CN103065324A - Detection method and device of moving object - Google Patents
Detection method and device of moving object Download PDFInfo
- Publication number
- CN103065324A CN103065324A CN2012105396858A CN201210539685A CN103065324A CN 103065324 A CN103065324 A CN 103065324A CN 2012105396858 A CN2012105396858 A CN 2012105396858A CN 201210539685 A CN201210539685 A CN 201210539685A CN 103065324 A CN103065324 A CN 103065324A
- Authority
- CN
- China
- Prior art keywords
- image
- video camera
- light
- aperture
- moving object
- 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
Images
Landscapes
- Image Analysis (AREA)
- Studio Devices (AREA)
Abstract
The invention provides a detection method of a moving object. The detection method of the moving object comprises steps as below: obtaining a first image and a second image of an objective scene, wherein the first image is shot by a first aperture in a first shutter speed, the second image is shot by a second aperture in a second shutter speed; the first aperture is larger than the second aperture; the first shutter speed is faster than the second shutter speed; obtaining the absolute value of the difference value of each pixel point in the first image and the second image; when the absolute value is larger than the pre-set value, the corresponding pixel points are identified as objective pixels. The invention further provides a detection device of the moving object, and the detection device of the moving object is capable of improving real-time capability and reliability of the detection of the moving object.
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, people are more and more higher to the requirement of closed-circuit TV monitoring system, and intellectuality is also more and more used in the monitoring field.Place in some monitoring is higher to security requirement, need to carry out timely detection and tracking to the object of motion, so we needs some accurate image detecting technique that automatic alarm and target detection are provided.The motion detection conduct is in security protection intelligent Application field the earliest, and its technical development and application prospect all receive publicity.
Motion detection refers to the variation at appointed area energy recognition image, detects the existence of moving object and also avoids changing the interference that brings by light.But how from real-time sequence image, region of variation to be extracted from background image, also to consider the moving region effectively to cut apart for post-processed such as target classification, tracking be very important because later processing procedure is only considered in the image pixel corresponding to the moving region.Yet, because the dynamic change of background image, such as the impact of weather, illumination, shadow and chaotic interference etc., so that motion detection becomes the work of a difficult.
Present several methods commonly used
1. background subtraction (Background Subtraction)
The background subtraction method is a kind of method the most frequently used in the present motion detection, and it is to utilize the difference of present image and background image to detect a kind of technology of moving region.It generally can provide the most completely characteristic, but for the variation of dynamic scene, and is responsive especially such as the interference of illumination and external extraneous events etc.The simplest background model is the time average image, and most researchist is devoted to develop different background models at present, to reducing the dynamic scene variation for the impact of motion segmentation.
2. time difference (Temporal Difference)
Time difference (claiming again neighbor frame difference) method is to adopt between two or three consecutive frames based on the time difference of pixel and thresholding to extract moving region in the image in continuous image sequence.The time difference method for testing motion has stronger adaptivity for dynamic environment, but generally can not extract all relevant feature pixels fully, at the inner cavitation that easily produces of movement entity.
3. light stream (Optical Flow)
The motion detection of optical flow-based method has adopted the time dependent light stream characteristic of moving target, such as Meyer[2] etc. by coming initialization based on the track algorithm of profile in displacement calculating optical flow vector field, thereby effectively extract and the pursuit movement target.The advantage of the method is also can detect independently moving target under the prerequisite that camera motion exists.Yet, most optical flow computation method very complex, and noiseproof feature is poor, if there is not special hardware unit can not be applied to the real-time processing of full frame video stream.
Wherein, the neighbor frame difference method simply is used widely because of its algorithm, but traditional neighbor frame difference method needs continuous several two field pictures just can obtain moving target, and real-time is not high; Edge extracting for the movement entity slowly of moving is often sufficiently complete; Also easily produce the cavity in the inside of moving target, the cavity is that so cause this part to be cut off by difference, reliability is not high because there is the very approaching intersection of pixel in a certain large-scale moving object between its two frames.
Summary of the invention
The object of the invention is to propose a kind of moving target detecting method and device, can improve real-time and the reliability of moving object detection.
The scheme that adopts:
A kind of moving target detecting method comprises step:
Same visual angle obtains the first image and second image of purpose scene at one time;
Wherein, described the first image is taken with the first aperture the first shutter speed and is obtained; Described the second image is taken with the second aperture the second shutter speed and is obtained; Described the first aperture is greater than described the second aperture; Described the first shutter speed is greater than described the second shutter speed;
Obtain the absolute value of each pixel difference in described the first image and described the second image;
When described absolute value during greater than preset value, the sign corresponding pixel points is the moving target pixel.
And a kind of moving object detection device comprises:
The front end camera lens is for the light that obtains the purpose scene;
Light-dividing device is for the light that the light of described purpose scene is divided into some bundle same intensity;
The first video camera is used for the wherein light beam after the light splitting is taken;
The second video camera is used for the in addition light beam after the light splitting is taken; Wherein, the aperture of described the second video camera is less than the aperture of described the first video camera; The shutter speed of described the second video camera is less than the shutter speed of described the second video camera;
The moving object detection device is for obtaining described the first video camera and described the second video camera image in shooting; Obtain the absolute value of each pixel difference of the two field picture that described the first video camera and described the second video camera take at one time; When described absolute value during greater than predetermined value, the sign corresponding pixel points is the moving target pixel.
Among the present invention, obtain 2 kinds of images of the purpose scene at same same visual angle of time, wherein a kind of image is taken with normal aperture and shutter and is obtained, and the clear picture that obtains like this is sharp keen; Another kind of image is taken with less aperture and slower shutter and is obtained, and the image that obtains like this is fuzzyyer in the moving region, and stagnant zone is clear; Then these 2 kinds of images are carried out pixel relatively, when the absolute difference of pixel during greater than predetermined value, think that this pixel is the pixel of moving target; Like this can be complete determine the moving region, avoid the cavitation in the classic method, improved the reliability of moving object detection, simultaneously, can determine moving target in current image frame, improved real-time.
Description of drawings
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, same visual angle obtains the first image and second image of purpose scene at one time;
Wherein, the first image is taken with the first aperture the first shutter speed and is obtained; The second image is taken with the second aperture the second shutter speed and is obtained; The first aperture is greater than the second aperture; The first shutter speed is greater than the second shutter speed.
Generally speaking, the first aperture and the first shutter speed are all adjusted in advance by the normal parameter of capture apparatus, and this sentences first count and takes the photograph equipment and obtain the first image, can obtain clearly normal picture like this; Select aperture than the little equipment of the first capture apparatus as another capture apparatus; In advance the shutter speed of this another capture apparatus is transferred littlely than the shutter speed of the first capture apparatus, to obtain clearly rest image and fuzzy moving region image.
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 present 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 purpose scene at one time; The first image and the second image can be thought the same picture of Same Scene so; When comparing, the difference of each pixel comparison in the first image and the second image, actual is the difference comparison of each pixel in the two field picture; That is to say, this moment the first capture apparatus take obtain a two field picture, the second capture apparatus is taken and is obtained a two field picture, and the pixel value of the pixel of this 2 two field picture is carried out difference relatively.
For the image that different time is taken, repeat the difference of pixel value relatively.The reentry absolute value of pixel value of each pixel.
S3, when absolute value during greater than preset value, the sign corresponding pixel points is the moving target pixel.
Wherein, preset value is the numerical value that sets in advance, and can arrange according to those skilled in the art's experimental data, in general, can be set to 15.If the absolute value of the difference of certain any pixel value is then thought the pixel of moving target greater than this predetermined value, sign out in the first image.Because the first image is taken according to normal aperture and shutter speed, so should in the first image, identify, make things convenient for user's request.
During concrete judgement, can carry out as follows:
Judge | CF1 (x, y)-CF2 (x, y) | whether＞predetermined value is set up, and wherein, CF1 is the video image that the first capture apparatus is clapped, and CF2 is the video image that the second capture apparatus is clapped, and x, y are the pixel coordinates.
Among the present invention, obtain 2 kinds of images of the purpose scene at same same visual angle of time, wherein a kind of image is taken with normal aperture and shutter and is obtained, and the clear picture that obtains like this is sharp keen; Another kind of image is taken with less aperture and slower shutter and is obtained, and the image that obtains like this is fuzzyyer in the moving region, and stagnant zone is clear; Then these 2 kinds of images are carried out pixel relatively, when the absolute difference of pixel during greater than predetermined value, think that this pixel is the pixel of moving target; Like this can be complete determine the moving region, avoid the cavitation in the classic method, improved the reliability of moving object detection, simultaneously, can determine moving target in current image frame, improved real-time.
In order further to improve the reliability of moving object detection, behind step S1, before the step S2, comprising:
Be adjusted to the light sensitivity of the first image and the light sensitivity of the second image consistent.The purpose of doing like this is for so that stagnant zone does 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 end camera lens, light-dividing device, the first video camera, the second video camera and moving object detection device;
According to following requirement the moving object detection device is set in advance:
So that the light of purpose scene arrives light-dividing device by the front end camera 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 second camera alignment in addition light beam is taken.
Wherein, the effect of each several part is as follows:
The front end camera lens is for the light that obtains the purpose scene;
Light-dividing device is for the light that the light of purpose scene is divided into some bundle same intensity;
The first video camera is used for the wherein light beam after the light splitting is taken;
The second video camera is used for the in addition light beam after the light splitting is taken; 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 are all adjusted in advance by the normal parameter of capture apparatus, can obtain clearly normal picture like this; Select aperture less than the second video camera of the first video camera; In advance the shutter speed of the second video camera is transferred littlely than the shutter speed of the first video camera, to obtain clearly rest image and fuzzy moving region image.
The moving object detection device is 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 take at one time; When absolute value during greater than predetermined value, the sign corresponding pixel points is the 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 purpose scene at same same visual angle of time, wherein a kind of image is taken with normal aperture and shutter and is obtained, and the clear picture that obtains like this is sharp keen; Another kind of image is taken with less aperture and slower shutter and is obtained, and the image that obtains like this is fuzzyyer in the moving region, and stagnant zone is clear; Then these 2 kinds of images are carried out pixel relatively, when the absolute difference of pixel during greater than predetermined value, think that this pixel is the pixel of moving target; Like this can be complete determine the moving region, avoid the cavitation in the classic method, improved the reliability of moving object detection, simultaneously, can determine moving target in current image frame, improved real-time.
In order further to improve the reliability of moving object detection, carry out following improvement:
In the moving object detection device, the image light sensitivity furnishing of first the first video camera and the second video camera being taken is consistent; Then, obtain the absolute value of each pixel difference of the two field picture that the first video camera and the second video camera take at one time.
Or the light sensitivity with the first video camera is identical with the light sensitivity furnishing of the second video camera in advance.
The above embodiment has only expressed several embodiment of the present invention, and it describes comparatively concrete and detailed, but can not therefore be interpreted as the restriction to claim of the present invention.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 purpose scene at one time;
Wherein, described the first image is taken with the first aperture the first shutter speed and is obtained; Described the second image is taken with the second aperture the second shutter speed and is obtained; Described the first aperture is greater than described the second aperture; Described the first shutter speed is greater than described the second shutter speed;
Obtain the absolute value of each pixel difference in described the first image and described the second image;
When described absolute value during greater than preset value, the sign corresponding pixel points is the moving target pixel.
2. moving target detection method according to claim 1 is characterized in that,
Obtain the step of the first image of purpose scene and the second image at described at one time same visual angle after, before the described step of obtaining the absolute value of each pixel difference in described the first image and described the second image, comprising:
Be adjusted to the light sensitivity of described the first image and the light sensitivity of described the second image consistent.
3. a moving object detection device is characterized in that, comprising:
The front end camera lens is for the light that obtains the purpose scene;
Light-dividing device is for the light that the light of described purpose scene is divided into some bundle same intensity;
The first video camera is used for the wherein light beam after the light splitting is taken;
The second video camera is used for the in addition light beam after the light splitting is taken; Wherein, the aperture of described the second video camera is less than the aperture of described the first video camera; The shutter speed of described the second video camera is less than the shutter speed of described the second video camera;
The moving object detection device is for obtaining described the first video camera and described the second video camera image in shooting; Obtain the absolute value of each pixel difference of the two field picture that described the first video camera and described the second video camera take at one time; When described absolute value during greater than predetermined value, the sign corresponding pixel points is the moving target pixel.
4. moving object detection device according to claim 3 is characterized in that,
Described moving object detection device is consistent with the image light sensitivity furnishing that described the first video camera and described the second video camera are taken first; Then, obtain the absolute value of each pixel difference of the two field picture that described the first video camera and described the second video camera take at one time.
5. moving object detection device according to claim 3 is characterized in that, the light sensitivity of described the first video camera is identical with the light sensitivity of described the second video camera.
6. according to claim 3 to 5 each described moving object detection devices, it 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 true CN103065324A (en) | 2013-04-24 |
| CN103065324B 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) |
Cited By (2)
| 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 |
| CN113129242A (en) * | 2019-12-31 | 2021-07-16 | 北京中安未来科技有限公司 | Image identification triggering method and device |
Citations (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 |
| EP1368971A2 (en) * | 2001-03-15 | 2003-12-10 | Konstantinidis Apostolos | System for multiple viewpoint video signal recording and reproduction |
| CN102572245A (en) * | 2011-12-22 | 2012-07-11 | 深圳市赛格导航科技股份有限公司 | Method and device for extending image dynamic ranges |
| CN102740082A (en) * | 2011-04-01 | 2012-10-17 | 佳能株式会社 | Image processing apparatus and control method thereof |
-
2012
- 2012-12-13 CN CN201210539685.8A patent/CN103065324B/en not_active Expired - Fee Related
Patent Citations (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 |
| EP1368971A2 (en) * | 2001-03-15 | 2003-12-10 | Konstantinidis Apostolos | System for multiple viewpoint video signal recording and reproduction |
| CN102740082A (en) * | 2011-04-01 | 2012-10-17 | 佳能株式会社 | Image processing apparatus and control method thereof |
| CN102572245A (en) * | 2011-12-22 | 2012-07-11 | 深圳市赛格导航科技股份有限公司 | Method and device for extending image dynamic ranges |
Cited By (2)
| 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 |
| CN113129242A (en) * | 2019-12-31 | 2021-07-16 | 北京中安未来科技有限公司 | Image identification triggering method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103065324B (en) | 2016-03-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110049206B (en) | Image processing method, image processing apparatus, and computer-readable storage medium | |
| CN103824070B (en) | A kind of rapid pedestrian detection method based on computer vision | |
| EP3088910A1 (en) | Method and system for tracking moving trajectory based on human features | |
| CN102799883A (en) | Method and device for extracting movement target from video image | |
| Fan et al. | Modeling of temporarily static objects for robust abandoned object detection in urban surveillance | |
| CN105760846A (en) | Object detection and location method and system based on depth data | |
| Bouma et al. | Real-time tracking and fast retrieval of persons in multiple surveillance cameras of a shopping mall | |
| CN105046719B (en) | A kind of video frequency monitoring method and system | |
| CN101715070B (en) | Method for automatically updating background in specifically monitored video | |
| CN204305213U (en) | The interactive sighting device of multi-cam human body tracking | |
| Karpagavalli et al. | Estimating the density of the people and counting the number of people in a crowd environment for human safety | |
| Cai et al. | Intelligent video analysis-based forest fires smoke detection algorithms | |
| CN109948474A (en) | AI thermal imaging all-weather intelligent monitoring method | |
| Liang et al. | Methods of moving target detection and behavior recognition in intelligent vision monitoring. | |
| CN109658437A (en) | A kind of method and device of quick detection moving object | |
| CN101719280A (en) | Method for detecting petty infrared target | |
| Tao et al. | Real-time detection and tracking of moving object | |
| CN103065324B (en) | A kind of moving target detecting method and device | |
| Dong et al. | Adaptive Object Detection and Visibility Improvement in Foggy Image. | |
| Patel et al. | Human tracking in video surveillance | |
| Luo et al. | A real-time people counting approach in indoor environment | |
| Karamiani et al. | Detecting and tracking moving objects in video sequences using moving edge features | |
| NL2025625B1 (en) | System and method for detecting flickering target based on moving camera in specific environment | |
| Li et al. | A shadow detection method based on improved Gaussian Mixture Model | |
| Hatimi et al. | New approach for detecting and tracking a moving object |
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 | ||
| 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. |
|
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20160330 Termination date: 20211213 |