CN113298867A - Accurate positioning method and device for ground object target position based on line matching and storage medium - Google Patents
Accurate positioning method and device for ground object target position based on line matching and storage medium Download PDFInfo
- Publication number
- CN113298867A CN113298867A CN202110666345.0A CN202110666345A CN113298867A CN 113298867 A CN113298867 A CN 113298867A CN 202110666345 A CN202110666345 A CN 202110666345A CN 113298867 A CN113298867 A CN 113298867A
- Authority
- CN
- China
- Prior art keywords
- point
- image
- picture
- coordinates
- panoramic
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
Abstract
The invention discloses a method, a device and a storage medium for accurately positioning a ground object target position based on line matching, wherein the method comprises the following steps: establishing a coordinate mapping relation between the edge lines of the panoramic image and the depth image by taking the pan-tilt camera as the center based on a line matching mode; acquiring a picture to be positioned containing a to-be-positioned point and image information of the picture to be positioned, which is shot by a pan-tilt camera; calculating to obtain the corresponding coordinates of the to-be-positioned point in the panoramic image with the holder camera as the center according to the image information of the to-be-positioned picture; obtaining the corresponding coordinates of the to-be-positioned point in the depth map according to the coordinates of the to-be-positioned point in the panoramic map and the coordinate mapping relation between the edge lines of the panoramic map and the depth map; and obtaining the longitude and latitude of the point to be located according to the corresponding relation between the coordinates of the point to be located in the depth map and the coordinates and the longitude and latitude of each point in the depth map. The invention can realize the accurate positioning of longitude and latitude on the map of the ground object target in the picture shot by the pan-tilt camera.
Description
Technical Field
The invention relates to the technical field of surface feature target positioning, in particular to a surface feature target position accurate positioning method and device based on line matching and a storage medium.
Background
In a monitoring alarm detection system based on a pan-tilt camera and established for forest zones based on machine vision, a mode of cross positioning of a target ground object through a plurality of pan-tilt cameras is generally not adopted due to the consideration of hardware cost, and the target ground object is often positioned through a single pan-tilt camera. However, in an actual three-dimensional scene, a single coordinate cannot be accurately located.
In the prior art, based on through-view domain analysis, the longitude and latitude of a live-action image target ground object are calculated by utilizing certain PTZ data and target surface information of a pan-tilt camera, but the calculation mode is easily influenced by the elevation data precision of a positioning area, the installation correction error of the pan-tilt camera, the precision obtained by equipment PTZ and the like, the calculation positioning error of the ground object target in a complex terrain area with large mountain-shaped fluctuation is easily caused to be large, the subsequent coping processing can be seriously influenced under the application scenes of post-disaster monitoring and early warning, emergency command and the like, and the loss which is difficult to compensate is caused.
Disclosure of Invention
The invention aims to at least solve the technical problems in the prior art, and particularly provides a method and a device for accurately positioning a ground object target position based on line matching and a computer readable storage medium, so that accurate positioning of the longitude and latitude of the ground object target position is realized.
In order to achieve the above object, according to a first aspect of the present invention, there is provided a method for accurately positioning a ground object target position based on line matching, the method comprising the steps of:
establishing a coordinate mapping relation between a panoramic image taking a pan-tilt camera as a center and an edge line of a depth image based on a line matching mode, wherein coordinates of each point in the depth image have corresponding longitude and latitude;
acquiring a picture to be positioned containing a to-be-positioned point and image information of the picture to be positioned, which are shot by the pan-tilt camera;
calculating to obtain the corresponding coordinates of the to-be-positioned point in the panoramic image with the holder camera as the center according to the image information of the to-be-positioned picture;
obtaining the corresponding coordinates of the to-be-positioned point in the depth map according to the coordinates of the to-be-positioned point in the panoramic map and the coordinate mapping relation between the edge lines of the panoramic map and the depth map;
and obtaining the longitude and latitude of the point to be located according to the corresponding relation between the coordinates of the point to be located in the depth map and the coordinates and the longitude and latitude of each point in the depth map.
Preferably, the method further comprises:
splicing a single-layer picture shot by the pan-tilt camera in a fixed vertical direction or a plurality of layers of pictures shot by changing shooting angles in the vertical direction into the panoramic picture taking the pan-tilt camera as the center, wherein each layer of picture comprises a plurality of live-action pictures shot at certain angles in the horizontal direction;
and storing the PTZ value of the central point of each live-action picture spliced into the panoramic picture and the coordinate data of the central point of each live-action picture obtained by transformation after splicing into a database.
Preferably, the method further comprises:
generating a data file recorded with DEM elevation information by taking the holder camera as a center through a GIS tool or programming;
and generating the depth map based on the DEM elevation information contained in the data file.
Preferably, the method further comprises:
respectively extracting image edge lines used for representing a geodesic line from the panoramic image and the depth image which take the pan-tilt camera as the center;
selecting an edge line of the panoramic image and an edge line of the depth image on a user interaction interface;
and associating the selected edge line of the panoramic image with the edge line of the depth image, and establishing a coordinate mapping relation between the two edge lines.
Preferably, the calculating, according to the image information of the picture to be located, to obtain the corresponding coordinates of the location point in the panorama centered on the pan-tilt camera includes:
calculating to obtain the corresponding coordinates of the to-be-positioned point in the panoramic image with the holder camera as the center by utilizing an image matching algorithm according to the image information of the to-be-positioned picture;
or
Calculating the coordinate of the to-be-positioned point in the panoramic image according to the PTZ value of the central point of the to-be-positioned image, the position relation between the central point of the to-be-positioned image and the to-be-positioned point, the PTZ value stored when the panoramic image is spliced and coordinate data;
or
And calculating to obtain the corresponding coordinates of the to-be-positioned point in the panoramic image with the holder camera as the center by combining an image matching algorithm according to the PTZ value of the center point of the to-be-positioned picture, the position relation between the center point of the to-be-positioned picture and the to-be-positioned point, the PTZ value and the coordinate data which are saved during splicing of the panoramic image.
Preferably, the method further comprises:
and saving the PTZ value of the point to be located and the corresponding coordinate thereof in the panoramic image to the database so as to update the database.
In order to achieve the above object, according to a second aspect of the present invention, there is provided a ground object target position precision positioning device based on line matching, the device comprising:
the mapping relation establishing module is used for establishing a coordinate mapping relation between the panoramic image taking the pan-tilt camera as the center and the edge line of the depth image based on a line matching mode, wherein the coordinates of each point in the depth image have corresponding longitude and latitude;
the system comprises a to-be-positioned picture acquisition module, a positioning point locating module and a positioning point locating module, wherein the to-be-positioned picture acquisition module is used for acquiring a to-be-positioned picture containing a to-be-positioned point and image information of the to-be-positioned picture shot by a pan-tilt camera;
the first coordinate calculation module is used for calculating to obtain the corresponding coordinates of the to-be-positioned point in the panoramic image with the holder camera as the center according to the image information of the to-be-positioned picture;
the second coordinate calculation module is used for obtaining the corresponding coordinates of the to-be-positioned point in the depth map according to the coordinates of the to-be-positioned point in the panoramic map and the coordinate mapping relation between the edge lines of the panoramic map and the depth map;
and the longitude and latitude calculation module is used for obtaining the longitude and latitude of the point to be located according to the corresponding relation between the coordinates of the point to be located in the depth map and the coordinates and the longitude and latitude of each point in the depth map.
Preferably, the apparatus further comprises:
the panorama splicing module is used for splicing a single-layer picture shot by the pan-tilt camera in a fixed vertical direction or a plurality of layers of pictures shot by changing shooting angles in a vertical direction into the panorama taking the pan-tilt camera as a center, wherein each layer of pictures comprises a plurality of live-action pictures shot at certain angles in the horizontal direction, and the PTZ value of the central point of each live-action picture spliced into the panorama and the coordinate data of the central point of each live-action picture obtained by conversion after splicing are stored in a database;
and/or
The depth map generating module is used for generating a data file which is recorded with DEM elevation information with the holder camera as the center through a GIS tool or programming, and generating the depth map based on the DEM elevation information contained in the data file;
and/or
And the mapping relation establishing module is used for respectively extracting image edge lines used for representing a geodesic line from the panoramic image and the depth image which take the holder camera as the center, associating the edge lines of the panoramic image and the depth image obtained by selecting the edge lines of the panoramic image and the depth image on a user interaction interface, and establishing a coordinate mapping relation between the two edge lines.
Preferably, the first coordinate calculation module is specifically configured to:
calculating to obtain the corresponding coordinates of the to-be-positioned point in the panoramic image with the holder camera as the center by utilizing an image matching algorithm according to the image information of the to-be-positioned picture;
or
Calculating the coordinate of the to-be-positioned point in the panoramic image according to the PTZ value of the central point of the to-be-positioned image, the position relation between the central point of the to-be-positioned image and the to-be-positioned point, the PTZ value stored when the panoramic image is spliced and coordinate data;
or
And calculating to obtain the corresponding coordinates of the to-be-positioned point in the panoramic image with the holder camera as the center by combining an image matching algorithm according to the PTZ value of the center point of the to-be-positioned picture, the position relation between the center point of the to-be-positioned picture and the to-be-positioned point, the PTZ value and the coordinate data which are saved during splicing of the panoramic image.
In order to achieve the above object, according to a third aspect of the present invention, there is provided a computer-readable storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the steps of the above method for accurately positioning the position of the ground object target based on line matching.
In order to achieve the above object of the present invention, according to a fourth aspect of the present invention, there is provided an electronic apparatus comprising:
a memory for storing a computer program; and
and the processor is used for realizing the steps of the ground object target position accurate positioning method based on line matching when the computer program is executed.
According to the scheme, the invention provides a ground object target position accurate positioning method based on line matching, which comprises the steps of establishing a coordinate mapping relation between a panoramic image taking a holder camera as a center and an edge line of a depth image based on a line matching mode, wherein coordinates of each point in the depth image have corresponding longitude and latitude; acquiring a picture to be positioned containing a to-be-positioned point and image information of the picture to be positioned, which are shot by the pan-tilt camera; calculating to obtain the corresponding coordinates of the to-be-positioned point in the panoramic image with the holder camera as the center according to the image information of the to-be-positioned picture; obtaining the corresponding coordinates of the to-be-positioned point in the depth map according to the coordinates of the to-be-positioned point in the panoramic map and the coordinate mapping relation between the edge lines of the panoramic map and the depth map; and obtaining the longitude and latitude of the point to be located according to the corresponding relation between the coordinates of the point to be located in the depth map and the coordinates and the longitude and latitude of each point in the depth map. The accurate positioning method for the ground object target position based on line matching provided by the invention utilizes the panoramic image and the depth image which take the pan-tilt camera as the center and the coordinate mapping relation established between the panoramic image and the depth image based on edge line matching to position the point to be positioned in the image to be positioned shot by the pan-tilt camera, thereby realizing the accurate positioning of the longitude and latitude of the target ground object position. The application also discloses a ground object target position accurate positioning device based on line matching, a computer readable storage medium and an electronic device, and the technical effects can be realized.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The above and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a flow chart of a method for accurately positioning a ground object target position based on line matching in a preferred embodiment of the present invention;
FIG. 2 is a flow chart of a method for accurately positioning the target position of a ground object based on line matching in another preferred embodiment of the present invention;
FIG. 3 is a schematic structural diagram of a device for accurately positioning a ground object target position based on line matching according to a preferred embodiment of the present invention;
FIG. 4 is a schematic illustration of a user interaction interface in an embodiment of the invention;
FIG. 5 is a diagram illustrating an example of a method for calculating coordinates of a point in a depth map from coordinates of the point in a panorama according to an embodiment of the present invention;
fig. 6 is a schematic diagram of another example of a method for calculating the coordinates of a point in a depth map from the coordinates of the point in a panoramic image in an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
Interpretation of terms:
DEM: a Digital Elevation Model (Digital Elevation Model) is used for realizing Digital simulation of ground terrain through limited terrain Elevation data to form a three-dimensional figure.
Depth map: refers to an image in which the distance (i.e., depth) from an image collector to each point in a scene, each point having its corresponding latitude and longitude, is represented in terms of pixel values. The image collector in the invention is the tripod head camera. In addition, the data used to obtain the depth map may be obtained from GIS software or the like.
PTZ value: p, horizontal Pan-tilt angle (Pan); t, vertical rotation angle (Tilt) of the holder; z, lens magnification (Zoom) of the pan/tilt camera.
Edge line: a boundary line generated by a difference in pixel value, hue, gradient, or the like between adjacent pixels in an image. In the invention, the geodesic line of the actual mountain is represented by an edge line in the image.
The geodesic: the skeleton line of the landform form is a control line for describing the landform form, and mainly comprises a ridge line, a valley line, a river bank line and the like.
As shown in fig. 1, the method for accurately positioning the target position of a surface feature based on line matching according to the embodiment of the present invention may include the following steps:
s101, establishing a coordinate mapping relation between a panoramic image taking a pan-tilt camera as a center and an edge line of a depth image based on a line matching mode, wherein coordinates of each point in the depth image have corresponding longitude and latitude;
s102, acquiring a picture to be positioned containing a point to be positioned and image information of the picture to be positioned, which are shot by a pan-tilt camera;
s103, calculating to obtain the corresponding coordinates of the to-be-positioned point in the panoramic image with the holder camera as the center according to the image information of the to-be-positioned picture;
s104, obtaining the corresponding coordinates of the to-be-positioned point in the depth map according to the coordinates of the to-be-positioned point in the panoramic map and the coordinate mapping relation between the edge lines of the panoramic map and the depth map;
and S105, obtaining the longitude and latitude of the point to be located according to the corresponding relation between the coordinates of the point to be located in the depth map and the coordinates and the longitude and latitude of each point in the depth map.
In summary, the present embodiment provides a method for accurately positioning a ground object target position based on line matching, which includes first establishing a coordinate mapping relationship between edge lines of a panoramagram and a depth map, the edge lines being centered on a pan-tilt camera, based on a line matching manner; then, acquiring a picture to be positioned containing a to-be-positioned point and image information of the picture to be positioned, which is shot by a pan-tilt camera; then, calculating to obtain the corresponding coordinates of the to-be-positioned point in the panoramic image with the holder camera as the center according to the image information of the to-be-positioned picture; then, obtaining the corresponding coordinates of the point to be located in the depth map according to the coordinates of the point to be located in the panoramic map and the coordinate mapping relation between the edge lines of the panoramic map and the depth map; and finally, obtaining the longitude and latitude of the point to be located according to the corresponding relation between the coordinates of the point to be located in the depth map and the coordinates and the longitude and latitude of each point in the depth map, namely the longitude and latitude of the target position of the ground object. In the embodiment, the panoramic image and the depth image which are centered by the pan-tilt camera and the coordinate mapping relationship established between the panoramic image and the depth image based on the edge line matching are utilized to position the longitude and latitude of the point to be positioned in the image to be positioned shot by the pan-tilt camera, so that the accurate positioning of the longitude and latitude of the ground object target position is realized.
As shown in fig. 2, another method for accurately positioning a ground object target position based on line matching according to an embodiment of the present invention may include the following steps:
s201, splicing a single-layer picture shot by a pan-tilt camera in a fixed vertical direction or a plurality of layers of pictures shot by changing shooting angles in a vertical direction into a panoramic picture taking the pan-tilt camera as a center, wherein each layer of picture comprises a plurality of live-action pictures shot at certain angles in the horizontal direction;
s202, storing the PTZ value of the central point of each live-action picture spliced into the panoramic picture and the coordinate data of the central point of each live-action picture obtained by transformation after splicing into a database;
s203, generating a data file recorded with DEM elevation information by using a holder camera as a center through a GIS tool or programming;
s204, generating a depth map based on DEM elevation information contained in the data file, wherein coordinates of each point in the depth map have corresponding longitude and latitude;
s205, respectively extracting image edge lines for representing the geodesic lines from the panoramic image and the depth image which take the pan-tilt camera as the center;
s206, selecting the edge line of the panoramic image and the edge line of the depth image on the user interaction interface;
s207, associating the edge line of the selected panoramic image with the edge line of the depth image, and establishing a coordinate mapping relation between the two edge lines;
s208, acquiring a picture to be positioned containing a point to be positioned and image information of the picture to be positioned, which are shot by the pan-tilt camera;
s209, calculating to obtain the corresponding coordinates of the to-be-positioned point in the panoramic image with the holder camera as the center according to the image information of the to-be-positioned picture;
s210, obtaining the corresponding coordinates of the to-be-positioned point in the depth map according to the coordinates of the to-be-positioned point in the panoramic map and the coordinate mapping relation between the edge lines of the panoramic map and the depth map;
s211, obtaining the longitude and latitude of the point to be located according to the corresponding relation between the coordinates of the point to be located in the depth map and the coordinates and the longitude and latitude of each point in the depth map.
In this embodiment, in step S209, the coordinates of the to-be-positioned point in the panorama centered on the pan-tilt camera obtained by calculation according to the image information of the to-be-positioned picture may specifically adopt one of the following three methods:
calculating to obtain the corresponding coordinates of a to-be-positioned point in a panoramic image taking a pan-tilt camera as the center by utilizing an image matching algorithm according to the image information of the to-be-positioned picture;
the method comprises the steps of obtaining a coordinate calculation relation of any point in a picture to be positioned in a panoramic picture, and calculating the corresponding coordinate of the point to be positioned in the panoramic picture taking a pan-tilt camera as the center according to the obtained calculation relation.
Calculating the coordinates of the to-be-positioned point in the panoramic image according to the PTZ value of the central point of the to-be-positioned image, the position relation between the central point of the to-be-positioned image and the to-be-positioned point, the PTZ value stored during splicing of the panoramic image and coordinate data;
the specific calculation steps are as follows:
calculating a PTZ value of a to-be-positioned point according to the PTZ value of the central point of the to-be-positioned picture and the position relation between the central point of the to-be-positioned picture and the to-be-positioned point;
calculating a group of PTZ values closest to the PTZ value of the point to be positioned in the PTZ values of the central points of each live-action picture spliced into the panoramic picture taking the pan-tilt camera as the center;
and calculating the accurate coordinates of the picture to be positioned in the panoramic image by using a proportional method according to the corresponding relation between the PTZ value of the point to be positioned and a group of PTZ values closest to the PTZ value of the point to be positioned.
And calculating to obtain the corresponding coordinates of the to-be-positioned point in the panoramic image with the holder camera as the center by combining an image matching algorithm according to the PTZ value of the center point of the to-be-positioned image, the position relation between the center point of the to-be-positioned image and the to-be-positioned point, the PTZ value and the coordinate data saved during splicing of the panoramic image.
The specific calculation steps are as follows:
calculating a PTZ value of a to-be-positioned point according to the PTZ value of the central point of the to-be-positioned picture and the position relation between the central point of the to-be-positioned picture and the to-be-positioned point;
calculating a group of PTZ values closest to the PTZ value of the point to be positioned in the PTZ values of the central points of each live-action picture spliced into the panoramic picture taking the pan-tilt camera as the center;
determining a picture matching region centered on the closest set of PTZ values;
and performing feature matching on the picture to be positioned and the picture matching area by using a picture matching algorithm, and obtaining the accurate coordinates of the picture to be positioned in the panoramic image according to a matching result.
In the third method, the corresponding coordinates of the to-be-positioned point in the to-be-positioned picture in the panoramic image can be obtained by matching the to-be-positioned picture with the panoramic image, but the panoramic image has too large pixels, a complex scene, high possibility of mismatching and long matching time. Therefore, a group of PTZ values closest to the PTZ value of the point to be located can be calculated, an image matching area is determined by taking the corresponding point of the PTZ value as the center, the matching range is narrowed, the narrowed image matching area is subjected to feature matching with the image to be located, more accurate coordinates of the point to be located in the panoramic image can be obtained, the matching precision is improved, and the matching time can be effectively reduced.
It should be noted that, in the third method, the calculation result has a smaller deviation when the magnification of the picture to be located is different from the magnification of the panorama, and at this time, a picture matching area may be determined according to the coordinates of the picture to be located, which may have a smaller deviation, in the panorama, which are obtained through the PTZ value calculation, and the picture matching area is used as a constraint condition for image feature matching.
In the above embodiment, in the first method, when the coordinates of the to-be-positioned point in the panorama are calculated only through the image matching algorithm, the image matching method is very accurate in the case of appropriate weather and lighting conditions due to the high quality of the shot image of the to-be-positioned image, but may not be matched in the case of large changes in weather and lighting conditions, such as heavy fog, heavy rain and night; in the second method, when the coordinates of the to-be-located point in the panorama are calculated through the PTZ value, when the PTZ value of the to-be-located point can directly find the corresponding PTZ value in the existing PTZ data in the database, the calculation result is very accurate, and the farther the PTZ value is from the existing PTZ data in the database (that is, the farther the PTZ value is from the existing PTZ data in the database), the more the calculation result is accurate
Larger) the deviation value of the calculation result is larger.
Therefore, in the present embodiment, a method in which the PTZ value described in method three is combined with image matching is preferably employed.
Specifically, in the above embodiment, after the PTZ value of the to-be-located point in the to-be-located picture and the corresponding coordinate thereof in the panorama are obtained through calculation, the PTZ value of the to-be-located point and the corresponding coordinate thereof in the panorama can be stored in the database, so as to update the database.
For example, when the image matching result is confirmed to be correct, the PTZ value corresponding to the to-be-positioned point in the to-be-positioned image is stored in the existing PTZ data in the database, and the more PTZ data, the more possibility that the distance between the PTZ value of the to-be-positioned point and the existing PTZ data is closer is indicated, and the more accurate the calculation is. When the image matching cannot be matched when the illumination and weather conditions change, such as heavy fog, heavy rain and night, the result of calculation by using the PTZ is more accurate.
Specifically, the image matching result is correct, a biased value is calculated by using the PTZ, an area is determined, and if the key points in the image to be located after the image matching, such as the center point and the four corners, all the coordinates in the panorama fall in the area, the matching is considered to be successful. When the images cannot be matched to the point to be positioned only by image matching because of different weather and illumination, the PTZ data of the matched images are recorded, and the PTZ data which can be inquired about the images which cannot be matched are increased. For example, in the midday, because the weather and the illumination condition are good, if a point to be positioned in a picture to be positioned is matched, the PTZ data is recorded, and an alarm is given at the same place in the evening, but the coordinate of the point to be positioned in the panorama cannot be found through image matching at this time. Then, the PTZ data can be searched, and just the PTZ data of an alarm picture (picture to be positioned) at noon is the same as the PTZ data, so that the coordinates of the PTZ data in the panoramic image can be directly found out, and the longitude and latitude of the picture to be positioned can be obtained.
In summary, in the embodiment, a preparation step of constructing a panoramic image and a depth image with a pan-tilt camera as a center, extracting edge lines from the panoramic image and the depth image, and establishing a coordinate mapping relationship between the edge lines of the panoramic image and the depth image is added on the basis of the embodiment shown in fig. 1. In the embodiment, the panoramic image and the depth image which are centered by the pan-tilt camera and the coordinate mapping relationship established between the panoramic image and the depth image based on the edge line matching are utilized to position the longitude and latitude of the point to be positioned in the image to be positioned shot by the pan-tilt camera, so that the accurate positioning of the longitude and latitude of the ground object target position is realized.
Corresponding to the method for accurately positioning the target location of the ground object based on line matching provided in the embodiment shown in fig. 1, as shown in fig. 3, the apparatus for accurately positioning the target location of the ground object based on line matching provided in the embodiment of the present application may include:
a mapping relation establishing module 301, configured to establish a coordinate mapping relation between edge lines of a panoramic image and a depth image, where coordinates of each point in the depth image have a longitude and a latitude corresponding to the coordinate, and the pan-tilt camera is used as a center, based on a line matching manner;
the to-be-positioned picture acquisition module 302 is used for acquiring the to-be-positioned picture containing the to-be-positioned point and the image information of the to-be-positioned picture shot by the pan-tilt camera;
the first coordinate calculation module 303 is configured to calculate, according to image information of a picture to be located, a coordinate corresponding to a point to be located in a panoramic image with a pan-tilt camera as a center;
the second coordinate calculation module 304 is configured to obtain a corresponding coordinate of the point to be located in the depth map according to a coordinate of the point to be located in the panorama and a coordinate mapping relationship between edge lines of the panorama and the depth map;
the latitude and longitude calculation module 305 is configured to obtain the latitude and longitude of the point to be located according to the coordinates of the point to be located in the depth map and the corresponding relationship between the coordinates of each point in the depth map and the latitude and longitude.
In summary, in the present embodiment, a device for accurately positioning a ground object target position based on line matching is provided, in which a mapping relationship between a panoramic image centered on a pan-tilt camera and an edge line of a depth image is first established by a mapping relationship establishing module 301 based on a line matching manner, where coordinates of each point in the depth image have a longitude and a latitude corresponding to the coordinate; then, an image to be positioned containing a to-be-positioned point and image information of the to-be-positioned image shot by the pan-tilt camera are obtained through the to-be-positioned image obtaining module 302; then, calculating to obtain the corresponding coordinates of the to-be-positioned point in the panoramic image taking the pan-tilt camera as the center through a first coordinate calculation module 303 according to the image information of the to-be-positioned picture; then, obtaining the corresponding coordinates of the point to be located in the depth map through a second coordinate calculation module 304 according to the coordinates of the point to be located in the panoramic map and the coordinate mapping relationship between the edge lines of the panoramic map and the depth map; and finally, the longitude and latitude of the point to be located are obtained through the longitude and latitude calculation module 305 according to the coordinates of the point to be located in the depth map and the corresponding relation between the coordinates of each point in the depth map and the longitude and latitude. In the embodiment, the panoramic image and the depth image which are centered by the pan-tilt camera and the coordinate mapping relationship established between the panoramic image and the depth image based on the edge line matching are utilized to position the longitude and latitude of the point to be positioned in the image to be positioned shot by the pan-tilt camera, so that the accurate positioning of the longitude and latitude of the ground object target position is realized.
On the basis of the above-mentioned embodiment of the apparatus shown in fig. 3, as a preferred embodiment, the apparatus may further include:
the panoramic picture splicing module is used for splicing a single-layer picture shot by the pan-tilt camera in a fixed vertical direction or a plurality of layers of pictures shot by changing shooting angles in a vertical direction into a panoramic picture taking the pan-tilt camera as a center, and storing a PTZ value of the central point of each live-action picture spliced into the panoramic picture and coordinate data of the central point of each live-action picture obtained by conversion after splicing into a database, wherein each layer of picture comprises a plurality of live-action pictures shot at certain angles in the horizontal direction;
the depth map generating module is used for generating a data file which is recorded with DEM elevation information with a holder camera as the center through a GIS tool or programming, and generating a depth map based on the DEM elevation information contained in the data file; and
and the mapping relation establishing module is used for respectively extracting image edge lines for representing the geodesic lines from the panoramic image and the depth image which take the pan-tilt camera as the center, associating the edge lines of the panoramic image and the depth image obtained by selecting the edge lines of the panoramic image and the depth image on the user interaction interface, and establishing a coordinate mapping relation between the two edge lines.
On the basis of the foregoing embodiment, as a preferred implementation manner, the first coordinate calculation module 303 is specifically configured to calculate, according to image information of a picture to be located, a coordinate corresponding to a point to be located in a panoramic image with a pan-tilt camera as a center by using one of the following three methods:
calculating to obtain the corresponding coordinates of a to-be-positioned point in a panoramic image taking a pan-tilt camera as the center by utilizing an image matching algorithm according to the image information of the to-be-positioned picture;
the method comprises the steps of obtaining a coordinate calculation relation of any point in a picture to be positioned in a panoramic picture, and calculating the corresponding coordinate of the point to be positioned in the panoramic picture taking a pan-tilt camera as the center according to the obtained calculation relation.
Calculating the coordinates of the to-be-positioned point in the panoramic image according to the PTZ value of the central point of the to-be-positioned image, the position relation between the central point of the to-be-positioned image and the to-be-positioned point, the PTZ value stored during splicing of the panoramic image and coordinate data;
the specific calculation steps are as follows:
calculating a PTZ value of a to-be-positioned point according to the PTZ value of the central point of the to-be-positioned picture and the position relation between the central point of the to-be-positioned picture and the to-be-positioned point;
calculating a group of PTZ values closest to the PTZ value of the point to be positioned in the PTZ values of the central points of each live-action picture spliced into the panoramic picture taking the pan-tilt camera as the center;
and calculating the accurate coordinates of the picture to be positioned in the panoramic image by using a proportional method according to the corresponding relation between the PTZ value of the point to be positioned and a group of PTZ values closest to the PTZ value of the point to be positioned.
And calculating to obtain the corresponding coordinates of the to-be-positioned point in the panoramic image with the holder camera as the center by combining an image matching algorithm according to the PTZ value of the center point of the to-be-positioned image, the position relation between the center point of the to-be-positioned image and the to-be-positioned point, the PTZ value and the coordinate data saved during splicing of the panoramic image.
The specific calculation steps are as follows:
calculating a PTZ value of a to-be-positioned point according to the PTZ value of the central point of the to-be-positioned picture and the position relation between the central point of the to-be-positioned picture and the to-be-positioned point;
calculating a group of PTZ values closest to the PTZ value of the point to be positioned in the PTZ values of the central points of each live-action picture spliced into the panoramic picture taking the pan-tilt camera as the center;
determining a picture matching region centered on the closest set of PTZ values;
and performing feature matching on the picture to be positioned and the picture matching area by using a picture matching algorithm, and obtaining the accurate coordinates of the picture to be positioned in the panoramic image according to a matching result.
In the third method, the corresponding coordinates of the to-be-positioned point in the to-be-positioned picture in the panoramic image can be obtained by matching the to-be-positioned picture with the panoramic image, but the panoramic image has too large pixels, a complex scene, high possibility of mismatching and long matching time. Therefore, a group of PTZ values closest to the PTZ value of the point to be located can be calculated, an image matching area is determined by taking the corresponding point of the PTZ value as the center, the matching range is narrowed, the narrowed image matching area is subjected to feature matching with the image to be located, more accurate coordinates of the point to be located in the panoramic image can be obtained, the matching precision is improved, and the matching time can be effectively reduced.
It should be noted that, in the third method, the calculation result has a smaller deviation when the magnification of the picture to be located is different from the magnification of the panorama, and at this time, a picture matching area may be determined according to the coordinates of the picture to be located, which may have a smaller deviation, in the panorama, which are obtained through the PTZ value calculation, and the picture matching area is used as a constraint condition for image feature matching.
In the above embodiment, in the first method, when the coordinates of the to-be-positioned point in the panorama are calculated only through the image matching algorithm, the image matching method is very accurate in the case of appropriate weather and lighting conditions due to the high quality of the shot image of the to-be-positioned image, but may not be matched in the case of large changes in weather and lighting conditions, such as heavy fog, heavy rain and night; in the second method, when the coordinates of the to-be-positioned point in the panorama are calculated through the PTZ values, when the PTZ values of the to-be-positioned point can directly find the corresponding PTZ values in the existing PTZ data in the database, the calculation result is very accurate, and the farther the distance between the to-be-positioned point and the existing PTZ data in the database is, the larger the deviation value of the calculation result is.
Therefore, in the present embodiment, a method in which the PTZ value described in method three is combined with image matching is preferably employed.
Specifically, in the above embodiment, after the PTZ value of the to-be-located point in the to-be-located picture and the corresponding coordinate thereof in the panorama are obtained through calculation, the PTZ value of the to-be-located point and the corresponding coordinate thereof in the panorama can be stored in the database, so as to update the database.
For example, when the image matching result is confirmed to be correct, the PTZ value corresponding to the to-be-positioned point in the to-be-positioned image is stored in the existing PTZ data in the database, and the more PTZ data, the more possibility that the distance between the PTZ value of the to-be-positioned point and the existing PTZ data is closer is indicated, and the more accurate the calculation is. When the image matching cannot be matched when the illumination and weather conditions change, such as heavy fog, heavy rain and night, the result of calculation by using the PTZ is more accurate.
Specifically, the image matching result is correct, a biased value is calculated by using the PTZ, an area is determined, and if the key points in the image to be located after the image matching, such as the center point and the four corners, all the coordinates in the panorama fall in the area, the matching is considered to be successful. When the images cannot be matched to the point to be positioned only by image matching because of different weather and illumination, the PTZ data of the matched images are recorded, and the PTZ data which can be inquired about the images which cannot be matched are increased. For example, in the midday, because the weather and the illumination condition are good, if a point to be positioned in a picture to be positioned is matched, the PTZ data is recorded, and an alarm is given at the same place in the evening, but the coordinate of the point to be positioned in the panorama cannot be found through image matching at this time. Then, the PTZ data can be searched, and just the PTZ data of an alarm picture (picture to be positioned) at noon is the same as the PTZ data, so that the coordinates of the PTZ data in the panoramic image can be directly found out, and the longitude and latitude of the picture to be positioned can be obtained.
Specifically, the coordinates in the above embodiments may be cartesian coordinates.
The embodiment of the invention also provides a computer readable storage medium, wherein a computer program is stored on the computer readable storage medium, and when the computer program is executed by a processor, the steps of the above method for accurately positioning the position of the ground object target based on line matching are realized.
An embodiment of the present invention further provides an electronic device, where the electronic device includes:
a memory for storing a computer program; and
and the processor is used for realizing the steps of the ground object target position accurate positioning method based on line matching when the computer program is executed.
Specifically, the electronic device may be a desktop computer, a notebook computer, a tablet computer, a smart phone, or a smart wearable device.
Specifically, in the foregoing embodiments, the user interaction interface for selecting the edge line of the panoramic image and the edge line of the depth map is as shown in fig. 4, an upper window and a lower window of the user interaction interface are respectively used for displaying the panoramic image and the depth map, and the main operation buttons and functions thereof on the user interaction interface are introduced as follows:
"load picture": calling a file selection window to enable a user to select a panoramic picture to be loaded;
"load dem file": calling a file selection window to enable a user to select a DEM data file to be loaded;
"load PT data": calling a file selection window to enable a user to select a PT data file to be loaded;
"select starting point": allowing a user to click on the picture, and taking the corresponding coordinate as a starting point of the geodesic line to be selected;
"select endpoint": allowing a user to click on the picture, and taking the corresponding coordinate as the terminal point of the geodesic line to be selected;
"select line": when the extraction condition of the edge line is poor, allowing a user to press a mouse on the picture to perform dragging operation, and drawing a line;
"match" is performed: establishing a mapping relation between the geodesic lines selected from the two graphs;
"calculate": calculating the position of the PT value in the panoramic image according to the input PT value, and then calculating the position of the PT value in the depth image to obtain the corresponding longitude and latitude;
"save record": storing the loaded data and the established line mapping relation into a local binary file;
"read record": reading a local binary file, and restoring the local binary file to a user interaction interface;
tab page switching button: and switching the panoramic image/the depth image and the corresponding image with the extracted edge.
Specifically, in the above embodiments, the method for calculating the coordinates of a point in the depth map from the coordinates of the point in the panorama through the established edge line (geodesic line) mapping pair of the panorama and the depth map is as follows:
1) as shown in FIG. 5, if there is only one mapped geodesic line above and below the point A to be calculated, i.e. the curve L1。
Wherein L is1The height of the area occupied by the curve is h, the width is w, B is the vertical projection of the point A on the curve, namely A and B have the same abscissa, and the ratio p of the distance from the point B to the left end of the area to the width of the whole area is recordedxIs composed of
Ratio p of distance of point A, B to overall area heightyIs composed of
Finding out the corresponding geodesic line in the depth map by using the geodesic line in the panoramic image, and obtaining a curve L1' means that the width of the occupied area is w ', the height is h ', and the abscissa of the leftmost end is x0', then the abscissa of the mapped point B' of the point B in the depth map is
At curve L1'find this abscissa, find y's ordinate of BB′。
The coordinates of the mapping point a' of point a in the depth map are then
2) As shown in FIG. 6, if there is a geodesic line with a mapping established above and below the point A to be calculated, i.e. the curve L1、L2。
Wherein L is1The width of the area occupied by the curve is w1，L2The width of the area occupied by the curve is w2，B1Point A on curve L1Vertical projection of (A), B2Point A on curve L2Vertical projection of (a). Then A, B1、B2All having the same abscissa, as in 1), find B1、B2Respectively mapped points B in the depth map1′(xB1′,yB1′)、B2′(xB2′,yB2') then the coordinates of the mapped point A' of point A in the depth map are
xA′＝xB1′＝xB2′ (6)
Specifically, the accurate positioning method for the ground object target position based on line matching can be applied to positioning of fire and fire point positions in forest regions, and in a scene of positioning of the fire and fire point positions in the forest regions, the to-be-positioned picture in each embodiment can be a fire alarm picture containing fire and fire points, which is shot by a cloud deck camera arranged in the forest regions in a fire prevention monitoring alarm detection system in the forest regions, wherein the to-be-positioned points are the fire and fire points.
The functions described in the method of the embodiment of the present application may be stored in a computer-readable storage medium if they are implemented in the form of software functional units and sold or used as independent products. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of said computer program code, recording medium, U-disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signal, telecommunications signal, software distribution medium, etc. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.
The embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same or similar parts among the embodiments are referred to each other.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A ground object target position accurate positioning method based on line matching is characterized by comprising the following steps:
establishing a coordinate mapping relation between a panoramic image taking a pan-tilt camera as a center and an edge line of a depth image based on a line matching mode, wherein coordinates of each point in the depth image have corresponding longitude and latitude;
acquiring a picture to be positioned containing a to-be-positioned point and image information of the picture to be positioned, which are shot by the pan-tilt camera;
calculating to obtain the corresponding coordinates of the to-be-positioned point in the panoramic image with the holder camera as the center according to the image information of the to-be-positioned picture;
obtaining the corresponding coordinates of the to-be-positioned point in the depth map according to the coordinates of the to-be-positioned point in the panoramic map and the coordinate mapping relation between the edge lines of the panoramic map and the depth map;
and obtaining the longitude and latitude of the point to be located according to the corresponding relation between the coordinates of the point to be located in the depth map and the coordinates and the longitude and latitude of each point in the depth map.
2. The method for accurately positioning the target position of the ground object based on line matching according to claim 1, further comprising:
splicing a single-layer picture shot by the pan-tilt camera in a fixed vertical direction or a plurality of layers of pictures shot by changing shooting angles in the vertical direction into the panoramic picture taking the pan-tilt camera as the center, wherein each layer of picture comprises a plurality of live-action pictures shot at certain angles in the horizontal direction;
and storing the PTZ value of the central point of each live-action picture spliced into the panoramic picture and the coordinate data of the central point of each live-action picture obtained by transformation after splicing into a database.
3. The method for accurately positioning the target position of the ground object based on line matching according to claim 1, further comprising:
generating a data file recorded with DEM elevation information by taking the holder camera as a center through a GIS tool or programming;
and generating the depth map based on the DEM elevation information contained in the data file.
4. The method for accurately positioning the ground object target position based on line matching according to claim 1, wherein the establishing the coordinate mapping relationship between the pan-tilt-camera-centered panoramic image and the edge line of the depth image based on the line matching comprises:
respectively extracting image edge lines used for representing a geodesic line from the panoramic image and the depth image which take the pan-tilt camera as the center;
selecting an edge line of the panoramic image and an edge line of the depth image on a user interaction interface;
and associating the selected edge line of the panoramic image with the edge line of the depth image, and establishing a coordinate mapping relation between the two edge lines.
5. The method for accurately positioning the target position of the ground object based on the line matching as claimed in claim 2, wherein the step of calculating the coordinates of the to-be-positioned point in the panorama centering on the pan-tilt camera according to the image information of the to-be-positioned picture comprises:
calculating to obtain the corresponding coordinates of the to-be-positioned point in the panoramic image with the holder camera as the center by utilizing an image matching algorithm according to the image information of the to-be-positioned picture;
or
Calculating the coordinate of the to-be-positioned point in the panoramic image according to the PTZ value of the central point of the to-be-positioned image, the position relation between the central point of the to-be-positioned image and the to-be-positioned point, the PTZ value stored when the panoramic image is spliced and coordinate data;
or
And calculating to obtain the corresponding coordinates of the to-be-positioned point in the panoramic image with the holder camera as the center by combining an image matching algorithm according to the PTZ value of the center point of the to-be-positioned picture, the position relation between the center point of the to-be-positioned picture and the to-be-positioned point, the PTZ value and the coordinate data which are saved during splicing of the panoramic image.
6. The method for accurately positioning the target position of the ground object based on line matching according to claim 5, further comprising:
and saving the PTZ value of the point to be located and the corresponding coordinate thereof in the panoramic image to the database so as to update the database.
7. The utility model provides a ground object target location accurate positioning device based on line matching which characterized in that includes:
the mapping relation establishing module is used for establishing a coordinate mapping relation between the panoramic image taking the pan-tilt camera as the center and the edge line of the depth image based on a line matching mode, wherein the coordinates of each point in the depth image have corresponding longitude and latitude;
the system comprises a to-be-positioned picture acquisition module, a positioning point locating module and a positioning point locating module, wherein the to-be-positioned picture acquisition module is used for acquiring a to-be-positioned picture containing a to-be-positioned point and image information of the to-be-positioned picture shot by a pan-tilt camera;
the first coordinate calculation module is used for calculating to obtain the corresponding coordinates of the to-be-positioned point in the panoramic image with the holder camera as the center according to the image information of the to-be-positioned picture;
the second coordinate calculation module is used for obtaining the corresponding coordinates of the to-be-positioned point in the depth map according to the coordinates of the to-be-positioned point in the panoramic map and the coordinate mapping relation between the edge lines of the panoramic map and the depth map;
and the longitude and latitude calculation module is used for obtaining the longitude and latitude of the point to be located according to the corresponding relation between the coordinates of the point to be located in the depth map and the coordinates and the longitude and latitude of each point in the depth map.
8. The device for accurately positioning the target position of the ground object based on line matching according to claim 7, further comprising:
the panorama splicing module is used for splicing a single-layer picture shot by the pan-tilt camera in a fixed vertical direction or a plurality of layers of pictures shot by changing shooting angles in a vertical direction into the panorama centered on the pan-tilt camera, and storing the PTZ value of the central point of each live-action picture spliced into the panorama and the coordinate data of the central point of each live-action picture obtained by conversion after splicing into a database, wherein each layer of picture comprises a plurality of live-action pictures shot at certain angles in the horizontal direction;
and/or
The depth map generating module is used for generating a data file which is recorded with DEM elevation information with the holder camera as the center through a GIS tool or programming, and generating the depth map based on the DEM elevation information contained in the data file;
and/or
And the mapping relation establishing module is used for respectively extracting image edge lines used for representing a geodesic line from the panoramic image and the depth image which take the holder camera as the center, associating the edge lines of the panoramic image and the depth image obtained by selecting the edge lines of the panoramic image and the depth image on a user interaction interface, and establishing a coordinate mapping relation between the two edge lines.
9. The device for accurately positioning the target position of a ground object based on line matching according to claim 8, wherein the first coordinate calculation module is specifically configured to:
calculating to obtain the corresponding coordinates of the to-be-positioned point in the panoramic image with the holder camera as the center by utilizing an image matching algorithm according to the image information of the to-be-positioned picture;
or
Calculating the coordinate of the to-be-positioned point in the panoramic image according to the PTZ value of the central point of the to-be-positioned image, the position relation between the central point of the to-be-positioned image and the to-be-positioned point, the PTZ value stored when the panoramic image is spliced and coordinate data;
or
And calculating to obtain the corresponding coordinates of the to-be-positioned point in the panoramic image with the holder camera as the center by combining an image matching algorithm according to the PTZ value of the center point of the to-be-positioned picture, the position relation between the center point of the to-be-positioned picture and the to-be-positioned point, the PTZ value and the coordinate data which are saved during splicing of the panoramic image.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a computer program, which when executed by a processor implements the steps of the line matching-based ground object target position precision positioning method according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110666345.0A CN113298867A (en) | 2021-06-16 | 2021-06-16 | Accurate positioning method and device for ground object target position based on line matching and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110666345.0A CN113298867A (en) | 2021-06-16 | 2021-06-16 | Accurate positioning method and device for ground object target position based on line matching and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113298867A true CN113298867A (en) | 2021-08-24 |
Family
ID=77328472
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110666345.0A Pending CN113298867A (en) | 2021-06-16 | 2021-06-16 | Accurate positioning method and device for ground object target position based on line matching and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113298867A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114217618A (en) * | 2021-12-14 | 2022-03-22 | 重庆富沛和科技有限公司 | Method for performing automatic cruise within selected range in three-dimensional map |
| CN116433756A (en) * | 2023-06-15 | 2023-07-14 | 浪潮智慧科技有限公司 | Surface object space analysis method, device and medium of monocular camera |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103198488A (en) * | 2013-04-16 | 2013-07-10 | 北京天睿空间科技有限公司 | PTZ surveillance camera realtime posture rapid estimation method |
| CN103971375A (en) * | 2014-05-22 | 2014-08-06 | 中国人民解放军国防科学技术大学 | Panoramic gaze camera space calibration method based on image splicing |
| CN109523592A (en) * | 2018-10-19 | 2019-03-26 | 天津大学 | A kind of interior flame localization method based on camera |
| CN110749311A (en) * | 2019-09-12 | 2020-02-04 | 浙江大华技术股份有限公司 | Positioning method, positioning device and storage medium |
| CN112017111A (en) * | 2020-08-28 | 2020-12-01 | 杭州海康威视数字技术股份有限公司 | Panorama synthesis method and device and electronic equipment |
-
2021
- 2021-06-16 CN CN202110666345.0A patent/CN113298867A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103198488A (en) * | 2013-04-16 | 2013-07-10 | 北京天睿空间科技有限公司 | PTZ surveillance camera realtime posture rapid estimation method |
| CN103971375A (en) * | 2014-05-22 | 2014-08-06 | 中国人民解放军国防科学技术大学 | Panoramic gaze camera space calibration method based on image splicing |
| CN109523592A (en) * | 2018-10-19 | 2019-03-26 | 天津大学 | A kind of interior flame localization method based on camera |
| CN110749311A (en) * | 2019-09-12 | 2020-02-04 | 浙江大华技术股份有限公司 | Positioning method, positioning device and storage medium |
| CN112017111A (en) * | 2020-08-28 | 2020-12-01 | 杭州海康威视数字技术股份有限公司 | Panorama synthesis method and device and electronic equipment |
Non-Patent Citations (1)
| Title |
|---|
| 贾道祥等: "基于地形匹配的图像烟火定位方法研究", 《北京林业大学学报》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114217618A (en) * | 2021-12-14 | 2022-03-22 | 重庆富沛和科技有限公司 | Method for performing automatic cruise within selected range in three-dimensional map |
| CN114217618B (en) * | 2021-12-14 | 2024-04-16 | 重庆富沛和科技有限公司 | Method for automatically cruising in selected range in three-dimensional map |
| CN116433756A (en) * | 2023-06-15 | 2023-07-14 | 浪潮智慧科技有限公司 | Surface object space analysis method, device and medium of monocular camera |
| CN116433756B (en) * | 2023-06-15 | 2023-08-18 | 浪潮智慧科技有限公司 | Surface object space analysis method, device and medium of monocular camera |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110660023B (en) | Video stitching method based on image semantic segmentation | |
| US10681271B2 (en) | Image processing apparatus, image capturing system, image processing method, and recording medium | |
| US10757327B2 (en) | Panoramic sea view monitoring method and device, server and system | |
| CN113298867A (en) | Accurate positioning method and device for ground object target position based on line matching and storage medium | |
| CN111915483B (en) | Image stitching method, device, computer equipment and storage medium | |
| WO2021184302A1 (en) | Image processing method and apparatus, imaging device, movable carrier, and storage medium | |
| CN111582022B (en) | Fusion method and system of mobile video and geographic scene and electronic equipment | |
| JP6924064B2 (en) | Image processing device and its control method, and image pickup device | |
| US20100118040A1 (en) | Method, system and computer-readable recording medium for providing image data | |
| CN110021055A (en) | The method and its image processing apparatus and system of generation disparity map | |
| CN111353965B (en) | Image restoration method, device, terminal and storage medium | |
| CN113012383A (en) | Fire detection alarm method, related system, related equipment and storage medium | |
| Agisoft | Metashape python reference | |
| CN110120012B (en) | Video stitching method for synchronous key frame extraction based on binocular camera | |
| CN113297344B (en) | Three-dimensional remote sensing image-based ground linear matching method and device and ground object target position positioning method | |
| CN114615480A (en) | Projection picture adjusting method, projection picture adjusting device, projection picture adjusting apparatus, storage medium, and program product | |
| CN116402934A (en) | Automatic texture mapping method, terminal and storage medium for three-dimensional reconstruction | |
| CN116310899A (en) | YOLOv 5-based improved target detection method and device and training method | |
| CN114898321A (en) | Method, device, equipment, medium and system for detecting road travelable area | |
| CN113570531A (en) | Image processing method, image processing device, electronic equipment and computer readable storage medium | |
| JP3576759B2 (en) | Image processing device | |
| CN111914048B (en) | Automatic generation method for corresponding points of longitude and latitude coordinates and image coordinates | |
| CN114513612B (en) | AR photographing image light supplementing method and system based on machine learning | |
| US20210183082A1 (en) | Image registration method, apparatus, computer system, and mobile device | |
| CN116071396A (en) | Synchronous positioning method |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210824 |