedestrian
In the final probability that pixel enters or leaves.
Second aspect, the embodiment of the invention provides a kind of pedestrian's quantity statistics methods, comprising:
Obtain several frames of video flowing；
Determine the characteristic information of the pedestrian in several frames；
According to the characteristic information, the probability that pedestrian's track route and pedestrian enter or leave in pixel is determined；
The probability that the pedestrian enters or leaves in pixel is corrected according to pedestrian's track route, obtains pedestrian
In the final probability that pixel enters or leaves；
According to the final probability that the pedestrian enters or leaves in pixel, the preset monitoring area of future time section is counted
Interior entrance or the pedestrian's quantity left.
The third aspect, the embodiment of the invention provides a kind of determining pedestrians in pixel entrance or the dress of the probability left
It sets, comprising:
Acquiring unit, for obtaining several frames of video flowing；
Determination unit, for determining the characteristic information of the pedestrian in several frames；
Pedestrian tracking unit, for determining that pedestrian's track route and pedestrian enter in pixel according to the characteristic information
Or the probability left；
Amending unit enters or leaves initial in pixel for correcting the pedestrian according to pedestrian's track route
Probability obtains the final probability that pedestrian enters or leaves in pixel.
Fourth aspect, the embodiment of the invention provides a kind of pedestrian's quantity statistics devices, comprising:
Acquiring unit, for obtaining several frames of video flowing；
Determination unit, for determining the characteristic information of the pedestrian in several frames；
Pedestrian tracking unit, for determining that pedestrian's track route and pedestrian enter in pixel according to the characteristic information
Or the probability left；
Amending unit enters or leaves initial in pixel for correcting the pedestrian according to pedestrian's track route
Probability obtains the final probability that pedestrian enters or leaves in pixel；
Statistic unit counts future time section with the dry final probability for entering or leaving in pixel according to the pedestrian
The pedestrian's quantity for entering or leaving in preset monitoring area.
At least one above-mentioned technical solution used in the embodiment of the present invention can reach following the utility model has the advantages that this method utilizes
Pedestrian's track route is modified pedestrian in the probability that pixel enters or leaves, and can reduce blocking, handing over for pedestrian
It is influenced caused by pixel false statistic caused by fork.The final probability that the pedestrian obtained according to amendment enters or leaves in pixel
Statistics Bar people's quantity can be improved the reliability of statistical result and reduce cost of labor.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, 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 the present invention
Some embodiments for those of ordinary skill in the art without creative efforts, can also basis
These attached drawings obtain other attached drawings.
Fig. 1 is a kind of method of the determining pedestrian provided by one embodiment of the present invention in the probability that pixel enters or leaves
Flow chart；
Fig. 2 is a kind of location of pixels schematic diagram of the pedestrian provided by one embodiment of the present invention in frame；
Fig. 3 is a kind of schematic diagram of direction of travel of the pedestrian provided by one embodiment of the present invention in pixel；
Fig. 4 is a kind of flow chart of pedestrian's quantity statistics method provided by one embodiment of the present invention；
Fig. 5 is a kind of device of the determining pedestrian provided by one embodiment of the present invention in the probability that pixel enters or leaves
Structural schematic diagram；
Fig. 6 is a kind of structural schematic diagram of pedestrian's quantity statistics device provided by one embodiment of the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments, based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
As shown in Figure 1, the embodiment of the invention provides a kind of determining pedestrians in the side for the probability that pixel enters or leaves
Method, this method may comprise steps of:
Step 101: obtaining several frames of video flowing.
Video flowing can be obtained by shootings such as RGB camera, RGBD cameras.It, can be according in practical application scene
The preset period intercepts different frame from video flowing, for example, every 20ms intercepts a frame.
Step 102: determining the characteristic information of the pedestrian in several frames.
In embodiments of the present invention, the pedestrian in each frame is identified by object detection method in deep learning, and determines row
The location of pixels of people.Wherein, deep learning method includes but is not limited to Faster R-CNN algorithm, YOLO algorithm (You Only
Look Once need to only have a look at) etc..During target detection, multipoint positioning can be carried out to pedestrian, and according to multiple spot
Position determines the location of pixels of pedestrian.Location of pixels can be characterized with pixel coordinate and pixel other identifier.In addition, each frame
Including pixel quantity be identical.
As shown in Fig. 2, the frame includes 9 pixels, the position of pedestrian is the 5th pixel.
According to the image of each frame middle row people, the external appearance characteristic of each frame middle row people is determined.External appearance characteristic may include face position
It sets, profile etc..
Step 103: according to characteristic information, determining pedestrian's track route and pedestrian in pixel entrance or leave initial general
Rate.
The application includes two kinds of situations, first is that pedestrian enters, corresponding is that pedestrian enters probability graph；Second is that pedestrian leaves,
Corresponding is that pedestrian leaves probability graph.The pixel that pedestrian enters or leaves is corresponding with entrance in practical application scene, example
Such as, lift port, market doorway etc..
Characteristic information includes: external appearance characteristic and location of pixels.Based on this, step 103 is specifically included:
A1: according to external appearance characteristic and location of pixels, the pedestrian in several frames is distinguished.
In practical application scene, the pedestrian in several frames can also be distinguished according only to external appearance characteristic.
In a step 102, it although can detecte the pedestrian in each frame by object detection method, but can not determine difference
Whether the pedestrian in frame is the same person.
A1 is specifically included:
A11: by the external appearance characteristic of the first pedestrian in target frame and location of pixels respectively with each pedestrian in other frames
External appearance characteristic and location of pixels matched, determine the similarity of each pedestrian in the first pedestrian and other frames.
When other frames are there are when multiframe, target frame is matched with other frames one by one.I.e. target frame is T1, other frame packets
T2, T3, T4 are included, by each pedestrian in T1 first compared with each pedestrian in T2, then compared with each pedestrian in T3, finally
Compared with each pedestrian in T4.Now only it is illustrated by taking the matching of two frames as an example.
For example, there are pedestrian e, f, g in other frames there are pedestrian a, b in target frame.In distinguishing target frame and other frames
Pedestrian during, the external appearance characteristic of a and location of pixels are carried out with the external appearance characteristic of e, f, g and location of pixels respectively first
Match, then matches b external appearance characteristic and location of pixels with the external appearance characteristic of e, f, g and location of pixels respectively.For example, a
External appearance characteristic and location of pixels are matched with the external appearance characteristic of e and location of pixels, determine the similarity of the two.In practical application
In scene, feature vector can be generated according to external appearance characteristic and location of pixels, and then determine the corresponding feature vector of two pedestrians
Similarity.
A12: when there are when the second pedestrian, determine that the second pedestrian and the first row are artificially same in each pedestrian in other frames
A pedestrian；Wherein, the similarity of the second pedestrian and the first pedestrian are greater than preset similarity threshold.
A2: according to the location of pixels of pedestrian each in each frame, fitting obtains pedestrian's track route.
A2 is specifically included:
A21: according to the location of pixels of pedestrian each in each frame, the quantity of the pedestrian occurred in each pixel is counted.
A22: according to the location of pixels of pedestrian each in each frame, the walking side of the pedestrian occurred in each pixel is determined
To.
In different application scenarios, direction of travel may be different, for example, direction of travel includes four in a kind of scene
A direction, in another scene, direction of travel includes eight directions.
As shown in figure 3, arrangement mode pixel-based, the direction of travel of pedestrian includes eight kinds of possibility.
A23: according to the quantity and direction of travel of the pedestrian occurred in each pixel, fitting obtains pedestrian's track route.
A23 is specifically included:
A231: according to the quantity and direction of travel of the pedestrian occurred in target pixel points, determination is each in target pixel points
Pedestrian's quantity accounting of direction of travel.
For example, have 10 people in the pedestrian that pixel M occurs, wherein 5 people walk eastwards, then, and the pedestrian's quantity walked eastwards
Accounting is 1/2.
A232: according to pedestrian's quantity accounting in each direction of travel of target pixel points, the fitting of target pixel points is determined
Direction.
It can be using the highest direction of travel of pedestrian's quantity accounting as fitting direction.
A233: it is fitted according to the fitting direction of each pixel, obtains pedestrian's track route.
It, can be according to locating for pedestrian's quantity accounting in order to obtain a plurality of pedestrian's track route in practical application scene
Accounting grade is fitted, and obtains different pedestrian's track routes.
In the case, according to pedestrian's quantity accounting, the accounting grade of each direction of travel of current pixel point is determined, according to
The direction of travel of each same accounting grade of pixel is fitted, and obtains pedestrian's walking corresponding from different accounting grades road
Line.
A3: according to the location of pixels of pedestrian each in each frame, determine that pedestrian enters or leaves initial in each pixel
Probability.
A3 is specifically included:
A31: according to the location of pixels of pedestrian each in each frame, the pixel that each pedestrian enters or leaves is determined.
A31 is specifically included:
A311: it when not occurring third pedestrian in the first number of frames after occur third pedestrian, first frame in first frame, determines
The corresponding pixel of the location of pixels of third pedestrian is the pixel that third pedestrian leaves in first frame.
A312: it when not occurring third pedestrian in the second number of frames before occur third pedestrian, the second frame in the second frame, determines
The corresponding pixel of the location of pixels of third pedestrian is the pixel that third pedestrian enters in second frame.
Wherein, the first quantity and the second quantity are related to practical application scene, can be one, are also possible to multiple.
For example, first frame and the second frame are two continuous frames, with reference to Fig. 2, row when the first quantity and the second quantity are all 1
People W appears in the first pixel in first frame, does not occur in the second frame, then pedestrian W leaves in the first pixel.
A32: the pixel for entering or leaving according to each pedestrian is determined the pedestrian's that each pixel enters or leaves
Quantity.
It is respectively 0,1,0,3,2,6,3,9,2 in the quantity for the pedestrian that pixel 1-9 enters with reference to Fig. 2.
A33: according to the quantity of pedestrian for entering or leaving in each pixel, determine pedestrian enter in each pixel or
The probability left.
A33 is specifically included:
A331: according to the corresponding relationship in preset quantity section and regulation coefficient, determine each pixel enter or from
The corresponding regulation coefficient of the quantity of the pedestrian opened.
The corresponding regulation coefficient in quantity section [0-5] is 0.8, and quantity section [6,10] corresponding regulation coefficient is 1.1.
Can increase by adjusting coefficient enter or the pedestrian that leaves more than pixel weight, reduce the shadow for blocking generation
It rings.
A332: entering or the quantity of pedestrian left and its corresponding regulation coefficient according in each pixel, determine into
The sum of pedestrian for entering or leaving.
The sum of the pedestrian of entrance=(1+3+2+3+2) * 0.8+ (6+9) * 1.1=25.3.
A333: according to the sum in each pixel enters or leaves the quantity of pedestrian and entrance or the pedestrian left,
Determine the probability that pedestrian enters or leaves in each pixel.
Pedestrian is in probability=3/25.3 that the 4th pixel enters.
Step 104: the probability that pedestrian enters or leaves in pixel being corrected according to pedestrian's track route, obtains pedestrian
In the final probability that pixel enters or leaves.
Due to camera during shooting video flowing position be it is fixed, when pedestrian's quantity is more, it is understood that there may be
The case where pedestrian is mutually blocked, causing statistical result, there are mistakes.Use the example above, pedestrian W may not the 1st pixel from
It opens, but is blocked by the pedestrian Q appeared in other frames, since pedestrian W is blocked, row is only recognized during target detection
People Q is not pair so as to cause statistical result later.For example, pedestrian is that there are errors in the probability that the 1st Probability Point leaves
's.
In consideration of it, the application repairs pedestrian in the probability that pixel enters or leaves by pedestrian's track route
Just.
Step 104 specifically includes:
B1: according to pedestrian's track route, pixel to be modified is determined.
By taking pedestrian's track route as an example, according to the endpoint of pedestrian's track route, correcting region is determined, in correcting region
Pixel be pixel to be modified.Correcting region can be made of the circle of the endpoint by pedestrian's track route, or by passing through
Other geometries for crossing the endpoint of pedestrian's track route are constituted, herein without limitation.
Pixel to be modified can also be determined in other way in practical application scene, for example, positive pixel to be repaired
Point is on pedestrian's track route and there are pixels pedestrian entrance or left.
B2: according to preset amendment amplitude, pedestrian is repaired in the probability that pixel to be modified enters or leaves
Just, the final probability that pedestrian enters or leaves in pixel is obtained.
Different pedestrian's track routes can correspond to different amendment amplitudes.
By amendment amplitude can make pedestrian the final probability that pixel to be modified enters or leaves be greater than pedestrian to
The probability that amendment pixel enters or leaves.
With reference to the explanation in A233, when there are a plurality of pedestrian's track route, the amendment amplitude and accounting grade of setting
(or, pedestrian's quantity accounting) is corresponding, for the different corresponding positive pixels to be repaired of accounting grade (or, pedestrian's quantity accounting)
Point, amendment amplitude are different.It is accounted for for example, the corresponding amendment amplitude of biggish pedestrian's quantity accounting is greater than lesser pedestrian's quantity
Than corresponding amendment amplitude.
This method is modified pedestrian in the probability that pixel enters or leaves using pedestrian's track route, can
Reduce influence caused by pixel false statistic caused by the blocking, intersect of pedestrian.
As shown in figure 4, the embodiment of the invention provides a kind of pedestrian's quantity statistics methods, comprising:
Step 401: obtaining several frames of video flowing.
Step 402: determining the characteristic information of the pedestrian in several frames.
Step 403: according to characteristic information, determining pedestrian's track route and pedestrian in pixel entrance or leave initial general
Rate.
Step 404: the probability that pedestrian enters or leaves in pixel being corrected according to pedestrian's track route, obtains pedestrian
In the final probability that pixel enters or leaves.
For the content of step 401- step 404, it is illustrated in previous embodiment, details are not described herein again.
Step 405: the final probability for entering or leaving in pixel according to pedestrian counts the preset monitoring of future time section
The pedestrian's quantity for entering or leaving in region.
It should be noted that for several frames corresponding time that future time section is opposite acquisition, for example, obtain
Several frames corresponding period is 8 points to 9 points of yesterday, and future time section can be 8 points to 9 points of today.
Step 405 specifically includes:
C1: when detecting that current pedestrian enters in current pixel point or when leaving, exist according to pedestrian in future time section
The final probability that pixel enters or leaves determines the final probability that pedestrian enters or leaves in current pixel point.
It detects whether current pedestrian has been described in previous embodiment in the method that current pixel point enters or leaves, asks
With reference to A31.
C2: when pedestrian enters or the final probability that leaves and generated by preset random function random in current pixel point
When number meets preset increase condition, the pedestrian's quantity for entering in monitoring area or leaving is added 1.
For example, pedestrian is 0.8 in the final probability that current pixel point enters or leaves, the random number that random function generates is
0.7, the condition that increases is " pedestrian is greater than the random number that random function generates in the final probability that current pixel point enters or leaves ",
The pedestrian's quantity for entering in monitoring area or leaving then is added 1.
It is, of course, also possible to by pedestrian in the final probability that current pixel point enters or leaves directly as pedestrian's quantity, i.e.,
The final probability that the pedestrian's quantity for entering in monitoring area or leaving is entered or left in current pixel point plus pedestrian.
Alternatively, judge whether pedestrian is greater than preset probability threshold value in the final probability that current pixel point enters or leaves,
When being greater than probability threshold value, the pedestrian's quantity for entering in monitoring area or leaving is added 1.
This method is modified pedestrian in the probability that pixel enters or leaves using pedestrian's track route, can
Reduce influence caused by pixel false statistic caused by the blocking, intersect of pedestrian.The pedestrian obtained according to amendment clicks through in pixel
The final probability statistics pedestrian quantity for entering or leaving can be improved the reliability of statistical result and reduce cost of labor.
The embodiment of the invention provides a kind of pedestrian's quantity statistics methods, comprising the following steps:
S1: several frames of video flowing are obtained.
S2: the characteristic information of the pedestrian in several frames is determined, wherein characteristic information includes: external appearance characteristic and location of pixels.
S3: by the external appearance characteristic of the first pedestrian in target frame and location of pixels respectively with each pedestrian's in other frames
External appearance characteristic and location of pixels are matched, and determine the similarity of each pedestrian in the first pedestrian and other frames.
S4: when there are when the second pedestrian, determine that the second pedestrian and the first row are artificially same in each pedestrian in other frames
A pedestrian；Wherein, the similarity of the second pedestrian and the first pedestrian are greater than preset similarity threshold.
S5: according to the location of pixels of pedestrian each in each frame, the quantity of the pedestrian occurred in each pixel is counted.
S6: according to the location of pixels of pedestrian each in each frame, the direction of travel of the pedestrian occurred in each pixel is determined.
S7: it according to the quantity and direction of travel of the pedestrian occurred in target pixel points, determines in each row of target pixel points
Walk pedestrian's quantity accounting in direction.
S8: according to pedestrian's quantity accounting in each direction of travel of target pixel points, the fitting side of target pixel points is determined
To.
S9: it is fitted according to the fitting direction of each pixel, obtains pedestrian's track route.
S10: it when not occurring third pedestrian in the first number of frames after occur third pedestrian, first frame in first frame, determines
The corresponding pixel of the location of pixels of third pedestrian is the pixel that third pedestrian leaves in first frame.
S11: it when not occurring third pedestrian in the second number of frames before occur third pedestrian, the second frame in the second frame, determines
The corresponding pixel of the location of pixels of third pedestrian is the pixel that third pedestrian enters in second frame.
S12: the pixel for entering or leaving according to each pedestrian is determined the pedestrian's that each pixel enters or leaves
Quantity.
S13: it according to the corresponding relationship in preset quantity section and regulation coefficient, determines and enters or leave in each pixel
Pedestrian the corresponding regulation coefficient of quantity.
S14: it according to quantity and its corresponding regulation coefficient in the entrance of each pixel or the pedestrian left, determines and enters
Or the sum of the pedestrian left.
S15: according to the sum in the quantity for the pedestrian that each pixel enters or leaves and entrance or the pedestrian left, really
Determine the probability that pedestrian enters or leaves in each pixel.
S16: according to pedestrian's track route, pixel to be modified is determined.
S17: according to preset amendment amplitude, pedestrian is repaired in the probability that pixel to be modified enters or leaves
Just, the final probability that pedestrian enters or leaves in pixel is obtained.
S18: when detecting that current pedestrian enters in current pixel point or when leaving, exist according to pedestrian in future time section
The final probability that pixel enters or leaves determines the final probability that pedestrian enters or leaves in current pixel point.
S19: when pedestrian current pixel point enter or the final probability that leaves and by preset random function generate with
When machine number meets preset increase condition, the pedestrian's quantity for entering in monitoring area or leaving is added 1.
As shown in figure 5, the embodiment of the invention provides a kind of determining pedestrians in pixel entrance or the dress of the probability left
It sets, comprising:
Acquiring unit 501, for obtaining several frames of video flowing；
Determination unit 502, for determining the characteristic information of the pedestrian in several frames；
Pedestrian tracking unit 503, enter in pixel for according to characteristic information, determining pedestrian's track route and pedestrian or
The probability left；
Amending unit 504, for correcting the probability that pedestrian enters or leaves in pixel according to pedestrian's track route,
Obtain the final probability that pedestrian enters or leaves in pixel.
In one embodiment of the invention, characteristic information includes: external appearance characteristic and location of pixels；
Pedestrian tracking unit 503, for distinguishing the pedestrian in several frames according to external appearance characteristic and location of pixels；According to each
The location of pixels of each pedestrian in frame, fitting obtain pedestrian's track route；According to the location of pixels of pedestrian each in each frame, determine
The probability that pedestrian enters or leaves in each pixel.
In one embodiment of the invention, pedestrian tracking unit 503, for by the appearance of the first pedestrian in target frame
Feature and location of pixels are matched with the external appearance characteristic of each pedestrian in other frames and location of pixels respectively, determine the first row
The similarity of people and each pedestrian in other frames；When, there are when the second pedestrian, determining second in each pedestrian in other frames
The artificial same pedestrian of pedestrian and the first row；Wherein, the similarity of the second pedestrian and the first pedestrian are greater than preset similarity threshold
Value.
In one embodiment of the invention, pedestrian tracking unit 503, for the pixel position according to pedestrian each in each frame
It sets, counts the quantity of the pedestrian occurred in each pixel；According to the location of pixels of pedestrian each in each frame, determine in each picture
The direction of travel for the pedestrian that vegetarian refreshments occurs；According to the quantity and direction of travel of the pedestrian occurred in each pixel, fitting is obtained
Pedestrian's track route.
In one embodiment of the invention, pedestrian tracking unit 503, for according to the pedestrian occurred in target pixel points
Quantity and direction of travel, determine each direction of travel of target pixel points pedestrian's quantity accounting；According in target pixel points
Pedestrian's quantity accounting of each direction of travel, determines the fitting direction of target pixel points；According to the fitting direction of each pixel
It is fitted, obtains pedestrian's track route.
In one embodiment of the invention, pedestrian tracking unit 503, for the pixel position according to pedestrian each in each frame
It sets, determines the pixel that each pedestrian enters or leaves；The pixel for entering or leaving according to each pedestrian is determined in each picture
The quantity of vegetarian refreshments entrance or the pedestrian left；According to the quantity in the pedestrian that each pixel enters or leaves, determine that pedestrian exists
The probability that each pixel enters or leaves.
In one embodiment of the invention, pedestrian tracking unit 503, for occurring third pedestrian, the in the first frame
When not occurring third pedestrian after one frame in the first number of frames, the corresponding pixel of the location of pixels of third pedestrian in first frame is determined
The pixel left for third pedestrian；Do not occur third in the second number of frames before occurring third pedestrian, the second frame in the second frame
When pedestrian, determine that the corresponding pixel of the location of pixels of third pedestrian in the second frame is the pixel that third pedestrian enters.
In one embodiment of the invention, pedestrian tracking unit 503, for being according to preset quantity section and adjustment
Several corresponding relationships determines the corresponding regulation coefficient of quantity in the pedestrian that each pixel enters or leaves；According to each
Quantity and its corresponding regulation coefficient of pixel entrance or the pedestrian left, determine the sum of entrance or the pedestrian left；Root
According to the sum in the quantity for the pedestrian that each pixel enters or leaves and entrance or the pedestrian left, determine pedestrian in each picture
The probability that vegetarian refreshments enters or leaves.
In one embodiment of the invention, amending unit 504, for determining erect image to be repaired according to pedestrian's track route
Vegetarian refreshments；According to preset amendment amplitude, pedestrian is modified in the probability that pixel to be modified enters or leaves, is obtained
The final probability that pedestrian enters or leaves in pixel.
As shown in fig. 6, the embodiment of the invention provides a kind of pedestrian's quantity statistics devices, comprising:
Acquiring unit 601, for obtaining several frames of video flowing；
Determination unit 602, for determining the characteristic information of the pedestrian in several frames；
Pedestrian tracking unit 603, enter in pixel for according to characteristic information, determining pedestrian's track route and pedestrian or
The probability left；
Amending unit 604, for correcting the probability that pedestrian enters or leaves in pixel according to pedestrian's track route,
Obtain the final probability that pedestrian enters or leaves in pixel；
Statistic unit 605, the final probability for entering or leaving in pixel according to pedestrian, statistics future time section are pre-
If monitoring area in enter or pedestrian's quantity for leaving.
In one embodiment of the invention, statistic unit 605 detect current pedestrian for working as in future time section
When current pixel point enters or leaves, according to the final probability that pedestrian enters or leaves in pixel, determine pedestrian current
The final probability that pixel enters or leaves；When pedestrian current pixel point enter or the final probability that leaves and by it is preset with
When the random number that machine function generates meets preset increase condition, the pedestrian's quantity for entering in monitoring area or leaving is added 1.
In the 1990s, the improvement of a technology can be distinguished clearly be on hardware improvement (for example,
Improvement to circuit structures such as diode, transistor, switches) or software on improvement (improvement for method flow).So
And with the development of technology, the improvement of current many method flows can be considered as directly improving for hardware circuit.
Designer nearly all obtains corresponding hardware circuit by the way that improved method flow to be programmed into hardware circuit.Cause
This, it cannot be said that the improvement of a method flow cannot be realized with hardware entities module.For example, programmable logic device
(Programmable Logic Device, PLD) (such as field programmable gate array (Field Programmable Gate
Array, FPGA)) it is exactly such a integrated circuit, logic function determines device programming by user.By designer
Voluntarily programming comes a digital display circuit " integrated " on a piece of PLD, designs and makes without asking chip maker
Dedicated IC chip.Moreover, nowadays, substitution manually makes IC chip, this programming is also used instead mostly " is patrolled
Volume compiler (logic compiler) " software realizes that software compiler used is similar when it writes with program development,
And the source code before compiling also write by handy specific programming language, this is referred to as hardware description language
(Hardware Description Language, HDL), and HDL is also not only a kind of, but there are many kind, such as ABEL
(Advanced Boolean Expression Language)、AHDL(Altera Hardware Description
Language)、Confluence、CUPL(Cornell University Programming Language)、HDCal、JHDL
(Java Hardware Description Language)、Lava、Lola、MyHDL、PALASM、RHDL(Ruby
Hardware Description Language) etc., VHDL (Very-High-Speed is most generally used at present
Integrated Circuit Hardware Description Language) and Verilog.Those skilled in the art also answer
This understands, it is only necessary to method flow slightly programming in logic and is programmed into integrated circuit with above-mentioned several hardware description languages,
The hardware circuit for realizing the logical method process can be readily available.
Controller can be implemented in any suitable manner, for example, controller can take such as microprocessor or processing
The computer for the computer readable program code (such as software or firmware) that device and storage can be executed by (micro-) processor can
Read medium, logic gate, switch, specific integrated circuit (Application Specific Integrated Circuit,
ASIC), the form of programmable logic controller (PLC) and insertion microcontroller, the example of controller includes but is not limited to following microcontroller
Device: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20 and Silicone Labs C8051F320 are deposited
Memory controller is also implemented as a part of the control logic of memory.It is also known in the art that in addition to
Pure computer readable program code mode is realized other than controller, can be made completely by the way that method and step is carried out programming in logic
Controller is obtained to come in fact in the form of logic gate, switch, specific integrated circuit, programmable logic controller (PLC) and insertion microcontroller etc.
Existing identical function.Therefore this controller is considered a kind of hardware component, and to including for realizing various in it
The device of function can also be considered as the structure in hardware component.Or even, it can will be regarded for realizing the device of various functions
For either the software module of implementation method can be the structure in hardware component again.
System, device, module or the unit that above-described embodiment illustrates can specifically realize by computer chip or entity,
Or it is realized by the product with certain function.It is a kind of typically to realize that equipment is computer.Specifically, computer for example may be used
Think personal computer, laptop computer, cellular phone, camera phone, smart phone, personal digital assistant, media play
It is any in device, navigation equipment, electronic mail equipment, game console, tablet computer, wearable device or these equipment
The combination of equipment.
For convenience of description, it is divided into various units when description apparatus above with function to describe respectively.Certainly, implementing this
The function of each unit can be realized in the same or multiple software and or hardware when application.
It should be understood by those skilled in the art that, the embodiment of the present invention can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the present invention
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the present invention, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
The present invention be referring to according to the method for the embodiment of the present invention, the process of equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
In a typical configuration, calculating equipment includes one or more processors (CPU), input/output interface, net
Network interface and memory.
Memory may include the non-volatile memory in computer-readable medium, random access memory (RAM) and/or
The forms such as Nonvolatile memory, such as read-only memory (ROM) or flash memory (flash RAM).Memory is computer-readable medium
Example.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method
Or technology come realize information store.Information can be computer readable instructions, data structure, the module of program or other data.
The example of the storage medium of computer includes, but are not limited to phase change memory (PRAM), static random access memory (SRAM), moves
State random access memory (DRAM), other kinds of random access memory (RAM), read-only memory (ROM), electric erasable
Programmable read only memory (EEPROM), flash memory or other memory techniques, read-only disc read only memory (CD-ROM) (CD-ROM),
Digital versatile disc (DVD) or other optical storage, magnetic cassettes, tape magnetic disk storage or other magnetic storage devices
Or any other non-transmission medium, can be used for storage can be accessed by a computing device information.As defined in this article, it calculates
Machine readable medium does not include temporary computer readable media (transitory media), such as the data-signal and carrier wave of modulation.
It should also be noted that, the terms "include", "comprise" or its any other variant are intended to nonexcludability
It include so that the process, method, commodity or the equipment that include a series of elements not only include those elements, but also to wrap
Include other elements that are not explicitly listed, or further include for this process, method, commodity or equipment intrinsic want
Element.In the absence of more restrictions, the element limited by sentence " including one ... ", it is not excluded that including described
There is also other identical elements in the process, method of element, commodity or equipment.
The application can describe in the general context of computer-executable instructions executed by a computer, such as program
Module.Generally, program module includes routines performing specific tasks or implementing specific abstract data types, programs, objects, group
Part, data structure etc..The application can also be practiced in a distributed computing environment, in these distributed computing environments, by
Task is executed by the connected remote processing devices of communication network.In a distributed computing environment, program module can be with
In the local and remote computer storage media including storage equipment.
All the embodiments in this specification are described in a progressive manner, same and similar portion between each embodiment
Dividing may refer to each other, and each embodiment focuses on the differences from other embodiments.Especially for system reality
For applying example, since it is substantially similar to the method embodiment, so being described relatively simple, related place is referring to embodiment of the method
Part explanation.
The above description is only an example of the present application, is not intended to limit this application.For those skilled in the art
For, various changes and changes are possible in this application.All any modifications made within the spirit and principles of the present application are equal
Replacement, improvement etc., should be included within the scope of the claims of this application.
Claims (22)
1. a kind of determining pedestrian is in the method for the probability that pixel enters or leaves, comprising:
Obtain several frames of video flowing；
Determine the characteristic information of the pedestrian in several frames；
According to the characteristic information, the probability that pedestrian's track route and pedestrian enter or leave in pixel is determined；
The probability that the pedestrian enters or leaves in pixel is corrected according to pedestrian's track route, obtains pedestrian in picture
The final probability that vegetarian refreshments enters or leaves.
2. the method for probability that pedestrian enters or leaves in pixel is determined as described in claim 1,
The characteristic information includes: external appearance characteristic and location of pixels；
It is described that the probability that pedestrian's track route and pedestrian enter or leave in pixel is determined according to the characteristic information,
Include:
According to the external appearance characteristic and the location of pixels, the pedestrian in several frames is distinguished；
According to the location of pixels of pedestrian each in each frame, fitting obtains pedestrian's track route；
According to the location of pixels of each pedestrian in each frame, determine pedestrian each pixel enters or leaves initial general
Rate.
3. the method for probability that pedestrian enters or leaves in pixel is determined as claimed in claim 2,
It is described according to the external appearance characteristic and the location of pixels, distinguish the pedestrian in several frames, comprising:
The external appearance characteristic of the first pedestrian in target frame and location of pixels is special with the appearance of each pedestrian in other frames respectively
Location of pixels of seeking peace is matched, and determines the similarity of each pedestrian in first pedestrian and other described frames；
When there are when the second pedestrian, determine that second pedestrian and the first row are artificial in each pedestrian in other described frames
The same pedestrian；Wherein, the similarity of second pedestrian and first pedestrian are greater than preset similarity threshold.
4. the method for probability that pedestrian enters or leaves in pixel is determined as claimed in claim 2,
The location of pixels according to pedestrian each in each frame, fitting obtain pedestrian's track route, comprising:
According to the location of pixels of each pedestrian in each frame, the quantity of the pedestrian occurred in each pixel is counted；
According to the location of pixels of each pedestrian in each frame, the direction of travel of the pedestrian occurred in each pixel is determined；
According to the quantity and direction of travel of the pedestrian occurred in each pixel, fitting obtains pedestrian's track route.
5. the method for probability that pedestrian enters or leaves in pixel is determined as claimed in claim 4,
The quantity and direction of travel for the pedestrian that the basis occurs in each pixel, fitting obtain pedestrian's track route,
Include:
According to the quantity and direction of travel of the pedestrian occurred in target pixel points, determine in each walking side of the target pixel points
To pedestrian's quantity accounting；
According to pedestrian's quantity accounting in each direction of travel of the target pixel points, the fitting side of the target pixel points is determined
To；
It is fitted according to the fitting direction of each pixel, obtains pedestrian's track route.
6. the method for probability that pedestrian enters or leaves in pixel is determined as claimed in claim 2,
The location of pixels according to each pedestrian in each frame determines that pedestrian enters or leaves initial in each pixel
Probability, comprising:
According to the location of pixels of each pedestrian in each frame, the pixel that each pedestrian enters or leaves is determined；
According to the pixel that each pedestrian enters or leaves, the number in the pedestrian that each pixel enters or leaves is determined
Amount；
According to the quantity of pedestrian for entering or leaving in each pixel, determine the pedestrian enter in each pixel or
The probability left.
7. the method for probability that pedestrian enters or leaves in pixel is determined as claimed in claim 6,
The location of pixels according to each pedestrian in each frame determines the pixel that each pedestrian enters or leaves, comprising:
When not occurring the third pedestrian in the first number of frames after occur third pedestrian, the first frame in first frame, determine
The corresponding pixel of the location of pixels of third pedestrian is the pixel that the third pedestrian leaves in the first frame；
When not occurring the third pedestrian in the second number of frames before occur the third pedestrian, second frame in the second frame,
The corresponding pixel of location of pixels for determining third pedestrian in second frame is the pixel that the third pedestrian enters.
8. the method for probability that pedestrian enters or leaves in pixel is determined as claimed in claim 6,
The quantity of pedestrian for entering or leaving in each pixel according to, determines that the pedestrian clicks through in each pixel
The probability for entering or leaving, comprising:
According to the corresponding relationship in preset quantity section and regulation coefficient, the row for entering or leaving in each pixel is determined
The corresponding regulation coefficient of the quantity of people；
Entered or the quantity of pedestrian left and its corresponding regulation coefficient according to described in each pixel, determine enter or from
The sum of the pedestrian opened；
According to the quantity in the pedestrian that each pixel enters or leaves and the entrance or the sum of the pedestrian left, really
The probability that the fixed pedestrian enters or leaves in each pixel.
9. such as the method for probability that determining pedestrian described in any one of claims 1-8 enters or leaves in pixel,
It is described that the probability that the pedestrian enters or leaves in pixel is corrected according to pedestrian's track route, obtain pedestrian
In the final probability that pixel enters or leaves, comprising:
According to pedestrian's track route, pixel to be modified is determined；
According to preset amendment amplitude, pedestrian is modified in the probability that the pixel to be modified enters or leaves,
Obtain the final probability that the pedestrian enters or leaves in pixel.
10. a kind of pedestrian's quantity statistics method, comprising:
Obtain several frames of video flowing；
Determine the characteristic information of the pedestrian in several frames；
According to the characteristic information, the probability that pedestrian's track route and pedestrian enter or leave in pixel is determined；
The probability that the pedestrian enters or leaves in pixel is corrected according to pedestrian's track route, obtains pedestrian in picture
The final probability that vegetarian refreshments enters or leaves；
Entered or the final probability that leaves according to the pedestrian in pixel, in the statistics preset monitoring area of future time section into
The pedestrian's quantity for entering or leaving.
11. pedestrian's quantity statistics method as claimed in claim 10,
The final probability for entering or leaving in pixel according to the pedestrian, counts the preset monitoring area of future time section
Interior entrance or the pedestrian's quantity left, comprising:
When detecting that current pedestrian enters in current pixel point or when leaving, exist according to the pedestrian in the future time section
The final probability that pixel enters or leaves, determines pedestrian in the final probability that the current pixel point enters or leaves；
When pedestrian is in the final probability that the current pixel point enters or leaves and the random number generated by preset random function
When meeting preset increase condition, the pedestrian's quantity for entering in the monitoring area or leaving is added 1.
12. a kind of determining pedestrian is in the device for the probability that pixel enters or leaves, comprising:
Acquiring unit, for obtaining several frames of video flowing；
Determination unit, for determining the characteristic information of the pedestrian in several frames；
Pedestrian tracking unit, for according to the characteristic information, determine pedestrian's track route and pedestrian pixel enter or from
The probability opened；
Amending unit, for correcting the pedestrian in pixel entrance according to pedestrian's track route or leaving initial general
Rate obtains the final probability that pedestrian enters or leaves in pixel.
13. the device of probability that pedestrian enters or leaves in pixel is determined as claimed in claim 12,
The characteristic information includes: external appearance characteristic and location of pixels；
The pedestrian tracking unit, for distinguishing the row in several frames according to the external appearance characteristic and the location of pixels
People；According to the location of pixels of pedestrian each in each frame, fitting obtains pedestrian's track route；According to each row in each frame
The location of pixels of people determines the probability that pedestrian enters or leaves in each pixel.
14. the device of probability that pedestrian enters or leaves in pixel is determined as claimed in claim 13,
The pedestrian tracking unit, for by the external appearance characteristic of the first pedestrian in target frame and location of pixels respectively with other frames
In each pedestrian external appearance characteristic and location of pixels match, determine first pedestrian with it is each in other described frames
The similarity of pedestrian；When in each pedestrian in other described frames there are when the second pedestrian, determine second pedestrian with it is described
The artificial same pedestrian of the first row；Wherein, the similarity of second pedestrian and first pedestrian are greater than preset similarity
Threshold value.
15. the device of probability that pedestrian enters or leaves in pixel is determined as claimed in claim 13,
The pedestrian tracking unit, for the location of pixels according to each pedestrian in each frame, statistics is pointed out in each pixel
The quantity of existing pedestrian；According to the location of pixels of each pedestrian in each frame, the determining pedestrian's occurred in each pixel
Direction of travel；According to the quantity and direction of travel of the pedestrian occurred in each pixel, fitting obtains pedestrian's track route.
16. the device of probability that pedestrian enters or leaves in pixel is determined as claimed in claim 15,
The pedestrian tracking unit is determined for the quantity and direction of travel according to the pedestrian occurred in target pixel points in institute
State pedestrian's quantity accounting of each direction of travel of target pixel points；According to the pedestrian in each direction of travel of the target pixel points
Quantity accounting determines the fitting direction of the target pixel points；It is fitted according to the fitting direction of each pixel, obtains institute
State pedestrian's track route.
17. the device of probability that pedestrian enters or leaves in pixel is determined as claimed in claim 13,
The pedestrian tracking unit, for the location of pixels according to each pedestrian in each frame, determine each pedestrian enter or
The pixel left；The pixel for entering or leaving according to each pedestrian is determined each pixel enters or leaves
The quantity of pedestrian；According to the quantity in the pedestrian that each pixel enters or leaves, determine the pedestrian in each pixel
The probability that point enters or leaves.
18. the device of probability that pedestrian enters or leaves in pixel is determined as claimed in claim 17,
The pedestrian tracking unit, for not going out in the first number of frames after occurring third pedestrian, the first frame in first frame
When the existing third pedestrian, determine that the corresponding pixel of the location of pixels of third pedestrian in the first frame is the third pedestrian
The pixel left；Do not occur described in the second number of frames before occurring the third pedestrian, second frame in the second frame
When three pedestrians, determine that the corresponding pixel of location of pixels of third pedestrian in second frame is the picture that the third pedestrian enters
Vegetarian refreshments.
19. the device of probability that pedestrian enters or leaves in pixel is determined as claimed in claim 17,
The pedestrian tracking unit determines described each for the corresponding relationship according to preset quantity section and regulation coefficient
The corresponding regulation coefficient of quantity of a pixel entrance or the pedestrian left；Enter or leave in each pixel according to described
The quantity of pedestrian and its corresponding regulation coefficient determine the sum of entrance or the pedestrian left；According to described in each pixel
Into or the sum of the quantity of pedestrian and the entrance or the pedestrian left that leaves, determine that the pedestrian clicks through in each pixel
The probability for entering or leaving.
20. determination pedestrian as described in any in claim 12-19 is in the device for the probability that pixel enters or leaves,
The amending unit, for determining pixel to be modified according to pedestrian's track route；According to preset amendment width
Degree is modified pedestrian in the probability that the pixel to be modified enters or leaves, obtains the pedestrian in pixel
Into or the final probability that leaves.
21. a kind of pedestrian's quantity statistics device, comprising:
Acquiring unit, for obtaining several frames of video flowing；
Determination unit, for determining the characteristic information of the pedestrian in several frames；
Pedestrian tracking unit, for according to the characteristic information, determine pedestrian's track route and pedestrian pixel enter or from
The probability opened；
Amending unit, for correcting the pedestrian in pixel entrance according to pedestrian's track route or leaving initial general
Rate obtains the final probability that pedestrian enters or leaves in pixel；
Statistic unit, the final probability for entering or leaving in pixel according to the pedestrian, statistics future time section are default
Monitoring area in enter or pedestrian's quantity for leaving.
22. pedestrian's quantity statistics device as claimed in claim 21,
The statistic unit detects that current pedestrian enters or leaves in current pixel point for working as in the future time section
When, entered or the final probability that leaves according to the pedestrian in pixel, determine pedestrian the current pixel point enter or from
The final probability opened；When pedestrian generates in the final probability that the current pixel point enters or leaves and by preset random function
Random number when meeting preset increase condition, the pedestrian's quantity for entering in the monitoring area or leaving is added 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910125702.5A CN110033430B (en) | 2019-02-20 | 2019-02-20 | Pedestrian number statistics method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910125702.5A CN110033430B (en) | 2019-02-20 | 2019-02-20 | Pedestrian number statistics method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110033430A true CN110033430A (en) | 2019-07-19 |
| CN110033430B CN110033430B (en) | 2023-06-20 |
Family
ID=67235672
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910125702.5A Active CN110033430B (en) | 2019-02-20 | 2019-02-20 | Pedestrian number statistics method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110033430B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110705494A (en) * | 2019-10-10 | 2020-01-17 | 北京东软望海科技有限公司 | People flow monitoring method and device, electronic equipment and computer readable storage medium |
| CN110717918A (en) * | 2019-10-11 | 2020-01-21 | 北京百度网讯科技有限公司 | Pedestrian detection method and device |
| CN110826482A (en) * | 2019-11-04 | 2020-02-21 | 北京爱笔科技有限公司 | Method and device for detecting number of people in fixed area |
| CN113763270A (en) * | 2021-08-30 | 2021-12-07 | 青岛信芯微电子科技股份有限公司 | Mosquito noise removing method and electronic device |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20100093797A (en) * | 2009-02-17 | 2010-08-26 | 한남대학교 산학협력단 | Method and system for vision-based people counting in cctv |
| CN103136534A (en) * | 2011-11-29 | 2013-06-05 | 汉王科技股份有限公司 | Method and device of self-adapting regional pedestrian counting |
-
2019
- 2019-02-20 CN CN201910125702.5A patent/CN110033430B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20100093797A (en) * | 2009-02-17 | 2010-08-26 | 한남대학교 산학협력단 | Method and system for vision-based people counting in cctv |
| CN103136534A (en) * | 2011-11-29 | 2013-06-05 | 汉王科技股份有限公司 | Method and device of self-adapting regional pedestrian counting |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110705494A (en) * | 2019-10-10 | 2020-01-17 | 北京东软望海科技有限公司 | People flow monitoring method and device, electronic equipment and computer readable storage medium |
| CN110717918A (en) * | 2019-10-11 | 2020-01-21 | 北京百度网讯科技有限公司 | Pedestrian detection method and device |
| CN110717918B (en) * | 2019-10-11 | 2022-06-07 | 北京百度网讯科技有限公司 | Pedestrian detection method and device |
| CN110826482A (en) * | 2019-11-04 | 2020-02-21 | 北京爱笔科技有限公司 | Method and device for detecting number of people in fixed area |
| CN110826482B (en) * | 2019-11-04 | 2022-05-17 | 北京爱笔科技有限公司 | Method and device for detecting number of people in fixed area |
| CN113763270A (en) * | 2021-08-30 | 2021-12-07 | 青岛信芯微电子科技股份有限公司 | Mosquito noise removing method and electronic device |
| CN113763270B (en) * | 2021-08-30 | 2024-05-07 | 青岛信芯微电子科技股份有限公司 | Mosquito noise removing method and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110033430B (en) | 2023-06-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110033430A (en) | A kind of pedestrian's quantity statistics method and device | |
| CN108629791B (en) | Pedestrian tracking method and device and cross-camera pedestrian tracking method and device | |
| US10713472B2 (en) | Face location tracking method, apparatus, and electronic device | |
| US11227397B2 (en) | Block-matching optical flow and stereo vision for dynamic vision sensors | |
| CN103477355B (en) | Number measurement mechanism | |
| CN104732187B (en) | A kind of method and apparatus of image trace processing | |
| CN111179311A (en) | Multi-target tracking method and device and electronic equipment | |
| CN110222673B (en) | Passenger flow statistical method based on head detection | |
| CN105760836A (en) | Multi-angle face alignment method based on deep learning and system thereof and photographing terminal | |
| KR102316230B1 (en) | Image processing method and device | |
| CN112949508A (en) | Model training method, pedestrian detection method, electronic device and readable storage medium | |
| TW202036375A (en) | Method and device for real-time statistical analysis of pedestrian flow in open space | |
| Xing et al. | DE‐SLAM: SLAM for highly dynamic environment | |
| CN111738225B (en) | Crowd gathering detection method, device, equipment and storage medium | |
| CN108109175A (en) | The tracking and device of a kind of image characteristic point | |
| CN110008789A (en) | Multiclass object detection and knowledge method for distinguishing, equipment and computer readable storage medium | |
| EP3925204A1 (en) | Method of processing a series of events received asynchronously from an array of pixels of an event-based light sensor | |
| CN111553298A (en) | Fire disaster identification method and system based on block chain | |
| CN110378400A (en) | A kind of model training method and device for image recognition | |
| CN110415263A (en) | Image partition method and image segmentation device | |
| WO2021056450A1 (en) | Method for updating image template, device, and storage medium | |
| CN110414572A (en) | A kind of method and device of image recognition | |
| WO2021239000A1 (en) | Method and apparatus for identifying motion blur image, and electronic device and payment device | |
| CN104123716A (en) | Image stability detection method, device and terminal | |
| CN110443007A (en) | A kind of Traceability detection method of multi-medium data, device and equipment |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20201019 Address after: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Applicant after: Advanced innovation technology Co.,Ltd. Address before: A four-storey 847 mailbox in Grand Cayman Capital Building, British Cayman Islands Applicant before: Alibaba Group Holding Ltd. Effective date of registration: 20201019 Address after: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Applicant after: Innovative advanced technology Co.,Ltd. Address before: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Applicant before: Advanced innovation technology Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |