CN203840438U - Device for extracting saliency by using optical imaging - Google Patents
Device for extracting saliency by using optical imaging Download PDFInfo
- Publication number
- CN203840438U CN203840438U CN201420179903.6U CN201420179903U CN203840438U CN 203840438 U CN203840438 U CN 203840438U CN 201420179903 U CN201420179903 U CN 201420179903U CN 203840438 U CN203840438 U CN 203840438U
- Authority
- CN
- China
- Prior art keywords
- semi
- image
- ccd
- input object
- light path
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Landscapes
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The utility model discloses a device for extracting the saliency by using optical imaging. The device comprises an incoherent light source, a collimation collimator, an image of an input object surface, a semi-transparent and semi-reflection mirror, four Fourier lenses, two spatial filters and two CCD/CMOS imaging cameras. The incoherent light source generates parallel light after passing through the collimation collimator, and the parallel light is irradiated on the image of the input object surface so as to realize lighting, thereby acting as an object; a light path of the object is split through the semi-transparent and semi-reflection mirror, one path is imaged to the first CCD/CMOS imaging camera through a 4f system, and the other path is imaged to the second CCD/CMOS imaging camera through another 4f system. The device disclosed by the utility model is simple in structure implementation, can be effectively integrated into various imaging detection instruments in the prior art, and guides the image acquisition process in real time through saliency images, thereby being capable of simulating the process of biological vision more effectively.
Description
Technical field
The utility model relates to optical imagery and image processing techniques, relates in particular to a kind of conspicuousness extraction element that utilizes optical imagery.
Background technology
Visual information is the topmost information source in the human knowledge world, and what the mankind received approximately have, and 75% information is obtained by these means.The information of obtaining real world with human eye and brain is the same, and the image that optical image sensor obtains, as simulating human visual performance, has also recorded a large amount of information.Along with the development of optical image technology and picture signal treatment theory, Image Engineering also become one abundant in content and develop subject rapidly.Image (process and analyze) system comprise image collection, demonstration, storage, communicate by letter, processing and analysis, and be widely used in the every field in national economy, as scientific research, industrial production, health care, education etc., to promoting social development, improving people's living standard and all play important effect.
Along with the fast development of computing power and technology, people more and more wish that computer can more independently and intelligently complete many tasks.If realize so target, computer must be able to be understood environment around.Vision is the main mode of human perception external information, and the computer simulation mankind so also will understand surrounding environment by the relevant ability of visually-perceptible, and this is intelligently one of crucial.
The mankind's visually-perceptible ability is by evolving for a long time, and analysis environments quickly and efficiently, extracts rapidly interested object and region, and this is a kind of vision significance extractability.Corresponding with people's vision significance detection behavior, in image is processed, can realize by saliency detection method the extraction of saliency information.Saliency is surveyed and is intended to obtain high-quality Saliency maps, has reflected the significance degree of zones of different in image---the degree of concern/interest level of human eye.
Salient region detection technique has a wide range of applications, in the fast browsing of target automatic detection, image retrieval, object identification image divided video and gather, the field such as the picture editting of image and video compression, image automation pruning and perception of content can apply.At present the application of conspicuousness detection technique also cannot be satisfactory, and except the quality of remarkable figure itself is not high enough, conspicuousness information application mode and method be maturation not enough, need to find more gratifying implementation method; In addition, general conspicuousness extracting method is all to set up corresponding mathematics model for image, on electronic computer, just calculates, and efficiency and effect generally can not be taken into account simultaneously.How to set up the quick conspicuousness extracting method that more meets human visual system and be also one of difficult problem that current image processes boundary.
Summary of the invention
The utility model, for the deficiencies in the prior art, provides a kind of conspicuousness extraction element that utilizes optical imagery, the complexity that effectively simplified image conspicuousness is extracted, and raising system is processed the processing speed of image.
Utilize a conspicuousness extraction element for optical imagery, comprise image, semi-transparent semi-reflecting lens, four fourier lenses, two spatial filters and two CCD/CMOS imaging cameras of incoherent light source, collimation parallel light tube, input object plane;
Described incoherent light source is arranged in the front focus of collimation parallel light tube, light source is outgoing directional light after punctual parallel light tube, input object plane in parallel light path is placed image as object, semi-transparent semi-reflecting lens is set afterwards, semi-transparent semi-reflecting lens and optical axis angle at 45 °, along transmitted light path, interval light path f from input object plane, set gradually the first fourier lense, the first spatial filter, the second fourier lense and a CCD/CMOS imaging camera, along reflected light path, interval light path f from input object plane, set gradually the 3rd fourier lense, second space filter, the 4th fourier lense and the 2nd CCD/CMOS imaging camera,
Four described fourier lense structures are identical;
Two described spatial filter aperture differences.
Compared with prior art, the technical program has the following advantages: the utility model utility model device, and efficient and stable.Thereby be efficiently owing to using the Fourier transform that realizes image and the inverse transformation that optics operation method can be real-time, improve greatly the arithmetic speed of conspicuousness extraction algorithm, simultaneously by the method for point optical detection on imaging optical path, so can acquire the each resolution Saliency maps picture that is the systemic resolution limit to the maximum; Stable is to realize simply due to the structure of whole system, can effectively be integrated in existing various imaging detection instrument, by Saliency maps as real-time instruction image acquisition procedures, thereby can more effective simulation biological vision process.
Brief description of the drawings
Fig. 1 is the concrete operations flow chart of the utility model method;
Fig. 2 is the two-way 4f light path system that the utility model method builds.
Embodiment
For the conspicuousness of obtaining image distributes, the utility model utilizes optical imagery mode, utilizes the real-time feature of the Calculation of Optical Path, realizes fast the extraction of conspicuousness, obtains Saliency maps.
Below in conjunction with accompanying drawing, by specific embodiment, the technical solution of the utility model is carried out to clear, complete description.
As shown in Figure 2, a kind of conspicuousness extraction element that utilizes optical imagery, comprises the image 3, semi-transparent semi-reflecting lens 4 of incoherent light source 1, collimation parallel light tube 2, input object plane, four fourier lenses, two spatial filters and two CCD/CMOS imaging cameras;
Described incoherent light source 1 is arranged in the front focus of collimation parallel light tube 2, incoherent light source is outgoing directional light after punctual parallel light tube, the image 3 of the placement input object plane in parallel light path, semi-transparent semi-reflecting lens 4 is set afterwards, semi-transparent semi-reflecting lens and optical axis angle at 45 °, along transmitted light path, interval light path f from input object plane, set gradually the first fourier lense 5, the first spatial filter 6, the second fourier lense 7 and a CCD/CMOS imaging camera 8, along reflected light path, interval light path f from input object plane, set gradually the 3rd fourier lense 9, second space filter 10, the 4th fourier lense 11 and the 2nd CCD/CMOS imaging camera 12, four described fourier lense structures are identical, two described spatial filter aperture differences.
As shown in Figure 1, incoherent light source generates directional light after collimation parallel light tube, and the image that irradiates input object plane is realized illumination, as object; Object light path is through semi-transparent semi-reflecting lens light splitting, and a road is through 4f system imaging to a CCD/CMOS imaging camera, and another road is also through another one 4f system imaging to the two CCD/CMOS imaging cameras; Two of 4f system separately frequency plane use different accurate pin holes to carry out filtering operation, for image is selected different frequencies.
Although the utility model with preferred embodiment openly as above; but it is not for limiting the utility model; any those skilled in the art are not departing from spirit and scope of the present utility model; can utilize method and the technology contents of above-mentioned announcement to make possible variation and amendment to technical solutions of the utility model; therefore; every content that does not depart from technical solutions of the utility model; any simple modification, equivalent variations and the modification above embodiment done according to technical spirit of the present utility model, all belong to the protection range of technical solutions of the utility model.
Claims (3)
1. utilize a conspicuousness extraction element for optical imagery, comprise image, semi-transparent semi-reflecting lens, four fourier lenses, two spatial filters and two CCD/CMOS imaging cameras of incoherent light source, collimation parallel light tube, input object plane;
It is characterized in that: described incoherent light source is arranged in the front focus of collimation parallel light tube, incoherent light source is outgoing directional light after punctual parallel light tube, the image of the placement input object plane in parallel light path, semi-transparent semi-reflecting lens is set afterwards, semi-transparent semi-reflecting lens and optical axis angle at 45 °, along transmitted light path, interval light path f from input object plane, set gradually the first fourier lense, the first spatial filter, the second fourier lense and a CCD/CMOS imaging camera, along reflected light path, interval light path f from input object plane, set gradually the 3rd fourier lense, second space filter, the 4th fourier lense and the 2nd CCD/CMOS imaging camera.
2. a kind of conspicuousness extraction element that utilizes optical imagery according to claim 1, is characterized in that: four described fourier lense structures are identical.
3. a kind of conspicuousness extraction element that utilizes optical imagery according to claim 1, is characterized in that: two described spatial filter aperture differences.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201420179903.6U CN203840438U (en) | 2014-04-14 | 2014-04-14 | Device for extracting saliency by using optical imaging |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201420179903.6U CN203840438U (en) | 2014-04-14 | 2014-04-14 | Device for extracting saliency by using optical imaging |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN203840438U true CN203840438U (en) | 2014-09-17 |
Family
ID=51518231
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201420179903.6U Expired - Fee Related CN203840438U (en) | 2014-04-14 | 2014-04-14 | Device for extracting saliency by using optical imaging |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN203840438U (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103973976A (en) * | 2014-04-14 | 2014-08-06 | 杭州电子科技大学 | Saliency extraction device and method with optical imaging adopted |
| WO2019218895A1 (en) * | 2018-05-15 | 2019-11-21 | 成都理想境界科技有限公司 | Feature extraction method and system for deep learning |
-
2014
- 2014-04-14 CN CN201420179903.6U patent/CN203840438U/en not_active Expired - Fee Related
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103973976A (en) * | 2014-04-14 | 2014-08-06 | 杭州电子科技大学 | Saliency extraction device and method with optical imaging adopted |
| CN103973976B (en) * | 2014-04-14 | 2017-06-06 | 杭州电子科技大学 | The conspicuousness extraction element and method of a kind of utilization optical imagery |
| WO2019218895A1 (en) * | 2018-05-15 | 2019-11-21 | 成都理想境界科技有限公司 | Feature extraction method and system for deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103973976A (en) | Saliency extraction device and method with optical imaging adopted | |
| CN201854353U (en) | Multi-spectral image fusion camera | |
| EP3144879A1 (en) | A method and an apparatus for generating data representative of a light field | |
| RU2012143140A (en) | SYSTEM FOR ANALYSIS IN TREATMENT OF SKIN USING SPECTRAL IMAGE DATA FOR THE GENERATION OF THE 3D 3D MODEL | |
| CN115220211B (en) | Microscopic imaging system and method based on deep learning and light field imaging | |
| CN203840438U (en) | Device for extracting saliency by using optical imaging | |
| CN110827355B (en) | Moving target rapid positioning method and system based on video image coordinates | |
| CN105488780A (en) | Monocular vision ranging tracking device used for industrial production line, and tracking method thereof | |
| Hua et al. | Kinect‐Based Real‐Time Acquisition Algorithm of Crop Growth Depth Images | |
| Zhai et al. | Image real-time augmented reality technology based on spatial color and depth consistency | |
| KR20140003107A (en) | Apparatus and method for providing augmented reality | |
| CN105809159A (en) | Imaging-based visual weight graph extraction method | |
| CN103269413A (en) | Multi-source video fusion system | |
| CN109492654B (en) | Detection method and device for indoor endoscopic camera | |
| CN111754543B (en) | Image processing method, device and system | |
| Xu et al. | Real-time panoramic map modeling method based on multisource image fusion and three-dimensional rendering | |
| CN109257524B (en) | Full-focus scanning imaging method based on Wigner distribution function | |
| CN106776838A (en) | A kind of massive video analysis and quick retrieval system based on cloud computing | |
| CN108583115B (en) | Manufacturing system of mouse early embryo model | |
| Agrawal et al. | Digitization of biomimetic vision sensor based on the common housefly (Musca Domestica) | |
| CN103927757B (en) | Target object stereo vision three-dimensional analysis and processing method based on cascade sampling | |
| CN110460756A (en) | A kind of scene removes rain image processing method and device automatically in real time | |
| Gu et al. | SATD based fast intra prediction for HEVC | |
| CN103997642A (en) | Stereo camera remote convergence shooting quality objective evaluation method | |
| CN104010188B (en) | The parallel shooting quality method for objectively evaluating of a kind of stereoscopic camera long distance |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| ASS | Succession or assignment of patent right |
Owner name: HANGZHOU QINGQU TECHNOLOGY CO., LTD. Free format text: FORMER OWNER: HANGZHOU ELECTRONIC SCIENCE AND TECHNOLOGY UNIV Effective date: 20150602 |
|
| C41 | Transfer of patent application or patent right or utility model | ||
| COR | Change of bibliographic data |
Free format text: CORRECT: ADDRESS; FROM: 310018 HANGZHOU, ZHEJIANG PROVINCE TO: 310000 HANGZHOU, ZHEJIANG PROVINCE |
|
| TR01 | Transfer of patent right |
Effective date of registration: 20150602 Address after: 310000 Hangzhou economic and Technological Development Zone, Hangzhou Dianzi University, room 519, Pioneer Park, Patentee after: Hangzhou Qing Qu Science and Technology Ltd. Address before: Hangzhou City, Zhejiang province 310018 Xiasha Higher Education Park No. 2 street Patentee before: Hangzhou Electronic Science and Technology Univ |
|
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20140917 Termination date: 20180414 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |