CN112565607A - Intelligent safety helmet image anti-shaking method and device - Google Patents
Intelligent safety helmet image anti-shaking method and device Download PDFInfo
- Publication number
- CN112565607A CN112565607A CN202011411164.5A CN202011411164A CN112565607A CN 112565607 A CN112565607 A CN 112565607A CN 202011411164 A CN202011411164 A CN 202011411164A CN 112565607 A CN112565607 A CN 112565607A
- Authority
- CN
- China
- Prior art keywords
- image
- reference image
- environment
- images
- remote monitoring
- 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
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/68—Control of cameras or camera modules for stable pick-up of the scene, e.g. compensating for camera body vibrations
- H04N23/682—Vibration or motion blur correction
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Helmets And Other Head Coverings (AREA)
Abstract
The invention discloses an intelligent safety helmet image anti-shaking method and a device thereof, wherein the method comprises the following steps: sending the current position information to a remote monitoring center; acquiring a background image provided by a remote monitoring center, and taking the background image as a reference image; performing gridding and blocking on the reference image to form a plurality of image blocks, calculating the texture characteristics of each image block, and selecting a plurality of image blocks with rich texture information as reference image blocks; searching in the current monitoring image to find an area which is most matched with the reference image block, and if the number of the successfully matched reference image blocks reaches a preset number, calculating the relative displacement of the current monitoring image relative to the reference image from a plurality of relative displacements of the successfully matched reference image blocks; and carrying out translation correction on the current video image according to the calculated relative displacement in the monitored image, and obtaining the monitored image after eliminating the jitter after the translation correction. The invention has the advantages of high processing speed, high reliability and high stability.
Description
Technical Field
The invention relates to the technical field of building equipment, in particular to an intelligent anti-shaking method and device for safety helmet images.
Background
In the real-time monitoring process of intelligent safety helmet video monitoring, due to the fact that the position of a camera is high, the camera can shake up, down, left and right in windy weather or due to ground vibration, and therefore the video image output by the camera shakes, picture quality is affected, technical means are needed to be adopted to enable the image to be stable, video shaking is eliminated, and monitoring quality is improved.
The basic method of video anti-jitter is image registration, i.e. geometric transformation (e.g. affine transformation) between two images is calculated based on image feature similarity, and then a mapping relation of pixel points between the images is established on the basis of the geometric transformation. The current popular image registration technology is based on image feature points, firstly, key points (such as angular points) are respectively extracted from two images, then, the geometric transformation between the images is calculated through the similarity measurement of the key points between the images and the geometric consistency between point sets, and finally, the geometric transformation is used for mapping pixel points in one image to corresponding pixel points in the other image. Such a feature point-based method can achieve higher registration accuracy even when the distortion between images is large, but has the problems of large calculation amount and low processing speed.
Disclosure of Invention
The invention aims to provide an intelligent safety helmet image anti-shaking method and device capable of improving processing speed.
The invention provides an image anti-shaking method for an intelligent safety helmet, which comprises the following steps:
sending the current position information to a remote monitoring center;
acquiring a background image provided by a remote monitoring center, and taking the background image as a reference image;
performing gridding and blocking on the reference image to form a plurality of image blocks, calculating the texture characteristics of each image block, and selecting a plurality of image blocks with rich texture information as reference image blocks;
searching in the current monitoring image to find an area which is most matched with the reference image block, and if the number of the successfully matched reference image blocks reaches a preset number, calculating the relative displacement of the current monitoring image relative to the reference image from a plurality of relative displacements of the successfully matched reference image blocks;
and carrying out translation correction on the current video image according to the calculated relative displacement in the monitored image, and obtaining the monitored image after eliminating the jitter after the translation correction.
In one embodiment, before the step of "sending the current location information to the remote monitoring center", the method further comprises the following steps:
shooting an environment image through an infrared camera arranged on a pneumatic damping device, and sending the environment image and the position of the environment image to the remote monitoring center, wherein a plurality of environment images are shot at the same position;
and the remote monitoring center selects the optimal environment image at the position and marks the position corresponding to the environment image according to the environment image and the position of the environment image.
In one embodiment, before the step "shooting an environment image by an infrared camera installed on a pneumatic shock absorption device, and sending the environment image and the position where the environment image is located to the remote monitoring center, wherein the same position is used for shooting a plurality of environment images", the method further comprises the following steps:
acquiring a shooting preparation signal;
detecting the atmospheric pressure in the pneumatic damping device according to the shooting preparation signal;
and when the atmospheric pressure is greater than a first preset value, the camera shooting button works normally, otherwise, a damping abnormity alarm signal is sent out.
In one embodiment, before the step "shooting an environment image by an infrared camera installed on a pneumatic shock absorption device, and sending the environment image and the position where the environment image is located to the remote monitoring center, wherein the same position is used for shooting a plurality of environment images", the method further comprises the following steps:
acquiring a shooting preparation signal;
detecting the atmospheric pressure in the pneumatic damping device for multiple times within a preset time period according to the shooting preparation signal;
and when the difference value between the atmospheric pressure detected for the first time and the atmospheric pressure detected for the last time in a preset time period is smaller than a second preset value, the camera shooting button works normally, otherwise, a shock absorption abnormity alarm signal is sent out.
In one embodiment, the intelligent helmet image anti-shaking method further comprises the following steps:
collecting the angle and the acceleration of the lens;
calculating the angle and the acceleration to obtain the shake quantity of the thermal infrared camera lens;
and controlling a part of the air bags of the pneumatic damping device, which surround the plurality of air bags in the lens, to inflate, and deflating the part of the air bags.
In one embodiment, the method of "selecting the best environment image at the position" is: and modeling the acquired images to acquire a scene image of a shooting scene.
In one embodiment, the intelligent helmet image anti-shaking method further comprises the following steps: the current image is corrected according to the relative displacement of the image, and pixel interpolation processing is needed when the image is subjected to translation correction transformation.
In a second aspect, the present invention also discloses an image anti-shaking device for an intelligent safety helmet, comprising:
the position information sending module is used for sending the current position information to the remote monitoring center;
the background image acquisition module is used for acquiring a background image provided by a remote monitoring center and taking the background image as a reference image;
the image segmentation module is used for gridding and blocking the reference image to form a plurality of image blocks, calculating the texture characteristics of each image block, and selecting a plurality of image blocks with rich texture information as reference image blocks;
the image searching module is used for searching in the current monitoring image to find out an area which is most matched with the reference image block, and if the number of the successfully matched reference image blocks reaches a preset number, the relative displacement of the current monitoring image relative to the reference image is calculated from a plurality of relative displacements of the successfully matched reference image blocks;
and the image correction module is used for carrying out translation correction on the current video image according to the calculated relative displacement in the monitored image, and obtaining the monitored image after the shake is eliminated after the translation correction.
The invention has the following beneficial effects:
1. the processing speed is high: the video monitoring requires real-time processing, and because the background image is processed and provided by the remote monitoring center, the algorithm only extracts the features of the reference image and requires fewer matching features, the calculation amount of the algorithm is not large, the real-time requirement can be met, the hardware requirement is low, the cost is reduced, and the popularization and the application are convenient;
2. reliability and stability are high: the video monitoring scenes are various, and the algorithm provided by the invention can automatically select image characteristics according to the image content and adaptively adjust algorithm parameters, so that the reliability and the stability are higher under various environmental conditions.
Drawings
FIG. 1 is a flow chart of an image anti-shaking method for an intelligent helmet according to the present invention.
Fig. 2 is a schematic block diagram of the image anti-shaking device of the intelligent safety helmet of the present invention.
Detailed Description
The present invention will be described in detail below with reference to the accompanying drawings and examples. It should be noted that, if not conflicting, the embodiments of the present invention and the features of the embodiments may be combined with each other within the scope of protection of the present invention.
Referring to fig. 1, the present invention provides an image anti-shaking method for an intelligent safety helmet, comprising the following steps:
s1, sending the current position information to a remote monitoring center;
the current position is the position where the intelligent safety helmet is located, and the remote monitoring center is a monitoring center in communication connection with the intelligent safety helmet through the Internet of things.
S2, obtaining a background image provided by a remote monitoring center, and taking the background image as a reference image;
the remote monitoring center stores background images related to the scene of the construction site, and the images can be obtained through real-time shooting and also can be pre-stored in a server of the remote monitoring center.
S3, performing gridding and blocking on the reference image to form a plurality of image blocks, calculating the texture characteristics of each image block, and selecting a plurality of image blocks with rich texture information as reference image blocks;
the calculating the texture features of each image block comprises the following steps: the method comprises the steps of firstly translating an image block along 8 directions (up, down, left, right, left up, right up, left down and right down) respectively to obtain 8 sub-images, then differentiating the image block and the sub-images in the 8 directions respectively, taking an accumulated value of pixel difference absolute values as image block similarity measurement of an area, taking the minimum value of the 8 image block similarity measurement as an image block texture feature richness index, and selecting a plurality of image blocks with rich texture information as a reference image block.
S4, searching in the current monitoring image to find the area which is most matched with the reference image block, if the number of the successfully matched reference image blocks reaches the preset number, calculating the relative displacement of the current monitoring image relative to the reference image from the relative displacement of the successfully matched reference image blocks;
searching for a matching area of a reference image block within a current image includes: firstly, traversing and searching areas matched with the reference image blocks in a 16 x 16 neighborhood of a corresponding position of a current image, calculating the similarity of each area, taking the area with the minimum similarity as a matching area, and recording the relative displacement and the matching similarity of the matching area and the reference image blocks; and if the matching similarity measure is smaller than the image block matching threshold, the reference image block is considered to be successfully searched and matched.
And S5, performing translation correction on the current video image according to the calculated relative displacement in the monitored image, and acquiring the monitored image after removing the jitter after the translation correction.
The current image is corrected according to the relative displacement of the image, and pixel interpolation processing is needed when the image is subjected to translation correction conversion. The correcting the current image according to the relative displacement of the image includes: and translating the current image according to the relative displacement, and determining the mapping relation of pixel points of the two images before and after translation, wherein the pixel value of the pixel point corresponding to the new image is calculated through bilinear interpolation because the relative displacement is sub-pixel precision.
Before the step of sending the current position information to the remote monitoring center, the method further comprises the following steps:
shooting an environment image through an infrared camera arranged on a pneumatic damping device, and sending the environment image and the position of the environment image to the remote monitoring center, wherein a plurality of environment images are shot at the same position;
and the remote monitoring center selects the optimal environment image at the position and marks the position corresponding to the environment image according to the environment image and the position of the environment image.
Because before the normal shooting of workers, the environmental images of areas such as construction sites and the like are sent to the remote monitoring center, and the images are processed through the remote monitoring center, the computing capability requirement and the hardware requirement of the intelligent safety helmet are reduced, and the computing efficiency is improved.
The method for selecting the best environment image at the position comprises the following steps: and modeling the acquired images to acquire a scene image of a shooting scene.
The modeling mode can adopt a Gaussian mixture model, and the model can be multi-modal and models each pixel independently.
Before the step of shooting the environment image through the infrared camera installed on the pneumatic damping device and sending the environment image and the position where the environment image is located to the remote monitoring center, wherein the same position is used for shooting a plurality of environment images, the method also comprises the following steps:
acquiring a shooting preparation signal;
when the user starts the camera, a shooting preparation signal is formed.
Detecting the atmospheric pressure in the pneumatic damping device according to the shooting preparation signal;
and when the atmospheric pressure is greater than a first preset value, the camera shooting button works normally, otherwise, a damping abnormity alarm signal is sent out.
The intelligent safety helmet is used for the pneumatic damping device of absorbing through the self-checking to can ensure the shock attenuation effect, wherein, pneumatic damping device can establish a plurality of annular gasbags around the camera lens including the cover, equidistant setting between the gasbag.
In another embodiment, before the step "shooting an environment image by an infrared camera installed on a pneumatic damping device, and sending the environment image and the position where the environment image is located to the remote monitoring center, wherein the same position is used for shooting a plurality of environment images", the method further comprises the following steps:
acquiring a shooting preparation signal;
detecting the atmospheric pressure in the pneumatic damping device for multiple times within a preset time period according to the shooting preparation signal;
and when the difference value between the atmospheric pressure detected for the first time and the atmospheric pressure detected for the last time in a preset time period is smaller than a second preset value, the camera shooting button works normally, otherwise, a shock absorption abnormity alarm signal is sent out.
The atmospheric pressure in the pneumatic damping device is detected for multiple times in the preset time period, so that the performance of the current pneumatic damping device can be judged more accurately, and the damping effect is better ensured.
The intelligent safety helmet image anti-shaking method further comprises the following steps:
collecting the angle and the acceleration of the lens;
calculating the angle and the acceleration to obtain the shake quantity of the thermal infrared camera lens;
and controlling a part of the air bags of the pneumatic damping device, which surround the plurality of air bags in the lens, to inflate, and deflating the part of the air bags.
The camera is dynamically adjusted by inflating and deflating the air bag of the pneumatic damping device, so that the damping effect can be improved.
Referring to fig. 2, the present invention also discloses an image anti-shaking device for an intelligent safety helmet, comprising:
the position information sending module 1 is used for sending the current position information to a remote monitoring center;
the background image acquisition module 2 is used for acquiring a background image provided by a remote monitoring center and taking the background image as a reference image;
the image segmentation module 3 is used for gridding and blocking the reference image to form a plurality of image blocks, calculating the texture characteristics of each image block, and selecting a plurality of image blocks with rich texture information as reference image blocks;
the image searching module 4 is configured to search in the current monitored image to find an area that best matches the reference image block, and if the number of successfully matched reference image blocks reaches a preset number, calculate a relative displacement amount of the current monitored image with respect to the reference image from a plurality of relative displacement amounts of the successfully matched reference image blocks;
and the image correction module 5 is used for carrying out translation correction on the current video image according to the calculated relative displacement amount in the monitored image, and obtaining the monitored image after the shake is eliminated after the translation correction.
The invention has the following beneficial effects:
1. the processing speed is high: the video monitoring requires real-time processing, and because the background image is processed and provided by the remote monitoring center, the algorithm only extracts the features of the reference image and requires fewer matching features, the calculation amount of the algorithm is not large, the real-time requirement can be met, the hardware requirement is low, the cost is reduced, and the popularization and the application are convenient;
2. reliability and stability are high: the video monitoring scenes are various, and the algorithm provided by the invention can automatically select image characteristics according to the image content and adaptively adjust algorithm parameters, so that the reliability and the stability are higher under various environmental conditions.
The intelligent safety helmet image anti-shaking method provided by the invention is described in detail, a specific example is applied in the text to explain the principle and the implementation mode of the invention, and the description of the embodiment is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In summary, the present disclosure is only an embodiment of the present disclosure, and not intended to limit the scope of the present disclosure, and all equivalent structures or equivalent flow transformations made by using the present disclosure and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present disclosure, and should not be construed as limiting the present disclosure.
Claims (8)
1. An intelligent anti-shaking method for images of safety helmets is characterized by comprising the following steps:
sending the current position information to a remote monitoring center;
acquiring a background image provided by a remote monitoring center, and taking the background image as a reference image;
performing gridding and blocking on the reference image to form a plurality of image blocks, calculating the texture characteristics of each image block, and selecting a plurality of image blocks with rich texture information as reference image blocks;
searching in the current monitoring image to find an area which is most matched with the reference image block, and if the number of the successfully matched reference image blocks reaches a preset number, calculating the relative displacement of the current monitoring image relative to the reference image from a plurality of relative displacements of the successfully matched reference image blocks;
and carrying out translation correction on the current video image according to the calculated relative displacement in the monitored image, and obtaining the monitored image after eliminating the jitter after the translation correction.
2. The intelligent helmet image anti-shaking method according to claim 1, characterized in that, before said step "transmitting the current position information to the remote monitoring center", further comprising the steps of:
shooting an environment image through an infrared camera arranged on a pneumatic damping device, and sending the environment image and the position of the environment image to the remote monitoring center, wherein a plurality of environment images are shot at the same position;
and the remote monitoring center selects the optimal environment image at the position and marks the position corresponding to the environment image according to the environment image and the position of the environment image.
3. The intelligent anti-shake method for helmet images according to claim 2, wherein before the step of capturing the environment images by the infrared camera installed on the pneumatic shock absorber and sending the environment images and the position where the environment images are located to the remote monitoring center, the method further comprises the following steps:
acquiring a shooting preparation signal;
detecting the atmospheric pressure in the pneumatic damping device according to the shooting preparation signal;
and when the atmospheric pressure is greater than a first preset value, the camera shooting button works normally, otherwise, a damping abnormity alarm signal is sent out.
4. The intelligent anti-shake method for helmet images according to claim 2, wherein before the step of capturing the environment images by the infrared camera installed on the pneumatic shock absorber and sending the environment images and the position where the environment images are located to the remote monitoring center, the method further comprises the following steps:
acquiring a shooting preparation signal;
detecting the atmospheric pressure in the pneumatic damping device for multiple times within a preset time period according to the shooting preparation signal;
and when the difference value between the atmospheric pressure detected for the first time and the atmospheric pressure detected for the last time in a preset time period is smaller than a second preset value, the camera shooting button works normally, otherwise, a shock absorption abnormity alarm signal is sent out.
5. The intelligent helmet image anti-shaking method of claim 1, wherein the intelligent helmet image anti-shaking method further comprises the steps of:
collecting the angle and the acceleration of the lens;
calculating the angle and the acceleration to obtain the shake quantity of the thermal infrared camera lens;
and controlling a part of the air bags of the pneumatic damping device, which surround the plurality of air bags in the lens, to inflate, and deflating the part of the air bags.
6. The intelligent helmet image anti-shake method according to claim 2, wherein the method of "choosing the best environment image at the position" is: and modeling the acquired images to acquire a scene image of a shooting scene.
7. The intelligent headgear image anti-shake apparatus according to claim 6, wherein the intelligent headgear image anti-shake apparatus further comprises: the current image is corrected according to the relative displacement of the image, and pixel interpolation processing is needed when the image is subjected to translation correction transformation.
8. An intelligent anti-shake apparatus for images on safety helmets, comprising:
the position information sending module is used for sending the current position information to the remote monitoring center;
the background image acquisition module is used for acquiring a background image provided by a remote monitoring center and taking the background image as a reference image;
the image segmentation module is used for gridding and blocking the reference image to form a plurality of image blocks, calculating the texture characteristics of each image block, and selecting a plurality of image blocks with rich texture information as reference image blocks;
the image searching module is used for searching in the current monitoring image to find out an area which is most matched with the reference image block, and if the number of the successfully matched reference image blocks reaches a preset number, the relative displacement of the current monitoring image relative to the reference image is calculated from a plurality of relative displacements of the successfully matched reference image blocks;
and the image correction module is used for carrying out translation correction on the current video image according to the calculated relative displacement in the monitored image, and obtaining the monitored image after the shake is eliminated after the translation correction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011411164.5A CN112565607A (en) | 2020-12-03 | 2020-12-03 | Intelligent safety helmet image anti-shaking method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011411164.5A CN112565607A (en) | 2020-12-03 | 2020-12-03 | Intelligent safety helmet image anti-shaking method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112565607A true CN112565607A (en) | 2021-03-26 |
Family
ID=75048790
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011411164.5A Pending CN112565607A (en) | 2020-12-03 | 2020-12-03 | Intelligent safety helmet image anti-shaking method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112565607A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115297285A (en) * | 2022-10-09 | 2022-11-04 | 天津希格玛微电子技术有限公司 | Method, device, computer and storage medium for reading image data |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1991440A (en) * | 2005-12-26 | 2007-07-04 | 佳能株式会社 | Image stabilizing apparatus and image pickup apparatus |
| CN103581614A (en) * | 2012-08-01 | 2014-02-12 | 通号通信信息集团有限公司 | Method and system for tracking targets in video based on PTZ |
| CN104079800A (en) * | 2014-06-24 | 2014-10-01 | 上海波汇通信科技有限公司 | Shaking preventing method for video image in video surveillance |
| CN205862486U (en) * | 2016-08-08 | 2017-01-04 | 宜昌市向日葵能源科技有限公司 | A kind of photovoltaic plant operation monitoring system |
| CN110602393A (en) * | 2019-09-04 | 2019-12-20 | 南京博润智能科技有限公司 | Video anti-shake method based on image content understanding |
| CN211860312U (en) * | 2020-05-27 | 2020-11-03 | 深圳市权志信息技术有限公司 | Protection device of camera |
-
2020
- 2020-12-03 CN CN202011411164.5A patent/CN112565607A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1991440A (en) * | 2005-12-26 | 2007-07-04 | 佳能株式会社 | Image stabilizing apparatus and image pickup apparatus |
| CN103581614A (en) * | 2012-08-01 | 2014-02-12 | 通号通信信息集团有限公司 | Method and system for tracking targets in video based on PTZ |
| CN104079800A (en) * | 2014-06-24 | 2014-10-01 | 上海波汇通信科技有限公司 | Shaking preventing method for video image in video surveillance |
| CN205862486U (en) * | 2016-08-08 | 2017-01-04 | 宜昌市向日葵能源科技有限公司 | A kind of photovoltaic plant operation monitoring system |
| CN110602393A (en) * | 2019-09-04 | 2019-12-20 | 南京博润智能科技有限公司 | Video anti-shake method based on image content understanding |
| CN211860312U (en) * | 2020-05-27 | 2020-11-03 | 深圳市权志信息技术有限公司 | Protection device of camera |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115297285A (en) * | 2022-10-09 | 2022-11-04 | 天津希格玛微电子技术有限公司 | Method, device, computer and storage medium for reading image data |
| CN115297285B (en) * | 2022-10-09 | 2023-01-06 | 天津希格玛微电子技术有限公司 | Method, device, computer and storage medium for reading image data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11285613B2 (en) | Robot vision image feature extraction method and apparatus and robot using the same | |
| US10764559B2 (en) | Depth information acquisition method and device | |
| CN110009681B (en) | IMU (inertial measurement unit) assistance-based monocular vision odometer pose processing method | |
| CN111083380B (en) | Video processing method, electronic equipment and storage medium | |
| US8466970B2 (en) | Imaging apparatus, method, system integrated circuit, and program for correcting inclination of subjects in an image | |
| CN103873758B (en) | The method, apparatus and equipment that panorama sketch generates in real time | |
| CN105187723B (en) | A kind of image pickup processing method of unmanned vehicle | |
| CN110022444B (en) | Panoramic photographing method for unmanned aerial vehicle and unmanned aerial vehicle using panoramic photographing method | |
| KR20130051501A (en) | Online reference generation and tracking for multi-user augmented reality | |
| CN111382613B (en) | Image processing method, device, equipment and medium | |
| CN115439424A (en) | Intelligent detection method for aerial video image of unmanned aerial vehicle | |
| CN104537659A (en) | Automatic two-camera calibration method and system | |
| CN108537844B (en) | Visual SLAM loop detection method fusing geometric information | |
| CN109520500A (en) | One kind is based on the matched accurate positioning of terminal shooting image and streetscape library acquisition method | |
| CN111583386B (en) | Multi-view human body posture reconstruction method based on label propagation algorithm | |
| CN110634138A (en) | Bridge deformation monitoring method, device and equipment based on visual perception | |
| CN111123962A (en) | Rotor unmanned aerial vehicle repositioning photographing method for power tower inspection | |
| US11195297B2 (en) | Method and system for visual localization based on dual dome cameras | |
| CN104079800A (en) | Shaking preventing method for video image in video surveillance | |
| CN108596837A (en) | Image split-joint method, device, equipment and computer media | |
| CN105721776A (en) | Sports camera device with digital image stabilization function and digital image stabilization method | |
| CN114979489A (en) | Gyroscope-based heavy equipment production scene video monitoring and image stabilizing method and system | |
| CN112565607A (en) | Intelligent safety helmet image anti-shaking method and device | |
| WO2022016909A1 (en) | Method and apparatus for acquiring spatial distribution of wi-fi fingerprints, and electronic device | |
| CN113340405A (en) | Bridge vibration mode measuring method, device and system |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210326 |
|
| RJ01 | Rejection of invention patent application after publication |