CN103065324B - A kind of moving target detecting method and device - Google Patents
A kind of moving target detecting method and device Download PDFInfo
- Publication number
- CN103065324B CN103065324B CN201210539685.8A CN201210539685A CN103065324B CN 103065324 B CN103065324 B CN 103065324B CN 201210539685 A CN201210539685 A CN 201210539685A CN 103065324 B CN103065324 B CN 103065324B
- Authority
- CN
- China
- Prior art keywords
- image
- video camera
- shutter speed
- aperture
- light
- 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.)
- Expired - Fee Related
Links
Landscapes
- Image Analysis (AREA)
- Studio Devices (AREA)
Abstract
The present invention proposes a kind of moving target detecting method, comprises step: same visual angle obtains the first image and second image of object scene at one time; Wherein, described first image obtains with the first aperture first shutter speed shooting; Described second image obtains with the second aperture second shutter speed shooting; Described first aperture is greater than described second aperture; Described first shutter speed is greater than described second shutter speed; Obtain the absolute value of each pixel difference in described first image and described second image; When described absolute value is greater than preset value, mark corresponding pixel points is moving target pixel.The present invention also proposes a kind of moving object detection device, can improve real-time and the reliability of moving object detection.
Description
Technical field
The present invention relates to image processing field, particularly relate to a kind of moving target detecting method and device.
Background technology
Along with the develop rapidly of technology, the requirement of people to closed-circuit TV monitoring system is more and more higher, and intellectuality is also more and more applied in monitoring field.Higher to security requirement in the place of some monitoring, need to carry out detection and tracking timely to the object of motion, therefore we need some accurate image detecting technique to provide automatic alarm and target detection.Motion detects as in security protection intelligent Application field the earliest, and its technical development and application prospect all receive publicity.
Motion detects the change referred at appointed area energy recognition image, detects the existence of moving object and avoids changing by light the interference brought.But how from real-time sequence image, region of variation to be extracted from background image, also to consider that effective segmentation of moving region is very important for the post-processed such as target classification, tracking, because later processing procedure only considers the pixel corresponding to moving region in image.But due to the dynamic change of background image, as the impact of weather, illumination, shadow and chaotic interference etc., make to move the work detecting and become a suitable difficulty.
Current several conventional method
1. background subtraction (BackgroundSubtraction)
Background subtraction method is a kind of method that motion is the most frequently used in detecting at present, and it utilizes the difference of present image and background image to detect a kind of technology of moving region.It generally can provide characteristic the most completely, but for the change of dynamic scene, and the interference etc. as illumination and external extraneous events is responsive especially.The simplest background model is time average image, and most researchist is devoted to develop different background models at present, to reducing the impact of dynamic scene change for motion segmentation.
2. time difference (TemporalDifference)
Time difference (also known as neighbor frame difference) method in continuous print image sequence, adopts the time difference based on pixel between two or three consecutive frames and thresholding extracts the moving region in image.Time difference method for testing motion has stronger adaptivity for dynamic environment, but generally can not extract all relevant feature pixels completely, easily produces cavitation in movement entity inside.
3. light stream (OpticalFlow)
Motion based on optical flow approach detects and have employed the time dependent light stream characteristic of moving target, as Meyer [2] etc. carrys out the track algorithm of initialization based on profile by displacement calculating optical flow vector field, thus effectively extracts and pursuit movement target.The advantage of the method also can detect independently moving target under the prerequisite of camera motion existence.But most optical flow computation method is quite complicated, and noiseproof feature is poor, if there is no special hardware unit, the real-time process of full frame video stream can not be applied to.
Wherein, neighbor frame difference method is simply used widely because of its algorithm, but traditional neighbor frame difference method needs a few two field picture of continuous print to obtain moving target, and real-time is not high; Edge extracting for the movement entity slowly of moving is often sufficiently complete; Also the easy inside at moving target produces cavity, and cavity is due to a certain large-scale moving object, there is the very close intersection of pixel between its two frames, so cause this part to be cut off by difference, reliability is not high.
Summary of the invention
The object of the invention is to propose a kind of moving target detecting method and device, real-time and the reliability of moving object detection can be improved.
The scheme adopted:
A kind of moving target detecting method, comprises step:
Same visual angle obtains the first image and second image of object scene at one time;
Wherein, described first image obtains with the first aperture first shutter speed shooting; Described second image obtains with the second aperture second shutter speed shooting; Described first aperture is greater than described second aperture; Described first shutter speed is greater than described second shutter speed;
Obtain the absolute value of each pixel difference in described first image and described second image;
When described absolute value is greater than preset value, mark corresponding pixel points is moving target pixel.
And a kind of moving object detection device, comprising:
Front lens, for obtaining the light of object scene;
Light-dividing device, for being divided into the light of some bundle same intensity by the light of described object scene;
First video camera, for taking the wherein light beam after light splitting;
Second video camera, for taking the another light beam after light splitting; Wherein, the aperture of described second video camera is less than the aperture of described first video camera; The shutter speed of described second video camera is less than the shutter speed of described second video camera;
Moving object detection device, for obtaining described first video camera and the described second video camera image in shooting; Obtain the absolute value of each pixel difference of the two field picture that described first video camera and described second video camera are taken at one time; When described absolute value is greater than predetermined value, mark corresponding pixel points is moving target pixel.
In the present invention, obtain 2 kinds of images of the object scene at same visual angle of same time, wherein a kind of image obtains with normal aperture and shutter shooting, and the clear picture obtained like this is sharp keen; Another kind of image obtains with less aperture and the shooting of slower shutter, and the image obtained like this is fuzzyyer in moving region, and stagnant zone is clear; Then carry out pixel to these 2 kinds of images to compare, when the absolute difference of pixel is greater than predetermined value, think that this pixel is the pixel of moving target; Like this can be complete determine moving region, avoid the cavitation in classic method, improve the reliability of moving object detection, meanwhile, moving target can be determined in current image frame, improve real-time.
Accompanying drawing explanation
Fig. 1 is a process flow diagram of the inventive method;
Fig. 2 is a structural representation of apparatus of the present invention.
Embodiment
As shown in Figure 1, the moving target detecting method that the present invention proposes, comprises following flow process:
S1, at one time same visual angle obtain the first image and second image of object scene;
Wherein, the first image obtains with the first aperture first shutter speed shooting; Second image obtains with the second aperture second shutter speed shooting; First aperture is greater than the second aperture; First shutter speed is greater than the second shutter speed.
Generally speaking, the first aperture and the first shutter speed all adjust in advance by the normal parameter of capture apparatus, and this sentences first count and takes the photograph equipment to obtain the first image, can obtain normal picture clearly like this; Select the aperture equipment less than the first capture apparatus as another capture apparatus; In advance the shutter speed of this another capture apparatus is adjusted less than the shutter speed of the first capture apparatus, to obtain rest image and fuzzy moving region image clearly.
Although the shutter speed of the first capture apparatus is faster than the shutter speed of the second capture apparatus, in view of the slowest shutter speed of current general capture apparatus is 1/50 second, namely 0.02 second.Because the time is very short, what can think that two capture apparatus take at one time is same picture.
S2, obtain the absolute value of each pixel difference in the first image and the second image;
Because step S1 is that same visual angle acquires the first image and second image of object scene at one time; So the first image and the second image can think the same picture of Same Scene; When comparing, the difference comparsion of each pixel in the first image and the second image, actual is the difference comparsion of each pixel in a two field picture; In other words, now the first capture apparatus shooting obtains a two field picture, the second capture apparatus shooting obtains a two field picture, and the pixel value of the pixel of this 2 two field picture is carried out difference comparsion.
For the image of different time shooting, repeat the difference comparsion of pixel value.To reentry the absolute value of pixel value of each pixel.
S3, when absolute value is greater than preset value, mark corresponding pixel points be moving target pixel.
Wherein, preset value is the numerical value pre-set, and can arrange according to the experimental data of those skilled in the art, in general, can be set to 15.If the absolute value of the difference of certain any pixel value is greater than this predetermined value, then thinks the pixel of moving target, identify out in the first image.Because the first image, according to normal aperture and shutter speed shooting, so should identify in the first image, facilitates user's request.
During concrete judgement, can carry out as follows:
Judge | CF1 (x, y)-CF2 (x, y) | whether > predetermined value is set up, wherein, the video image that CF1 claps for the first capture apparatus, the video image that CF2 claps for the second capture apparatus, x, y are pixel coordinates.
In the present invention, obtain 2 kinds of images of the object scene at same visual angle of same time, wherein a kind of image obtains with normal aperture and shutter shooting, and the clear picture obtained like this is sharp keen; Another kind of image obtains with less aperture and the shooting of slower shutter, and the image obtained like this is fuzzyyer in moving region, and stagnant zone is clear; Then carry out pixel to these 2 kinds of images to compare, when the absolute difference of pixel is greater than predetermined value, think that this pixel is the pixel of moving target; Like this can be complete determine moving region, avoid the cavitation in classic method, improve the reliability of moving object detection, meanwhile, moving target can be determined in current image frame, improve real-time.
In order to improve the reliability of moving object detection further, after step S1, before step S2, comprising:
The light sensitivity of the first image is adjusted to consistent with the light sensitivity of the second image.The object done like this is to make stagnant zone not have significant difference in the first image and the second image.
The present invention also proposes a kind of moving object detection device, comprising: front lens, light-dividing device, the first video camera, the second video camera and moving object detection device;
In advance moving object detection device is set according to following requirement:
Make the light of object scene arrive light-dividing device by front lens, these light obtain the light of some bundle same intensity by light-dividing device, and the first camera alignment wherein light beam is taken, and the another light beam of the second camera alignment is taken.
Wherein, the effect of each several part is as follows:
Front lens, for obtaining the light of object scene;
Light-dividing device, for being divided into the light of some bundle same intensity by the light of object scene;
First video camera, for taking the wherein light beam after light splitting;
Second video camera, for taking the another light beam after light splitting; Wherein, the aperture of the second video camera is less than the aperture of the first video camera; The shutter speed of the second video camera is less than the shutter speed of the second video camera; Generally speaking, the aperture of the first video camera and shutter speed all adjust in advance by the normal parameter of capture apparatus, can obtain normal picture clearly like this; Aperture is selected to be less than the second video camera of the first video camera; In advance the shutter speed of the second video camera is adjusted less than the shutter speed of the first video camera, to obtain rest image and fuzzy moving region image clearly.
Moving object detection device, for obtaining the first video camera and the second video camera image in shooting; Obtain the absolute value of each pixel difference of the two field picture that the first video camera and the second video camera are taken at one time; When absolute value is greater than predetermined value, mark corresponding pixel points is moving target pixel.
One of them structural representation please refer to Fig. 2, utilizes spectroscope as light-dividing device, but this light-dividing device is not limited to spectroscope.Utilize apparatus of the present invention to obtain 2 kinds of images of the object scene at same visual angle of same time, wherein a kind of image obtains with normal aperture and shutter shooting, and the clear picture obtained like this is sharp keen; Another kind of image obtains with less aperture and the shooting of slower shutter, and the image obtained like this is fuzzyyer in moving region, and stagnant zone is clear; Then carry out pixel to these 2 kinds of images to compare, when the absolute difference of pixel is greater than predetermined value, think that this pixel is the pixel of moving target; Like this can be complete determine moving region, avoid the cavitation in classic method, improve the reliability of moving object detection, meanwhile, moving target can be determined in current image frame, improve real-time.
In order to improve the reliability of moving object detection further, improve as follows:
In moving object detection device, first that the first video camera is consistent with the image sensitive degree furnishing that the second video camera is taken; Then, the absolute value of each pixel difference of the two field picture that the first video camera and the second video camera are taken at one time is obtained.
Or, in advance that the light sensitivity of the first video camera is identical with the light sensitivity furnishing of the second video camera.
The above embodiment only have expressed several embodiment of the present invention, and it describes comparatively concrete and detailed, but therefore can not be interpreted as the restriction to the scope of the claims of the present invention.It should be pointed out that for the person of ordinary skill of the art, without departing from the inventive concept of the premise, can also make some distortion and improvement, these all belong to protection scope of the present invention.Therefore, the protection domain of patent of the present invention should be as the criterion with claims.
Claims (6)
1. a moving target detecting method, is characterized in that, comprises step:
Same visual angle obtains the first image and second image of object scene at one time;
Wherein, described first image obtains with the first aperture first shutter speed shooting; Described second image obtains with the second aperture second shutter speed shooting; Described first aperture is greater than described second aperture; Described first shutter speed is greater than described second shutter speed; First aperture and the first shutter speed all adjust in advance by the normal parameter of capture apparatus, utilize described first capture apparatus to obtain the first image; Select the aperture equipment less than the first capture apparatus as the second capture apparatus, in advance the shutter speed of this second capture apparatus is adjusted less than the shutter speed of the first capture apparatus, described second capture apparatus is utilized to obtain rest image and fuzzy moving region image clearly, wherein, described second capture apparatus obtains rest image and fuzzy moving region image is clearly the second image;
Obtain the absolute value of each pixel difference in described first image and described second image;
When described absolute value is greater than preset value, mark corresponding pixel points is moving target pixel.
2. moving target detecting method according to claim 1, is characterized in that,
After described same visual angle at one time obtains the first image of object scene and the step of the second image, in described first image of described acquisition and described second image the absolute value of each pixel difference step before, comprising:
The light sensitivity of described first image is adjusted to consistent with the light sensitivity of described second image.
3. a moving object detection device, is characterized in that, comprising:
Front lens, for obtaining the light of object scene;
Light-dividing device, for being divided into the light of some bundle same intensity by the light of described object scene;
First video camera, for taking the wherein light beam after light splitting;
Second video camera, for taking the another light beam after light splitting; Wherein, the aperture of described second video camera is less than the aperture of described first video camera; The shutter speed of described second video camera is less than the shutter speed of described second video camera; The aperture of the first video camera and shutter speed all adjust in advance by the normal parameter of capture apparatus, obtain normal picture clearly; Aperture is selected to be less than the second video camera of the first video camera; In advance the shutter speed of the second video camera is adjusted less than the shutter speed of the first video camera, to obtain rest image and fuzzy moving region image clearly;
Moving object detection device, for obtaining described first video camera and the described second video camera image in shooting; Obtain the absolute value of each pixel difference of the two field picture that described first video camera and described second video camera are taken at one time; When described absolute value is greater than predetermined value, mark corresponding pixel points is moving target pixel.
4. moving object detection device according to claim 3, is characterized in that,
Described moving object detection device is first consistent with the image sensitive degree furnishing of described second video camera shooting by described first video camera; Then, the absolute value of each pixel difference of the two field picture that described first video camera and described second video camera are taken at one time is obtained.
5. moving object detection device according to claim 3, is characterized in that, the light sensitivity of described first video camera is identical with the light sensitivity of described second video camera.
6. the moving object detection device according to any one of claim 3 to 5, is characterized in that, described light-dividing device is spectroscope.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210539685.8A CN103065324B (en) | 2012-12-13 | 2012-12-13 | A kind of moving target detecting method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210539685.8A CN103065324B (en) | 2012-12-13 | 2012-12-13 | A kind of moving target detecting method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103065324A CN103065324A (en) | 2013-04-24 |
| CN103065324B true CN103065324B (en) | 2016-03-30 |
Family
ID=48107941
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210539685.8A Expired - Fee Related CN103065324B (en) | 2012-12-13 | 2012-12-13 | A kind of moving target detecting method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103065324B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109255798A (en) * | 2018-09-18 | 2019-01-22 | 中国矿业大学 | Monitoring alarm method is used in a kind of safety in production |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4971409A (en) * | 1989-04-24 | 1990-11-20 | Rockwell International Corporation | Real-time optical image subtraction |
| GR1004309B (en) * | 2001-03-15 | 2003-08-28 | . | System and method of multi-camera recording of images and simultaneous transmission thereof to a television or cinema system |
| JP5791336B2 (en) * | 2011-04-01 | 2015-10-07 | キヤノン株式会社 | Image processing apparatus and control method thereof |
| CN102572245B (en) * | 2011-12-22 | 2014-12-17 | 深圳市赛格导航科技股份有限公司 | Method and device for extending image dynamic ranges |
-
2012
- 2012-12-13 CN CN201210539685.8A patent/CN103065324B/en not_active Expired - Fee Related
Also Published As
| Publication number | Publication date |
|---|---|
| CN103065324A (en) | 2013-04-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Tian et al. | Robust and efficient foreground analysis for real-time video surveillance | |
| Jain et al. | Real-time upper-body human pose estimation using a depth camera | |
| CN102542289B (en) | Pedestrian volume statistical method based on plurality of Gaussian counting models | |
| CA2692424C (en) | System and process for detecting, tracking and counting human objects of interest | |
| WO2020215552A1 (en) | Multi-target tracking method, apparatus, computer device, and storage medium | |
| CN103997624B (en) | Overlapping domains dual camera Target Tracking System and method | |
| CN105760846A (en) | Object detection and location method and system based on depth data | |
| CN101699862A (en) | High-resolution region-of-interest image acquisition method of PTZ camera | |
| CN103150549A (en) | Highway tunnel fire detecting method based on smog early-stage motion features | |
| Lengvenis et al. | Application of computer vision systems for passenger counting in public transport | |
| CN101715070B (en) | Method for automatically updating background in specifically monitored video | |
| WO2020114116A1 (en) | Pedestrian detection method based on dense crowds, and storage medium and processor | |
| Karpagavalli et al. | Estimating the density of the people and counting the number of people in a crowd environment for human safety | |
| CN106778488B (en) | Low-light (level) smog video detecting method based on image correlation | |
| CN107862713A (en) | Video camera deflection for poll meeting-place detects method for early warning and module in real time | |
| CN105913464A (en) | Multi-body target online measurement method based on videos | |
| CN101719280B (en) | Method for detecting petty infrared target | |
| CN109658437A (en) | A kind of method and device of quick detection moving object | |
| CN103049748A (en) | Behavior-monitoring method and behavior-monitoring system | |
| Tao et al. | Real-time detection and tracking of moving object | |
| CN103065324B (en) | A kind of moving target detecting method and device | |
| CN104200455A (en) | Key posture extraction method based on motion statistical feature analysis | |
| CN106650639A (en) | Monitoring system pedestrian re-identification method suitable for security and protection | |
| Qiuyu et al. | Design and implementation of video-based detection system for wharf ship | |
| Luo et al. | A real-time people counting approach in indoor environment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address |
Address after: 510670 Guangdong Province, Guangzhou high tech Industrial Development Zone Kezhu Road No. 233 Patentee after: VTRON GROUP Co.,Ltd. Address before: 510663 Guangzhou province high tech Industrial Development Zone, Guangdong, Cai road, No. 6, No. Patentee before: VTRON TECHNOLOGIES Ltd. |
|
| CP03 | Change of name, title or address | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20160330 Termination date: 20211213 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |