CN107122746A - Video analysis equipment, method and computer-readable recording medium - Google Patents
Video analysis equipment, method and computer-readable recording medium Download PDFInfo
- Publication number
- CN107122746A CN107122746A CN201710294505.7A CN201710294505A CN107122746A CN 107122746 A CN107122746 A CN 107122746A CN 201710294505 A CN201710294505 A CN 201710294505A CN 107122746 A CN107122746 A CN 107122746A
- Authority
- CN
- China
- Prior art keywords
- video analysis
- multiple object
- video
- transformation
- predetermined arrangement
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Probability & Statistics with Applications (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Apparatus Associated With Microorganisms And Enzymes (AREA)
- Image Analysis (AREA)
Abstract
This disclosure relates to video analysis equipment, method and computer-readable recording medium, including a kind of video analysis equipment, it is characterised in that including:Ideal position determining unit, the predetermined arrangement pattern for the multiple objects being configured to, with video, determines the ideal position of the multiple object;Unit is set up in geometric transformation, is configured to, with coordinate transformation method, sets up the initial position of the multiple object to the geometric transformation of ideal position;And exact position obtaining unit, the inverse transformation of the mapping matrix according to the geometric transformation is configured as, the exact position of the multiple object is obtained.By using the predetermined arrangement pattern of multiple objects in video, the positioning precision to object in video can be improved according to video analysis equipment, method and the computer-readable recording medium of each side of the disclosure.
Description
Technical field
This disclosure relates to which multiple objects in video are more particularly to determined by video analysis field by video analysis
Position.
Background technology
Video analysis, positioning analysis etc. especially is carried out to the object that occurs in video there is extensive use interdisciplinary.
For example, under the situation of biology, Animal Behavior Science is an important research direction, and animal behavior video is automatically analyzed
Algorithm be applied to the field more and more.Object in the video is automatically extracted and segmentation is the side of automatically analyzing
The important step of method.But, extraction algorithm traditional at present generally there are the problems such as poor positioning precision, object's position missing inspection, sternly
The automation of flow is had influence on again.
The content of the invention
Inventors have realized that, existing video analysis algorithm does not make full use of the intrinsic letter between object in video
Breath.In view of this, the present disclosure proposes a kind of video analysis equipment, method and computer-readable recording medium.
According to the one side of the disclosure, there is provided a kind of video analysis equipment, it is characterised in that including:Ideal position is true
Order member, the predetermined arrangement pattern for the multiple objects being configured to, with video determines the ideal position of the multiple object;
Unit is set up in geometric transformation, is configured to, with coordinate transformation method, sets up the initial position of the multiple object to ideal bit
The geometric transformation put;And exact position obtaining unit, the inverse transformation of the mapping matrix according to the geometric transformation is configured as,
Obtain the exact position of the multiple object.By using the predetermined arrangement pattern of multiple objects in video, according to the disclosure
Video analysis equipment, method and the computer-readable recording medium of each side can improve the positioning precision to object in video.
In a kind of possible implementation, the predetermined arrangement pattern is symmetrically arranged including approximate centre.
In a kind of possible implementation, the ideal position determining unit is configured as the predetermined arrangement mould
Formula, specifies direction, yardstick and the origin of coordinates of its arrangement, to determine the ideal position of ideally the multiple object.
In a kind of possible implementation, the geometric transformation includes affine transformation or perspective transform;The accurate position
The inverse transformation that obtaining unit is configured as solving the mapping matrix of the affine transformation or perspective transform is put, the inverse transformation is made
For the ideal position of the multiple object, to obtain the exact position of the multiple object.
In a kind of possible implementation, the multiple object is multiple insect activity platforms, and insect can be in the elder brother
It is movable at worm traveling table, and the predetermined arrangement pattern is regular polygon arrangement.
In a kind of possible implementation, the video analysis equipment also includes:Initial position obtaining unit, is configured
Using the shape information of the multiple object, tentatively to obtain the position of the multiple object as the initial position, wherein,
Tentatively obtaining the position of the multiple object includes:Multiple frames are extracted from video, and detect described many in the multiple frame
Position where the shape of individual object, the number for the object is clustered by the position, obtains the initial position.
According to another aspect of the present disclosure, there is provided a kind of video analysis method, it is characterised in that including:Utilize video
In multiple objects predetermined arrangement pattern, determine the ideal position of the multiple object;Using coordinate transformation method, institute is set up
The initial position of multiple objects is stated to the geometric transformation of ideal position;According to the inverse transformation of the mapping matrix of the geometric transformation,
Obtain the exact position of the multiple object.
In a kind of possible implementation, the video analysis method also includes:Utilize the shape of the multiple object
Information, tentatively obtains the position of the multiple object as the initial position;Wherein, the position of the multiple object is tentatively obtained
Put including:Extract multiple frames from video, and detect the position where the shape of the multiple object in the multiple frame, will
The position cluster is the number of the object, obtains the initial position.
In a kind of possible implementation, the predetermined arrangement pattern is symmetrically arranged including approximate centre.
In a kind of possible implementation, determined using the predetermined arrangement pattern of multiple objects in video the multiple
The ideal position of object includes:For the predetermined arrangement pattern, direction, yardstick and the origin of coordinates of its arrangement are specified, with true
The ideal position of fixed ideally the multiple object.
In a kind of possible implementation, the geometric transformation includes affine transformation or perspective transform;And according to institute
Stating the exact position of the multiple object of inverse transformation acquisition of the mapping matrix of geometric transformation includes:Solve the affine transformation or
The inverse transformation of the mapping matrix of perspective transform, the inverse transformation is acted on the ideal position of the multiple object, to obtain
State the exact position of multiple objects.
In a kind of possible implementation, the multiple object is multiple insect activity platforms, and insect can be in the elder brother
It is movable at worm traveling table, and the predetermined arrangement pattern is regular polygon arrangement.
According to another aspect of the present disclosure there is provided a kind of video analysis equipment, including:Processor;For storage processing
The memory of device executable instruction;Wherein, the processor is configured as performing the above method.
According to another aspect of the present disclosure there is provided a kind of computer-readable recording medium, the computer program is processed
Device realizes the above method when performing.
By using the predetermined arrangement pattern of multiple objects in video, set according to the video analysis of each side of the disclosure
Standby, method and computer-readable recording medium can improve the positioning precision to object in video.
According to below with reference to the accompanying drawings to detailed description of illustrative embodiments, the further feature and aspect of the disclosure will become
It is clear.
Brief description of the drawings
Comprising in the description and constituting accompanying drawing and the specification of a part of specification and together illustrate the disclosure
Exemplary embodiment, feature and aspect, and for explaining the principle of the disclosure.
Fig. 1 shows the indication device block diagram of the video analysis equipment according to illustrative embodiments.
Fig. 2 shows the signal details block diagram according to the video analysis implemented shown in example a equipment.
Fig. 3 shows the schematic flow diagram of the video analysis method according to illustrative embodiments.
Fig. 4 shows the signal details flow chart according to the video analysis implemented shown in example a method.
Fig. 5 is the schematic diagram that the multiple object A~F implemented according to one shown in example are arranged by regular hexagon.
Fig. 6 is the block diagram of the video analysis equipment 1900 according to illustrative embodiments.
Embodiment
Describe various exemplary embodiments, feature and the aspect of the disclosure in detail below with reference to accompanying drawing.It is identical in accompanying drawing
Reference represent the same or analogous element of function.Although the various aspects of embodiment are shown in the drawings, remove
Non-specifically is pointed out, it is not necessary to accompanying drawing drawn to scale.
Special word " exemplary " is meant " being used as example, embodiment or illustrative " herein.Here as " exemplary "
Illustrated any embodiment should not necessarily be construed as preferred or advantageous over other embodiments.
In addition, in order to better illustrate the disclosure, numerous details are given in embodiment below.
It will be appreciated by those skilled in the art that without some details, the disclosure can equally be implemented.In some instances, for
Method well known to those skilled in the art, means, element and circuit are not described in detail, in order to highlight the purport of the disclosure.
Although the disclosure is made with the insect activity platform (insect can at the insect activity platform movable) used in biological field
It is illustrative for the positioning object in video, but it should be readily apparent to one skilled in the art that the disclosure is equally applicable to pair
Types of objects in the video of various different fields is positioned.
Fig. 1 shows the indication device block diagram of the video analysis equipment 100 according to illustrative embodiments.Video analysis equipment
100, which include ideal position determining unit 102, geometric transformation, sets up unit 104 and exact position obtaining unit 106.Wherein, it is preferable
Position determination unit 102 is configured to, with the predetermined arrangement pattern of multiple objects in video, determines the ideal of multiple objects
Position.Here, predetermined arrangement pattern can be times that object has the known arrangement regulation for video analysis equipment 100
What pattern of rows and columns.In a specific example, predetermined arrangement pattern is symmetrically arranged including approximate centre.Those skilled in the art
Know about, the arrangement of object is extremely difficult to geometrically strict Central Symmetry in practice." approximate centre is symmetrical " represents object
Arranged in as well known to those skilled in the art or generally accepted error range in Central Symmetry mode.In a specific example
In, it is preferable that predetermined arrangement pattern can include grid arrangement or square arrangement, rectangle arrangement (square and rectangle
Arrangement can be collectively referred to as rectangular arranged) or regular hexagon arrangement.Certainly, as the skilled personnel can understand, row is made a reservation for
Row pattern can other regular polygon arrangements such as including octagon.Geometric transformation sets up unit 104 and is configured to, with coordinate
Transform method, sets up the initial position of multiple objects to the geometric transformation of ideal position.Exact position obtaining unit 106 is configured
For the inverse transformation of the mapping matrix according to the geometric transformation, the exact position of the multiple object is obtained.
Fig. 2 shows the signal details block diagram according to the video analysis implemented shown in example a equipment 200.Except ideal
Position determination unit 102, geometric transformation are set up beyond unit 104 and exact position obtaining unit 106, video analysis equipment 200
Initial position obtaining unit 202 can be further comprised on the basis of video analysis equipment 100.At one in the specific implementation,
Video analysis equipment 200 receives input video.Initial position obtaining unit 202 extracts multiple frames from input video, using regarding
The shape information of multiple objects in frequency, detects the position where the shape of multiple objects, and the position is clustered as object
Number, so as to obtain the initial position where the shape of multiple objects.Thus, video analysis equipment 200 can be tentatively somebody's turn to do
The initial position of multiple objects.
Fig. 3 shows the schematic flow diagram of the video analysis method according to illustrative embodiments.Video analysis method can be with
Comprise the following steps.In step s 302, using the predetermined arrangement pattern of multiple objects in video, the multiple object is determined
Ideal position.In step s 304, using coordinate transformation method, the initial position of the multiple object is set up to ideal position
Geometric transformation.In step S306, according to the inverse transformation of the mapping matrix of the geometric transformation, the accurate of multiple objects is obtained
Position.
Fig. 4 shows the signal details flow chart according to the video analysis implemented shown in example a method.At one
Implement in example, the video analysis method of the disclosure can apply to analyze the insect activity as object in video
Platform.But those skilled in the art are not obviously it is understood that the object that the disclosure can be analyzed is limited with insect activity platform.Such as Fig. 4
It is shown, following steps can be performed.
● the preliminary position for extracting insect activity platform
Some frames are extracted from input video, and detect the position where insect activity platform shape therein.For example, for
Circular insect activity platform, can use hough-circle transform algorithm.For other shapes, it can use corresponding with other shapes
Known SHAPE DETECTION algorithm.The insect activity platform position detected is clustered, for example, can use Kmeans or GMM
Scheduling algorithm, obtains the initial position P of N number of cluster centre, i.e. insect activity platform1,P2..., PN, wherein N is the number of insect activity platform
Mesh.P1,P2..., PNIt has been pointed generally in the position of insect activity platform.
For known insect activity platform arrangement mode, direction, yardstick and the origin of coordinates of its arrangement are specified, and determines reason
The position of traveling table in the case of thinking.For example, in a specific example, insect activity platform can be arranged according to grid.At this moment, may be used
To assume that the ideal position of insect activity platform is respectively Q1,Q2,…,QN, wherein Qi=(mi, ni), miAnd niIt is illustrated respectively in grid
Line number and columns in arrangement.It is of course also possible to specify others yardstick, direction and the origin of coordinates.Under different coordinate systems
Q1,Q2,…,QNThere are different expressions.For example, in another specific example, the arrangement of insect activity platform can be regular hexagon
Arrangement.Fig. 5 is the schematic diagram that the multiple object A~F implemented according to one shown in example are arranged by regular hexagon, positive six side
The symmetrical centre of shape is shown as O.At this moment, it can be expressed as the coordinate of the insect activity platform of the example of objectWherein, m and n correspond to line number and columns of the insect activity platform along OC directions and OB directions respectively.Should
Work as understanding, yardstick can represent size degree of the predetermined arrangement pattern of for example, object of insect activity platform under preferable coordinate system
Amount.In one example, in the case where predetermined arrangement pattern is regular hexagon or rectangular arranged, yardstick can be regular hexagon
Or size of the length of side of rectangle under preferable coordinate system.In other examples, in the feelings that predetermined arrangement pattern is circular arrangement
Under condition, yardstick can be circular radius.
● set up the initial position P of insect activity platform1,P2..., PNWith ideal position Q1,Q2,…,QNBetween mapping close
System.Assuming that P1,P2..., PNWithCorrespond, then will be put from initial coordinate P in the presence of mapping A1,P2..., PNReflect
Penetrate as ideal coordinatesMapping matrix A can represent perspective transform or affine transformation.It should be noted that rotation becomes
Change, shear transformation, translation transformation, scale transformation, it is turning-over changed etc. can be realized by affine transformation, no longer go to live in the household of one's in-laws on getting married herein
State.
If mapping matrix
Obtain overdetermined equation
In a specific example, for example, mapping matrix A can be solved according to least square method, and solve mapping matrix A
Inverse transformation B.
● the ideal position of insect activity platformActed on by inverse transformation B, obtain the accurate of insect activity platform
Position P '1,P’2..., P 'N, i.e.,
It should be noted that in fact, video that the disclosure is applied to and the object analyzed in video are not regarded with insect
Frequency and insect activity platform are limited.User can flexibly set selection according to practical application scene completely, as long as multiple right in video
As being arranged with predetermined arrangement pattern.
Fig. 6 is the block diagram of the video analysis equipment 1900 according to illustrative embodiments.For example, device 1900 can be with
It is provided as a server.Reference picture 5, device 1900 includes processing assembly 1922, and it further comprises one or more processing
Device, and as the memory resource representated by memory 1932, the instruction that can be performed for storage by processing assembly 1922, for example
Application program.The application program stored in memory 1932 can include one or more module, each module pair
Ying Yuyi groups are instructed.In addition, processing assembly 1922 is configured as execute instruction, to perform above-mentioned video analysis method.
Device 1900 can also include the power management that a power supply module 1926 is configured as performs device 1900, one
Wired or wireless network interface 1950 is configured as device 1900 being connected to network, and input and output (I/O) interface
1958.Device 1900 can be operated based on the operating system for being stored in memory 1932, such as Windows ServerTM, Mac
OS XTM, UnixTM, LinuxTM, FreeBSDTMOr it is similar.
In the exemplary embodiment, a kind of non-volatile computer readable storage medium storing program for executing including instructing, example are additionally provided
Such as include the memory 1932 of instruction, above-mentioned instruction can be performed to complete the above method by the processing assembly 1922 of device 1900.
The disclosure can be system, method and/or computer program product.Computer program product can include computer
Readable storage medium storing program for executing, containing for making processor realize the computer-readable program instructions of various aspects of the disclosure.
Computer-readable recording medium can keep and store to perform the tangible of the instruction that equipment is used by instruction
Equipment.Computer-readable recording medium can for example be but not limited to storage device electric, magnetic storage apparatus, light storage device, electricity
Magnetic storage apparatus, semiconductor memory apparatus or above-mentioned any appropriate combination.Computer-readable recording medium it is more specific
Example (non exhaustive list) include:Portable computer diskette, hard disk, random access memory (RAM), read-only storage
(ROM), erasable programmable read only memory (EPROM or flash memory), static RAM (SRAM), Portable compressed
Disk read-only storage (CD-ROM), digital versatile disc (DVD), memory stick, floppy disk, mechanical coding equipment, for example store thereon
There are the punch card or groove internal projection structure of instruction and above-mentioned any appropriate combination.Computer used herein above can
Read storage medium and be not construed as instantaneous signal in itself, the electromagnetic wave of such as radio wave or other Free propagations, pass through ripple
Lead or other transmission mediums propagate electromagnetic wave (for example, the light pulse for passing through fiber optic cables) or the electricity transmitted by electric wire
Signal.
Computer-readable program instructions as described herein can be downloaded to from computer-readable recording medium each calculate/
Processing equipment, or outer computer is downloaded to or outer by network, such as internet, LAN, wide area network and/or wireless network
Portion's storage device.Network can be transmitted, be wirelessly transferred including copper transmission cable, optical fiber, router, fire wall, interchanger, gateway
Computer and/or Edge Server.Adapter or network interface in each calculating/processing equipment are received from network to be counted
Calculation machine readable program instructions, and the computer-readable program instructions are forwarded, for the meter being stored in each calculating/processing equipment
In calculation machine readable storage medium storing program for executing.
For perform the disclosure operation computer program instructions can be assembly instruction, instruction set architecture (ISA) instruction,
Machine instruction, machine-dependent instructions, microcode, firmware instructions, condition setup data or with one or more programming languages
Source code or object code that any combination is write, programming language of the programming language including object-oriented-such as
Smalltalk, C++ etc., and conventional procedural programming languages-such as " C " language or similar programming language.Computer
Readable program instructions can perform fully on the user computer, partly perform on the user computer, as one solely
Vertical software kit is performed, part is performed or completely in remote computer on the remote computer on the user computer for part
Or performed on server.In the situation of remote computer is related to, remote computer can be by network-bag of any kind
LAN (LAN) or wide area network (WAN)-be connected to subscriber computer are included, or, it may be connected to outer computer is (such as sharp
With ISP come by Internet connection).In certain embodiments, by using computer-readable program instructions
Status information carry out personalized customization electronic circuit, such as PLD, field programmable gate array (FPGA) or can
Programmed logic array (PLA) (PLA), the electronic circuit can perform computer-readable program instructions, so as to realize each side of the disclosure
Face.
Referring herein to the method according to the embodiment of the present disclosure, device (system) and computer program product flow chart and/
Or block diagram describes various aspects of the disclosure.It should be appreciated that each square frame and flow chart of flow chart and/or block diagram and/
Or in block diagram each square frame combination, can be realized by computer-readable program instructions.
These computer-readable program instructions can be supplied to all-purpose computer, special-purpose computer or other programmable datas
The processor of processing unit, so as to produce a kind of machine so that these instructions are passing through computer or other programmable datas
During the computing device of processing unit, work(specified in one or more of implementation process figure and/or block diagram square frame is generated
The device of energy/action.Can also be the storage of these computer-readable program instructions in a computer-readable storage medium, these refer to
Order causes computer, programmable data processing unit and/or other equipment to work in a specific way, so that, be stored with instruction
Computer-readable medium then includes a manufacture, and it is included in one or more of implementation process figure and/or block diagram square frame
The instruction of the various aspects of defined function/action.
Computer-readable program instructions can also be loaded into computer, other programmable data processing units or other
In equipment so that perform series of operation steps on computer, other programmable data processing units or miscellaneous equipment, to produce
Raw computer implemented process, so that performed on computer, other programmable data processing units or miscellaneous equipment
Instruct function/action specified in one or more of implementation process figure and/or block diagram square frame.
So, by making full use of predetermined arrangement pattern information, according to the video analysis equipment of disclosure above-described embodiment,
Method and computer-readable recording medium can improve the accuracy that object is positioned in video.
Flow chart and block diagram in accompanying drawing show the system, method and computer journey of multiple embodiments according to the disclosure
Architectural framework in the cards, function and the operation of sequence product.At this point, each square frame in flow chart or block diagram can generation
One module of table, program segment or a part for instruction, the module, program segment or a part for instruction are used comprising one or more
In the executable instruction for realizing defined logic function.In some realizations as replacement, the function of being marked in square frame
Can be with different from the order marked in accompanying drawing generation.For example, two continuous square frames can essentially be held substantially in parallel
OK, they can also be performed in the opposite order sometimes, and this is depending on involved function.It is also noted that block diagram and/or
The combination of each square frame in flow chart and the square frame in block diagram and/or flow chart, can use function as defined in execution or dynamic
The special hardware based system made is realized, or can be realized with the combination of specialized hardware and computer instruction.
It is described above the presently disclosed embodiments, described above is exemplary, and non-exclusive, and
It is not limited to disclosed each embodiment.In the case of without departing from the scope and spirit of illustrated each embodiment, for this skill
Many modifications and changes will be apparent from for the those of ordinary skill in art field.The selection of term used herein, purport
The principle, practical application or the technological improvement to the technology in market of each embodiment are best being explained, or is leading this technology
Other those of ordinary skill in domain are understood that each embodiment disclosed herein.
Claims (14)
1. a kind of video analysis equipment, it is characterised in that including:
Ideal position determining unit, the predetermined arrangement pattern for the multiple objects being configured to, with video, is determined the multiple
The ideal position of object;
Unit is set up in geometric transformation, is configured to, with coordinate transformation method, sets up the initial position of the multiple object to reason
Think the geometric transformation of position;And
Exact position obtaining unit, is configured as the inverse transformation of the mapping matrix according to the geometric transformation, obtains the multiple
The exact position of object.
2. video analysis equipment according to claim 1, wherein, it is symmetrical that the predetermined arrangement pattern includes approximate centre
Arrangement.
3. video analysis equipment according to claim 1, wherein, the ideal position determining unit is configured as institute
Predetermined arrangement pattern is stated, direction, yardstick and the origin of coordinates of its arrangement is specified, to determine ideally the multiple object
Ideal position.
4. video analysis equipment according to claim 1, wherein, the geometric transformation includes affine transformation or perspective becomes
Change;And
The exact position obtaining unit is configured as solving the inverse transformation of the mapping matrix of the affine transformation or perspective transform,
The inverse transformation is acted on to the ideal position of the multiple object, to obtain the exact position of the multiple object.
5. video analysis equipment according to claim 1, wherein, the multiple object is multiple insect activity platforms, insect
Can be movable at the insect activity platform, and the predetermined arrangement pattern is regular hexagon or rectangular arranged.
6. video analysis equipment according to claim 1, in addition to:
Initial position obtaining unit, is configured to, with the shape information of the multiple object, tentatively obtains the multiple object
Position as the initial position,
Wherein, tentatively obtaining the position of the multiple object includes:Multiple frames are extracted from video, and are detected in the multiple frame
The multiple object shape where position, the position is clustered into the number for the object, the initial bit is obtained
Put.
7. a kind of video analysis method, it is characterised in that including:
Using the predetermined arrangement pattern of multiple objects in video, the ideal position of the multiple object is determined;
Using coordinate transformation method, the initial position of the multiple object is set up to the geometric transformation of ideal position;
According to the inverse transformation of the mapping matrix of the geometric transformation, the exact position of the multiple object is obtained.
8. video analysis method according to claim 7, in addition to:
Using the shape information of the multiple object, the position of the multiple object is tentatively obtained as the initial position;
Wherein, tentatively obtaining the position of the multiple object includes:Multiple frames are extracted from video, and are detected in the multiple frame
The multiple object shape where position, the position is clustered into the number for the object, the initial bit is obtained
Put.
9. video analysis method according to claim 7, wherein, it is symmetrical that the predetermined arrangement pattern includes approximate centre
Arrangement.
10. video analysis method according to claim 7, wherein, utilize the predetermined arrangement mould of multiple objects in video
Formula determines that the ideal position of the multiple object includes:For the predetermined arrangement pattern, specify the direction of its arrangement, yardstick and
The origin of coordinates, to determine the ideal position of ideally the multiple object.
11. video analysis method according to claim 7, wherein, the geometric transformation includes affine transformation or perspective becomes
Change;And
Included according to the exact position that the inverse transformation of the mapping matrix of the geometric transformation obtains the multiple object:Solve described
The inverse transformation of affine transformation or the mapping matrix of perspective transform, the inverse transformation is acted on the ideal bit of the multiple object
Put, to obtain the exact position of the multiple object.
12. video analysis method according to claim 7, wherein, the multiple object is multiple insect activity platforms, insect
Can be movable at the insect activity platform, and the predetermined arrangement pattern is regular hexagon or rectangular arranged.
13. a kind of video analysis equipment, it is characterised in that including:
Processor;
Memory for storing processor-executable instruction;
Wherein, the processor is configured as the method any one of perform claim requirement 7~12.
14. a kind of computer-readable recording medium, is stored thereon with computer program, it is characterised in that the computer program quilt
The method any one of claim 7~12 is realized during computing device.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710294505.7A CN107122746B (en) | 2017-04-28 | 2017-04-28 | Video analysis apparatus, method, and computer-readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710294505.7A CN107122746B (en) | 2017-04-28 | 2017-04-28 | Video analysis apparatus, method, and computer-readable storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107122746A true CN107122746A (en) | 2017-09-01 |
CN107122746B CN107122746B (en) | 2020-01-21 |
Family
ID=59725179
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710294505.7A Active CN107122746B (en) | 2017-04-28 | 2017-04-28 | Video analysis apparatus, method, and computer-readable storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107122746B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109409321A (en) * | 2018-11-08 | 2019-03-01 | 北京奇艺世纪科技有限公司 | A kind of determination method and device of camera motion mode |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1725246A (en) * | 2005-07-14 | 2006-01-25 | 中国科学院计算技术研究所 | A kind of human body posture deforming method based on video content |
CN1836185A (en) * | 2003-08-11 | 2006-09-20 | 莱卡微系统Cms有限责任公司 | Method and system for device-independent determination of coordinates of a point displayed by means of a microscope |
CN105354578A (en) * | 2015-10-27 | 2016-02-24 | 安徽大学 | Multi-target object image matching method |
CN106056625A (en) * | 2016-05-25 | 2016-10-26 | 中国民航大学 | Airborne infrared moving target detection method based on geographical homologous point registration |
-
2017
- 2017-04-28 CN CN201710294505.7A patent/CN107122746B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1836185A (en) * | 2003-08-11 | 2006-09-20 | 莱卡微系统Cms有限责任公司 | Method and system for device-independent determination of coordinates of a point displayed by means of a microscope |
CN1725246A (en) * | 2005-07-14 | 2006-01-25 | 中国科学院计算技术研究所 | A kind of human body posture deforming method based on video content |
CN105354578A (en) * | 2015-10-27 | 2016-02-24 | 安徽大学 | Multi-target object image matching method |
CN106056625A (en) * | 2016-05-25 | 2016-10-26 | 中国民航大学 | Airborne infrared moving target detection method based on geographical homologous point registration |
Non-Patent Citations (3)
Title |
---|
M KABRA等: "interactive machine learning for automatic annotation of animal behavior", 《NATURE METHODS》 * |
杨猛等: "一种新的基于多特征的图像自动配准技术", 《计算机应用研究》 * |
谷源涛等: "低成本受控环境下的果蝇识别算法研究", 《计算机仿真》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109409321A (en) * | 2018-11-08 | 2019-03-01 | 北京奇艺世纪科技有限公司 | A kind of determination method and device of camera motion mode |
Also Published As
Publication number | Publication date |
---|---|
CN107122746B (en) | 2020-01-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP3452959B1 (en) | Model construction in a neural network for object detection | |
US10614575B2 (en) | Searching trees: live time-lapse cell-cycle progression modeling and analysis | |
Li et al. | Automatic comic page segmentation based on polygon detection | |
Liu et al. | An improved method based on deep learning for insulator fault detection in diverse aerial images | |
CN110674808A (en) | Transformer substation pressure plate state intelligent identification method and device | |
US20220092407A1 (en) | Transfer learning with machine learning systems | |
CN110188495A (en) | A method of the two-dimentional floor plan based on deep learning generates three-dimensional floor plan | |
Lu et al. | A GIS partial discharge defect identification method based on YOLOv5 | |
Panahi et al. | Tracking volumetric units in modular factories for automated progress monitoring using computer vision | |
CN110807754B (en) | Fungus microscopic image segmentation detection method and system based on deep semantic segmentation | |
Dong et al. | PHAM-YOLO: A parallel hybrid attention mechanism network for defect detection of meter in substation | |
CN110738272A (en) | method for labeling visualized mechanical continuous alarm samples of power transmission line channel | |
CN107122746A (en) | Video analysis equipment, method and computer-readable recording medium | |
CN112967248A (en) | Method, apparatus, medium, and program product for generating defect image sample | |
Hu et al. | Research on an improved detection algorithm based on yolov5s for power line self-exploding insulators | |
CN109934185A (en) | Data processing method and device, medium and calculating equipment | |
Wu et al. | Construction of Stretching-Bending Sequential Pattern to Recognize Work Cycles for Earthmoving Excavator from Long Video Sequences | |
Hidayatullah et al. | A semiautomatic sperm cell data annotator for convolutional neural network | |
Gabriel et al. | Wildlife Detection and Recognition in Digital Images Using YOLOv3 | |
Doshvarpassand et al. | An automated pipeline for dynamic detection of sub-surface metal loss defects across cold thermography images | |
JP6845169B2 (en) | Image processing equipment, image processing methods and programs | |
del Olmo Lianes et al. | Technical upgrade of an open-source liquid handler to support bacterial colony screening | |
US11361438B2 (en) | Techniques for analyzing and detecting executional artifacts in microwell plates | |
CN111046929B (en) | Analysis method and device for model error cases and electronic equipment | |
AU2021316176B2 (en) | Techniques for analyzing and detecting executional artifacts in microwell plates |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |