CN104573664A - Reconstruction system and method of 3D scene of shooting path - Google Patents
Reconstruction system and method of 3D scene of shooting path Download PDFInfo
- Publication number
- CN104573664A CN104573664A CN201510029342.0A CN201510029342A CN104573664A CN 104573664 A CN104573664 A CN 104573664A CN 201510029342 A CN201510029342 A CN 201510029342A CN 104573664 A CN104573664 A CN 104573664A
- Authority
- CN
- China
- Prior art keywords
- shooting
- screen
- infrared laser
- image
- scene
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/64—Three-dimensional objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a reconstruction system and method of a 3D scene of a shooting path. The method comprises the steps that a reference point is set on a screen in advance; when aligned to shoot the screen, a toy gun emits an infrared laser to the screen; a camera shoots the screen, a light filter in the front of the camera filters out other light except for the infrared laser, and then a shooting point in a shot image is recognized; the 3D scene of the shooting path is reconstructed through the shooting point, the reference point and the angle of the toy gun. According to the method, the camera snapshots the screen to form the image, and then the image is processed; because the light filter at the front end of the camera filters out other light except for the infrared laser, the shooting point in the shot image can be recognized according to the snapshot image, and the 3D scene of the shooting path can be reconstructed through angle calculation. The reconstruction system is high in recognition accuracy, simple in structure, low in manufacturing cost and suitable for application and popularization, and the gun which moves freely is not prone to damage.
Description
Technical field
The present invention relates to 3D scene reconstruction field, particularly relate to a kind of 3D scene reconstruction system and method shooting path.
Background technology
Along with multimedia technology, the fast development of computer technology and large screen Display Technique etc., large screen 3D shooting game is more and more popular to people, thus causes people to the research of screen shooting point recognition technology with the 3D scene reconstruction in shooting path.
The 3D scene reconstruction in existing screen shooting point recognition technology and shooting path is that rifle is fixed on a certain platform, then by going according to angle analysis shooting point in the position of screen and reconstructing the 3D scene that path is hit in outgoing.But existing this method calculates angle and there is larger error, the 3D scene deviation in actual shooting point and shooting path is larger.
Therefore, prior art has yet to be improved and developed.
Summary of the invention
In view of above-mentioned the deficiencies in the prior art, the object of the present invention is to provide a kind of shooting based on infrared laser point recognition system and method, be intended to solve the larger problem of existing 3D reconfiguration technique deviation.
Technical scheme of the present invention is as follows:
Shoot the 3D scene reconstruction method in path, wherein, comprise step:
In advance reference point is set in screen;
When the screen of peashooter aligning is shot, send infrared laser to screen;
Take screen by video camera, and utilize the filter before video camera to be filtered out by other light outside infrared laser, thus identify the shooting point in the image of shooting;
The 3D scene of shooting path is reconstructed by the angle of this shooting point, reference point and peashooter.
The 3D scene reconstruction method in described shooting path, wherein, the infrared laser shape that each peashooter sends when shooting is different.
The 3D scene reconstruction method in described shooting path, wherein, also comprises step:
Video camera is by image transmitting to control centre of shooting, and control centre identifies the infrared laser shape in image, then responds the firing operation of corresponding peashooter.
The 3D scene reconstruction method in described shooting path, wherein,
Recognition result is sent to screen by described control centre, by the firing operation of screen reaction toy rifle at shooting point.
A kind of 3D scene reconstruction system of shooting path, wherein, comprise a screen, be arranged on the projector in screen front and some peashooters being provided with infrared laser, described video camera front end is provided with filter, when the screen of peashooter aligning is shot, send infrared laser to screen, take screen by video camera, and utilize filter to be filtered out by other light outside infrared laser, thus identify the shooting point in the image of shooting; The 3D scene of shooting path is reconstructed by the angle of this shooting point, reference point and peashooter.
The 3D scene reconstruction system in described shooting path, wherein, the infrared laser shape that each peashooter sends when shooting is different.
The 3D scene reconstruction system in described shooting path, wherein, described video camera connects a control centre, and described control centre is used for identifying the infrared laser shape in image, then responds the firing operation of corresponding peashooter.
The 3D scene reconstruction system in described shooting path, wherein, recognition result is sent to screen by described control centre, by the firing operation of screen reaction toy rifle at shooting point.
Beneficial effect: in the present invention, image is formed by video capture screen, then image procossing is carried out to image, because other light except infrared laser filter out by the filter of video camera front end, so shooting point in the image of shooting can be identified according to capturing the image of returning, the 3D scene of shooting path just can be reconstructed through angle calculation.Recognition accuracy of the present invention is high, and rifle moves freely, not fragile, and structure is simple, and cost of manufacture is low, is suitable for promoting the use of.
Accompanying drawing explanation
Fig. 1 is the relational structure schematic diagram of video camera and screen in the present invention.
Fig. 2 is the image that circular shooting point beats shot by camera in screen.
Fig. 3 is the image that triangle shooting point beats shot by camera in screen.
Fig. 4 is the image that triangle and circular shooting point beat shot by camera in screen simultaneously.
Fig. 5 is the formation basic theory figure shooting path L in the present invention.
Embodiment
The invention provides a kind of 3D scene reconstruction system and method shooting path, for making object of the present invention, technical scheme and effect clearly, clearly, the present invention is described in more detail below.Should be appreciated that specific embodiment described herein only in order to explain the present invention, be not intended to limit the present invention.
A kind of 3D scene reconstruction method of shooting path provided by the present invention, it comprises step:
S1, in advance reference point is set in screen;
S2, when peashooter aim at screen shoot time, send infrared laser to screen;
S3, take screen by video camera, and utilize the filter before video camera to be filtered out by other light outside infrared laser, thus identify the shooting point in the image of shooting;
S4, reconstructed the 3D scene of shooting path by the angle of this shooting point, reference point and peashooter.
As shown in Figure 1, screen 100 front is provided with video camera 200, video camera 200 carries out photographic images for aiming at screen, also comprise some peashooters being provided with infrared laser in addition, described video camera 200 front end is provided with filter, this filter can be wholely set on video camera 200, and this filter can filter out whole visible ray.
When laser is not penetrated in screen 100, because video camera 200 camera lens is provided with the filter (the whole light outside infrared laser) filtering out whole visible ray, the image of its shooting is essentially entirely black, can calculate by carrying out process to image, now laser is not shot in screen, does not namely shoot a little.
And when the screen 100 of peashooter aligning is shot, infrared laser sends infrared laser to screen 100, screen 100 is taken by video camera 200, and utilize filter to be filtered out by other light outside infrared laser, now, the image that video camera 200 captures is as shown in Figures 2 and 3, laser spots is close to white point, by carrying out picture processing the coordinate figure that can calculate residing for white laser point, after conversion, just can know that laser beats the position in screen.Because sightless infrared laser wavelength and filter is all known through wavelength, so do not need the wavelength value removing to identify laser by any equipment, thus recognition methods efficiency of the present invention and accuracy rate higher.
The infrared laser shape that each peashooter sends when shooting is different.Such as, when two difform laser are got in screen, as shown in Figure 4, the image that video camera 200 captures, by carrying out graphic correlation with shape library, triangle and circle can be identified respectively, so just can according to shooting point multiple in difform infrared laser identification screen 100, and identifiable design goes out the peashooter corresponding to shooting point.
Described video camera 200 connects a control centre, and described control centre is used for identifying the infrared laser shape in image, thus identifies the shooting point in the image of shooting, then responds the firing operation of corresponding peashooter.
Specifically, the step of image recognition comprises:
1, by coloured image gray processing, because video capture to image be 24 true color images, and image processing techniques of the present invention is for 256 grades of gray-scale maps, so be necessary cromogram to change into gray-scale map, the one pixel gray value of this point of byte representation, when image procossing, the processing speed of gray level image is also than comparatively fast.
Principle rgb value being converted to gray value is the gray difference utilized in image between background and object, convert to gray value can be rgb value and mean value; Its method is: each pixel of getting in coloured image extracts R, G, B value respectively, the value of three is added and is averaging the gray value being pixel.
2, the co-occurrence matrix on 4 directions is constructed, namely the gray level co-occurrence matrixes on 0 ° of direction, gray level co-occurrence matrixes on 45 ° of directions, gray level co-occurrence matrixes on 90 ° of directions, gray level co-occurrence matrixes on 135 ° of directions, generates the gray level image of 4 × 4 like this, generates the gray level co-occurrence matrixes of four direction, for 0 °, generating algorithm is as follows.
for（i=0;i<LocalImageWidth;i++）
{
For(j=0;i<LocalImageWidth-distance;i++)
{
PmatrixH[(unsigned int)NewImage[i][j][unsigned
Int)NewImage[i][j+distance]]+=1;
PmatrixH[(unsigned int)NewImage[i][j+distance][unsigned
Int)NewImage[i][j]]+=1;
}
3,5 textural characteristics parameters of 4 co-occurrence matrixs are calculated respectively: energy (ASM), entropy (ENT), contrast (the moment of inertia, CON), unfavourable balance square (local stationary, IDM), relevant (COR).
Formula is as follows:
Energy:
Entropy:
Contrast (the moment of inertia):
Relevant:
Unfavourable balance square (local stationary):
In formula, μ
x, μ
y, σ
xand σ
ym respectively
x, m
yaverage and standard deviation,
the every column element sum of co-occurrence matrix,
it is every row element sum.
Wherein, relevant concept calculates gets up to need first to calculate the mean value m of image in x direction
x, and image mean value m in y-direction
y, and calculate its standard deviation sigma
xand σ
y, then by above-mentioned formulae discovery
4, recording and preserve textural characteristics parameter value, preserving by preserving function Onsave:
typedef struct{
double energy;
double entropy;
double quadrature;
double correlation;
double localCalm;
} S_data_T;
S_data_T M_data;
M_data.energy=m_dEnergy;
M_data.entropy=m_dEntropy;
M_data.quadrature=m_dInertiaQuadrature;
M_data.correlation=m_dCorrelation;
M_data.localCalm=m_dLocalCalm;
If((fp1=fopen(“data.txt”, “w”))=NULL)
Fprintf(fp1, “{%f,%f, %f, %f, %f,}”,M_ data.energy, M_data.entropy, M_data.quadrature, M_data.correlation, M_data.localCalm);
Specifically by defining a structure S_data_T by calculated textural characteristics parameter value:
M_ data.energy, M_data.entropy, M_data.quadrature, M_data.correlation, M_data.localCalm record, and be kept at name and be called in the text document of data, the content of preserving in this text document is exactly the characteristic value of the contrast images calculated, if only read a width figure, and not computation of characteristic values, or after having calculated not numerical value stored in data, the identification so cannot carrying out image later judges.
The textural characteristics parameter value of each infrared laser shape can be saved by said method.
5, the textural characteristics parameter value of present image is calculated by above-mentioned same method, compare with the textural characteristics parameter value previously preserved, if characteristic value is the same, then represent it is same width figure, if difference, not same width figure, for having selected 5 typical parameters in the extraction of textural characteristics: energy, entropy, the moment of inertia, local stationary, relevant.When judging recognition image, any one parameter can be selected compare.Namely meet any one, all can be judged to be it is same width figure, the image with same infrared laser shape can be analyzed like this by above-mentioned contrast.
Recognition result is sent to screen 100 by described control centre, by the firing operation of screen 100 reaction toy rifle at shooting point, such as screen connects described control centre, after control centre calculates shooting point, then recognition result is sent to screen, makes the firing operation of its reaction toy rifle.
The 3D scene of shooting path is reconstructed by the angle of this shooting point, reference point and peashooter.As shown in Figure 5, utilize this shooting point to calculate angle of departure A and B, thus determine the scene of shooting path L in 3D.
Based on said method, the present invention also provides a kind of 3D scene reconstruction system of shooting path, it comprises a screen, is arranged on the projector in screen front and some peashooters being provided with infrared laser, described video camera front end is provided with filter, when the screen of peashooter aligning is shot, send infrared laser to screen, take screen by video camera, and utilize filter to be filtered out by other light outside infrared laser, thus identify the shooting point in the image of shooting; The 3D scene of shooting path is reconstructed by the angle of this shooting point, reference point and peashooter.
Further, each peashooter infrared laser shape of sending when shooting is different.
Further, described video camera connects a control centre, and described control centre is used for identifying the infrared laser shape in image, then responds the firing operation of corresponding peashooter.
Further, recognition result is sent to screen by described control centre, by the firing operation of screen reaction toy rifle at shooting point.
In sum, in the present invention, image is formed by video capture screen, then image procossing is carried out to image, because other light except infrared laser filter out by the filter of video camera front end, so shooting point in the image of shooting can be identified according to capturing the image of returning, the 3D scene of shooting path just can be reconstructed through angle calculation.Recognition accuracy of the present invention is high, and rifle moves freely, not fragile, and structure is simple, and cost of manufacture is low, is suitable for promoting the use of.
Should be understood that, application of the present invention is not limited to above-mentioned citing, for those of ordinary skills, can be improved according to the above description or convert, and all these improve and convert the protection range that all should belong to claims of the present invention.
Claims (8)
1. shoot the 3D scene reconstruction method in path, it is characterized in that, comprise step:
In advance reference point is set in screen;
When the screen of peashooter aligning is shot, send infrared laser to screen;
Take screen by video camera, and utilize the filter before video camera to be filtered out by other light outside infrared laser, thus identify the shooting point in the image of shooting;
The 3D scene of shooting path is reconstructed by the angle of this shooting point, reference point and peashooter.
2. the 3D scene reconstruction method in shooting path according to claim 1, is characterized in that, the infrared laser shape that each peashooter sends when shooting is different.
3. the 3D scene reconstruction method in shooting path according to claim 2, is characterized in that, also comprise step:
Video camera is by image transmitting to control centre of shooting, and control centre identifies the infrared laser shape in image, then responds the firing operation of corresponding peashooter.
4. the 3D scene reconstruction method in shooting path according to claim 3, is characterized in that,
Recognition result is sent to screen by described control centre, by the firing operation of screen reaction toy rifle at shooting point.
5. shoot the 3D scene reconstruction system in path for one kind, it is characterized in that, comprise a screen, be arranged on the projector in screen front and some peashooters being provided with infrared laser, described video camera front end is provided with filter, when the screen of peashooter aligning is shot, send infrared laser to screen, take screen by video camera, and utilize filter to be filtered out by other light outside infrared laser, thus identify the shooting point in the image of shooting; The 3D scene of shooting path is reconstructed by the angle of this shooting point, reference point and peashooter.
6. the 3D scene reconstruction system in shooting path according to claim 5, is characterized in that, the infrared laser shape that each peashooter sends when shooting is different.
7. the 3D scene reconstruction system in shooting path according to claim 6, it is characterized in that, described video camera connects a control centre, and described control centre is used for identifying the infrared laser shape in image, then responds the firing operation of corresponding peashooter.
8. the 3D scene reconstruction system in shooting path according to claim 7, it is characterized in that, recognition result is sent to screen by described control centre, by the firing operation of screen reaction toy rifle at shooting point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510029342.0A CN104573664A (en) | 2015-01-21 | 2015-01-21 | Reconstruction system and method of 3D scene of shooting path |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510029342.0A CN104573664A (en) | 2015-01-21 | 2015-01-21 | Reconstruction system and method of 3D scene of shooting path |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104573664A true CN104573664A (en) | 2015-04-29 |
Family
ID=53089686
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510029342.0A Pending CN104573664A (en) | 2015-01-21 | 2015-01-21 | Reconstruction system and method of 3D scene of shooting path |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104573664A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112316409A (en) * | 2020-10-29 | 2021-02-05 | 江苏环球之星影视设备科技有限公司 | Method for identifying different shooting points of screen by infrared laser |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020010021A1 (en) * | 1999-08-03 | 2002-01-24 | Mccauley Jack Jean | Method and device for optical gun interaction with a computer game system |
| CN2591547Y (en) * | 2002-08-21 | 2003-12-10 | 余军涛 | Shooting simulator |
| CN2793674Y (en) * | 2005-04-21 | 2006-07-05 | 余军涛 | Shooting simulator with deficiency and excess combined display effect |
| CN101034440A (en) * | 2007-01-12 | 2007-09-12 | 浙江工业大学 | Identification method for spherical fruit and vegetables |
| CN201267713Y (en) * | 2008-07-29 | 2009-07-08 | 曹思明 | Gun type multifunctional game input handle |
| CN101770644A (en) * | 2010-01-19 | 2010-07-07 | 浙江林学院 | Forest-fire remote video monitoring firework identification method |
| CN101789005A (en) * | 2010-01-22 | 2010-07-28 | 深圳创维数字技术股份有限公司 | Image searching method based on region of interest (ROI) |
| CN102114344A (en) * | 2010-12-28 | 2011-07-06 | 深圳华强游戏软件有限公司 | Game control method and system |
| CN102289671A (en) * | 2011-09-02 | 2011-12-21 | 北京新媒传信科技有限公司 | Method and device for extracting texture feature of image |
| CN102622108A (en) * | 2012-01-18 | 2012-08-01 | 深圳市中科睿成智能科技有限公司 | Interactive projecting system and implementation method for same |
| CN102935288A (en) * | 2012-10-31 | 2013-02-20 | 深圳市德力信科技有限公司 | Man-machine interaction game implementing device and method |
-
2015
- 2015-01-21 CN CN201510029342.0A patent/CN104573664A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020010021A1 (en) * | 1999-08-03 | 2002-01-24 | Mccauley Jack Jean | Method and device for optical gun interaction with a computer game system |
| CN2591547Y (en) * | 2002-08-21 | 2003-12-10 | 余军涛 | Shooting simulator |
| CN2793674Y (en) * | 2005-04-21 | 2006-07-05 | 余军涛 | Shooting simulator with deficiency and excess combined display effect |
| CN101034440A (en) * | 2007-01-12 | 2007-09-12 | 浙江工业大学 | Identification method for spherical fruit and vegetables |
| CN201267713Y (en) * | 2008-07-29 | 2009-07-08 | 曹思明 | Gun type multifunctional game input handle |
| CN101770644A (en) * | 2010-01-19 | 2010-07-07 | 浙江林学院 | Forest-fire remote video monitoring firework identification method |
| CN101789005A (en) * | 2010-01-22 | 2010-07-28 | 深圳创维数字技术股份有限公司 | Image searching method based on region of interest (ROI) |
| CN102114344A (en) * | 2010-12-28 | 2011-07-06 | 深圳华强游戏软件有限公司 | Game control method and system |
| CN102289671A (en) * | 2011-09-02 | 2011-12-21 | 北京新媒传信科技有限公司 | Method and device for extracting texture feature of image |
| CN102622108A (en) * | 2012-01-18 | 2012-08-01 | 深圳市中科睿成智能科技有限公司 | Interactive projecting system and implementation method for same |
| CN102935288A (en) * | 2012-10-31 | 2013-02-20 | 深圳市德力信科技有限公司 | Man-machine interaction game implementing device and method |
Non-Patent Citations (1)
| Title |
|---|
| 杨淑莹: "《VC++图像处理程序设计》", 30 November 2003 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112316409A (en) * | 2020-10-29 | 2021-02-05 | 江苏环球之星影视设备科技有限公司 | Method for identifying different shooting points of screen by infrared laser |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110246163B (en) | Image processing method, image processing device, image processing apparatus, and computer storage medium | |
| CN108537844B (en) | Visual SLAM loop detection method fusing geometric information | |
| JP2016513843A (en) | Reduction of object detection time by using feature spatial localization | |
| CN104424640A (en) | Method and device for carrying out blurring processing on images | |
| US9936128B2 (en) | Automatic detection of panoramic gestures | |
| CN113592989A (en) | Three-dimensional scene reconstruction system, method, equipment and storage medium | |
| CN107560592A (en) | A kind of precision ranging method for optronic tracker linkage target | |
| CN109214254B (en) | Method and device for determining displacement of robot | |
| CN110634138A (en) | Bridge deformation monitoring method, device and equipment based on visual perception | |
| CN111161347A (en) | Method and equipment for initializing SLAM | |
| CN112085031A (en) | Target detection method and system | |
| CN111899345B (en) | Three-dimensional reconstruction method based on 2D visual image | |
| CN106295657A (en) | A kind of method extracting human height's feature during video data structure | |
| CN111723656B (en) | Smog detection method and device based on YOLO v3 and self-optimization | |
| CN113674335A (en) | Depth imaging method, electronic device, and storage medium | |
| CN108229281B (en) | Neural network generation method, face detection device and electronic equipment | |
| CN113298177B (en) | Night image coloring method, device, medium and equipment | |
| KR101797814B1 (en) | Teaching apparatus, method for child based on image comparison algorithm | |
| CN114266823A (en) | Monocular SLAM method combining SuperPoint network characteristic extraction | |
| CN104667526A (en) | Shooting point identification system and method based on infrared laser | |
| CN104573664A (en) | Reconstruction system and method of 3D scene of shooting path | |
| CN113902947B (en) | Method for constructing air target infrared image generation type countermeasure network by natural image | |
| CN114882106A (en) | Pose determination method and device, equipment and medium | |
| US20200294186A1 (en) | Method of plane tracking | |
| CN112802112A (en) | Visual positioning method, device, server and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C53 | Correction of patent of invention or patent application | ||
| CB02 | Change of applicant information |
Address after: 518053 Guangdong city of Shenzhen province Nanshan District Xiangshan Road on the 1st floor after Liyuan Village Applicant after: SHENZHEN OCT VISION INC. Address before: 518053 Guangdong city of Shenzhen province Nanshan District Xiangshan Road on the 1st floor after Liyuan Village Applicant before: Shenzhen OCT Vision Inc. |
|
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150429 |
|
| RJ01 | Rejection of invention patent application after publication |