CN101494772A - Method and apparatus for detecting image - Google Patents
Method and apparatus for detecting image Download PDFInfo
- Publication number
- CN101494772A CN101494772A CNA2009100774815A CN200910077481A CN101494772A CN 101494772 A CN101494772 A CN 101494772A CN A2009100774815 A CNA2009100774815 A CN A2009100774815A CN 200910077481 A CN200910077481 A CN 200910077481A CN 101494772 A CN101494772 A CN 101494772A
- Authority
- CN
- China
- Prior art keywords
- information
- target
- detected
- image
- demarcation
- 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
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000001514 detection method Methods 0.000 claims abstract description 73
- 238000010606 normalization Methods 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 9
- 238000012360 testing method Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 abstract description 11
- 238000012806 monitoring device Methods 0.000 abstract 2
- 238000003384 imaging method Methods 0.000 description 11
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000007423 decrease Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007429 general method Methods 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- GOLXNESZZPUPJE-UHFFFAOYSA-N spiromesifen Chemical compound CC1=CC(C)=CC(C)=C1C(C(O1)=O)=C(OC(=O)CC(C)(C)C)C11CCCC1 GOLXNESZZPUPJE-UHFFFAOYSA-N 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Landscapes
- Image Analysis (AREA)
Abstract
The present invention provides an image detection method and device. The method includes: a first step, obtaining the monitoring video data of the monitoring device; a second step, obtaining the calibration information of the monitoring device and the true form information of the target to be detected; and a third step, obtaining the form and size information of the target to be detected at the detection position based on the detection position in the target to be detected of the video data, the calibration information and the true form information. The invention is an image detection method based on single-view calibration, which can determine the size and form of the target to be detected at the detection position.
Description
Technical field
The present invention relates to camera calibration and intelligent video monitoring field, particularly a kind of method and device of image detection of demarcating based on single-view.
Background technology
In present widely used intelligent video monitoring, usually need to know position and size in image after specific objective (as car, human body, the people the is first-class) imaging based on single-view.But according to image-forming principle, the identical target range projection centre not size of imaging simultaneously is also different, distance imaging is more little more, the target detection based on statistics causes very big trouble in the intelligent video monitoring so this phenomenon can be given, this is because if do not know size behind the target imaging, algorithm of target detection based on statistics will be searched for image at different yardsticks, will cause algorithm operation quantity to increase like this, can't reach the effect of real-time detection.
For the speed of accelerating to detect, present accelerated method commonly used is the method for motion detection, comprising: at first determine the moving region, divide yardstick to search for then in the moving region.Though this accelerated method can Intelligent Measurement arrive moving object, can't detect static target, but also be to need to divide yardstick to search for.Other accelerated method also comprises the respective function model roughly of setting up an imageable target size and image line information and simplifies statistical nature.The method of setting up the respective function model can only roughly calculate the size of target diverse location in image, and what can cause detecting is inaccurate.The method of simplifying statistical nature then can cause the decline of verification and measurement ratio.
Therefore, in the target detection based on statistics, how determining size and the shape of target in the detection position, so that directly carry out the search of corresponding yardstick, accelerate the speed of target detection, is that problem to be solved is arranged.
Summary of the invention
The purpose of the embodiment of the invention provides a kind of method and device of image detection, can determine size and the shape of target to be detected in the detection position.
To achieve these goals, on the one hand, provide a kind of method of image detection, comprised the steps:
Step 1, the monitor video data of acquisition watch-dog;
Step 2 obtains the demarcation information of described watch-dog and the true form information of detected target;
Step 3 according to the detection position in the image to be detected of described video data, described demarcation information and described true form information, is obtained shape and the dimension information of described detected target in described detection position.
Preferably, in the above-mentioned method, also comprise,
Step 4 in the target detection process based on statistics, is carried out the target search of corresponding yardstick according to described shape and dimension information.
Preferably, in the above-mentioned method, described demarcation information comprises: the line vector that goes out after the normalization
And the vanishing point vector v on the vertical direction; Actual height Z that described true form information is described detected target and actual length-width ratio, described detection position are the top coordinate t of described detected target in described image to be detected.
Preferably, in the above-mentioned method, described step 3 specifically comprises:
Utilize formula:
Calculate the bottom coordinate b of described detected target in described image to be detected, wherein the priori value of parameter alpha for obtaining by test;
According to the difference of top coordinate t and bottom coordinate b, obtain the picture altitude h of described detected target in described image to be detected;
According to described picture altitude h and described actual length-width ratio, determine described shape and the dimension information of described detected target in described detection position.
Preferably, in the above-mentioned method, described parameter alpha obtains in the following way: measure the top coordinate t and the bottom coordinate b of the known target in the known image of described video data, and the line vector that will go out
The actual height Z of vanishing point vector v and described known target brings described formula into and obtains described parameter alpha.
Preferably, in the above-mentioned method, in described step 2, described demarcation information is the Given information of storing in the described watch-dog; Perhaps,
Obtain described demarcation information in the following way: from described video data, obtain the geological information of demarcating usefulness, calculate described demarcation information according to described geological information.
Preferably, in the above-mentioned method, described geological information comprises: parallel to the ground but two pairs of parallel lines that direction is inequality, and perpendicular to the pair of parallel line on ground.
Another aspect of the present invention provides a kind of device of image detection, comprising:
Data acquisition module is used for: the monitor video data that obtain watch-dog;
Demarcation information acquisition module is used for: the demarcation information that obtains described watch-dog;
True form information acquisition module is used for: the true form information that obtains detected target;
Computing module is used for: according to detection position, described demarcation information and the described true form information of the image to be detected of described video data, obtain shape and the dimension information of described detected target in described detection position.
Preferably, in the above-mentioned device, detection module is used for: in the target detection process based on statistics, carry out the target search of corresponding yardstick according to described shape and dimension information.
Preferably, in the above-mentioned device, described computing module passes through formula
Calculate the bottom coordinate b of described detected target in described image to be detected, wherein α is the priori value by the test acquisition, and Z is the actual height of described detected target, and t is the top coordinate of described detected target in described image to be detected,
Be the line vector that goes out after the normalization, v is the vanishing point vector on the vertical direction.
Preferably, in the above-mentioned device, described demarcation information acquisition module comprises:
The geological information extraction unit is used for obtaining the geological information of demarcating usefulness from described video data, and described geological information comprises: parallel to the ground but two pairs of parallel lines that direction is inequality, and perpendicular to the pair of parallel line on ground;
Demarcate the unit, be used for according to the line vector that goes out after the described geological information acquisition normalization
And the vanishing point vector v on the vertical direction.
Preferably, in the above-mentioned device, described true form information acquisition module also includes memory cell, and described cell stores has the actual height and the actual length-width ratio of multiple target to be detected.
Preferably, in the above-mentioned device, described multiple target to be detected comprises personnel targets and vehicle target, the actual height of described personnel targets is set at the assembly average of personnel's height, the assembly average of described personnel's height is the arbitrary value between 165 centimetres to 175 centimetres, and the actual length-width ratio of described personnel targets is set at the assembly average of personnel's length-width ratio.
There is following technique effect at least in the embodiment of the invention:
1) embodiment of the invention is that the application of demarcating based on single-view is expanded, can be according to the demarcation information of single-view and the true form information of detected target, inverse goes out shape and the dimension information of detected target in the detection position, has just obtained shape and dimension information after the real goal projection imaging.
2) the embodiment of the invention detected target that will obtain is applied to target detection process based on statistics at the shape of detection position and dimension information, carry out the target search of corresponding yardstick according to described shape and dimension information, reduce amount of calculation, accelerated detection speed.
3) embodiment of the invention to real goal (such as car, the people is first-class) true form information store in advance, because same classification target shape size is relatively more consistent, so average shape value that the embodiment of the invention has been inhomogeneous goal-setting, can be applied directly to the detection target of corresponding types, and ensure accuracy of detection.
Description of drawings
The flow chart of steps of the method that Fig. 1 provides for the embodiment of the invention;
The schematic diagram of the shape of the actual object that Fig. 2 provides for the embodiment of the invention;
The structure chart of the device that Fig. 3 provides for the embodiment of the invention.
Embodiment
For the purpose, technical scheme and the advantage that make the embodiment of the invention is clearer, specific embodiment is described in detail below in conjunction with accompanying drawing.
At present, the demarcation of single-view imaging has been had a lot of researchs, the typical geological information (as parallel lines, right angle etc.) that most research all is based in the image calculates some or all of calibrating parameters.The application of demarcating based on single-view mainly is the three-dimensional reconstruction of regular building or the true altitude of calculating target according to the positional information of target in image etc.
The application that the embodiment of the invention is demarcated based on single-view is expanded.With above-mentioned to calculate three-dimensional information according to image information different, the embodiment of the invention a kind of method of calculating shape behind the target imaging according to Three-dimension Target information of having derived.Can be used for assisting target detection, accelerate the speed of target detection based on statistics.
The flow chart of steps of the method that Fig. 1 provides for the embodiment of the invention, the method of the image detection of the embodiment of the invention, the image object shape that is based on the single-view demarcation is determined method, can obtain the target shape information of optional position in the monitor video image, as shown in Figure 1, method comprises:
Determine shape and the dimension information of detected target, just can directly carry out the search of corresponding yardstick, in target detection process, just can reduce the yardstick of search like this, significantly reduce amount of calculation, accelerate detection speed based on statistics in described detection position.
Therefore, when the target detection that the present invention is applied to based on statistics, also comprise: in target detection process, carry out the target search of corresponding yardstick according to described shape and dimension information based on statistics.
In an embodiment of the present invention, true form information and demarcation information are to calculate detected target on the shape of detection position and the basis of dimension information (shape after the real goal projection imaging just and dimension information), because real goal is (such as car, the people is first-class) true form information be known, and same classification target shape size is relatively more consistent, so the present invention for inhomogeneous goal-setting average shape value and storing, therefore true form information is to set in advance before detecting, and is the known quantity before calculating.
As for demarcation information, in video camera, store before can detecting, and, can adopt following method () to demarcate for the video camera that does not have to demarcate.
(1) based on the camera marking method of single-view
The mode that video monitoring generally all adopts single camera that the target area is monitored.In monitoring scene, the method that the control thing is demarcated in traditional placement has bigger limitation, because the zone of monitoring usually is the zone that the people can't reach or can not place scaling reference, and such as highway, deathtrap and forbid zone that personnel enter etc.So general method that adopts based on the vanishing point or the line that goes out of the demarcation in the video monitoring, such as the geological information that utilizes building in the scene and utilize the marginal information of road to wait and extract go out line and vanishing point, the method for utilizing pedestrian or vehicle to extract the line that goes out is arranged also.
The embodiment of the invention also is based on the principle of go out line and vanishing point and demarcates.Obtain for convenience the to go out position of line, the present invention utilizes in the monitoring scene target information perpendicular to ground, such as the image-forming information of same person after diverse location is stood, electric pole information, the lane line information on the road etc.According to the principle of projective geometry, the parallel lines in the three-dimensional theorem in Euclid space can intersect at a vanishing point after the projection on image, and two vanishing points just can determine the line that goes out.As long as, just can calculate the line position that goes out so known parallel to the ground in the three dimensions but the two pairs of parallel lines that direction is different.
Principle according to demarcating except the line that goes out, also needs to know the vanishing point position of direction perpendicular to the ground.This vanishing point information can be according to calculating perpendicular to the pair of parallel line on ground (such as according to the body of wall information of building or perpendicular to the electric pole on ground).In order to simplify calculating, the vanishing point that also can suppose vertical direction is positioned at the infinite distant place on the y direction.
Therefore, the embodiment of the invention is by two pairs of parallel lines parallel to the ground but that direction is inequality, obtains the line vector that goes out after the normalization
By pair of parallel line, obtain the vanishing point vector v on the vertical direction perpendicular to ground.Certainly, can obtain to go out line vector
Be not limited to only pass through above geometric element with the mode of vanishing point vector v, those skilled in the art can obtain by other geometric elements.
After obtaining demarcation information by above method, just need carry out the inverse of target sizes according to true form information and demarcation information, calculate shape and the dimension information of detected target in the detection position.The reverse calculation algorithms of target sizes is as follows:
(2) reverse calculation algorithms of target sizes
In target detection based on statistics, usually need to know the target sizes of optional position in the monitoring scene, such as the size of the number of people in the image, the size of traffic monitoring optional position vehicle etc.Monitoring program equipment generally all is photographed scene from the side, and therefore according to the principle of projection imaging, the target imaging near apart from video camera is big, otherwise then little.In order to calculate the size of target in image after the projection, need know the demarcation information of camera and the height of target.The shape of actual object is for example shown in Figure 2, so:
The formula of computed altitude is:
Wherein
Be the line vector that goes out after the normalization, v is the vanishing point vector on the vertical direction.B, t are the bottom and the top coordinates of the target on the image.Because target is perpendicular to ground, so b, the abscissa of t is identical, and ordinate differs h, then has:
Above-mentioned respectively the value in the substitution formula (1) can be obtained
If A=‖ is v * t ‖, then have:
Just can calculate h according to formula (2).
From foregoing description, can know, when top coordinate t in image of the true altitude Z of known target and target, can calculate the height value h of target in image by above-mentioned formula.According to the ratio of width to height of real goal, just can determine the shape information of target then.
With number of people detection is example.Need know people's area of bed of any one position in the image, promptly when knowing t, how calculate the number of people size of this point.Can suppose t, the x coordinate of b is identical, and the y coordinate differs a h.When on behalf of the number of people, the h value be positioned at t, space human body height was projected in the height on the image.Because the number of people and people's height roughly satisfies certain ratio, during therefore to known h, just can roughly calculate the size of the number of people.Z can think the people's of a calibrated altitude height, and present embodiment is made as 170cm.α is a priori value that obtains according to test, according to the people of known altitude on the known image in certain position the number of people and the sole coordinate when static, utilize formula (1) just can calculated in advance to go out the value of α.
The structure chart of the device that Fig. 3 provides for the embodiment of the invention.As figure, the device of the image detection of the embodiment of the invention comprises:
Demarcation information acquisition module 320 is used for: the demarcation information that obtains described watch-dog;
True form information acquisition module 330 is used for: the true form information that obtains detected target;
Comprise in the computing module 340: detection position acquiring unit 341 is used for obtaining the detection position of the image to be detected of described video data; Arithmetic element 342 is used to calculate described shape and dimension information.
After computing module 340 obtains the shape and dimension information of detected target in described detection position, this shape and dimension information can be input to detection module (figure does not show), this detection module is used for: in the target detection process based on statistics, carry out the target search of corresponding yardstick according to described shape and dimension information.
Described computing module 340 passes through formula
Calculate the bottom coordinate b of described detected target in described image to be detected, wherein α is the priori value by the test acquisition, and Z is the actual height of described detected target, and t is the top coordinate of described detected target in described image to be detected,
Be the line vector that goes out after the normalization, v is the vanishing point vector on the vertical direction; After obtaining bottom coordinate b,, obtain the picture altitude h of described detected target in described image to be detected according to the difference of top coordinate t and bottom coordinate b; Afterwards, according to described picture altitude h and described actual length-width ratio, determine described shape and the dimension information of described detected target in described detection position.
Under the situation that does not also have to demarcate at video camera, described demarcation information 320 acquisition modules can also comprise:
Geological information extraction unit 321 is used for obtaining the geological information of demarcating usefulness from described video data, and described geological information comprises: parallel to the ground but two pairs of parallel lines that direction is inequality, and perpendicular to the pair of parallel line on ground;
Described true form information acquisition module also includes memory cell, and described cell stores has the actual height and the actual length-width ratio of multiple target to be detected.Described multiple target to be detected comprises personnel targets and vehicle target, the actual height of described personnel targets is set at the assembly average of personnel's height, the assembly average of described personnel's height is the arbitrary value between 165 centimetres to 175 centimetres, and the actual length-width ratio of described personnel targets is set at the assembly average of personnel's length-width ratio.
As from the foregoing, the embodiment of the invention has following advantage:
1) embodiment of the invention is that the application of demarcating based on single-view is expanded, can be according to the demarcation information of single-view and the true form information of detected target, inverse goes out shape and the dimension information of detected target in the detection position, has just obtained shape and dimension information after the real goal projection imaging.
2) the embodiment of the invention detected target that will obtain is applied to target detection process based on statistics at the shape of detection position and dimension information, carry out the target search of corresponding yardstick according to described shape and dimension information, reduce amount of calculation, accelerated detection speed.
3) embodiment of the invention to real goal (such as car, the people is first-class) true form information store in advance, because same classification target shape size is relatively more consistent, so average shape value that the embodiment of the invention has been inhomogeneous goal-setting, can be applied directly to the detection target of corresponding types, and ensure accuracy of detection.
The above only is a preferred implementation of the present invention; should be pointed out that for those skilled in the art, under the prerequisite that does not break away from the principle of the invention; can also make some improvements and modifications, these improvements and modifications also should be considered as protection scope of the present invention.
Claims (13)
1. the method for an image detection is characterized in that, comprises the steps:
Step 1, the monitor video data of acquisition watch-dog;
Step 2 obtains the demarcation information of described watch-dog and the true form information of detected target;
Step 3 according to the detection position in the image to be detected of described video data, described demarcation information and described true form information, is obtained shape and the dimension information of described detected target in described detection position.
2. method according to claim 1 is characterized in that, also comprises,
Step 4 in the target detection process based on statistics, is carried out the target search of corresponding yardstick according to described shape and dimension information.
3. method according to claim 1 is characterized in that, described demarcation information comprises: the line vector that goes out after the normalization
And the vanishing point vector v on the vertical direction; Actual height Z that described true form information is described detected target and actual length-width ratio, described detection position are the top coordinate t of described detected target in described image to be detected.
4. method according to claim 3 is characterized in that, described step 3 specifically comprises:
Utilize formula:
Calculate the bottom coordinate b of described detected target in described image to be detected, wherein the priori value of parameter alpha for obtaining by test;
According to the difference of top coordinate t and bottom coordinate b, obtain the picture altitude h of described detected target in described image to be detected;
According to described picture altitude h and described actual length-width ratio, determine described shape and the dimension information of described detected target in described detection position.
5. method according to claim 4 is characterized in that, described parameter alpha obtains in the following way: measure the top coordinate t and the bottom coordinate b of the known target in the known image of described video data, and the line vector that will go out
The actual height Z of vanishing point vector v and described known target brings described formula into and obtains described parameter alpha.
6. method according to claim 1 is characterized in that, in described step 2, described demarcation information is the Given information of storing in the described watch-dog; Perhaps,
Obtain described demarcation information in the following way: from described video data, obtain the geological information of demarcating usefulness, calculate described demarcation information according to described geological information.
7. method according to claim 6 is characterized in that, described geological information comprises: parallel to the ground but two pairs of parallel lines that direction is inequality, and perpendicular to the pair of parallel line on ground.
8. the device of an image detection is characterized in that, comprising:
Data acquisition module is used for: the monitor video data that obtain watch-dog;
Demarcation information acquisition module is used for: the demarcation information that obtains described watch-dog;
True form information acquisition module is used for: the true form information that obtains detected target;
Computing module is used for: according to detection position, described demarcation information and the described true form information of the image to be detected of described video data, obtain shape and the dimension information of described detected target in described detection position.
