CN114173058A - Video image stabilization processing method, device and equipment - Google Patents
Video image stabilization processing method, device and equipment Download PDFInfo
- Publication number
- CN114173058A CN114173058A CN202111441812.6A CN202111441812A CN114173058A CN 114173058 A CN114173058 A CN 114173058A CN 202111441812 A CN202111441812 A CN 202111441812A CN 114173058 A CN114173058 A CN 114173058A
- Authority
- CN
- China
- Prior art keywords
- image
- image frame
- area
- pixel
- determining
- 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.)
- Granted
Links
- 230000006641 stabilisation Effects 0.000 title claims abstract description 55
- 238000011105 stabilization Methods 0.000 title claims abstract description 55
- 238000003672 processing method Methods 0.000 title claims abstract description 11
- 239000013598 vector Substances 0.000 claims abstract description 67
- 238000012545 processing Methods 0.000 claims abstract description 39
- 238000000034 method Methods 0.000 claims description 54
- 238000006073 displacement reaction Methods 0.000 claims description 6
- 239000000126 substance Substances 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 abstract description 4
- 238000005516 engineering process Methods 0.000 description 15
- 230000008569 process Effects 0.000 description 14
- 238000010586 diagram Methods 0.000 description 13
- 238000004590 computer program Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 9
- 230000006872 improvement Effects 0.000 description 9
- 238000004364 calculation method Methods 0.000 description 4
- 239000002245 particle Substances 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000000087 stabilizing effect Effects 0.000 description 3
- 230000003068 static effect Effects 0.000 description 3
- 235000019646 color tone Nutrition 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 229920001296 polysiloxane Polymers 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
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
- H04N23/80—Camera processing pipelines; Components thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/66—Analysis of geometric attributes of image moments or centre of gravity
-
- 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
- H04N23/681—Motion detection
- H04N23/6811—Motion detection based on the image signal
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Studio Devices (AREA)
Abstract
The embodiment of the specification discloses a video image stabilization processing method, a video image stabilization processing device and video image stabilization processing equipment, and the video image stabilization processing method, the video image stabilization processing device and the video image stabilization processing equipment can comprise the following steps: acquiring a first image frame in a target video, wherein the first image frame is obtained by carrying out image acquisition on a specified area; determining the area of the moving target in the first image frame by using the position information of the moving target in the designated area acquired by the radar sensor; deleting the area where the moving object is located from the first image frame to obtain a background area of the first image frame; determining a motion vector of a background region of a first image frame; and performing reverse compensation on the background area of the first image frame according to the motion vector to obtain a stabilized image. Under the condition that the camera shooting visual field is shaken, the stabilization treatment of the first image frame can be simplified into the stabilization treatment of the background area of the first image frame, and the radar sensor can be used for accurately and quickly collecting the moving target, so that the accuracy and the efficiency of the image stabilization treatment scheme are improved.
Description
Technical Field
The present application relates to the field of computer vision technologies, and in particular, to a method, an apparatus, and a device for video image stabilization.
Background
In recent years, with the emergence of new technologies such as mobile communication technology, lightweight deep learning network, vehicle-mounted high-performance processor and the like, internet-connected automatic driving technology is rapidly developed, and an intelligent road-side system is gradually popularized as an important support of the internet-connected automatic driving technology. In practical application, the intelligent road side system based on vision becomes a common intelligent road side system implementation scheme due to the advantages of low cost, convenience in deployment and the like. However, under the influence of installation and deployment conditions and fastening modes, under the influence of external factors such as road shaking and strong wind, a rod piece where the intelligent road side system is located slightly shakes, so that the visual field of the camera shakes, and the identification and positioning accuracy of the system is influenced. Therefore, processing using video image stabilization techniques is required.
At present, the original vehicle-mounted or mobile phone video image stabilization technology is generally used, and all features of an image collected by an intelligent roadside system are extracted to perform video image stabilization processing based on all features of the image. The video image stabilization processing scheme based on image feature extraction consumes a lot of time, and cannot meet the real-time requirement of the network connection automatic driving technology on roadside data.
Disclosure of Invention
The method, the device and the equipment for stabilizing the video image can improve the video image stabilization processing efficiency, and solve the problem that the conventional video image stabilization processing process consumes a long time and cannot meet the requirement of the network automatic driving technology on the real-time performance of roadside data.
In order to solve the above technical problem, the embodiments of the present specification are implemented as follows:
an embodiment of the present specification provides a video image stabilization processing method, including:
acquiring a first image frame in a target video, wherein the first image frame is obtained by carrying out image acquisition on a specified area;
determining the area of the moving object in the first image frame according to the position information of the moving object in the specified area acquired by a radar sensor at the acquisition moment of the first image frame;
deleting the area where the moving object is located from the first image frame to obtain a background area of the first image frame;
determining a motion vector for a background region of the first image frame;
and performing reverse compensation on the background area of the first image frame according to the motion vector to obtain a stabilized image.
An embodiment of this specification provides a video image stabilization processing apparatus, including:
the first acquisition module is used for acquiring a first image frame in a target video; the first image frame is obtained by carrying out image acquisition on a specified area;
the first determining module is used for determining the area of the moving object in the first image frame according to the position information of the moving object in the specified area acquired by a radar sensor at the acquisition moment of the first image frame;
the deleting module is used for deleting the area where the moving target is located from the first image frame to obtain a background area of the first image frame;
a second determining module for determining a motion vector of a background region of the first image frame;
and the reverse compensation module is used for performing reverse compensation on the background area of the first image frame according to the motion vector to obtain a stabilized image.
An embodiment of the present specification provides a video image stabilization processing apparatus, including:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to:
acquiring a first image frame in a target video, wherein the first image frame is obtained by carrying out image acquisition on a specified area;
determining the area of the moving object in the first image frame according to the position information of the moving object in the specified area acquired by a radar sensor at the acquisition moment of the first image frame;
deleting the area where the moving object is located from the first image frame to obtain a background area of the first image frame;
determining a motion vector for a background region of the first image frame;
and performing reverse compensation on the background area of the first image frame according to the motion vector to obtain a stabilized image.
One embodiment of the present description achieves the following advantageous effects:
under the condition that a camera shooting view corresponding to a target video is shaken, image acquisition is carried out on a designated area in the target video to obtain a first image frame, and the area where a moving target is located in the first image frame is determined by utilizing the position information of the moving target in the designated area acquired by a radar sensor; deleting the area where the moving object is located from the first image frame to obtain a background area of the first image frame, determining a motion vector of the background area of the first image frame, and performing reverse compensation on the background area of the first image frame according to the motion vector to obtain a stabilized image. The first image frame comprises a moving object and a background area, and under the condition that the camera shooting visual field is shaken, the motion vector generated by shaking is negligible relative to the motion vector generated by the moving object, so that the stabilization processing on the first image frame can be simplified into the stabilization processing on the background area of the first image frame; in the video image stabilization processing process, the moving target can be accurately and quickly acquired by using the radar sensor, so that the efficiency and the accuracy of extracting the background area in the first image frame are improved, and the accuracy and the efficiency of the image stabilization processing scheme are improved.
Drawings
In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without any creative effort.
Fig. 1 is a schematic diagram of an overall scheme of a video image stabilization processing method provided in an embodiment of the present specification;
fig. 2 is a schematic flowchart of a video image stabilization processing method provided in an embodiment of the present specification;
fig. 3 is a schematic structural diagram of a video image stabilization processing apparatus provided in an embodiment of the present specification;
fig. 4 is a schematic structural diagram of a video image stabilization processing apparatus provided in an embodiment of the present specification.
Detailed Description
To make the objects, technical solutions and advantages of one or more embodiments of the present disclosure more apparent, the technical solutions of one or more embodiments of the present disclosure will be described in detail and completely with reference to the specific embodiments of the present disclosure and the accompanying drawings. It is to be understood that the embodiments described are only a few embodiments of the present specification, and not all embodiments. All other embodiments that can be derived by a person skilled in the art from the embodiments given herein without making any creative effort fall within the scope of protection of one or more embodiments of the present specification.
The technical solutions provided by the embodiments of the present description are described in detail below with reference to the accompanying drawings.
In the prior art, based on the original vehicle-mounted or mobile phone video image stabilization technology, all features of an image need to be extracted, so that stabilization processing is performed based on all features of the image. The video image stabilization processing scheme has low operation efficiency and poor real-time performance due to large calculation amount when all the features of the image are extracted.
The video image stabilization technology based on the motion sensor estimates the motion vector of the camera through the motion sensor to realize the estimation of the motion vector of the image, so that the image can be reversely compensated according to the motion vector measured by the motion sensor to obtain the stabilized image. Therefore, the accuracy of the video image stabilization processing scheme depends on the accuracy of the motion sensor, but the existing motion sensor is difficult to realize accurate measurement on slight displacement, so that the accuracy of the video image stabilization processing scheme is poor.
In the video image stabilization technique based on the particle filtering, since it is considered that image fluctuation is caused by particle motion, the image motion vector is estimated by the particle filtering by forming particles with no difference in image content, and image stabilization processing is performed based on the determined image motion vector. In such a video image stabilization processing scheme, normally moving objects such as vehicles and pedestrians included in the image are particlized and subjected to motion vector estimation, so that the accuracy of the motion vector estimation of the image is affected, and the accuracy of the video image stabilization processing result is poor.
In order to solve the defects in the prior art, the following embodiments are given in the embodiments of the present specification:
fig. 1 is a schematic flowchart of an overall scheme of a video image stabilization processing method provided in an embodiment of the present specification.
As shown in fig. 1, in a case where a camera view corresponding to a target video is shaken, an image capturing device 101 (such as a camera) may be used to capture a video of a designated area 103 to obtain a first image frame, and position information of a moving target 104 in the designated area is captured by a radar sensor 102 while the first image frame is captured, so that an area 103 where the moving target 104 is located in the first image frame may be determined based on the position information of the moving target 104. After the area where the moving object 104 is located is deleted from the first image frame, the background area 105 of the first image frame can be obtained. Subsequently, it is further required to determine a motion vector of the background area 105 of the first image frame, so as to perform reverse compensation on the background area 105 of the first image frame according to the motion vector, thereby obtaining a stabilized image.
In the video image stabilization method provided in the embodiment of the present description, when a camera view corresponding to a target video is shaken, a motion vector generated by shaking is negligible with respect to a motion vector generated by a moving target itself, so that stabilizing the first image frame may be simplified to stabilizing a background region of the first image frame. In addition, in the video image stabilization processing process, the moving target can be accurately and quickly acquired by using the radar sensor, so that the efficiency and the accuracy of extracting the background area in the first image frame are improved, and the accuracy and the efficiency of the image stabilization processing scheme are improved.
Next, a video image stabilization processing method provided in an embodiment of the specification will be specifically described with reference to the accompanying drawings:
fig. 2 is a flowchart illustrating a video image stabilization processing method according to an embodiment of the present disclosure. From a program perspective, the execution subject of the flow may be a terminal, or an application program hosted at the terminal. As shown in fig. 2, the process may include the following steps:
step 210: acquiring a first image frame in a target video, wherein the first image frame is obtained by carrying out image acquisition on a specified area.
In this embodiment, the target video may be obtained by image capturing the specified area through an image capturing device, for example, a roadside monitoring device, a camera, a video camera, or the like, to image the environment, pedestrians, non-motor vehicles, traffic events, and the like in the specified area to obtain the target video. The designated area may refer to a shooting field of view of the image capture device fixed according to actual needs, and the first image frame may be any one frame image except a first frame image in the target video.
Step 220: and determining the area of the moving object in the first image frame according to the position information of the moving object in the specified area acquired by the radar sensor at the acquisition moment of the first image frame.
In the embodiment of the present specification, while the first image frame is imaged, the radar sensor may be used to acquire position information of a moving object in a fixed field of view (i.e., a designated area) corresponding to the image acquisition device. Since the first image frame is also acquired for the designated area, the moving target detected by the radar sensor usually appears in the first image frame, so that the moving target detected by the radar sensor is the moving target in the first image frame. Based on this, the area of the moving object in the first image frame may be determined according to the position information of the moving object detected by the radar sensor.
Step 230: and deleting the area where the moving object is located from the first image frame to obtain a background area of the first image frame.
In this embodiment of the present specification, a region where a moving object in the first image frame is located may be used as a foreground region, and a remaining region where all regions where the moving object is located in the first image frame are deleted may be used as a background region. The background region and the foreground region in the first image frame are distinguished because: the foreground area corresponds to a moving target, and a motion vector generated by shaking (specifically, shaking of the image acquisition equipment) of a camera view is negligible relative to a motion vector generated by the moving target, so that motion compensation can not be performed on the moving target; however, the background area should be in a static state, and therefore, the motion vector of the background area is usually caused by the shaking of the image capturing device, and the like, so that the reverse compensation process is required.
Step 240: a motion vector for a background region of the first image frame is determined.
In this embodiment of the present specification, the background region of the first image frame is formed by a plurality of target pixel points, and therefore, determining the motion vector of the background region of the first image frame requires determining the motion vector of the target pixel points included in the background region of the first image frame, and determining the motion vector of the target pixel points included in the background region of the first image frame may be performed by calculating a motion vector of a centroid of the background region of the first image frame, which is used as the motion vector of the target pixel points included in the background region of the first image frame.
Step 250: and performing reverse compensation on the background area of the first image frame according to the motion vector to obtain a stabilized image.
In this embodiment, step 250 may specifically include: reversely translating a background region of the first image frame according to the motion vector.
And performing reverse translation on the background area of the first image frame, wherein the translation distance can be a distance corresponding to the motion vector, and the unit is a pixel, so as to obtain the stabilized first image frame. For example, if the norm of the motion vector from the second image frame to the first image frame is 5 and the direction is 37 degrees north-east, the pixel point a with the pixel coordinate of (10, 10) in the background region of the first image frame is translated in the reverse direction according to the motion vector, that is, the pixel point a is moved by 5 degrees south-west in the direction of 37 degrees south-west, and the pixel coordinate of the translated pixel point a is changed to (6, 7).
In the method in fig. 2, when a video image is stabilized, an image sensor (e.g., a camera) may be used to acquire a video image for a designated area to obtain a first image frame, and while the first image frame is acquired, a radar sensor is used to detect a moving target in the designated area, determine an area where the moving target is located in the first image frame, delete the area where the moving target is located, obtain a background area of the first image frame, determine a motion vector of the background area of the first image frame, and perform reverse compensation on the background area of the first image frame according to the motion vector to obtain a stabilized image.
In the video image stabilization process, motion vectors generated by shaking (specifically, shaking of image acquisition equipment) of a camera view are negligible relative to motion vectors generated by a moving target, so that motion compensation can not be performed on the moving target; however, the background area in the image should be in a static state, and therefore, the motion vector of the background area is usually caused by factors such as shaking of the image capturing device, and thus, a reverse compensation process is required. Compared with the existing video image stabilization processing technology, all features in an image need to be extracted, the calculation amount is large, the efficiency is low, the embodiment of the specification can simplify the stabilization processing of the first image frame into the stabilization processing of the background area of the first image frame under the condition that the shooting visual field corresponding to the target video is shaken, and the radar sensor can be used for accurately and quickly acquiring the moving target, so that the efficiency and the accuracy of extracting the background area in the first image frame are improved, and the accuracy and the efficiency of an image stabilization processing scheme are improved.
Based on the method in fig. 2, some specific embodiments of the method are also provided in the examples of this specification, which are described below.
Scheme in fig. 2, step 240: determining the area where the moving object in the first image frame is located according to the position information of the moving object in the specified area acquired by the radar sensor at the acquisition time of the first image frame, which may specifically include:
acquiring a GPS coordinate of a moving target in a specified area acquired by a radar sensor at the acquisition moment of a first image frame; acquiring a preset corresponding relation between a preset pixel coordinate system and a GPS coordinate system in a first image frame; and determining the area of the moving target in the first image frame according to the GPS coordinate of the moving target based on the preset corresponding relation between the preset pixel coordinate system and the GPS coordinate system.
Before acquiring the preset corresponding relationship between the preset pixel coordinate system and the GPS coordinate system in the first image frame, the method may further include: determining pixel coordinates of target pixel points in a sample image in a preset pixel coordinate system, wherein the sample image is obtained by carrying out image acquisition on a specified area; determining a GPS coordinate corresponding to a target pixel point; and establishing a preset corresponding relation between the preset pixel coordinate system and the GPS coordinate system according to the pixel coordinate of the target pixel point in the preset pixel coordinate system and the GPS coordinate corresponding to the target pixel point.
In this embodiment of the present disclosure, a sample image may be statically calibrated by a camera, so as to pre-establish a corresponding relationship between a preset pixel coordinate System and a Global Positioning System (GPS) coordinate System in a fixed field of view (i.e., a designated area) of the camera, where the corresponding relationship may be represented in a form of a perspective transformation matrix, for example, a formula of a (pixel coordinate-GPS coordinate) matching point set.
Specifically, a GPS coordinate system corresponding to the sample image needs to be established, and because the GPS coordinate system is a three-dimensional space coordinate system, at least four points are needed to determine a three-dimensional space pattern, and any three points of the four points cannot be located on a straight line, at least four target pixel points are needed to establish the GPS coordinate system corresponding to the sample image, and any three points of the four target pixel points cannot be located on a straight line.
Moreover, since the corresponding relationship between the preset pixel coordinate system and the GPS coordinate system can be determined by the perspective transformation matrix form, and at least four target pixel points are required for forming the matrix, the preset corresponding relationship between the preset pixel coordinate system and the GPS coordinate system is established, at least four target pixel points in the sample image need to be selected, and any three of the four target pixel points cannot be located on a straight line.
Scheme in fig. 2, step 240: determining a motion vector of a background region of the first image frame may specifically include:
pixel coordinates of a centroid of a background region of the first image frame are acquired.
Acquiring pixel coordinates of a centroid of a background area of a second image frame; the second image frame is obtained by image acquisition of the designated area in the target video, and the acquisition time of the second image frame is earlier than that of the first image frame.
Determining a displacement vector from pixel coordinates of a centroid of a background region of the second image frame to pixel coordinates of a centroid of a background region of the first image frame.
In this embodiment, the second image frame and the first image frame are both obtained by image capture of the designated area in the target video, but the capture time of the second image frame is earlier than that of the first image frame.
With the second image frame as a reference, the motion vector of the background region of the first image frame may be a displacement vector from a centroid of the background region of the second image frame to a centroid of the background region of the first image frame, and the motion vector of the background region of the first image frame may reflect a displacement of the first image frame relative to the second image frame caused by shaking of the video capture device.
In the present embodiment, YcrCb is one of color spaces, and RGB represents a color system. Since only the image details are considered and the color tones are not considered, which is beneficial to improving the accuracy of the pixel coordinates of the centroid of the background area of the first image frame, if the first image frame belongs to an RGB image, the acquiring the pixel coordinates of the centroid of the background area of the first image frame may specifically include:
a YCrCb color space image of a background region of a first image frame is acquired.
And calculating the pixel coordinate of the mass center of the Y-channel image in the YCrCb color space image.
In the present specification embodiment, when acquiring a YCrCb color space image of a background region of a first image frame, the background region in the first image frame may be converted from an RGB image into a YCrCb color space image by the method shown in formula 1:
in formula 1, R, G, B represents color values of three channels, namely red, green and blue; cb，CrRefers to color, and Y refers to brightness (luminance), which represents the concentration of light.
In the embodiment of the present specification, the pixel coordinates of the centroid of the background area of the first image frame are generated based on only the Y-channel image of the background area of the first image frame, so that only the image details are considered and the color tone is not considered, which is beneficial to improving the accuracy of the pixel coordinates of the centroid of the background area of the first image frame obtained by calculation, and is further beneficial to improving the accuracy of the determined motion vector of the background area of the first image frame.
In the scheme of fig. 2, the calculating the pixel coordinate of the centroid of the Y-channel image in the YCrCb color space image of the background region may specifically include:
dividing the Y channel image to obtain a preset number of sub-images; calculating the pixel coordinate of the mass center of the subimage according to the pixel coordinate of the pixel point in each subimage and the gray value of the pixel point; and determining the pixel coordinate of the mass center of the Y-channel image according to the pixel coordinate of the mass center of each sub-image.
In practical application, the acquired Y channel image is segmented to obtain m × n sub-images, preferably, m is less than 100, n is less than 200, for example, m may be 20, n may be 30, and a specific segmentation manner may be determined by those skilled in the art according to actual conditions of the background area, which is not limited specifically.
In the present specification embodiment, the pixel coordinates of the centroid of the sub-image of each background region may be calculated according to formula 2.
In formula 2, XcPixel abscissa, Y, being the centroid of the sub-imagecPixel ordinate, which is the centroid of the subimage, (x)i,yi) Is the pixel coordinate, x, of the ith pixel point in the subimageiIs the pixel abscissa, y, of the ith pixel pointiIs the pixel ordinate, l, of the ith pixel pointiIs the gray value of the ith pixel point.
For ease of understanding, the pixel coordinates for calculating the centroid of the sub-image are illustrated. For example, a sub-image includes three pixels A, B, C, the pixel coordinates corresponding to the pixel A, B, C are (1, 0), (0, 1) and (1, 1), respectively, and the gray scale value corresponding to the pixel A, B, C is 0, 1, 0, respectively, then, according to the formula (2), the pixel abscissa of the centroid of the sub-image is 0, and the pixel ordinate of the centroid of the sub-image is 1, so that the pixel coordinate of the centroid of the sub-image can be determined to be (0, 1).
In the scenario of fig. 2, the pixel coordinates of the centroid of the sub-image may include: the abscissa of the centroid of the sub-image and the ordinate of the centroid of the sub-image.
Determining the pixel coordinates of the centroid of the Y-channel image of the background region according to the pixel coordinates of the centroid of each sub-image, which may specifically include:
calculating the mean value of the abscissa of the centroids of the preset number of sub-images to obtain the abscissa of the centroid of the Y-channel image; and calculating the mean value of the vertical coordinates of the mass centers of the preset number of sub-images to obtain the vertical coordinate of the mass center of the Y-channel image.
In this specification embodiment, the abscissa and the ordinate of the centroid of the Y-channel image of the background region can be calculated based on formula 3.
In formula 3, XmvPixel abscissa, Y, of centroid of Y-channel image as background regionmvPixel ordinate, x, of the centroid of a Y-channel image as a background regionciPixel abscissa, Y, of centroid of i-th sub-image in Y-channel image of background regionciThe pixel ordinate of the centroid of the ith sub-image in the Y-channel image of the background area is shown, and N is the total number of sub-images contained in the background area.
In this embodiment, a method for calculating the pixel coordinate of the centroid of the background area of the second image frame is the same as the method for calculating the pixel coordinate of the centroid of the background area of the first image frame, which is not described again.
In the embodiment of the description, the auxiliary sensor is used for sensing the moving target information, the image foreground area can be efficiently and accurately determined, compared with the traditional image enhancement scheme, the dimension of information acquisition is improved, and the foreground extraction accuracy is far higher than that of a pure image algorithm such as a frame difference method. And because the motion of the camera does not need to be measured, the method does not depend on the precision of a motion sensor, and can be suitable for a high-frequency slight vibration scene. And because the feature vectors of the whole image do not need to be extracted for matching, the calculation amount is small, and the method is suitable for an embedded application scene. Also, by performing the inverse compensation of the image only according to the motion vector of the background region not containing the moving object, the accuracy is better than that of the conventional method in which the image is directly compensated according to the motion vector of the whole image (containing the foreground moving object).
Based on the same idea, the embodiment of the present specification further provides a device corresponding to the above method. Fig. 3 is a schematic structural diagram of a video image stabilization processing apparatus corresponding to the method in fig. 2 according to an embodiment of the present disclosure. As shown in fig. 3, the apparatus 300 may include:
a first obtaining module 310, configured to obtain a first image frame in a target video; the first image frame is obtained by image acquisition aiming at the specified area.
The first determining module 320 is configured to determine a region where the moving object is located in the first image frame according to the position information of the moving object in the specified region acquired by the radar sensor at the acquisition time of the first image frame.
The deleting module 330 is configured to delete the area where the moving object is located from the first image frame, so as to obtain a background area of the first image frame.
A second determining module 340 for determining a motion vector of a background region of the first image frame.
And a reverse compensation module 350, configured to perform reverse compensation on the background area of the first image frame according to the motion vector, so as to obtain a stabilized image.
The present specification also provides some specific embodiments of the apparatus based on the apparatus in fig. 3, which is described below.
Optionally, the first determining module 320 may be specifically configured to: acquiring GPS coordinates of a moving object in the designated area acquired by a radar sensor at the acquisition moment of the first image frame; acquiring a preset corresponding relation between a preset pixel coordinate system and a GPS coordinate system in the first image frame; and determining the area of the moving target in the first image frame according to the GPS coordinate of the moving target based on the preset corresponding relation between the preset pixel coordinate system and the GPS coordinate system.
Optionally, the first determining module 320 may be further configured to: before the preset corresponding relation between the preset pixel coordinate system in the first image frame and the GPS coordinate system is obtained, determining the pixel coordinate of a target pixel point in the sample image in the preset pixel coordinate system; the sample image is obtained by carrying out image acquisition on the specified area; determining a GPS coordinate corresponding to the target pixel point; and establishing a preset corresponding relation between the preset pixel coordinate system and the GPS coordinate system according to the pixel coordinate of the target pixel point in the preset pixel coordinate system and the GPS coordinate corresponding to the target pixel point.
Optionally, the second determining module 340 may be specifically configured to: acquiring pixel coordinates of a centroid of a background area of the first image frame; acquiring pixel coordinates of a centroid of a background area of a second image frame; the second image frame is obtained by carrying out image acquisition on the designated area, and the acquisition time of the second image frame is earlier than that of the first image frame; determining a displacement vector from pixel coordinates of a centroid of a background region of the second image frame to pixel coordinates of a centroid of a background region of the first image frame.
Optionally, the second determining module 340 may be specifically configured to: acquiring a YCrCb color space image of a background area of the first image frame; and calculating the pixel coordinate of the mass center of the Y-channel image in the YCrCb color space image.
Optionally, the second determining module 340 may be specifically configured to: dividing the Y-channel image to obtain a preset number of sub-images; calculating the pixel coordinate of the mass center of each sub-image according to the pixel coordinate of the pixel point in each sub-image and the gray value of the pixel point; and determining the pixel coordinate of the mass center of the Y-channel image according to the pixel coordinate of the mass center of each sub-image.
Optionally, the second determining module 340 may be specifically configured to: calculating the mean value of the abscissa of the centroids of the preset number of sub-images to obtain the abscissa of the centroid of the Y-channel image; and calculating the mean value of the vertical coordinates of the mass centers of the preset number of sub-images to obtain the vertical coordinate of the mass center of the Y-channel image.
Optionally, the inverse compensation module 350 may be specifically configured to: reversely translating a background region of the first image frame according to the motion vector.
Based on the same idea, the embodiment of the present specification further provides a device corresponding to the above method.
Fig. 4 is a schematic structural diagram of a video image stabilization processing apparatus corresponding to the method in fig. 2 provided in an embodiment of this specification. As shown in fig. 4, the apparatus 400 may include:
at least one processor 410; and the number of the first and second groups,
a memory 430 communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory 430 stores instructions 420 executable by the at least one processor 410 to cause the at least one processor 410 to:
acquiring a first image frame in a target video, wherein the first image frame is obtained by carrying out image acquisition on a specified area;
determining the area of the moving object in the first image frame according to the position information of the moving object in the specified area acquired by a radar sensor at the acquisition moment of the first image frame;
deleting the area where the moving object is located from the first image frame to obtain a background area of the first image frame;
determining a motion vector for a background region of the first image frame;
and performing reverse compensation on the background area of the first image frame according to the motion vector to obtain a stabilized image.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, as for the apparatus shown in fig. 4, since it is substantially similar to the method embodiment, the description is simple, and the relevant points can be referred to the partial description of the method embodiment.
In the 90 s of the 20 th century, improvements in a technology could clearly distinguish between improvements in hardware (e.g., improvements in circuit structures such as diodes, transistors, switches, etc.) and improvements in software (improvements in process flow). However, as technology advances, many of today's process flow improvements have been seen as direct improvements in hardware circuit architecture. Designers almost always obtain the corresponding hardware circuit structure by programming an improved method flow into the hardware circuit. Thus, it cannot be said that an improvement in the process flow cannot be realized by hardware physical modules. For example, a Programmable Logic Device (PLD), such as a Field Programmable Gate Array (FPGA), is an integrated circuit whose Logic functions are determined by programming the Device by a user. A digital character system is "integrated" on a PLD by the designer's own programming without requiring the chip manufacturer to design and fabricate a dedicated integrated circuit chip. Furthermore, nowadays, instead of manually making an Integrated Circuit chip, such programming is often implemented by "logic compiler" software, which is similar to a software compiler used in program development and writing, but the original code before compiling is also written by a specific programming Language, which is called Hardware Description Language (HDL), and HDL is not only one but many, such as abel (advanced Boolean Expression Language), ahdl (alternate Language Description Language), traffic, pl (core universal programming Language), HDCal (jhdware Description Language), lang, Lola, HDL, laspam, hardward Description Language (vhr Description Language), and vhjrag-Language (Hardware Description Language), which are currently used in most popular fields. It will also be apparent to those skilled in the art that hardware circuitry that implements the logical method flows can be readily obtained by merely slightly programming the method flows into an integrated circuit using the hardware description languages described above.
The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic for the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller as pure computer readable program code, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may thus be considered a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.
The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functionality of the units may be implemented in one or more software and/or hardware when implementing the present application.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Disks (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission medium which can be used to store information which can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (10)
1. A video image stabilization processing method, comprising:
acquiring a first image frame in a target video, wherein the first image frame is obtained by carrying out image acquisition on a specified area;
determining the area of the moving object in the first image frame according to the position information of the moving object in the specified area acquired by a radar sensor at the acquisition moment of the first image frame;
deleting the area where the moving object is located from the first image frame to obtain a background area of the first image frame;
determining a motion vector for a background region of the first image frame;
and performing reverse compensation on the background area of the first image frame according to the motion vector to obtain a stabilized image.
2. The method as claimed in claim 1, wherein the determining the area in which the moving object in the first image frame is located according to the position information of the moving object in the designated area acquired by using the radar sensor at the acquisition time of the first image frame specifically comprises:
acquiring GPS coordinates of a moving object in the designated area acquired by a radar sensor at the acquisition moment of the first image frame;
acquiring a preset corresponding relation between a preset pixel coordinate system and a GPS coordinate system in the first image frame;
and determining the area of the moving target in the first image frame according to the GPS coordinate of the moving target based on the preset corresponding relation between the preset pixel coordinate system and the GPS coordinate system.
3. The method as claimed in claim 2, wherein before the obtaining of the preset correspondence between the preset pixel coordinate system and the GPS coordinate system in the first image frame, further comprises:
determining pixel coordinates of target pixel points in the sample image in the preset pixel coordinate system; the sample image is obtained by carrying out image acquisition on the specified area;
determining a GPS coordinate corresponding to the target pixel point;
and establishing a preset corresponding relation between the preset pixel coordinate system and the GPS coordinate system according to the pixel coordinate of the target pixel point in the preset pixel coordinate system and the GPS coordinate corresponding to the target pixel point.
4. The method as recited in claim 1, wherein said determining a motion vector for a background region of said first image frame comprises:
acquiring pixel coordinates of a centroid of a background area of the first image frame;
acquiring pixel coordinates of a centroid of a background area of a second image frame; the second image frame is obtained by image acquisition on the designated area in the target video, and the acquisition time of the second image frame is earlier than that of the first image frame;
determining a displacement vector from pixel coordinates of a centroid of a background region of the second image frame to pixel coordinates of a centroid of a background region of the first image frame.
5. The method as recited in claim 4, wherein obtaining pixel coordinates of a centroid of a background region of the first image frame comprises:
acquiring a YCrCb color space image of a background area of the first image frame;
and calculating the pixel coordinate of the mass center of the Y-channel image in the YCrCb color space image.
6. The method as claimed in claim 5, wherein said calculating pixel coordinates of a centroid of a Y-channel image in said YCrCb color space image comprises:
dividing the Y-channel image to obtain a preset number of sub-images;
calculating the pixel coordinate of the mass center of each sub-image according to the pixel coordinate of the pixel point in each sub-image and the gray value of the pixel point;
and determining the pixel coordinate of the mass center of the Y-channel image according to the pixel coordinate of the mass center of each sub-image.
7. The method of claim 6, wherein the pixel coordinates of the centroid of the sub-image comprise: the abscissa of the center of mass of the sub-image and the ordinate of the center of mass of the sub-image;
the determining the pixel coordinate of the centroid of the Y-channel image according to the pixel coordinate of the centroid of each sub-image specifically includes:
calculating the mean value of the abscissa of the centroids of the preset number of sub-images to obtain the abscissa of the centroid of the Y-channel image;
and calculating the mean value of the vertical coordinates of the mass centers of the preset number of sub-images to obtain the vertical coordinate of the mass center of the Y-channel image.
8. The method as claimed in claim 1, wherein said performing a reverse compensation of said first image frame based on said motion vector comprises:
reversely translating a background region of the first image frame according to the motion vector.
9. A video image stabilization processing apparatus, comprising:
the first acquisition module is used for acquiring a first image frame in a target video; the first image frame is obtained by carrying out image acquisition on a specified area;
the first determining module is used for determining the area of the moving object in the first image frame according to the position information of the moving object in the specified area acquired by a radar sensor at the acquisition moment of the first image frame;
the deleting module is used for deleting the area where the moving target is located from the first image frame to obtain a background area of the first image frame;
a second determining module for determining a motion vector of a background region of the first image frame;
and the reverse compensation module is used for performing reverse compensation on the background area of the first image frame according to the motion vector to obtain a stabilized image.
10. A video image stabilization processing apparatus comprising:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to:
acquiring a first image frame in a target video, wherein the first image frame is obtained by carrying out image acquisition on a specified area;
determining the area of the moving object in the first image frame according to the position information of the moving object in the specified area acquired by a radar sensor at the acquisition moment of the first image frame;
deleting the area where the moving object is located from the first image frame to obtain a background area of the first image frame;
determining a motion vector for a background region of the first image frame;
and performing reverse compensation on the background area of the first image frame according to the motion vector to obtain a stabilized image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111441812.6A CN114173058B (en) | 2021-11-30 | 2021-11-30 | Video image stabilization processing method, device and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111441812.6A CN114173058B (en) | 2021-11-30 | 2021-11-30 | Video image stabilization processing method, device and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114173058A true CN114173058A (en) | 2022-03-11 |
| CN114173058B CN114173058B (en) | 2023-12-26 |
Family
ID=80481706
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111441812.6A Active CN114173058B (en) | 2021-11-30 | 2021-11-30 | Video image stabilization processing method, device and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114173058B (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130243314A1 (en) * | 2010-10-01 | 2013-09-19 | Telefonica, S.A. | Method and system for real-time images foreground segmentation |
| US20160205323A1 (en) * | 2013-09-29 | 2016-07-14 | Nokia Technologies Oy | Method and apparatus for video anti-shaking |
| CN107133969A (en) * | 2017-05-02 | 2017-09-05 | 中国人民解放军火箭军工程大学 | A kind of mobile platform moving target detecting method based on background back projection |
| US20180293735A1 (en) * | 2017-04-11 | 2018-10-11 | Sony Corporation | Optical flow and sensor input based background subtraction in video content |
| CN109302545A (en) * | 2018-11-15 | 2019-02-01 | 深圳市炜博科技有限公司 | Video image stabilization method, device and computer readable storage medium |
| CN110401796A (en) * | 2019-07-05 | 2019-11-01 | 浙江大华技术股份有限公司 | A kind of jitter compensation method and device of image collecting device |
| CN111369469A (en) * | 2020-03-10 | 2020-07-03 | 北京爱笔科技有限公司 | Image processing method and device and electronic equipment |
| CN112330531A (en) * | 2020-11-04 | 2021-02-05 | 广州博冠信息科技有限公司 | Image processing method, image processing device, electronic equipment and storage medium |
| CN112637500A (en) * | 2020-12-22 | 2021-04-09 | 维沃移动通信有限公司 | Image processing method and device |
| WO2021115136A1 (en) * | 2019-12-10 | 2021-06-17 | 闻泰科技(深圳)有限公司 | Anti-shake method and apparatus for video image, electronic device, and storage medium |
| CN113486775A (en) * | 2021-07-02 | 2021-10-08 | 北京一维大成科技有限公司 | Target tracking method, system, electronic equipment and storage medium |
| CN113516680A (en) * | 2021-07-09 | 2021-10-19 | 南京荣新智能科技有限公司 | Moving target tracking and detecting method under moving background |
-
2021
- 2021-11-30 CN CN202111441812.6A patent/CN114173058B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130243314A1 (en) * | 2010-10-01 | 2013-09-19 | Telefonica, S.A. | Method and system for real-time images foreground segmentation |
| US20160205323A1 (en) * | 2013-09-29 | 2016-07-14 | Nokia Technologies Oy | Method and apparatus for video anti-shaking |
| US20180293735A1 (en) * | 2017-04-11 | 2018-10-11 | Sony Corporation | Optical flow and sensor input based background subtraction in video content |
| CN107133969A (en) * | 2017-05-02 | 2017-09-05 | 中国人民解放军火箭军工程大学 | A kind of mobile platform moving target detecting method based on background back projection |
| CN109302545A (en) * | 2018-11-15 | 2019-02-01 | 深圳市炜博科技有限公司 | Video image stabilization method, device and computer readable storage medium |
| CN110401796A (en) * | 2019-07-05 | 2019-11-01 | 浙江大华技术股份有限公司 | A kind of jitter compensation method and device of image collecting device |
| WO2021115136A1 (en) * | 2019-12-10 | 2021-06-17 | 闻泰科技(深圳)有限公司 | Anti-shake method and apparatus for video image, electronic device, and storage medium |
| CN111369469A (en) * | 2020-03-10 | 2020-07-03 | 北京爱笔科技有限公司 | Image processing method and device and electronic equipment |
| CN112330531A (en) * | 2020-11-04 | 2021-02-05 | 广州博冠信息科技有限公司 | Image processing method, image processing device, electronic equipment and storage medium |
| CN112637500A (en) * | 2020-12-22 | 2021-04-09 | 维沃移动通信有限公司 | Image processing method and device |
| CN113486775A (en) * | 2021-07-02 | 2021-10-08 | 北京一维大成科技有限公司 | Target tracking method, system, electronic equipment and storage medium |
| CN113516680A (en) * | 2021-07-09 | 2021-10-19 | 南京荣新智能科技有限公司 | Moving target tracking and detecting method under moving background |
Non-Patent Citations (1)
| Title |
|---|
| 崔武军;张桂林;: "航拍图像序列的地面运动目标跟踪", 红外与激光工程, no. 01 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114173058B (en) | 2023-12-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110246147B (en) | Visual inertial odometer method, visual inertial odometer device and mobile equipment | |
| CN111311709B (en) | Method and device for generating high-precision map | |
| CN111238450B (en) | Visual positioning method and device | |
| CN112001456B (en) | Vehicle positioning method and device, storage medium and electronic equipment | |
| JPWO2017094140A1 (en) | Object detection apparatus and object detection method | |
| CN113674424B (en) | Method and device for drawing electronic map | |
| CN112861831A (en) | Target object identification method and device, storage medium and electronic equipment | |
| CN112150522A (en) | Remote sensing image registration method, device, equipment, storage medium and system | |
| CN114926514B (en) | Registration method and device of event image and RGB image | |
| CN115358962B (en) | End-to-end visual odometer method and device | |
| CN114173058A (en) | Video image stabilization processing method, device and equipment | |
| CN116311135A (en) | Data dimension reduction method, data dimension reduction system and controller for semantic information | |
| CN114332648B (en) | Position identification method and electronic equipment | |
| CN109376653B (en) | Method, apparatus, device and medium for locating vehicle | |
| CN111798489B (en) | Feature point tracking method, device, medium and unmanned equipment | |
| CN114440903A (en) | High-precision map construction method and device, storage medium and electronic equipment | |
| CN113888611B (en) | Method and device for determining image depth and storage medium | |
| CN112561961A (en) | Instance tracking method and device | |
| CN112184901A (en) | Depth map determination method and device | |
| CN113205144B (en) | Model training method and device | |
| CN116597168B (en) | Matching method, device, equipment and medium of vehicle-mounted laser point cloud and panoramic image | |
| CN115578463B (en) | Monocular image object identification method and device and electronic equipment | |
| CN114413915A (en) | Map construction method and device | |
| CN117994740A (en) | Method, device, equipment, medium and product for identifying traffic elements | |
| CN116188919A (en) | Test method and device, readable storage medium and electronic equipment |
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 |