CN112258477B - High-precision thermal infrared imager start-up time testing system and method - Google Patents
High-precision thermal infrared imager start-up time testing system and method Download PDFInfo
- Publication number
- CN112258477B CN112258477B CN202011140061.XA CN202011140061A CN112258477B CN 112258477 B CN112258477 B CN 112258477B CN 202011140061 A CN202011140061 A CN 202011140061A CN 112258477 B CN112258477 B CN 112258477B
- Authority
- CN
- China
- Prior art keywords
- thermal infrared
- infrared imager
- time
- matching
- feature
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
-
- 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
- G06V10/50—Extraction of image or video features by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
- G06V10/507—Summing image-intensity values; Histogram projection analysis
-
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Signal Processing (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Investigating Or Analyzing Materials Using Thermal Means (AREA)
Abstract
The invention relates to the technical field of photoelectric equipment, and discloses a high-precision thermal infrared imager start-up time test system and a test method, which realize the process of automatically calculating the whole start-up time of the thermal infrared imager.
Description
Technical Field
The invention relates to the technical field of photoelectric equipment, in particular to a high-precision thermal infrared imager start-up time test system and a high-precision thermal infrared imager start-up time test method.
Background
The thermal infrared imager is mainly applied to the army and civil aspects. The military aspect is mainly applied to the fields of aviation, aerospace, observation and aiming of individual combat weapons, fire control and guidance of heavy weapons and the like; the civil use mainly comprises the industrial production and equipment detection, night vision, security and other applications. The starting-up time parameter of the thermal infrared imager is one of the key performance parameters of the thermal infrared imager which are studied currently, so that the development of the testing method of the starting-up time of the thermal infrared imager meets the current market demands. The traditional start-up time testing method is mostly completed by adopting a manual timing mode. Most of the tools are stopwatches, and the method has the defects of larger systematic error, low precision, larger artificial interpretation error and the like.
Disclosure of Invention
First, the technical problem to be solved
The embodiment of the invention provides a high-precision thermal infrared imager start-up time test system and a test method, which realize the process of automatically calculating the whole thermal infrared imager start-up time.
(II) summary of the invention
The embodiment of the invention provides a high-precision thermal infrared imager start-up time testing system which comprises an optical platform, an image acquisition and processing system and an upper computer, wherein the optical platform is used for bearing a thermal infrared instrument to be tested, the image acquisition and processing system is connected with the thermal infrared instrument to be tested through a data line, the image acquisition and processing system is also connected with the upper computer, and the upper computer is used for carrying out image feature matching.
The high-precision thermal infrared imager start-up time testing method uses the high-precision thermal infrared imager start-up time testing system, and comprises the following steps:
step one, preparing hardware; placing the thermal infrared imager to be measured on the optical platform and positioning;
step two, establishing a characteristic model library; opening an upper computer and an infrared thermal imager to be tested, establishing a characteristic model M0 of a starting-up ending picture by the upper computer, and storing the characteristic model M0 into a sample library;
step three, matching test; the upper computer performs matching test on the feature models in the sample library, if the matching is successful, the third step is executed, otherwise, the existing feature models in the sample library are deleted and the second step is executed again;
step four, testing preparation; closing the thermal infrared imager to be detected, and opening the upper computer to execute detection work;
step five, starting up test and collecting starting up video; restarting the thermal infrared imager to be tested, and collecting a startup video of the thermal infrared imager to be tested in real time through an image collecting and processing system;
step six, matching image features; and C, analyzing the starting-up video acquired in the step five through a machine vision technology, and determining the starting-up time T through a characteristic model in a sample library.
Preferably, in the sixth step, the Surf algorithm is adopted for image feature matching, which includes the following steps:
step A, constructing a Hessian matrix of M0, generating all interest points, and extracting feature points according to the interest points;
step B, constructing a scale space according to the extracted characteristic points;
step C, positioning the characteristic points, and screening out final stable characteristic points;
step D, distributing the main directions of the feature points;
step E, generating feature point descriptors;
and F, feature point matching, wherein the matching degree is determined by calculating the Euclidean distance between two feature points.
Preferably, after the starting time T is obtained in the step six, comparing the starting time T with preset experience starting threshold Tmin and Tmax, if T is smaller than Tmin or T is larger than Tmax, judging that the starting time T is invalid, and repeatedly executing the step one to the step six or feeding back to a tester.
Preferably, tmin=0.5 s, tmax=60 s.
(III) beneficial effects
The embodiment of the invention provides a high-precision thermal infrared imager start-up time testing method and a matched high-precision thermal infrared imager start-up time testing system, which are used for automatically calculating the whole process of the thermal infrared imager start-up time according to the acquisition and analysis of images by establishing the corresponding relation between the picture characteristics after the start-up and the acquired start-up pictures. In addition, the invention has the characteristics of simple and convenient operation, strong universality, automatic measurement, high precision and the like.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is an interface diagram of a picture after a host computer of a high-precision thermal infrared imager start-up time test system waits to establish a thermal infrared imager start-up in an embodiment of the invention.
Fig. 2 is an interface diagram of a feature model of a picture after the thermal infrared imager is started up, which is controlled by an upper computer of a high-precision thermal infrared imager start-up time test system in an embodiment of the invention.
Fig. 3 is an interface diagram of a high-precision thermal infrared imager start-up time test system in an embodiment of the invention, which is controlled by an upper computer to store a characteristic model of a picture after the thermal infrared imager is started up.
Fig. 4 is an interface diagram of a high-precision thermal infrared imager start-up time test system for testing whether a feature model of a start-up end picture is successfully matched by an upper computer in an embodiment of the invention.
Fig. 5 is an interface diagram of a high-precision thermal infrared imager after starting detection by an upper computer of a system for testing the startup time of the thermal infrared imager in an embodiment of the invention.
Fig. 6 is an interface diagram of an upper computer of a high-precision thermal infrared imager start-up time test system after detection in an embodiment of the invention.
Fig. 7 is an interface diagram of a real-time acquisition and analysis of video by an upper computer of a high-precision thermal infrared imager start-up time test system in an embodiment of the invention.
FIG. 8 is an interface diagram of an upper computer of a high-precision thermal infrared imager start-up time test system displaying test results after the test is completed in an embodiment of the invention.
FIG. 9 is a flow chart of a method for testing the on-time of a high-precision thermal infrared imager in an embodiment of the invention;
fig. 10 is a block diagram of Surf algorithm adopted by the method for testing the start-up time of the high-precision thermal infrared imager in the embodiment of the invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In describing embodiments of the present invention, it should be noted that the terms "first," "second," and "third" are used for clarity in describing the numbering of product components and do not represent any substantial distinction unless explicitly stated or defined otherwise. The directions of the upper, the lower, the left and the right are all the directions shown in the drawings. The specific meaning of the above terms in the embodiments of the present invention will be understood by those of ordinary skill in the art according to specific circumstances.
It should be noted that the term "coupled" is to be interpreted broadly, as being able to be coupled directly or indirectly via an intermediary, unless explicitly stated or defined otherwise. The specific meaning of the terms in the embodiments of the invention will be understood by those of ordinary skill in the art in a specific context.
Fig. 1 is a power-on time test system of a high-precision thermal infrared imager in an embodiment of the invention, which comprises an optical platform, an image acquisition and processing system and an upper computer, wherein the optical platform is used for bearing a thermal infrared instrument to be tested, the image acquisition and processing system is connected with the thermal infrared instrument to be tested through a data line, and the image acquisition and processing system is also connected with the upper computer which is used for carrying out image feature matching.
The high-precision thermal infrared imager start-up time testing method uses the high-precision thermal infrared imager start-up time testing system, and comprises the following steps:
a method for testing the start-up time of a high-precision thermal infrared imager, which automatically calculates the whole start-up time of the thermal infrared imager according to the acquisition and analysis of images by establishing the corresponding relation between the picture characteristics and the acquired start-up picture after the start-up is finished, and tests the thermal infrared imager start-up time by using the technologies of automatic image discrimination, image processing and the like, comprises the following steps:
placing the thermal infrared imager on an optical platform, and connecting a data line of the thermal infrared imager with an image acquisition card;
step two, the image acquisition card is connected with an upper computer;
step three, the upper computer test software is opened, a startup time test interface is entered, and a characteristic model of a picture after the startup of the thermal infrared imager is finished is waited to be established (as shown in figure 1);
step four, the thermal infrared imager is started, a characteristic model of a picture after the thermal infrared imager is started is established through control of an upper computer, and the characteristic model is stored in a sample library (shown in fig. 2 and 3);
step five, testing whether the characteristic model of the starting-up ending picture is successfully matched (shown in fig. 4);
step six, the thermal infrared imager is shut down, an instruction of 'start detection' is sent through the control of an upper computer, and the thermal infrared imager is waited for testing the startup time (shown in fig. 5 and 6);
step seven, restarting the thermal infrared imager, and enabling the upper computer to acquire and analyze video images in real time by means of a high-speed image acquisition and processing system for video display (shown in fig. 7);
and step eight, automatically calculating the whole starting time process of the thermal infrared imager by analyzing and judging by the upper computer, and displaying a starting time value on a screen (shown in fig. 8).
Preferably, in the step six, the Surf algorithm is adopted for image feature matching, and the basic flow of the Surf algorithm can be divided into three major parts: extracting local feature points, describing the feature points and matching the feature points.
1. Feature point extraction
The feature points of Sift are extracted in the DOG pyramid scale space, and the construction of the scale space involves Gaussian convolution, image downsampling and Gaussian difference operations. The interest points which are local extreme points in the scale space and the two-dimensional image space are initially extracted in the scale space, and unstable and wrong interest points with low energy are filtered out, so that final stable characteristic points are obtained.
2. Description of feature points
The feature point description includes two steps, feature point direction assignment and 128-dimensional vector description.
Directional assignment of features: sift obtains gradient directions of all pixels in the vicinity of the feature points, generates a gradient direction histogram, normalizes the gradient direction histogram to 0-360 degrees to 36 directions, and takes the direction represented by the main component of the gradient histogram as the direction of the feature points.
128-dimensional vector description: this is still based on gradient direction histogram expansion, removing 4*4 fast neighborhood around feature point, extracting 8 gradient directions per block, and totaling 128 directions as the descriptors of the feature.
3. Matching of feature points
The matching of the feature points is achieved by calculating the euclidean distance of the 128-dimensional feature points of the two sets of feature points. The smaller the euclidean distance is, the higher the similarity is, and when the euclidean distance is smaller than a set threshold value, it can be determined that the matching is successful.
The Sift algorithm has the advantages of stable characteristics, invariance to rotation, scale transformation and brightness, and stability to a certain degree on video angle transformation and noise; the defects are that the real-time performance is not high, and the feature point extraction capability of the edge smooth target is weak. The Surf improves the extraction and description modes of the features, and the extraction and description of the features are completed in a more efficient mode, and the specific implementation flow is as follows:
step A, constructing a Hessian matrix of M0, generating all interest points, and extracting feature points according to the interest points; the purpose of constructing the Hessian matrix is to generate edge points (mutation points) for image stabilization, which is similar to the effect of Canny and laplace edge detection, and forms a foundation for the following feature extraction. The process of constructing the Hessian matrix corresponds to the gaussian convolution process in the Sift algorithm. The box filter can increase the operation speed and this involves the use of an integral map. The filtering of the image by the box filter is converted into the addition and subtraction operation problem of pixel sums among different areas on the calculated image, which is the strong term of the integral graph, and the integral graph can be simply searched for several times.
Step B, constructing a scale space according to the extracted characteristic points; as with Sift, the scale space of Surf is also composed of O groups L, except that the size of the next group of images in Sift is half of that of the previous group, the sizes of the images in the same group are the same, but the Gaussian blur coefficients are gradually increased; in Surf, the sizes of images among different groups are consistent, the difference is that the sizes of templates of box-type filters used among different groups are gradually increased, and filters with the same size are used among different layers among the same group, but the blurring coefficients of the filters are gradually increased.
Step C, positioning the characteristic points, and screening out final stable characteristic points; and (3) keeping consistent in the positioning process Surf and Sift of the feature points, comparing each pixel point processed by the Hessian matrix with 26 points in the two-dimensional image space and the scale space neighborhood, primarily positioning key points, filtering out the key points with weak energy and the key points positioned in error, and screening out final stable feature points.
Step D, distributing the main directions of the feature points; the Sift feature point direction distribution is to count gradient histograms in a feature point neighborhood, and take directions with the maximum histogram bin value and more than 80% of the maximum bin value as main directions of feature points. In Surf, the characteristic of the harr wavelet in the circular neighborhood of the statistical characteristic point is adopted. In the circular neighborhood of the characteristic point, the sum of the horizontal and vertical harr wavelet characteristics of all points in a 60-degree fan is counted, then the fan rotates at intervals of 0.2 radian, the value of the harr wavelet characteristic in the area is counted again, and finally the direction of the fan with the largest value is taken as the main direction of the characteristic point.
Step E, generating feature point descriptors; similar to Sift, in Surf algorithm, a rectangular block of area 4*4 is taken around the feature point, but the taken rectangular direction is along the main direction of the feature point. Each sub-region counts haar wavelet characteristics for the horizontal and vertical directions of 25 pixels, where both horizontal and vertical directions are relative to the main direction. The haar wavelet is characterized by 4 directions, namely, after a horizontal direction value, after a vertical direction value, after a horizontal direction absolute value and after a vertical direction absolute value. These 4 values are used as feature vectors for each sub-block region, so that a total of 4 x 4 = 64 dimensional vectors are used as descriptors of Surf features, which are reduced by 2 times compared with the descriptors of Sift features.
And F, feature point matching, namely determining the matching degree by calculating Euclidean distance between two feature points, wherein similar to Sift feature point matching, surf is also used for determining the matching degree by calculating Euclidean distance between two feature points, and the shorter the Euclidean distance is, the better the matching degree between the two feature points is represented. The difference is that Surf also adds the judgment of Hessian matrix trace, if the signs of the matrix traces of two feature points are the same, the two features have contrast changes in the same direction, and if the features are different, the contrast change directions of the two feature points are opposite, and even if the Euclidean distance is 0, the page is directly excluded.
Preferably, after the starting time T is obtained in the step six, comparing the starting time T with preset experience starting threshold Tmin and Tmax, if T is smaller than Tmin or T is larger than Tmax, judging that the starting time T is invalid, and repeatedly executing the step one to the step six or feeding back to a tester. Obvious systematic errors caused by system hardware or software faults are prevented.
Preferably, tmin=0.5 s, tmax=60 s, which is given by a person skilled in the relevant art according to industry standards and his own experience.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (4)
1. The utility model provides a high accuracy thermal infrared imager start-up time test method, has used a high accuracy thermal infrared imager start-up time test system, this test system includes optical platform, image acquisition, processing system and host computer, optical platform is used for bearing the thermal infrared instrument that awaits measuring, image acquisition, processing system pass through the data line and are connected with the thermal infrared instrument that awaits measuring, image acquisition, processing system still are connected with the host computer, the host computer is used for carrying out image feature matching, its characterized in that includes the following steps: step one, preparing hardware; placing the thermal infrared imager to be measured on the optical platform and positioning; step two, establishing a characteristic model library; opening an upper computer and an infrared thermal imager to be tested, establishing a characteristic model M0 of a starting-up ending picture by the upper computer, and storing the characteristic model M0 into a sample library; step three, matching test; the upper computer performs matching test on the feature models in the sample library, if the matching is successful, the fourth step is executed, otherwise, the existing feature models in the sample library are deleted and the second step is executed again; step four, testing preparation; closing the thermal infrared imager to be detected, and opening the upper computer to execute detection work; step five, starting up test and collecting starting up video; restarting the thermal infrared imager to be detected, and collecting a startup video of the thermal infrared imager to be detected in real time through the image collecting and processing system; step six, matching image features; and C, analyzing the starting-up video acquired in the step five through a machine vision technology, and determining the starting-up time T through a characteristic model in a sample library.
2. The method for testing the start-up time of the high-precision thermal infrared imager according to claim 1, wherein in the sixth step, a Surf algorithm is adopted for image feature matching, and the method comprises the following steps: step A, constructing a Hessian matrix of M0, generating all interest points, and extracting feature points according to the interest points; step B, constructing a scale space according to the extracted characteristic points; step C, positioning the characteristic points, and screening out final stable characteristic points; step D, distributing the main directions of the feature points; step E, generating feature point descriptors; and F, feature point matching, wherein the matching degree is determined by calculating the Euclidean distance between two feature points.
3. The method for testing the startup time of the high-precision thermal infrared imager according to claim 2, wherein after the startup time T is obtained in the step six, manual verification is further needed, the startup time T is compared with preset empirical startup thresholds Tmin and Tmax, if T < Tmin or T > Tmax, the startup time T is determined to be invalid, and the steps one to six are repeatedly executed or fed back to a tester.
4. A method for testing the on-time of a high-precision thermal infrared imager according to claim 3, wherein tmin=0.5 s and tmax=60 s.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011140061.XA CN112258477B (en) | 2020-10-22 | 2020-10-22 | High-precision thermal infrared imager start-up time testing system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011140061.XA CN112258477B (en) | 2020-10-22 | 2020-10-22 | High-precision thermal infrared imager start-up time testing system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112258477A CN112258477A (en) | 2021-01-22 |
| CN112258477B true CN112258477B (en) | 2023-08-18 |
Family
ID=74263175
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011140061.XA Active CN112258477B (en) | 2020-10-22 | 2020-10-22 | High-precision thermal infrared imager start-up time testing system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112258477B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR19990042767A (en) * | 1997-11-28 | 1999-06-15 | 전주범 | How to automatically time the video cassette recorder |
| CN101901178A (en) * | 2009-05-31 | 2010-12-01 | 鸿富锦精密工业（深圳）有限公司 | Computer system on-off test device and method |
| CN105763917A (en) * | 2016-02-22 | 2016-07-13 | 青岛海信电器股份有限公司 | Terminal booting control method and terminal booting control system |
| CN106341682A (en) * | 2016-08-12 | 2017-01-18 | 广州视源电子科技股份有限公司 | Method, system and device for detecting aging function |
| CN110414353A (en) * | 2019-06-24 | 2019-11-05 | 炬星科技（深圳）有限公司 | Robot booting positioning, operation method for relocating, electronic equipment and storage medium |
| CN111124774A (en) * | 2019-11-24 | 2020-05-08 | 苏州浪潮智能科技有限公司 | Method and related device for testing stability of server in starting process |
-
2020
- 2020-10-22 CN CN202011140061.XA patent/CN112258477B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR19990042767A (en) * | 1997-11-28 | 1999-06-15 | 전주범 | How to automatically time the video cassette recorder |
| CN101901178A (en) * | 2009-05-31 | 2010-12-01 | 鸿富锦精密工业（深圳）有限公司 | Computer system on-off test device and method |
| CN105763917A (en) * | 2016-02-22 | 2016-07-13 | 青岛海信电器股份有限公司 | Terminal booting control method and terminal booting control system |
| CN106341682A (en) * | 2016-08-12 | 2017-01-18 | 广州视源电子科技股份有限公司 | Method, system and device for detecting aging function |
| CN110414353A (en) * | 2019-06-24 | 2019-11-05 | 炬星科技（深圳）有限公司 | Robot booting positioning, operation method for relocating, electronic equipment and storage medium |
| CN111124774A (en) * | 2019-11-24 | 2020-05-08 | 苏州浪潮智能科技有限公司 | Method and related device for testing stability of server in starting process |
Non-Patent Citations (1)
| Title |
|---|
| 国产光栅近红外光谱仪扫描条件对检测结果的影响;秦西云;李军会;杨宇虹;蔡贵民;;光谱学与光谱分析(第02期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112258477A (en) | 2021-01-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | Bottle detection in the wild using low-altitude unmanned aerial vehicles | |
| CN106897995B (en) | A kind of components automatic identifying method towards Automatic manual transmission process | |
| CN110910350B (en) | Nut loosening detection method for wind power tower cylinder | |
| CN105957082A (en) | Printing quality on-line monitoring method based on area-array camera | |
| US8699786B2 (en) | 3D model generating apparatus, method and CRM by line pattern imaging | |
| JP6899189B2 (en) | Systems and methods for efficiently scoring probes in images with a vision system | |
| CN107993258A (en) | A kind of method for registering images and device | |
| CN110533654A (en) | The method for detecting abnormality and device of components | |
| US8315457B2 (en) | System and method for performing multi-image training for pattern recognition and registration | |
| Rashwan et al. | Using curvilinear features in focus for registering a single image to a 3D object | |
| CN104966283A (en) | Imaging layered registering method | |
| Yang et al. | A research of feature-based image mosaic algorithm | |
| CN116935013B (en) | Circuit board point cloud large-scale splicing method and system based on three-dimensional reconstruction | |
| CN117870659A (en) | Visual inertial integrated navigation algorithm based on dotted line characteristics | |
| CN112258477B (en) | High-precision thermal infrared imager start-up time testing system and method | |
| CN116883893A (en) | Tunnel face underground water intelligent identification method and system based on infrared thermal imaging | |
| Feng et al. | Research on an image mosaic algorithm based on improved ORB feature combined with surf | |
| Kropp et al. | Object recognition in bim registered videos for indoor progress monitoring | |
| CN110472085A (en) | 3-D image searching method, system, computer equipment and storage medium | |
| Sun et al. | Vision odometer based on RGB-D camera | |
| CN116892880B (en) | Electronic component high-precision detection system based on machine vision | |
| CN111488785A (en) | Rotary kiln working condition detection method based on in-kiln image | |
| Li et al. | A real-time pineapple matching system based on speeded-up robust features | |
| Jolhip et al. | A comparative analysis of feature detection and matching algorithms for aerial image stitching | |
| CN116823737B (en) | Tunnel wall abnormity detection method and system in low-texture environment |
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 |