9. device according to claim 8 is characterized in that, also comprises:
Detection module is used for: in the target detection process based on statistics, carry out the target search of corresponding yardstick according to described shape and dimension information.
10. device according to claim 8 is characterized in that,
Described computing module passes through formula
Calculate the bottom coordinate b of described detected target in described image to be detected, wherein α is the priori value by the test acquisition, and Z is the actual height of described detected target, and t is the top coordinate of described detected target in described image to be detected,
Be the line vector that goes out after the normalization, v is the vanishing point vector on the vertical direction.
11. device according to claim 8 is characterized in that, described demarcation information acquisition module comprises:
The geological information extraction unit is used for obtaining the geological information of demarcating usefulness from described video data, and described geological information comprises: parallel to the ground but two pairs of parallel lines that direction is inequality, and perpendicular to the pair of parallel line on ground;
12. device according to claim 10 is characterized in that, described true form information acquisition module also includes memory cell, and described cell stores has the actual height and the actual length-width ratio of multiple target to be detected.
13. device according to claim 12, it is characterized in that, described multiple target to be detected comprises personnel targets and vehicle target, the actual height of described personnel targets is set at the assembly average of personnel's height, the assembly average of described personnel's height is the arbitrary value between 165 centimetres to 175 centimetres, and the actual length-width ratio of described personnel targets is set at the assembly average of personnel's length-width ratio.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CNA2009100774815A CN101494772A (en) | 2009-02-13 | 2009-02-13 | Method and apparatus for detecting image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CNA2009100774815A CN101494772A (en) | 2009-02-13 | 2009-02-13 | Method and apparatus for detecting image |
Publications (1)
Publication Number | Publication Date |
---|---|
CN101494772A true CN101494772A (en) | 2009-07-29 |
Family
ID=40925134
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CNA2009100774815A Pending CN101494772A (en) | 2009-02-13 | 2009-02-13 | Method and apparatus for detecting image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN101494772A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101876535A (en) * | 2009-12-02 | 2010-11-03 | 北京中星微电子有限公司 | Method, device and monitoring system for height measurement |
CN102074095A (en) * | 2010-11-09 | 2011-05-25 | 无锡中星微电子有限公司 | System and method for monitoring infant behaviors |
CN103164958A (en) * | 2011-12-15 | 2013-06-19 | 无锡中星微电子有限公司 | Method and system for vehicle monitoring |
CN104034316A (en) * | 2013-03-06 | 2014-09-10 | 深圳先进技术研究院 | Video analysis-based space positioning method |
CN108961305A (en) * | 2018-07-05 | 2018-12-07 | 四创科技有限公司 | A kind of wave climbing monitoring method based on image recognition |
CN110400263A (en) * | 2019-04-13 | 2019-11-01 | 泰州三凯工程技术有限公司 | Action executing system based on Data Detection |
CN111462096A (en) * | 2020-04-03 | 2020-07-28 | 浙江商汤科技开发有限公司 | Three-dimensional target detection method and device |
WO2021168838A1 (en) * | 2020-02-28 | 2021-09-02 | 深圳市大疆创新科技有限公司 | Position information determining method, device, and storage medium |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101339605A (en) * | 2008-08-14 | 2009-01-07 | 北京中星微电子有限公司 | Detection system and method for number of people based on video frequency monitoring |
-
2009
- 2009-02-13 CN CNA2009100774815A patent/CN101494772A/en active Pending
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101339605A (en) * | 2008-08-14 | 2009-01-07 | 北京中星微电子有限公司 | Detection system and method for number of people based on video frequency monitoring |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101876535B (en) * | 2009-12-02 | 2015-11-25 | 北京中星微电子有限公司 | A kind of height measurement method, device and supervisory system |
CN101876535A (en) * | 2009-12-02 | 2010-11-03 | 北京中星微电子有限公司 | Method, device and monitoring system for height measurement |
CN102074095A (en) * | 2010-11-09 | 2011-05-25 | 无锡中星微电子有限公司 | System and method for monitoring infant behaviors |
CN102074095B (en) * | 2010-11-09 | 2013-04-24 | 无锡中星微电子有限公司 | System and method for monitoring infant behaviors |
CN103164958A (en) * | 2011-12-15 | 2013-06-19 | 无锡中星微电子有限公司 | Method and system for vehicle monitoring |
CN103164958B (en) * | 2011-12-15 | 2015-01-07 | 无锡中星微电子有限公司 | Method and system for vehicle monitoring |
CN104034316A (en) * | 2013-03-06 | 2014-09-10 | 深圳先进技术研究院 | Video analysis-based space positioning method |
CN104034316B (en) * | 2013-03-06 | 2018-02-06 | 深圳先进技术研究院 | A kind of space-location method based on video analysis |
CN108961305A (en) * | 2018-07-05 | 2018-12-07 | 四创科技有限公司 | A kind of wave climbing monitoring method based on image recognition |
CN108961305B (en) * | 2018-07-05 | 2021-04-27 | 四创科技有限公司 | Sea wave climbing monitoring method based on image recognition |
CN110400263A (en) * | 2019-04-13 | 2019-11-01 | 泰州三凯工程技术有限公司 | Action executing system based on Data Detection |
WO2021168838A1 (en) * | 2020-02-28 | 2021-09-02 | 深圳市大疆创新科技有限公司 | Position information determining method, device, and storage medium |
CN111462096A (en) * | 2020-04-03 | 2020-07-28 | 浙江商汤科技开发有限公司 | Three-dimensional target detection method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110322702B (en) | Intelligent vehicle speed measuring method based on binocular stereo vision system | |
CN101494772A (en) | Method and apparatus for detecting image | |
CN110859044B (en) | Integrated sensor calibration in natural scenes | |
CN109961468B (en) | Volume measurement method and device based on binocular vision and storage medium | |
CN109583267B (en) | Vehicle target detection method, vehicle target detection device, and vehicle | |
CN106650708A (en) | Visual detection method and system for automatic driving obstacles | |
CN103487034B (en) | Method for measuring distance and height by vehicle-mounted monocular camera based on vertical type target | |
CN108596058A (en) | Running disorder object distance measuring method based on computer vision | |
CN101876535B (en) | A kind of height measurement method, device and supervisory system | |
CN104034305B (en) | A kind of monocular vision is the method for location in real time | |
CN103499337B (en) | Vehicle-mounted monocular camera distance and height measuring device based on vertical target | |
CN104700414A (en) | Rapid distance-measuring method for pedestrian on road ahead on the basis of on-board binocular camera | |
CN104173054A (en) | Measuring method and measuring device for height of human body based on binocular vision technique | |
CN106019264A (en) | Binocular vision based UAV (Unmanned Aerial Vehicle) danger vehicle distance identifying system and method | |
CN109118537B (en) | Picture matching method, device, equipment and storage medium | |
US10163341B2 (en) | Double stereoscopic sensor | |
CN106978774A (en) | A kind of road surface pit automatic testing method | |
CN108107462A (en) | The traffic sign bar gesture monitoring device and method that RTK is combined with high speed camera | |
US8174578B2 (en) | Vehicle periphery monitoring device | |
CN106197382B (en) | A kind of vehicle-mounted single camera target dynamic distance measuring method | |
CN102483881B (en) | Pedestrian-crossing marking detecting method and pedestrian-crossing marking detecting device | |
CN104778716A (en) | Truck carriage volume measurement method based on single image | |
CN112455502A (en) | Train positioning method and device based on laser radar | |
Seo et al. | Omnidirectional stereo vision based vehicle detection and distance measurement for driver assistance system | |
CN103453882B (en) | A kind of ceiling of clouds measuring system based on aircraft and ceiling of clouds measuring method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20090729 |