CN105898216A - Method of counting number of people by using unmanned plane - Google Patents
Method of counting number of people by using unmanned plane Download PDFInfo
- Publication number
- CN105898216A CN105898216A CN201610231442.6A CN201610231442A CN105898216A CN 105898216 A CN105898216 A CN 105898216A CN 201610231442 A CN201610231442 A CN 201610231442A CN 105898216 A CN105898216 A CN 105898216A
- Authority
- CN
- China
- Prior art keywords
- unmanned plane
- frame
- video
- valid frame
- valid
- 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
- 238000000034 method Methods 0.000 title claims abstract description 33
- 239000003086 colorant Substances 0.000 claims description 4
- 238000003909 pattern recognition Methods 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 claims description 3
- 230000001186 cumulative effect Effects 0.000 claims description 2
- 238000012545 processing Methods 0.000 abstract description 4
- 238000004364 calculation method Methods 0.000 abstract description 2
- 230000010339 dilation Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000005260 corrosion Methods 0.000 description 2
- 230000007797 corrosion Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000012806 monitoring device Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000003628 erosive effect Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 239000011435 rock Substances 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/08—Control of attitude, i.e. control of roll, pitch, or yaw
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06M—COUNTING MECHANISMS; COUNTING OF OBJECTS NOT OTHERWISE PROVIDED FOR
- G06M11/00—Counting of objects distributed at random, e.g. on a surface
-
- 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)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a method of counting number of people by using an unmanned plane. The unmanned plane is provided with a vertical downward camera, and flies over a party place, and is used to transmit acquired videos to a ground working bench in a wireless manner. The number of people in the empty place is calculated by carrying out the image processing of the videos. The fast calculation of the number of people in the closed and open environment is realized, and the method provided by the invention is suitable for personnel density management and security control in cities, squares, and large public places.
Description
Technical field
Patent of the present invention relates to image processing field, is specifically related to one and utilizes unmanned aerial vehicle onboard video to carry out demographics side
Method.
Background technology
Along with the fast development of Chinese society economy, people in material requisite while being continuously available and meeting, to spirit literary composition
Bright demand is continuously increased, and various large-scale activities are constantly held.But trample owing to substantial amounts of gathering of people easily brings
Safety problem, relevant more and more important for the management work of density of personnel, it would be desirable to the number of assembly place is entered
Row statistics.
At present developing rapidly due to pattern-recognition and image processing techniques, arranges fixing image capture device by statistics
Image has been obtained for substantial amounts of application by the method for number, but those are substantially for one crossing of statistics or joint
Point by number, for there being this methods of scene such as the megastore of fixing gateway, station, museum also to compare
Practical.For square, playground etc. opening do not fix gateway or be inconvenient to arrange fixing monitoring device area I
Just cannot count crowd's quantity rapidly.
Along with the development of unmanned air vehicle technique, unmanned air vehicle technique is obtained for utilization in every field, has electric inspection process, agricultural
Inspection, environmental observation etc., unmanned plane take photo by plane technology mapping take photo by plane photography on also have substantial amounts of application.Small-sized rotor
Unmanned plane is with its human-oriented cost, the most substantial amounts of universal, and small-sized rotor wing unmanned aerial vehicle has light portable, highly
The advantages such as the easy manipulation of the data such as speed.
Summary of the invention
The technical problem to be solved in the present invention is to provide a kind of population number meter counting method utilizing unmanned plane to carry out, it is possible in envelope
Close and carry out the express statistic of number quantity under open environment, can be used for city, square and the personnel in big assembly place
Density management and security.
The present invention solves above-mentioned technical problem, adopt the following technical scheme that
A kind of population number meter counting method utilizing unmanned plane to carry out, it is characterised in that: utilize and be mounted with camera vertically downward
Unmanned plane, controls unmanned plane and flies over place to be measured and gather video at flight course, by the video that collects by wireless biography
The defeated ground handling platform that passes to, ground handling platform by counting the number on place to be measured to Computer Vision;Described nothing
Man-machine mainly by unmanned plane body part, include vertically downward the video acquisition module of camera, wireless transport module,
Computer Vision module four part is constituted, and unmanned plane is remotely led to computer host computer by video wireless transmission module
News connect.
In technique scheme, mainly comprise the steps:
Step S1: by computer host computer, it is intended that path of taking photo by plane, starts unmanned plane and starts to leap to target place to be measured
Edge;
Step S2: by computer host computer, set flying height and the speed of unmanned plane, after selecting " starting statistics ",
Unmanned plane starts fly over target place to be measured and gather video flowing, and in flight course, unmanned plane will be hung down by wireless transmitting system
Straight camera collection downwards to video flowing be transferred to computer host computer;
Step S3: on computers on the machine of position, utilizes the attitude contrast of unmanned plane when extracting video to ensure camera vertically downward
To direction consistent;By utilizing unmanned plane during flying height to draw the size that single human body is corresponding in video;Profit
The non-overlapped part calculated in valid frame with unmanned plane during flying speedometer counts the number of unmanned plane flyover region.
In technique scheme, step S3 specifically includes following steps:
Step S31: select " starting statistics " delay adjustments time afterwards, after unmanned plane during flying is in stable condition, from video
Starting to select pending valid frame in stream, wherein the 1st frame is the 0th frame valid frame;Then every the interval time set,
Through to the roll angle γ shooting described valid frame unmanned planeaAnd pitching angle thetaaWith course angle with the 0th frame the most consistent enter
After row judges, the valid frame after choosing;
Step S32: adding up in order to avoid leakage and repeat statistics, in conjunction with flying height h of unmanned plane, speed v is to selecting
The valid frame gone out is sheared, a width of original width width of the live part being cut out, and a length of little unmanned plane two frame has
Physical length λ that the actual range leapt between effect frame is reconverted in picturehv(ti-ti-1), wherein, λhFor when flight height
Degree is practical flight distance during h and the conversion coefficient of the distance of display in video, and v is the flying speed of unmanned plane,
(ti-ti-1) it is the time difference between two frame valid frames.
Step S33: the live part of valid frame is carried out image procossing, pattern-recognition, identifies the crowd in valid frame
Quantity, constantly adds up, and shows particular number, and this quantity is exactly the crowd's quantity added up:
In conjunction with the flying height information of unmanned plane, calculate the pixel size that single human body is corresponding in video;Image is carried out base
Image binaryzation is carried out in HSV color space, the black of prominent human hair, weakens other colors;With single human body institute
Accounting for pixel size is yardstick, carries out closed operation, eliminates little black patch;By image is carried out spot detection, identify one
Number in the live part of individual valid frame;The cumulative total number of persons i.e. obtaining the region, target place to be measured that unmanned plane flies over.
In technique scheme, computer PC control unmanned plane flies over measured target, and unmanned plane keeps determining height, even automatically
Speed rectilinear flight.
In technique scheme, unmanned plane is small-sized many rotor wing unmanned aerial vehicles.
In technique scheme, select " starting statistics " time delay 3s afterwards, after unmanned plane during flying is in stable condition, from video
Stream starts select pending valid frame.
The present invention uses UAV flight's video capture device to carry out rally number counting, and instead of irremovable, the visual field has
The advantages such as the fixed monitoring device of limit, makes native system be provided with unmanned plane convenient and swift, light and flexible, and controllable property is strong,
Can the most effectively add up crowd's quantity in certain sheet spaciousness place, be particularly well-suited to outdoor open big assembly field
Institute's demographics and counting.
While the workload that in the present invention, unmanned plane keeps determining height automatically, unaccelerated flight can alleviate manipulation personnel,
The difficulty of Computer Vision can be greatly simplified;When extracting valid frame, the first attitude to unmanned plane, i.e. roll angle γaWith
Pitching angle thetaaWith course angleContrasting with the attitude of the 0th frame valid frame, the attitude keeping selected valid frame is consistent,
Avoid the impact that shake during unmanned plane during flying brings.When video flowing is carried out image procossing, multiple steps all make use of unmanned
The flying quality of machine, utilizes the algorithm complex of existing data reduction Computer Vision, improves arithmetic speed, it is ensured that
The real-time of demographics and accuracy.
One innovation of the present invention is the flight attitude data by reading rotor wing unmanned aerial vehicle, it is ensured that image capture device exists
State when collecting valid frame is the most identical, it is to avoid what ambulatory platform was brought rock waits instability.
One innovative point of the present invention is that rotor wing unmanned aerial vehicle flies when differing heights, and single human body is corresponding big in video
Little is fixing, and it is not human body that excessive and too small similar image can directly be judged as, substantially increases detection speed
With accuracy.
One innovative point of the present invention is the height velocity's data by rotor wing unmanned aerial vehicle, the demographics on a bulk of square
Problem is simply decomposed into the accumulative of number in the little picture of multiframe, it is to avoid the splicing to multiple image,
Accompanying drawing explanation
Fig. 1 is unmanned plane structural representation of the present invention;
Fig. 2 is the schematic diagram of the HSV color space that the population number meter counting method that the present invention utilizes unmanned plane to carry out relates to;
Fig. 3 is the population number meter counting method overall procedure schematic diagram that invention utilizes unmanned plane to carry out;
Fig. 4 is that the image procossing related in population number meter counting method step S3 that invention utilizes unmanned plane to carry out shows
Meaning flow chart.
It is embodied as measure
In order to further illustrate the technical scheme of patent of the present invention, patent of the present invention is described in detail by comparison accompanying drawing,
But it should explanation is following facilities and equipments and embodiment not limitation of the present invention, for according to embodiment party of the present invention
Equivalent transformation in formula work done energy, method or structure or replacement, within broadly falling into protection scope of the present invention.
The unmanned plane that the present invention this time uses is small-sized four rotor wing unmanned aerial vehicles, and video image acquisition equipment uses GoPro
Hero4 motion cameras, graphic transmission equipment is that big boundary DJI5.8G high definition simulation drawing passes, and computer host computer uses association
Y450 notebook computer, as it is shown in figure 1, video camera is arranged on unmanned plane vertically downward, unmanned plane is upper with computer
Machine wireless connection.Experimental site is spacious outdoor congregation plaza.
Fig. 3 is the population number meter counting method overall procedure schematic diagram that invention utilizes unmanned plane to carry out;Mainly include
Following steps:
Step S1: start small-sized many rotor wing unmanned aerial vehicles, by computer host computer, control small-sized many rotor wing unmanned aerial vehicles fly to
Edge, target square.
Step S2: by computer host computer, sets flying height and the speed of small-sized many rotor wing unmanned aerial vehicles, selects " to open
Beginning statistics " after, small-sized many rotor wing unmanned aerial vehicles start to fly over target square, and by wireless transmitting system by rotor wing unmanned aerial vehicle
The camera collection vertically downward of upper lift-launch to video flowing be transferred to computer host computer.
Step S31: select to start statistics, select available frame of video (namely valid frame) every a frame from video flowing:
Step S311: first choosing the 1st frame is the 0th frame valid frame.
Step S312: in addition to the 1st frame, at interval of a frame, contrasts according to attitude when now UAV Attitude and 1 frame,
If attitude is identical, then judging that this frame is effective, attitude difference is then spaced b frame and again contrasts, until there is valid frame, takes
Going out valid frame as the 2nd two field picture, a, b are positive integer.
Step S13: select effective (non-overlapped) part in each frame.
Step S14: the 0th whole frame of frame valid frame is not the most live part, number M=M now added up0=0.
Step S32: valid frame afterwards by with previous valid frame interlude and rotor wing unmanned aerial vehicle speed, calculate
The distance that newly increase actual than previous valid frame in a valid frame after going out, and combine the flying height of rotor wing unmanned aerial vehicle, select
With the non-overlapped part in former frame in this valid frame, this part is the live part of this valid frame.Extract live part
First determining the origin of coordinates a little for live part on the picture of valid frame, the origin of coordinates of live part is scheduled on here
(0,300).Then the width width marking live part, highly λ are givenhv(ti-ti-1), wherein λhFor when flight height
Degree is practical flight distance during h and the flight that conversion coefficient v the is small-sized many rotor wing unmanned aerial vehicles speed of the distance of display in video
Degree, (ti-ti-1) it is time difference of two frame valid frames.
Step S33: the live part of valid frame is carried out image procossing, pattern-recognition, identifies the crowd's number in this frame
Amount, constantly adds up, and shows, this quantity is exactly the crowd's quantity added up.
Step S331: image processing process is for first carrying out noise reduction herein, removes noise.
Step S332: the second step of image procossing is for carry out image binaryzation based on HSV color space herein, and people is from bowing
View being seen, the crown is black, so the V component i.e. bright colors degree according to HSV color space is the standard of binaryzation,
As shown in Figure 2.Here the computing formula of V component is:
V=max (R, G, B)/255
R, G, B i.e. primary colors red (red), green (green), the color value of blue (blue) three passages.
Step S333: the 3rd step of image procossing is for carrying out closed operation herein, closed operation is a kind of according to mathematical morphology collection
Close a kind of image processing method that opinion method develops, be divided into expansion (dilate) and corrosion (erode) two step.
The mathematical definition of dilation operation is represented by:
S=X B={x, y | Bxy∩X≠}
Image collection after S is computing in formula;B is used to do and corrodes, the structural element of dilation operation, and it is by 0 He
1 composition, have a central point, arbitrary shape, be chosen to be structural element close to number of people shape here
Circular;BxyIt it is the central point of structural element B;X is the live part that front step passes through the valid frame after binaryzation
Image collection.
The mathematical definition of erosion operation is represented by:
In formula, S is the image collection that computing is later;B is used to do and corrodes, and the structural element of dilation operation, we make here
With circular structural element the same in dilation operation;BxyIt it is the central point of structural element B;X is used here as corrosion fortune
Image after calculation.
Closed operation can get rid of small-sized black region, and flying height based on rotor wing unmanned aerial vehicle determines single people reality in picture
Border size, we can determine the parameter of closed operation based on this, get rid of the block less than single human body in a large number and also separate
Connection between the single human body of part.
Step S334: the 4th step of image procossing is herein, extracts each block in processed image,
Using cvFindContours to complete in opencv, this order act as extracting all of profile, passes through
CvContourArea calculates the area of i.e. each piece of each profile, the area of these blocks and the most single human body
The area of the block that should produce compares, and gets rid of the part that area is the biggest with the difference of single human body.Remaining area and list
The quantity of the block that individual human body top view size is similar is crowd's quantity M in this valid framei。
Many rotor wing unmanned aerial vehicles have leapt crowd's display number of part(M is total number of persons, MiIt is i-th
Open the number counted in valid frame).
Claims (6)
1. the population number meter counting method utilizing unmanned plane to carry out, it is characterised in that: utilize the nothing being mounted with camera vertically downward
Man-machine, control unmanned plane and fly over place to be measured and gather video at flight course, the video collected is passed to by being wirelessly transferred
Ground handling platform, ground handling platform by counting the number on place to be measured to Computer Vision;Described unmanned plane mainly by
Unmanned plane body part, include the video acquisition module of camera, wireless transport module, Computer Vision mould vertically downward
Block four part is constituted, and unmanned plane is connected with computer host computer telecommunication by video wireless transmission module.
The population number meter counting method utilizing unmanned plane to carry out the most according to claim 1, it is characterised in that: mainly include as follows
Step:
Step S1: by computer host computer, it is intended that path of taking photo by plane, starts unmanned plane and starts to leap to edge, target place to be measured;
Step S2: by computer host computer, set flying height and the speed of unmanned plane, after selecting " starting statistics ", unmanned
Machine starts fly over target place to be measured and gather video flowing, and in flight course, unmanned plane will be taken the photograph vertically downward by wireless transmitting system
The video flowing collected as head is transferred to computer host computer;
Step S3: on computers on the machine of position, camera institute is right vertically downward to utilize the attitude contrast of unmanned plane when extracting video to ensure
Direction consistent;By utilizing unmanned plane during flying height to draw the size that single human body is corresponding in video;Utilize unmanned plane
Flying speed calculates the non-overlapped part in valid frame and counts the number of unmanned plane flyover region.
The population number meter counting method utilizing unmanned plane to carry out the most according to claim 2, it is characterised in that: step S3 is specifically wrapped
Include following steps:
Step S31: select " starting statistics " delay adjustments time afterwards, after unmanned plane during flying is in stable condition, from video flowing
Starting to select pending valid frame, wherein the 1st frame is the 0th frame valid frame;Then every the interval time set, through right
The roll angle γ of unmanned plane when shooting described valid frameaAnd pitching angle thetaaAfter judging with the 0th frame is the most consistent with course angle, choosing
Valid frame after taking;
Step S32: adding up in order to avoid leakage and repeat statistics, in conjunction with flying height h of unmanned plane, speed v is to having of having selected
Effect frame is sheared, and a width of original width width of the live part being cut out leaps between a length of little unmanned plane two frame valid frame
Physical length λ that is reconverted in picture of actual rangehv(ti-ti-1), wherein, λhFor the practical flight when flying height is h away from
From with the conversion coefficient of distance of display in video, v is the flying speed of unmanned plane, (ti-ti-1) it is between two frame valid frames
Time difference.
Step S33: the live part of valid frame is carried out image procossing, pattern-recognition, identifies the crowd's quantity in valid frame,
The most accumulative, and show particular number, this quantity is exactly the crowd's quantity added up:
In conjunction with the flying height information of unmanned plane, calculate the pixel size that single human body is corresponding in video;Image is carried out based on HSV
Color space carries out image binaryzation, the black of prominent human hair, weakens other colors;With pixel size shared by single human body it is
Yardstick, carries out closed operation, eliminates little black patch;By image is carried out spot detection, identify effective portion of a valid frame
Number in Fen;The cumulative total number of persons i.e. obtaining the region, target place to be measured that unmanned plane flies over.
The population number meter counting method utilizing unmanned plane to carry out the most according to claim 3, it is characterised in that: computer host computer control
Unmanned plane processed flies over measured target, and unmanned plane keeps determining height, unaccelerated flight automatically.
The population number meter counting method utilizing unmanned plane to carry out the most according to claim 1, it is characterised in that: unmanned plane is small-sized
Many rotor wing unmanned aerial vehicles.
The population number meter counting method utilizing unmanned plane to carry out the most according to claim 4, it is characterised in that: select " to start system
Meter " time delay 3s afterwards, after unmanned plane during flying is in stable condition, start to select pending valid frame from video flowing.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610231442.6A CN105898216B (en) | 2016-04-14 | 2016-04-14 | A kind of number method of counting carried out using unmanned plane |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610231442.6A CN105898216B (en) | 2016-04-14 | 2016-04-14 | A kind of number method of counting carried out using unmanned plane |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105898216A true CN105898216A (en) | 2016-08-24 |
CN105898216B CN105898216B (en) | 2019-01-15 |
Family
ID=56704861
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610231442.6A Active CN105898216B (en) | 2016-04-14 | 2016-04-14 | A kind of number method of counting carried out using unmanned plane |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105898216B (en) |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106940789A (en) * | 2017-03-10 | 2017-07-11 | 广东数相智能科技有限公司 | A kind of method, system and device of the quantity statistics based on video identification |
CN108388838A (en) * | 2018-01-26 | 2018-08-10 | 重庆邮电大学 | Unmanned plane population surveillance system and monitoring method over the ground |
TWI632528B (en) * | 2017-09-15 | 2018-08-11 | 林永淵 | System and method for unmanned aircraft image analysis |
CN108877228A (en) * | 2018-08-31 | 2018-11-23 | 深圳市研本品牌设计有限公司 | A kind of unmanned plane guided for scenic spot |
WO2019023914A1 (en) * | 2017-07-31 | 2019-02-07 | 深圳市大疆创新科技有限公司 | Image processing method, unmanned aerial vehicle, ground console, and image processing system thereof |
CN109765931A (en) * | 2019-01-31 | 2019-05-17 | 交通运输部天津水运工程科学研究所 | A kind of near-infrared video automatic navigation method suitable for the patrol unmanned machine of breakwater |
CN109934148A (en) * | 2019-03-06 | 2019-06-25 | 华瑞新智科技(北京)有限公司 | A kind of real-time people counting method, device and unmanned plane based on unmanned plane |
CN110033452A (en) * | 2019-04-17 | 2019-07-19 | 北京云量互动科技有限公司 | Refrigerator shelf commodity statistics method and system based on image processing techniques |
CN110246174A (en) * | 2019-07-08 | 2019-09-17 | 北京派克盛宏电子科技有限公司 | A kind of farm live pig method of counting |
CN110235802A (en) * | 2019-07-08 | 2019-09-17 | 北京派克盛宏电子科技有限公司 | A kind of live pig amount of exercise statistical method |
CN111553904A (en) * | 2020-04-29 | 2020-08-18 | 厦门大学 | Unmanned aerial vehicle-based regional people counting method and system |
CN111696127A (en) * | 2020-06-02 | 2020-09-22 | 中国联合网络通信集团有限公司 | Locust plague analysis and early warning system and method |
CN112037579A (en) * | 2019-06-03 | 2020-12-04 | 索尼公司 | Monitoring vehicle movement to mitigate traffic risks |
CN112327893A (en) * | 2019-08-05 | 2021-02-05 | 旭日蓝天(武汉)科技有限公司 | AI (Artificial intelligence) technology-based unmanned aerial vehicle flight control front-end people counting system and method |
CN112381065A (en) * | 2020-12-07 | 2021-02-19 | 福建天创信息科技有限公司 | Face positioning method and terminal |
TWI727906B (en) * | 2020-10-27 | 2021-05-11 | 台灣物聯網股份有限公司 | Method for calculating regional visitor information |
CN113947732A (en) * | 2021-12-21 | 2022-01-18 | 北京航空航天大学杭州创新研究院 | Aerial visual angle crowd counting method based on reinforcement learning image brightness adjustment |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102289817A (en) * | 2011-07-19 | 2011-12-21 | 中国科学院自动化研究所 | pedestrian counting method based on group context |
US20120307042A1 (en) * | 2011-06-02 | 2012-12-06 | Hon Hai Precision Industry Co., Ltd. | System and method for controlling unmanned aerial vehicle |
CN105404894A (en) * | 2015-11-03 | 2016-03-16 | 湖南优象科技有限公司 | Target tracking method used for unmanned aerial vehicle and device thereof |
CN105447459A (en) * | 2015-11-18 | 2016-03-30 | 上海海事大学 | Unmanned plane automation detection target and tracking method |
-
2016
- 2016-04-14 CN CN201610231442.6A patent/CN105898216B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120307042A1 (en) * | 2011-06-02 | 2012-12-06 | Hon Hai Precision Industry Co., Ltd. | System and method for controlling unmanned aerial vehicle |
CN102289817A (en) * | 2011-07-19 | 2011-12-21 | 中国科学院自动化研究所 | pedestrian counting method based on group context |
CN105404894A (en) * | 2015-11-03 | 2016-03-16 | 湖南优象科技有限公司 | Target tracking method used for unmanned aerial vehicle and device thereof |
CN105447459A (en) * | 2015-11-18 | 2016-03-30 | 上海海事大学 | Unmanned plane automation detection target and tracking method |
Cited By (24)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106940789B (en) * | 2017-03-10 | 2021-08-31 | 广东数相智能科技有限公司 | Quantity counting method, system and device based on video identification |
CN106940789A (en) * | 2017-03-10 | 2017-07-11 | 广东数相智能科技有限公司 | A kind of method, system and device of the quantity statistics based on video identification |
WO2019023914A1 (en) * | 2017-07-31 | 2019-02-07 | 深圳市大疆创新科技有限公司 | Image processing method, unmanned aerial vehicle, ground console, and image processing system thereof |
TWI632528B (en) * | 2017-09-15 | 2018-08-11 | 林永淵 | System and method for unmanned aircraft image analysis |
CN108388838A (en) * | 2018-01-26 | 2018-08-10 | 重庆邮电大学 | Unmanned plane population surveillance system and monitoring method over the ground |
CN108388838B (en) * | 2018-01-26 | 2021-07-09 | 重庆邮电大学 | Unmanned aerial vehicle ground crowd monitoring system and monitoring method |
CN108877228A (en) * | 2018-08-31 | 2018-11-23 | 深圳市研本品牌设计有限公司 | A kind of unmanned plane guided for scenic spot |
CN108877228B (en) * | 2018-08-31 | 2021-04-09 | 辽宁博昊土地科技发展有限公司 | A unmanned aerial vehicle for scenic spot guides |
CN109765931B (en) * | 2019-01-31 | 2021-03-16 | 交通运输部天津水运工程科学研究所 | Near-infrared video automatic navigation method suitable for breakwater inspection unmanned aerial vehicle |
CN109765931A (en) * | 2019-01-31 | 2019-05-17 | 交通运输部天津水运工程科学研究所 | A kind of near-infrared video automatic navigation method suitable for the patrol unmanned machine of breakwater |
CN109934148A (en) * | 2019-03-06 | 2019-06-25 | 华瑞新智科技(北京)有限公司 | A kind of real-time people counting method, device and unmanned plane based on unmanned plane |
CN110033452B (en) * | 2019-04-17 | 2021-06-08 | 北京云量互动科技有限公司 | Refrigerator shelf commodity statistical method and system based on image processing technology |
CN110033452A (en) * | 2019-04-17 | 2019-07-19 | 北京云量互动科技有限公司 | Refrigerator shelf commodity statistics method and system based on image processing techniques |
CN112037579A (en) * | 2019-06-03 | 2020-12-04 | 索尼公司 | Monitoring vehicle movement to mitigate traffic risks |
CN110235802A (en) * | 2019-07-08 | 2019-09-17 | 北京派克盛宏电子科技有限公司 | A kind of live pig amount of exercise statistical method |
CN110246174A (en) * | 2019-07-08 | 2019-09-17 | 北京派克盛宏电子科技有限公司 | A kind of farm live pig method of counting |
CN112327893A (en) * | 2019-08-05 | 2021-02-05 | 旭日蓝天(武汉)科技有限公司 | AI (Artificial intelligence) technology-based unmanned aerial vehicle flight control front-end people counting system and method |
CN111553904A (en) * | 2020-04-29 | 2020-08-18 | 厦门大学 | Unmanned aerial vehicle-based regional people counting method and system |
CN111553904B (en) * | 2020-04-29 | 2022-11-22 | 厦门大学 | Unmanned aerial vehicle-based regional people counting method and system |
CN111696127A (en) * | 2020-06-02 | 2020-09-22 | 中国联合网络通信集团有限公司 | Locust plague analysis and early warning system and method |
TWI727906B (en) * | 2020-10-27 | 2021-05-11 | 台灣物聯網股份有限公司 | Method for calculating regional visitor information |
CN112381065A (en) * | 2020-12-07 | 2021-02-19 | 福建天创信息科技有限公司 | Face positioning method and terminal |
CN112381065B (en) * | 2020-12-07 | 2024-04-05 | 福建天创信息科技有限公司 | Face positioning method and terminal |
CN113947732A (en) * | 2021-12-21 | 2022-01-18 | 北京航空航天大学杭州创新研究院 | Aerial visual angle crowd counting method based on reinforcement learning image brightness adjustment |
Also Published As
Publication number | Publication date |
---|---|
CN105898216B (en) | 2019-01-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105898216A (en) | Method of counting number of people by using unmanned plane | |
CN106203265B (en) | A kind of Construction Fugitive Dust Pollution source monitors automatically and coverage forecasting system and method | |
CN110674746B (en) | Method and device for realizing high-precision cross-mirror tracking by using video spatial relationship assistance, computer equipment and storage medium | |
Akbari et al. | Applications, databases and open computer vision research from drone videos and images: a survey | |
CN105069429B (en) | A kind of flow of the people analytic statistics methods and system based on big data platform | |
CN103473554B (en) | Artificial abortion's statistical system and method | |
CN107729808A (en) | A kind of image intelligent acquisition system and method for power transmission line unmanned machine inspection | |
CN107504957A (en) | The method that three-dimensional terrain model structure is quickly carried out using unmanned plane multi-visual angle filming | |
CN104599243A (en) | Virtual and actual reality integration method of multiple video streams and three-dimensional scene | |
CN106815838A (en) | A kind of method and system of the detection of photovoltaic module hot spot | |
CN106210627A (en) | A kind of unmanned plane fire dispatch system | |
CN104484033A (en) | BIM based virtual reality displaying method and system | |
CN109801301A (en) | A kind of automatic collection method of tile work progress msg based on BIM and computer vision | |
CN108154110A (en) | A kind of intensive people flow amount statistical method based on the detection of the deep learning number of people | |
CN107273799A (en) | A kind of indoor orientation method and alignment system | |
CN103065520A (en) | Detection system for backing car into storage and detection method thereof | |
CN103729620B (en) | A kind of multi-view pedestrian detection method based on multi-view Bayesian network | |
CN104820995A (en) | Large public place-oriented people stream density monitoring and early warning method | |
CN107221006A (en) | A kind of communication single pipe tower slant detection method based on unmanned plane imaging platform | |
CN103076007A (en) | Side parking detecting system and method | |
CN108734655A (en) | The method and system that aerial multinode is investigated in real time | |
CN108471497A (en) | A kind of ship target real-time detection method based on monopod video camera | |
CN107808402A (en) | Scaling method, multicamera system and the terminal device of multicamera system | |
CN105892638A (en) | Virtual reality interaction method, device and system | |
CN110378292A (en) | Three dimension location system and method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |