CN109427072A - The method and apparatus for identifying moving target - Google Patents
The method and apparatus for identifying moving target Download PDFInfo
- Publication number
- CN109427072A CN109427072A CN201710759602.9A CN201710759602A CN109427072A CN 109427072 A CN109427072 A CN 109427072A CN 201710759602 A CN201710759602 A CN 201710759602A CN 109427072 A CN109427072 A CN 109427072A
- Authority
- CN
- China
- Prior art keywords
- moving target
- target
- attribute
- average speed
- speed
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- 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
- G06T2207/30241—Trajectory
Abstract
The invention discloses a kind of method and apparatus for identifying moving target, are related to computer vision and field of image recognition.This method comprises: obtaining the motion profile of moving target；The average speed of moving target is determined according to motion profile；Judge whether moving target matches with objective attribute target attribute according to average speed.The present invention judges whether moving target matches with objective attribute target attribute according to the average speed of moving target, can filter significantly with the unmatched object of objective attribute target attribute, improve the accuracy rate of identification.
Description
Technical field
The present invention relates to computer vision and field of image recognition more particularly to a kind of methods and dress for identifying moving target
It sets.
Background technique
HOG (Histogram of Oriented Gradient, histograms of oriented gradients) is characterized in one kind in computer
It is used to carry out the Feature Descriptor of object detection in vision and image procossing.HOG feature is by calculating and statistical picture partial zones
The gradient orientation histogram in domain carrys out constitutive characteristic.The presentation and shape of the localized target of image can be by gradient or the directions at edge
Density Distribution describes well.It is in the nature the statistical information of gradient, and gradient is primarily present in the place at edge.
Currently, HOG feature combination SVM classifier has been widely used in the image recognition of pedestrian, but each existing
Accuracy rate in the practical application of kind interference is not high.For example, portrait is printed in the vehicle advertisement moved at one, using HOG
Characteristic value comparison technology, analysis conclusion can be mistakenly identified as the portrait one movable people；Secondly, in order to improve in practical application
Target identification accuracy rate is tracked using the method for increasing HOG characteristic value dimension, the method will lead to processing speed index and increase again,
It can not be applied to practical.
Summary of the invention
The invention solves a technical problem be to provide it is a kind of identify moving target method and apparatus, can be improved
The accuracy rate of identification.
According to an aspect of the present invention, a kind of method for identifying moving target is proposed, comprising: obtain the movement rail of moving target
Mark；The average speed of moving target is determined according to motion profile；According to average speed judge moving target whether with objective attribute target attribute
Match.
Further, if average speed is greater than threshold speed, judge that moving target is not matched that with objective attribute target attribute.
Further, the average speed of moving target is determined according to the adjacent two frame positions difference of moving target and time difference.
Further, this method further include: determine the position attribution of each frame of moving target；According to the position of moving target
Whether determined property moving target matches with objective attribute target attribute.
Further, this method further include: moving target is identified and screened based on HOG characteristic value.
According to another aspect of the present invention, it is also proposed that a kind of device for identifying moving target, comprising: track acquiring unit,
For obtaining the motion profile of moving target；Speed computing unit, for determining the average speed of moving target according to motion profile
Degree；Target-recognition unit, for judging whether moving target matches with objective attribute target attribute according to average speed.
Further, if target-recognition unit is greater than threshold speed for average speed, judge moving target and target
Attribute does not match that.
Further, speed computing unit is used to determine movement according to the alternate position spike of adjacent two frame of moving target and time difference
The average speed of target.
Further, the device further include: position attribution determination unit, for determining that the position of each frame of moving target belongs to
Property；Target-recognition unit is also used to judge whether moving target matches with objective attribute target attribute according to the position attribution of moving target.
Further, the device further include: object filtering unit, for movement mesh to be identified and screened based on HOG characteristic value
Mark.
According to another aspect of the present invention, it is also proposed that a kind of device for identifying moving target characterized by comprising deposit
Reservoir；And it is coupled to the processor of memory, processor is configured as example above-mentioned based on the instruction execution for being stored in memory
Method.
According to another aspect of the present invention, it is also proposed that a kind of computer readable storage medium is stored thereon with computer journey
The step of sequence instruction, which realizes above-mentioned method when being executed by processor.
Compared with prior art, the present invention according to the average speed of moving target judge moving target whether with objective attribute target attribute
Match, can filter significantly with the unmatched object of objective attribute target attribute, improve the accuracy rate of identification.
By referring to the drawings to the detailed description of exemplary embodiment of the present invention, other feature of the invention and its
Advantage will become apparent.
Detailed description of the invention
The attached drawing for constituting part of specification describes the embodiment of the present invention, and together with the description for solving
Release the principle of the present invention.
The present invention can be more clearly understood according to following detailed description referring to attached drawing, in which:
Fig. 1 is the flow diagram of one embodiment of the method for present invention identification moving target.
Fig. 2 is movement objective orbit schematic diagram.
Fig. 3 is the flow diagram of one embodiment of the method for present invention identification moving target.
Fig. 4 is the structural schematic diagram of one embodiment of the device of present invention identification moving target.
Fig. 5 is the structural schematic diagram of another embodiment of the device of present invention identification moving target.
Fig. 6 is the structural schematic diagram of the further embodiment of the device of present invention identification moving target.
Fig. 7 is the structural schematic diagram of another embodiment of the device of present invention identification moving target.
Specific embodiment
Carry out the various exemplary embodiments of detailed description of the present invention now with reference to attached drawing.It should also be noted that unless in addition having
Body explanation, the unlimited system of component and the positioned opposite of step, numerical expression and the numerical value otherwise illustrated in these embodiments is originally
The range of invention.
Simultaneously, it should be appreciated that for ease of description, the size of various pieces shown in attached drawing is not according to reality
Proportionate relationship draw.
Be to the description only actually of at least one exemplary embodiment below it is illustrative, never as to the present invention
And its application or any restrictions used.
Technology, method and apparatus known to person of ordinary skill in the relevant may be not discussed in detail, but suitable
In the case of, the technology, method and apparatus should be considered as authorizing part of specification.
It is shown here and discuss all examples in, any occurrence should be construed as merely illustratively, without
It is as limitation.Therefore, the other examples of exemplary embodiment can have different values.
It should also be noted that similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined in a attached drawing, then in subsequent attached drawing does not need that it is further discussed.
To make the objectives, technical solutions, and advantages of the present invention clearer, below in conjunction with specific embodiment, and reference
Attached drawing, the present invention is described in more detail.
Fig. 1 is the flow diagram of one embodiment of the method for present invention identification moving target.This method includes following
Step:
In step 110, the motion profile of moving target is obtained.For example, as shown in Fig. 2, from t0From moment, each fortune is recorded
Position P (the t of each frame of moving-targeti), obtain the motion profile of each moving target.
In step 120, the average speed of moving target is determined according to motion profile.Due to knowing that each moving target is each
The position of frame (moment) determines the average speed of moving target according to adjacent two frame positions difference and time difference, for example, adjacent two frame
Between average speed SiAre as follows:
Wherein, (Xi,Yi) it is the position for moving the every frame of purpose, Ti-Ti-1For the time difference of adjacent two frame.
The average speed of moving target
In step 130, judge whether moving target matches with objective attribute target attribute according to average speed.Wherein, if average speed
Degree is greater than threshold speed, then judges that moving target is not matched that with objective attribute target attribute.For example, if the average speed of moving target is greater than
20m/s then may determine that the moving target is not pedestrian.Wherein, threshold speed can be adjusted by experiment.
In this embodiment, judge whether moving target matches with objective attribute target attribute according to the average speed of moving target,
Can filter significantly with the unmatched object of objective attribute target attribute, improve the accuracy rate of identification.
Fig. 3 is the flow diagram of one embodiment of the method for present invention identification moving target.It is moved in the embodiment
Target is illustrated by taking pedestrian as an example, method includes the following steps:
In step 310, pedestrian is identified and screened based on HOG characteristic value.
In step 320, the motion profile of pedestrian is recorded in same picture.
In step 330, the average speed of pedestrian is determined according to the adjacent two frame positions difference of pedestrian and time difference.
In step 340, judge that average speed is greater than threshold speed, if so, thening follow the steps 390, otherwise, executes step
350。
In step 350, the position attribution of each frame of pedestrian is determined.Position attribution is, for example, land, lake etc..It can basis
The position attribution of pedestrian judges whether pedestrian matches with objective attribute target attribute.
In step 360, judge whether position attribution is lake, if so, thening follow the steps 380, otherwise, executes step 370.
Since pedestrian will not walk on the water, if position attribution is lake, it may filter that the object.
In step 370, pedestrian's attribute is matched with objective attribute target attribute.
In step 380, pedestrian does not match that with objective attribute target attribute.
In this embodiment, using the average speed of moving target and position attribution judge moving target whether with target category
Property matches, and can be filtered with the unmatched object of objective attribute target attribute significantly, improve the accuracy rate of identification, and can greatly shortened
Processing speed enables video object track following to be applied in actual application.
Fig. 4 is the structural schematic diagram of one embodiment of the device of present invention identification moving target.The device includes track
Acquiring unit 410, speed computing unit 420 and target-recognition unit 430, in which:
Track acquiring unit 410 is used to obtain the motion profile of moving target.For example, as shown in Fig. 2, from t0From moment,
Record the position P (t of each frame of each moving targeti), obtain the motion profile of each moving target.
Speed computing unit 420 is used to determine the average speed of moving target according to motion profile.Due to knowing each fortune
The position of each frame of moving-target (moment) determines the average speed of moving target according to adjacent two frame positions difference and time difference.
Target-recognition unit 430 is used to judge whether moving target matches with objective attribute target attribute according to average speed.Wherein,
If average speed is greater than threshold speed, judge that moving target is not matched that with objective attribute target attribute.For example, if moving target is averaged
Speed is greater than 20m/s, then may determine that the moving target is not pedestrian.Wherein, threshold speed can be adjusted by experiment.
In this embodiment, judge whether moving target matches with objective attribute target attribute according to the average speed of moving target,
Can filter significantly with the unmatched object of objective attribute target attribute, improve the accuracy rate of identification.
Fig. 5 is the structural schematic diagram of another embodiment of the device of present invention identification moving target.The device includes mesh
Mark screening unit 510, track acquiring unit 520, speed computing unit 530 and target-recognition unit 540, in which:
Object filtering unit 510 is used to that moving target, such as pedestrian to be identified and screened based on HOG characteristic value.
Track acquiring unit 520 in same picture for recording the motion profile of pedestrian.
Speed computing unit 530 is used to determine the average speed of pedestrian according to the adjacent two frame positions difference of pedestrian and time difference
Degree.
Target-recognition unit 540 is for judging that average speed is greater than threshold speed, if average speed is greater than threshold speed,
Judge that moving target is not matched that with objective attribute target attribute.
The device can also include position attribution determination unit 550, for determining the position attribution of each frame of moving target.
Position attribution is, for example, land, lake etc..
Target-recognition unit 540 be also used to be judged according to the position attribution of moving target moving target whether with objective attribute target attribute
Match.For example, since pedestrian will not walk on the water, if position attribution is lake, it may filter that the object.
In this embodiment, using the average speed of moving target and position attribution judge moving target whether with target category
Property matches, and can be filtered with the unmatched object of objective attribute target attribute significantly, improve the accuracy rate of identification, and can greatly shortened
Processing speed enables video object track following to be applied in actual application.
Fig. 6 is the structural schematic diagram of the further embodiment of the device of present invention identification moving target.The device includes depositing
Reservoir 610 and processor 620.Wherein: memory 610 can be disk, flash memory or other any non-volatile memory mediums.It deposits
Reservoir is used to store Fig. 1, the instruction in embodiment corresponding to 3.Processor 620 is coupled to memory 610, can be used as one or
Multiple integrated circuits are implemented, such as microprocessor or microcontroller.The processor 620 is for executing the finger stored in memory
It enables.
It in one embodiment, can be as shown in fig. 7, the device 700 includes memory 710 and processor 720.Processing
Device 720 is coupled to memory 710 by BUS bus 730.The device 700 can also be connected to outside by memory interface 740 and deposit
Storage device 750 can also be connected to network or an other department of computer science to call external data by network interface 760
System (not shown), no longer describes in detail herein.
In this embodiment, it is instructed by memory stores data, then above-metioned instruction is handled by processor, can be improved
The accuracy rate of identification.
In another embodiment, a kind of computer readable storage medium, is stored thereon with computer program instructions, this refers to
Enable and realize Fig. 1 when being executed by processor, method in embodiment corresponding to 3 the step of.It should be understood by those skilled in the art that,
The embodiment of the present invention can provide as method, apparatus or computer program product.Therefore, complete hardware reality can be used in the present invention
Apply the form of example, complete software embodiment or embodiment combining software and hardware aspects.Moreover, the present invention can be used one
It is a or it is multiple wherein include computer usable program code computer can with non-transient storage medium (including but not limited to
Magnetic disk storage, CD-ROM, optical memory etc.) on the form of computer program product implemented.
The present invention be referring to according to the method for the embodiment of the present invention, the flow chart of equipment (system) and computer program product
And/or block diagram describes.It should be understood that each process in flowchart and/or the block diagram can be realized by computer program instructions
And/or the combination of the process and/or box in box and flowchart and/or the block diagram.It can provide these computer programs to refer to
Enable the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to generate
One machine so that by the instruction that the processor of computer or other programmable data processing devices executes generate for realizing
The device for the function of being specified in 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.
So far, the present invention is described in detail.In order to avoid covering design of the invention, it is public that this field institute is not described
The some details known.Those skilled in the art as described above, completely it can be appreciated how implementing technology disclosed herein
Scheme.
Although some specific embodiments of the invention are described in detail by example, the skill of this field
Art personnel it should be understood that above example merely to being illustrated, the range being not intended to be limiting of the invention.The skill of this field
Art personnel are it should be understood that can without departing from the scope and spirit of the present invention modify to above embodiments.This hair
Bright range is defined by the following claims.
Although some specific embodiments of the invention are described in detail by example, the skill of this field
Art personnel it should be understood that above example merely to being illustrated, the range being not intended to be limiting of the invention.The skill of this field
Art personnel are it should be understood that can without departing from the scope and spirit of the present invention modify to above embodiments.This hair
Bright range is defined by the following claims.
Claims (12)
1. a kind of method for identifying moving target characterized by comprising
Obtain the motion profile of moving target；
The average speed of the moving target is determined according to the motion profile；
Judge whether the moving target matches with objective attribute target attribute according to the average speed.
2. the method according to claim 1, wherein
If the average speed is greater than threshold speed, judge that the moving target is not matched that with objective attribute target attribute.
3. the method according to claim 1, wherein
The average speed of the moving target is determined according to the adjacent two frame positions difference of the moving target and time difference.
4. the method according to claim 1, wherein further include:
Determine the position attribution of each frame of the moving target；
Judge whether the moving target matches with objective attribute target attribute according to the position attribution of the moving target.
5. method according to claim 1 to 4, which is characterized in that further include:
The moving target is identified and screened based on HOG characteristic value.
6. a kind of device for identifying moving target characterized by comprising
Track acquiring unit, for obtaining the motion profile of moving target；
Speed computing unit, for determining the average speed of the moving target according to the motion profile；
Target-recognition unit, for judging whether the moving target matches with objective attribute target attribute according to the average speed.
7. device according to claim 6, which is characterized in that
If the target-recognition unit is greater than threshold speed for the average speed, the moving target and target category are judged
Property does not match that.
8. device according to claim 6, which is characterized in that
The speed computing unit is used to determine the movement according to the alternate position spike and time difference of adjacent two frame of the moving target
The average speed of target.
9. device according to claim 6, which is characterized in that further include:
Position attribution determination unit, for determining the position attribution of each frame of the moving target；
The target-recognition unit be also used to be judged according to the position attribution of the moving target moving target whether with mesh
Mark attribute matches.
10. according to any device of claim 6-9, which is characterized in that further include:
Object filtering unit, for identifying and screening the moving target based on HOG characteristic value.
11. a kind of device for identifying moving target characterized by comprising
Memory；And
It is coupled to the processor of the memory, the processor is configured to based on the instruction execution for being stored in the memory
Such as method described in any one of claim 1 to 5.
12. a kind of computer readable storage medium, is stored thereon with computer program instructions, real when which is executed by processor
The step of existing method described in any one of claim 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710759602.9A CN109427072A (en) | 2017-08-30 | 2017-08-30 | The method and apparatus for identifying moving target |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710759602.9A CN109427072A (en) | 2017-08-30 | 2017-08-30 | The method and apparatus for identifying moving target |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109427072A true CN109427072A (en) | 2019-03-05 |
Family
ID=65503795
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710759602.9A Pending CN109427072A (en) | 2017-08-30 | 2017-08-30 | The method and apparatus for identifying moving target |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109427072A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105046719A (en) * | 2015-07-03 | 2015-11-11 | 苏州科达科技股份有限公司 | Method and system for video monitoring |
| US20160365113A1 (en) * | 2015-06-12 | 2016-12-15 | JVC Kenwood Corporation | Playback device, playback method, and non-transitory recording medium |
| KR101697542B1 (en) * | 2016-07-29 | 2017-01-18 | 아스텔 주식회사 | Pulse doppler radar apparatus for motion detection using the same |
| CN106845352A (en) * | 2016-12-23 | 2017-06-13 | 北京旷视科技有限公司 | Pedestrian detection method and device |
-
2017
- 2017-08-30 CN CN201710759602.9A patent/CN109427072A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160365113A1 (en) * | 2015-06-12 | 2016-12-15 | JVC Kenwood Corporation | Playback device, playback method, and non-transitory recording medium |
| CN105046719A (en) * | 2015-07-03 | 2015-11-11 | 苏州科达科技股份有限公司 | Method and system for video monitoring |
| KR101697542B1 (en) * | 2016-07-29 | 2017-01-18 | 아스텔 주식회사 | Pulse doppler radar apparatus for motion detection using the same |
| CN106845352A (en) * | 2016-12-23 | 2017-06-13 | 北京旷视科技有限公司 | Pedestrian detection method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9754192B2 (en) | Object detection utilizing geometric information fused with image data | |
| Fernandez-Sanjurjo et al. | Real-time visual detection and tracking system for traffic monitoring | |
| CN106446150B (en) | A kind of method and device of vehicle precise search | |
| US9672634B2 (en) | System and a method for tracking objects | |
| US20160092727A1 (en) | Tracking humans in video images | |
| WO2013012091A1 (en) | Information processing apparatus, object tracking method, and program storage medium | |
| JP2012088881A (en) | Person motion detection device and program thereof | |
| KR101508310B1 (en) | Apparatus and method for tracking multiple moving objects in video surveillance system | |
| CN106446862A (en) | Face detection method and system | |
| CN104969261B (en) | For detecting the method and system of mobile object | |
| Liu et al. | Stochastic lane shape estimation using local image descriptors | |
| KR102116791B1 (en) | Apparatus, method and computer readable recording medium for detecting moving object using depth map | |
| CN110363790A (en) | Target tracking method, device and computer readable storage medium | |
| Liu et al. | A novel video forgery detection algorithm for blue screen compositing based on 3-stage foreground analysis and tracking | |
| CN106033613B (en) | Method for tracking target and device | |
| JP6713422B2 (en) | Learning device, event detection device, learning method, event detection method, program | |
| CN111753731A (en) | Face quality evaluation method, device and system and training method of face quality evaluation model | |
| CN109427072A (en) | The method and apparatus for identifying moving target | |
| US20180350102A1 (en) | Image processing apparatus, tracking method, and program | |
| Ha et al. | Improved Optical Flow Estimation In Wrong Way Vehicle Detection. | |
| Nayak et al. | Comparative analysis of different clustering techniques for video segmentation | |
| Hati et al. | Review and improvement areas of mean shift tracking algorithm | |
| Aye et al. | Salient object based action recognition using histogram of changing edge orientation (HCEO) | |
| Agrafiotis et al. | HDR Imaging for Enchancing People Detection and Tracking in Indoor Environments. | |
| Nagai et al. | 3D person tracking in world coordinates and attribute estimation with PDR |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190305 |