CN109492654B - Detection method and device for indoor endoscopic camera - Google Patents
Detection method and device for indoor endoscopic camera Download PDFInfo
- Publication number
- CN109492654B CN109492654B CN201811589538.5A CN201811589538A CN109492654B CN 109492654 B CN109492654 B CN 109492654B CN 201811589538 A CN201811589538 A CN 201811589538A CN 109492654 B CN109492654 B CN 109492654B
- Authority
- CN
- China
- Prior art keywords
- image
- camera
- indoor
- extracting
- region
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
- G06V10/443—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N17/00—Diagnosis, testing or measuring for television systems or their details
- H04N17/002—Diagnosis, testing or measuring for television systems or their details for television cameras
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Signal Processing (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention provides a detection method and a detection device for an indoor endoscopic camera, wherein the detection method comprises the following steps: carrying out image acquisition; carrying out self-adaptive threshold segmentation on the acquired image; extracting and cataloguing connected domains of the segmented images; and performing feature extraction on the extracted connected domain according to a judgment criterion to form a detection result image. The detection device includes: an image acquisition unit for acquiring an image; an image processing unit for performing segmentation, filtering and morphological operations on the acquired image; and the characteristic extraction unit is used for extracting the characteristics of the image and judging whether the image contains the target camera or not. The detection method and the device for the indoor peeping camera are convenient to be used for detecting various indoor hidden wireless and wired peeping cameras, and have clear images and high success rate.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a method and a device for detecting an indoor endoscopic camera.
Background
With the development of photoelectric and communication technologies, photoelectric peeping devices such as pinhole cameras and miniature cameras have been increasingly used in meeting places, exhibition halls and other environments, resulting in information leakage. A set of algorithm and device capable of effectively detecting and peeping the camera are designed, information is guaranteed not to be acquired by photoelectric peeping equipment of an enemy, and the method is a hotspot of current research. The reason for this is that: peep the camera generally the volume less, hide in various corners easily, naked eye is difficult to discover usually, needs an algorithm and a device that can carry out automated inspection to peeping the camera urgently for to the safety inspection of important place occasion, get rid of potential danger, ensure information safety.
Disclosure of Invention
The invention provides a detection method and a detection device for an indoor endoscopic camera, and aims to perform safety detection on important occasions, eliminate potential risks and ensure information safety.
In order to achieve the purpose, the invention provides the following technical scheme:
a detection method of an indoor endoscopic camera comprises the following steps:
1) carrying out image acquisition;
2) carrying out self-adaptive threshold segmentation on the acquired image;
3) extracting and cataloguing connected domains of the segmented images;
4) and performing feature extraction on the extracted connected domain according to a judgment criterion to form a detection result image.
Preferably, the image acquisition in step 1) is performed by a CCD camera, and the CCD camera is illuminated by a laser.
Preferably, the viewing angle of the laser coincides with the viewing angle of the CCD camera.
Preferably, the adaptive threshold segmentation of step 2) comprises the following steps:
1) performing Otsu self-adaptive threshold segmentation on the acquired image;
2) and carrying out filtering and morphological operation on the segmented image to eliminate scattered points and holes in the image.
Preferably, the connected component is extracted in step 3) by using the perimeter, area, major axis and minor axis information of the connected component contour of the image.
The invention also provides a detection device for the indoor endoscopic camera, which comprises:
an image acquisition unit for acquiring an image;
the image processing unit is used for carrying out segmentation, filtering and morphological operation processing on the acquired image;
and the characteristic extraction unit is used for extracting the characteristics of the processed image and judging whether the processed image contains the target camera.
Preferably, the image acquisition unit includes a CCD camera and a laser.
Preferably, the image acquisition unit further comprises a narrow-band filter.
The detection device of the indoor peeping camera provided by the invention utilizes the CCD camera in the image acquisition unit to acquire images, and the visual angle of the laser in the image acquisition unit is superposed with the visual angle of the CCD camera to provide a light source for the CCD camera, so that clear images are obtained. And then the image processing unit and the feature extraction unit are used for carrying out segmentation, filtering and morphological operation on the image, extracting the features of the image, and comprehensively utilizing the information of the perimeter, the area, the long axis, the short axis and the like of the connected domain contour, thereby improving the target detection precision.
The scheme of the invention has the following beneficial effects:
the detection device for the indoor peeping camera provided by the invention utilizes the image acquisition unit to acquire a clearer image, and then utilizes a series of algorithms in the image processing unit and the feature extraction unit to process the image and extract the image containing the target camera, so that the detection device is convenient for detecting various hidden wireless and wired peeping cameras. The detection method of the indoor peeping camera provided by the invention has the advantages that the camera can be detected by utilizing a single-frame image, and compared with the existing multi-frame detection method, the detection method has higher efficiency and strong real-time performance, is easy to realize in an FPGA (field programmable gate array), and has stronger practical value for the development of future handheld peeping camera detection equipment.
The detection method of the indoor peeping camera comprehensively utilizes the information of the perimeter, the area, the long axis, the short axis and the like of the outline of the connected domain to extract the characteristics, and has high detection precision on the target camera.
Drawings
Fig. 1 is a flow chart of a detection method of an indoor peeping camera according to the present invention;
fig. 2 is a block diagram of the detection device of the indoor peeping camera according to the present invention;
fig. 3 is an image including a peeping camera obtained by the detection method of an indoor peeping camera according to the present invention;
fig. 4 is a result image obtained by the detection method of the indoor peeping camera according to the present invention.
Detailed Description
In order to make the technical problems, technical solutions and advantages of the present invention more apparent, the following detailed description is given with reference to the accompanying drawings and specific embodiments.
Example 1
As shown in fig. 1, a method for detecting an indoor peeping camera according to an embodiment of the present invention includes the following steps:
s1, acquiring images under active illumination of a laser;
s2, carrying out self-adaptive threshold segmentation on the acquired image;
s3, extracting and cataloguing connected domains of the segmented images;
and S4, extracting the characteristics of each connected domain according to the judgment criterion to form a detection result image, and completing the detection of the peeping camera.
According to the detection method of the indoor peeping camera, image collection is completed by the CCD camera, the CCD camera is illuminated by the laser, and the visual angle of the laser is coincident with or close to the visual angle of the CCD camera, so that the image acquired by the CCD camera has higher definition.
The detection method of the indoor peeping camera comprises the following specific steps:
and acquiring an image under active illumination of a laser.
Due to the cat eye effect, the gray value of the area where the camera is located is obviously higher than the background gray value, and the image can be divided into a background part and a foreground part by a threshold segmentation method of the collected image, so that the suspected area where the target is located is obtained. And then, filtering the suspected area image, namely, inhibiting the extracted image noise and keeping the detail characteristics of the image. And performing morphological operation, namely extracting image components useful for expressing and describing the shape of the region, such as a boundary, a skeleton and a convex shell from the image, and further performing morphological filtering, thinning, trimming and the like for preprocessing or post-processing to eliminate scattered points and holes in the image to form a segmented image.
And (3) extracting and cataloguing connected domains of the segmented images, namely extracting and cataloguing mutually adjacent pixel sets with gray values of 1 and 255, and removing redundant data.
And performing feature extraction on the extracted connected domain according to a judgment criterion.
The above judgment criterion is expressed as follows:
|C_r-4π|+|a/b-1|≤η (1)
in the formula, C _ r represents the roundness of the region after contour extraction,l is the perimeter of the region after the contour extraction, S is the area of the region after the contour extraction, a and b are the distance between the farthest two points (major axis) and the distance between the nearest two points (minor axis) of the region after the contour extraction, and eta is a threshold. Since 99% or more of the optical lenses of the camera are circular, the spot of the reflected laser light is ideally circular. Due to the influences of actual imaging environment, focusing virtual and real, detection angle and the like, the imaging shape of the camera on the CCD slightly deviates from an ideal circle, but the imaging light spot of the camera can still be detected according to the circle under indoor conditions.
And when the characteristic value extracted from the connected domain meets the formula (1), judging that the target camera exists, and forming a detection result image. The process comprehensively utilizes the information of the perimeter, the area, the long axis, the short axis and the like of the connected domain outline, and improves the target detection precision.
The method has the advantages that the camera detection can be carried out by utilizing the single-frame image, compared with the existing multi-frame detection method, the method is higher in efficiency, strong in real-time performance, easy to realize in an FPGA (field programmable gate array), and higher in practical value for the development of future handheld peeping camera detection equipment.
Example 2
The invention also provides a device for detecting the indoor endoscopic camera, which is shown in fig. 2.
Indoor peep camera detection device includes: an image acquisition unit 1, an image processing unit 2, and a feature extraction unit 3.
The image acquisition unit 1 is used for acquiring images, and comprises a laser for providing illumination and a narrow-band filter. The image processing unit 2 is used to perform segmentation, filtering, morphological operations, etc. on the acquired image. The feature extraction unit 3 is configured to extract image features and determine whether the object to be detected is a real target.
According to the indoor peeping camera detection device provided by the invention, the image is acquired through the image acquisition unit. And then, performing Otsu self-adaptive threshold segmentation, filtering, morphological operation and connected domain extraction and cataloguing on the acquired images through a graphic processing unit, and removing redundant data. And finally, extracting the characteristics of each connected domain through a characteristic extraction unit, and comprehensively utilizing the information of the perimeter, the area, the long axis, the short axis and the like of the outline of the connected domain, thereby improving the target detection precision.
The detection device for the indoor peeping camera provided by the invention can be used for acquiring a clearer image by using the image acquisition unit, processing the image by using a series of algorithms in the image processing unit and the feature extraction unit and then extracting the image containing the target camera, is convenient to be used for detecting various hidden wireless and wired peeping cameras, and has the advantages of clear image and high success rate.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (7)
1. A detection method of an indoor endoscopic camera is characterized by comprising the following steps:
1) carrying out image acquisition;
2) carrying out self-adaptive threshold segmentation on the acquired image;
3) extracting and cataloguing connected domains of the segmented images;
4) extracting the characteristics of the extracted connected domain according to a discrimination criterion, carrying out camera detection by using a single-frame image to form a detection result image,
extracting the connected domain by using the perimeter, the area, the long axis and the short axis information of the connected domain outline of the image in the step 3);
the above criteria are expressed as follows:
|C_r-4π|+|a/b-1|≤η (1)
in the formula, C _ r represents the roundness of the region after contour extraction,l is the perimeter of the region after the contour extraction, S is the area of the region after the contour extraction, a and b are the distance between the farthest two points (major axis) and the distance between the nearest two points (minor axis) of the region after the contour extraction, and eta is a threshold.
2. The method for detecting an indoor peeping camera according to claim 1, wherein the image acquisition in step 1) is performed by a CCD camera, and the CCD camera is illuminated by a laser.
3. The method of claim 2, wherein the viewing angle of the laser coincides with the viewing angle of the CCD camera.
4. The method for detecting an indoor peeking camera according to claim 1, wherein the adaptive threshold segmentation of the step 2) comprises the steps of:
performing Otsu self-adaptive threshold segmentation on the acquired image;
and carrying out filtering and morphological operation on the segmented image, eliminating scattered points and cavities in the image and forming the segmented image.
5. A detection device for an indoor endoscopic camera is characterized by comprising:
an image acquisition unit for acquiring an image;
the image processing unit is used for carrying out segmentation, filtering and morphological operation processing on the acquired image;
the characteristic extraction unit is used for extracting the characteristics of the processed image and judging whether the processed image contains a target camera or not;
the method specifically comprises the following steps: extracting the connected domain by using the perimeter, the area, the long axis and the short axis information of the connected domain outline of the image;
further comprising: extracting the characteristics of the extracted connected domain according to a judgment criterion, and carrying out camera detection by using a single-frame image to form a detection result image;
the criteria are expressed as follows:
|C_r-4π|+|a/b-1|≤η (1)
in the formula, C _ r represents the roundness of the region after contour extraction,l is the perimeter of the region after the contour extraction, S is the area of the region after the contour extraction, a and b are the distance between the farthest two points (major axis) and the distance between the nearest two points (minor axis) of the region after the contour extraction, and eta is a threshold.
6. The apparatus for detecting the peeping camera according to claim 5, wherein the image capturing unit comprises a CCD camera and a laser.
7. The apparatus according to claim 5, wherein the image capturing unit further comprises a narrow band filter.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811589538.5A CN109492654B (en) | 2018-12-25 | 2018-12-25 | Detection method and device for indoor endoscopic camera |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811589538.5A CN109492654B (en) | 2018-12-25 | 2018-12-25 | Detection method and device for indoor endoscopic camera |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109492654A CN109492654A (en) | 2019-03-19 |
CN109492654B true CN109492654B (en) | 2021-02-12 |
Family
ID=65711746
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811589538.5A Active CN109492654B (en) | 2018-12-25 | 2018-12-25 | Detection method and device for indoor endoscopic camera |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109492654B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110991270B (en) * | 2019-11-15 | 2023-10-20 | 泰康保险集团股份有限公司 | Text recognition method, device, electronic equipment and storage medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101464952A (en) * | 2007-12-19 | 2009-06-24 | 中国科学院自动化研究所 | Abnormal behavior identification method based on contour |
CN106060473A (en) * | 2016-06-27 | 2016-10-26 | 秦艳 | Big data processing method and big data processing device |
CN106296644A (en) * | 2015-06-10 | 2017-01-04 | 浙江托普云农科技股份有限公司 | Method is analyzed in a kind of corn kernel species test based on image procossing |
CN108226953A (en) * | 2017-12-19 | 2018-06-29 | 中国人民解放军战略支援部队航天工程大学 | A kind of pinhole cameras detection method and device based on dual-beam alternate emission |
CN108320303A (en) * | 2017-12-19 | 2018-07-24 | 中国人民解放军战略支援部队航天工程大学 | A kind of pinhole cameras detection method based on binocular detection |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101469985A (en) * | 2007-12-26 | 2009-07-01 | 河海大学常州校区 | Single-frame image detection apparatus for vehicle queue length at road junction and its working method |
CN102760295A (en) * | 2012-08-02 | 2012-10-31 | 成都众合云盛科技有限公司 | Fire disaster image detection system for edge detection-based operator |
-
2018
- 2018-12-25 CN CN201811589538.5A patent/CN109492654B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101464952A (en) * | 2007-12-19 | 2009-06-24 | 中国科学院自动化研究所 | Abnormal behavior identification method based on contour |
CN106296644A (en) * | 2015-06-10 | 2017-01-04 | 浙江托普云农科技股份有限公司 | Method is analyzed in a kind of corn kernel species test based on image procossing |
CN106060473A (en) * | 2016-06-27 | 2016-10-26 | 秦艳 | Big data processing method and big data processing device |
CN108226953A (en) * | 2017-12-19 | 2018-06-29 | 中国人民解放军战略支援部队航天工程大学 | A kind of pinhole cameras detection method and device based on dual-beam alternate emission |
CN108320303A (en) * | 2017-12-19 | 2018-07-24 | 中国人民解放军战略支援部队航天工程大学 | A kind of pinhole cameras detection method based on binocular detection |
Non-Patent Citations (2)
Title |
---|
"Recognizing cat-eye targets with dual criterionsof shape and modulation frequency";Ximing Ren 等;《Chinese Optics Letters》;20110410;第041101-1至041101-4页 * |
"基于图像处理的地铁隧道裂缝检测技术研究";胡皙;《《中国优秀硕士学位论文全文数据库信息科技辑》》;20140615;第2-3章 * |
Also Published As
Publication number | Publication date |
---|---|
CN109492654A (en) | 2019-03-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105894499B (en) | A kind of space object three-dimensional information rapid detection method based on binocular vision | |
RU2595495C2 (en) | Image processing device, image processing method and image processing system | |
CN112614062B (en) | Colony counting method, colony counting device and computer storage medium | |
CN103177445B (en) | Based on the outdoor tomato recognition methods of fragmentation threshold Iamge Segmentation and spot identification | |
CN110599507B (en) | Tomato identification and positioning method and system | |
CN108305223B (en) | Image background blurring processing method and device | |
CN113252568A (en) | Lens surface defect detection method, system, product and terminal based on machine vision | |
CN109697444B (en) | Object identification method and device based on depth image, equipment and storage medium | |
WO2024051067A1 (en) | Infrared image processing method, apparatus, and device, and storage medium | |
CN110276831A (en) | Constructing method and device, equipment, the computer readable storage medium of threedimensional model | |
CN111257329A (en) | Smartphone camera defect detection method and detection system | |
CN113837065A (en) | Image processing method and device | |
CN110288623A (en) | The data compression method of unmanned plane marine cage culture inspection image | |
CN115100104A (en) | Defect detection method, device and equipment for glass ink area and readable storage medium | |
CN109492654B (en) | Detection method and device for indoor endoscopic camera | |
CN104715250B (en) | cross laser detection method and device | |
CN114018946B (en) | OpenCV-based high-reflectivity bottle cap defect detection method | |
CN103413318B (en) | Target ball mirror surface center positioning method | |
CN104992448A (en) | Automatic positioning method for robot picking grapes in a damage-free way | |
CN111611866B (en) | Flame detection and identification method and system based on YCrCb and LAB color spaces | |
CN109544535B (en) | Peeping camera detection method and system based on optical filtering characteristics of infrared cut-off filter | |
CN110827375B (en) | Infrared image true color coloring method and system based on low-light-level image | |
CN116883498A (en) | Visual cooperation target feature point positioning method based on gray centroid extraction algorithm | |
Karakaya et al. | An iris segmentation algorithm based on edge orientation for off-angle iris recognition | |
CN113033355B (en) | Abnormal target identification method and device based on intensive power transmission channel |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |