CN105136120A - Object displacement image detection system and method - Google Patents
Object displacement image detection system and method Download PDFInfo
- Publication number
- CN105136120A CN105136120A CN201510522271.8A CN201510522271A CN105136120A CN 105136120 A CN105136120 A CN 105136120A CN 201510522271 A CN201510522271 A CN 201510522271A CN 105136120 A CN105136120 A CN 105136120A
- Authority
- CN
- China
- Prior art keywords
- image
- band
- processing unit
- displacement
- frequency sub
- 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
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C11/00—Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention provides an object displacement image detection system and method. An image processing unit is connected with a work image unit and a CCD image sensor, CCD camera lens are connected with the image processing unit via the CCD image sensor and transmits a real captured image to the image processing unit which processes image information and outputs processing results to a CPU; a peripheral device is connected with a signal input terminal of the CPU; an output terminal of the CPU is connected with a signal input device; a detection system determines a displacement path of an object, compares the displacement path with a displacement path of the object predetermined by a control program, calculates an actual displacement path of the object, and outputs an control command to correct the displacement path of the object. The object displacement image detection system and method smartly solve the deviation between actual displacement and predetermined displacement of the object, and promote running accuracy and stability of the object; furthermore the whole detection system has a simple structure and is convenient for usage; the detection method is convenient to perform and use.
Description
Technical field
The present invention relates to a kind of based on image processing techniques and the modification method that carries out object of which movement, be specifically related to a kind of ohject displacement image detecting system and method.
Background technology
Along with the fast development of mankind's science and technology, at this block of digital field, can locate accurately as numerically-controlled machine, but on fixing track; Common robot ambulation is also travel on specific track, the unpiloted automobile run out of doors, by GPS positioning system, robotic vision system, that radar system realizes automobile is unmanned, but also just on ground surface, its system is too loaded down with trivial details, and cost is higher, but to intellectuality be realized in daily life, by so too complicated, the region also not sample of everyone life, slowly gone on intellectuality, how better solution is in daily life, how robot walks and does things freely as people, also has a segment distance.
Summary of the invention
The present invention is directed to the deficiencies in the prior art and provide a kind of ohject displacement image detecting system and method, make ohject displacement operation easy to detect, object controllability path is accurate.
Technical scheme of the present invention: a kind of ohject displacement image detecting system, it is characterized in that: comprise graphics processing unit, graphics processing unit connection work elementary area and ccd image sensor, ccd video camera camera lens to be connected with graphics processing unit by ccd image sensor and to be sent in graphics processing unit by the real image of shooting, result is also transported in CPU by graphics processing unit processing image information, peripheral apparatus connects the signal input part of CPU, CPU output terminal connection signal output unit.
Described work elementary area and peripheral apparatus are USB external storage equipment.
The method that ohject displacement image detects, is characterized in that, comprise the following steps:
The reference frame that S1, importing shop drawing picture, appointment and shop drawing picture match, the ohject displacement control program mated wanted by input and shop drawing picture;
S2, adjustment ccd video camera, control ccd video camera camera lens and find reference frame;
S3, control program control object and run along preset displacement path, and ccd video camera obtains object actual motion image simultaneously;
S4, graphics processing unit carry out denoising enhancing to object actual motion image, interpolation differentiates pre-service;
S5, pretreated image is input in CPU and carries out spot detection and pixel is demarcated, extract the positional information of object and reference frame;
S6, calculate distance between object and reference frame, determine ohject displacement path;
S7, compared with control program are preset ohject displacement path and are calculated object actual displacement path, export steering order and revise ohject displacement path.
The concrete steps that denoising enhancing in described step S4, difference are differentiated are:
1) quick bent Wave Decomposition is carried out to pending image, obtain low frequency sub-band and each high-frequency sub-band;
2) adopt homomorphic filtering process to remove uneven illumination to low frequency sub-band, adopt hard threshold values to remove noise to each high-frequency sub-band;
3) bi-cubic interpolation is carried out to improve pixel resolving power to low frequency sub-band and each high-frequency sub-band;
4) quick bent reconstructed wave is carried out to the low frequency sub-band after process and high-frequency sub-band, obtain high resolving power, rebuild image clearly.
Technique effect of the present invention: the position image detecting system of object and method solve object actual displacement and preset displacement Path error cleverly, improve the Stability and veracity that object runs, and whole detection system structure is simple, easy to use, detection method simple operation, easy to use.
Accompanying drawing explanation
Fig. 1 is detection system structural representation of the present invention;
Fig. 2 is the inventive method process flow diagram;
Fig. 3 is embodiment of the present invention realistic picture;
Fig. 4 is embodiment of the present invention mark reference frame figure;
Fig. 5 is that the present invention extracts image graph.
Embodiment
Below in conjunction with accompanying drawing, the present invention is further described:
As shown in Figure 1, a kind of ohject displacement image detecting system, it is characterized in that: comprise graphics processing unit 1, graphics processing unit 1 connects work elementary area 2 and ccd image sensor 4, ccd video camera camera lens 3 to be connected with graphics processing unit 1 by ccd image sensor 4 and to be sent in graphics processing unit 1 by the real image of shooting, result is also transported in CPU6 by graphics processing unit 1 processing image information, peripheral apparatus 5 connects the signal input part of CPU6, CPU6 output terminal connection signal output unit 7.
Work elementary area 2 and peripheral apparatus 5 are USB external storage equipment.
As shown in Figure 2: a kind of ohject displacement image detecting method, is characterized in that, comprise the following steps:
The reference frame that S1, importing shop drawing picture, appointment and shop drawing picture match, the ohject displacement control program mated wanted by input and shop drawing picture;
S2, adjustment ccd video camera, control ccd video camera camera lens and find reference frame;
S3, control program control object and run along preset displacement path, and ccd video camera obtains object actual motion image simultaneously;
S4, graphics processing unit carry out denoising enhancing to object actual motion image, interpolation differentiates pre-service;
S5, pretreated image is input in CPU and carries out spot detection and pixel is demarcated, extract the positional information of object and reference frame;
S6, calculate distance between object and reference frame, determine ohject displacement path;
S7, compared with control program are preset ohject displacement path and are calculated object actual displacement path, export steering order and revise ohject displacement path.
The concrete steps that denoising enhancing in step S4, difference are differentiated are:
1) quick bent Wave Decomposition is carried out to pending image, obtain low frequency sub-band and each high-frequency sub-band;
2) adopt homomorphic filtering process to remove uneven illumination to low frequency sub-band, adopt hard threshold values to remove noise to each high-frequency sub-band;
3) bi-cubic interpolation is carried out to improve pixel resolving power to low frequency sub-band and each high-frequency sub-band;
4) quick bent reconstructed wave is carried out to the low frequency sub-band after process and high-frequency sub-band, obtain high resolving power, rebuild image clearly.
A kind of ohject displacement image detecting system of the present invention and method, solve object actual displacement and preset displacement Path error cleverly, improves the Stability and veracity that object runs, and whole detection system structure is simple, easy to use, detection method simple operation, easy to use.
A kind of ohject displacement image detecting system of the present invention and method are applied on unpiloted auto navigation, by setting the edge of road and automobile position reference frame, can evade automobile and guide automobile to advance along correct road by automobile under steam.In agricultural application, crossing by edge, farmland and just operation the object stayed is reference frame, when farm machinery tillage, by facing to two reference frames, agricultural machinery can be allowed to avoid the gradient on the impact of intelligent farm machinery tillage when walking.Avoid the situation of balking with broadcast leakage.Certainly this is that digitizing agricultural machinery creates.Application is lain in the measurement of outer intelligent robot, directly specifies reference frame, preset sequence by selected for the photograph of shooting, and robot can be made to measure needing the topography and geomorphology measured.In the observation of wild animal, can select wild animal is reference frame, by the distance of setpoint distance wild animal in intelligent robot, wild animal so just can be avoided to produce interference to observation, also can be permanent observe the various actions of wild animal, avoids human factor and has an impact to wild animal.Than comparing at the camera that some local placement is a large amount of in advance, this operation is more simple, and workload is relatively less.Operate on three dimensions, be just difficult to good effect as locating and detecting devices such as GPRS, and by installing multiple camera, then detect by the method for the image detection of object actual displacement detection, will seem convenience very.
Application example (using for illustrative purposes only, specifically based on claims)
Fig. 3 is the sheet photo taken in community with mobile phone below, suppose this one end requiring robot from shooting, go to the position paralleled with white light cable mark post in figure (shown in Fig. 4) along this red tile floor (being no more than the white brick that common brick is other).
First, analyze from picture, based on common brick during the road surfacing of this community, white brick peripherally as setting off, and runs on the parallel Shang Zheduan road, road surface of white light cable mark post in robot, and all road surfaces are all this designs.So when choosing reference frame, select target with reference to being white light cable mark post, operationally can being selected near white light cable mark post white brick and is reference frame with the separatrix that surrounding enviroment produce, the image of extraction as figure five,
In the selection of the program of program, adopt " following edge " modular program.
Concrete operations are as follows, first photograph (Fig. 3) is imported, whether choosing then carries out landscaping treatment, by the image that obtains through row hot spot with the demarcation of pixel, picture is carried out to the detection (manually can carry out the correction at edge) at edge, select target reference frame white light cable mark post, select near white light cable mark post that on one side white brick and the separatrix produced with surrounding enviroment for reference to being the first operation reference frame, being selected the program of " following edge " (note 1) to run module and being run.Run in module in the program of " following edge " distance set between object and object reference system, and first runs distance between reference frame.
After program module is chosen, when real work, first robot is placed on the start position of shooting photograph, robot is transferred to running status, robot picked-up environment photograph, the photograph graphics processing unit of delivering to obtained is carried out denoising enhancing to object actual motion image, interpolation differentiates pre-service, pretreated image is input in CPU and carries out spot detection and pixel demarcation, carry out the detection at edge again, therefrom extract object reference system target and first and run reference frame, calculate the distance between oneself and object reference system, and first runs the distance of reference frame, and compare with setting program, output modifications program.Robot performs update routine, and robot runs on correct rail track.So must not obtain external environment information by CCD camera, guide robot motion to the position of specifying.
Note 1: " following edge " program runs module, and program design theory is: object is operationally forever equal with the position at appointment bar edge, specifies reference frame to terminate until run.
Claims (4)
1. an ohject displacement image detecting system, it is characterized in that: comprise graphics processing unit (1), graphics processing unit (1) connects work elementary area (2) and ccd image sensor (4), ccd video camera camera lens (3) to be connected with graphics processing unit (1) by ccd image sensor (4) and to be sent to by the real image of shooting in graphics processing unit (1), result is also transported in CPU (6) by graphics processing unit (1) processing image information, peripheral apparatus (5) connects the signal input part of CPU (6), CPU (6) output terminal connection signal output unit (7).
2. object actual displacement image detecting system according to claim 1, is characterized in that: described work elementary area (2) and peripheral apparatus (5) are USB external storage equipment.
3. utilize system described in claim 1 to carry out a method for object actual displacement image detection, it is characterized in that, comprise the following steps:
The reference frame that S1, importing shop drawing picture, appointment and shop drawing picture match, the ohject displacement control program mated wanted by input and shop drawing picture;
S2, adjustment ccd video camera, control ccd video camera camera lens and find reference frame;
S3, control program control object and run along preset displacement path, and ccd video camera obtains object actual motion image simultaneously;
S4, graphics processing unit carry out denoising enhancing to object actual motion image, interpolation differentiates pre-service;
S5, pretreated image is input in CPU and carries out spot detection and pixel is demarcated, extract the positional information of object and reference frame;
S6, calculate distance between object and reference frame, determine ohject displacement path;
S7, compared with control program are preset ohject displacement path and are calculated object actual displacement path, export steering order and revise ohject displacement path.
4. a kind of ohject displacement image detecting method according to claim 3, is characterized in that: the concrete steps that denoising enhancing in described step S4, difference are differentiated are:
1) quick bent Wave Decomposition is carried out to pending image, obtain low frequency sub-band and each high-frequency sub-band;
2) adopt homomorphic filtering process to remove uneven illumination to low frequency sub-band, adopt hard threshold values to remove noise to each high-frequency sub-band;
3) bi-cubic interpolation is carried out to improve pixel resolving power to low frequency sub-band and each high-frequency sub-band;
4) quick bent reconstructed wave is carried out to the low frequency sub-band after process and high-frequency sub-band, obtain high resolving power, rebuild image clearly.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510522271.8A CN105136120A (en) | 2015-08-24 | 2015-08-24 | Object displacement image detection system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510522271.8A CN105136120A (en) | 2015-08-24 | 2015-08-24 | Object displacement image detection system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105136120A true CN105136120A (en) | 2015-12-09 |
Family
ID=54721560
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510522271.8A Pending CN105136120A (en) | 2015-08-24 | 2015-08-24 | Object displacement image detection system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105136120A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106871872A (en) * | 2017-02-24 | 2017-06-20 | 吴慧明 | Build（Structure）Composition deformation, displacement and damage is built to be clustered into as Internet of Things monitoring method |
| CN107578626A (en) * | 2017-08-30 | 2018-01-12 | 无锡北斗星通信息科技有限公司 | A kind of night motorcycle alarming method for power |
| CN109144052A (en) * | 2017-07-07 | 2019-01-04 | 肖建雄 | Navigation system and its method for automatic driving vehicle |
| CN111767875A (en) * | 2020-07-06 | 2020-10-13 | 中兴飞流信息科技有限公司 | Tunnel smoke detection method based on instance segmentation |
| CN113724312A (en) * | 2021-08-13 | 2021-11-30 | 辽宁四季环境治理工程有限公司 | Real-time monitoring and early warning method and device for geological disasters |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110310245A1 (en) * | 2010-06-21 | 2011-12-22 | Nissan Motor Co., Ltd. | Travel distance detection device and travel distance detection method |
| CN102968119A (en) * | 2012-11-22 | 2013-03-13 | 日东电子发展（深圳）有限公司 | Automatic visual guide vehicle for constant illumination |
| CN103390259A (en) * | 2012-05-09 | 2013-11-13 | 徐世铭 | Ground image processing method in visual guidance AGV |
| CN103839276A (en) * | 2012-11-27 | 2014-06-04 | 大连灵动科技发展有限公司 | Method for motion tracking based on predication |
| CN104142685A (en) * | 2014-08-21 | 2014-11-12 | 深圳市佳顺伟业科技有限公司 | AGV trackless guide method and system based on optical positioning |
| CN104501720A (en) * | 2014-12-24 | 2015-04-08 | 河海大学常州校区 | Non-contact object size and distance image measuring instrument |
-
2015
- 2015-08-24 CN CN201510522271.8A patent/CN105136120A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110310245A1 (en) * | 2010-06-21 | 2011-12-22 | Nissan Motor Co., Ltd. | Travel distance detection device and travel distance detection method |
| CN103390259A (en) * | 2012-05-09 | 2013-11-13 | 徐世铭 | Ground image processing method in visual guidance AGV |
| CN102968119A (en) * | 2012-11-22 | 2013-03-13 | 日东电子发展（深圳）有限公司 | Automatic visual guide vehicle for constant illumination |
| CN103839276A (en) * | 2012-11-27 | 2014-06-04 | 大连灵动科技发展有限公司 | Method for motion tracking based on predication |
| CN104142685A (en) * | 2014-08-21 | 2014-11-12 | 深圳市佳顺伟业科技有限公司 | AGV trackless guide method and system based on optical positioning |
| CN104501720A (en) * | 2014-12-24 | 2015-04-08 | 河海大学常州校区 | Non-contact object size and distance image measuring instrument |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106871872A (en) * | 2017-02-24 | 2017-06-20 | 吴慧明 | Build（Structure）Composition deformation, displacement and damage is built to be clustered into as Internet of Things monitoring method |
| CN109144052A (en) * | 2017-07-07 | 2019-01-04 | 肖建雄 | Navigation system and its method for automatic driving vehicle |
| CN107578626A (en) * | 2017-08-30 | 2018-01-12 | 无锡北斗星通信息科技有限公司 | A kind of night motorcycle alarming method for power |
| CN111767875A (en) * | 2020-07-06 | 2020-10-13 | 中兴飞流信息科技有限公司 | Tunnel smoke detection method based on instance segmentation |
| CN111767875B (en) * | 2020-07-06 | 2024-05-10 | 中兴飞流信息科技有限公司 | Tunnel smoke detection method based on instance segmentation |
| CN113724312A (en) * | 2021-08-13 | 2021-11-30 | 辽宁四季环境治理工程有限公司 | Real-time monitoring and early warning method and device for geological disasters |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chen et al. | High-accuracy multi-camera reconstruction enhanced by adaptive point cloud correction algorithm | |
| CN110599540B (en) | Real-time three-dimensional human body shape and posture reconstruction method and device under multi-viewpoint camera | |
| CN105136120A (en) | Object displacement image detection system and method | |
| CN104848858B (en) | Quick Response Code and be used for robotic vision-inertia combined navigation system and method | |
| CN106558080B (en) | Monocular camera external parameter online calibration method | |
| CN101814185B (en) | Line structured light vision sensor calibration method for micro-size measurement | |
| Dong et al. | Robust circular marker localization under non-uniform illuminations based on homomorphic filtering | |
| WO2015024407A1 (en) | Power robot based binocular vision navigation system and method based on | |
| CN106607907A (en) | Mobile vision robot and measurement and control method thereof | |
| EP2917754A1 (en) | Image processing method, particularly used in a vision-based localization of a device | |
| CN105403143A (en) | Measurement method and system thereof for acquiring displacement changes of earthquake simulator | |
| CN109191527B (en) | Alignment method and device based on minimum distance deviation | |
| CN105307115A (en) | Distributed vision positioning system and method based on action robot | |
| CN105405126A (en) | Multi-scale air-ground parameter automatic calibration method based on monocular vision system | |
| Kurban et al. | Plane segmentation of kinect point clouds using RANSAC | |
| CN105307116A (en) | Distributed vision positioning system and method based on mobile robot | |
| CN110702101A (en) | Positioning method and system for power inspection scene | |
| CN113112543A (en) | Large-view-field two-dimensional real-time positioning system and method based on visual moving target | |
| CN103644894A (en) | Method for object identification and three-dimensional pose measurement of complex surface | |
| CN205466320U (en) | Intelligent machine hand based on many camera lenses | |
| Thaher et al. | Stereo vision distance estimation employing SAD with canny edge detector | |
| KR20110121343A (en) | Method for measuring 3d pose information using virtual plane information | |
| CN108564626B (en) | Method and apparatus for determining relative pose angle between cameras mounted to an acquisition entity | |
| KR101292074B1 (en) | Measurement system using a camera and camera calibration method using thereof | |
| CN110443123A (en) | A kind of power equipment crusing robot figure image collection processing system and 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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20151209 |