WO2022228321A1

WO2022228321A1 - Method and apparatus for identifying and positioning object within large range in video

Info

Publication number: WO2022228321A1
Application number: PCT/CN2022/088672
Authority: WO
Inventors: 何佳林
Original assignee: 何佳林
Priority date: 2021-04-25
Filing date: 2022-04-24
Publication date: 2022-11-03
Also published as: CN113518179A

Abstract

A method and apparatus for identifying and positioning an object within a large range in a video. The method comprises: acquiring a video image; identifying the video image, so as to determine position information of a moving object in the image; acquiring state parameters of a photographic device; and on the basis of the state parameters and the position information of the moving object in the image, determining position information of the moving object relative to the photographic device. According to the present invention, a moving part identified from a video acquired by a lens is processed, and the relative position of the moving part relative to the lens is solved, such that a user can clearly grasp the situation of a video recording area.

Description

Object recognition and positioning method and device in a large range of video

technical field

The present invention relates to the technical field of moving object identification and processing, and in particular, to a method and device for object identification and positioning in a large range of video.

Background technique

This section is intended to provide a background or context to the embodiments of the invention recited in the claims. The descriptions herein are not admitted to be prior art by inclusion in this section.

Existing cameras can record video over a wide range of areas. However, the user cannot know the position of the moving object relative to the camera in the video, and the absolute position of the moving object. In some scenarios, the location information is very important to the user.

SUMMARY OF THE INVENTION

An embodiment of the present invention provides a method for recognizing and locating objects in a large range of videos, which is used to know the position of a moving object in the video relative to a camera and the absolute position of the moving object. The method includes:

Get video images;

Identifying the video image to determine the position information of the moving object in the image;

Get the status parameters of the camera device;

Based on the state parameters and the position information of the moving object in the image, the position information of the moving object relative to the imaging device is determined.

The embodiment of the present invention also provides a device for identifying and positioning objects in a large range of videos, which is used to know the position of the moving object in the video relative to the camera and the absolute position of the moving object. The device includes:

A video image acquisition module for acquiring video images;

A video image recognition module, used for recognizing the video image and determining the position information of the moving object in the image;

The state parameter acquisition module is used to acquire the state parameters of the camera device;

The relative position information determination module of the moving object is configured to determine the position information of the moving object relative to the camera device based on the state parameter and the position information of the moving object in the image.

An embodiment of the present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and running on the processor, the processor implements the above-mentioned object recognition in a large range of video when the processor executes the computer program positioning method.

Embodiments of the present invention further provide a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, implements the steps of the above-mentioned method for recognizing and locating objects in a large range of video.

In the embodiment of the present invention, compared with the technical solution in the prior art in which the user cannot know the position of the moving object in the video relative to the camera and the absolute position of the moving object, the moving object is determined by acquiring a video image; identifying the video image position information in the image; obtain the state parameters of the camera device; determine the position information of the moving object relative to the camera device based on the state parameters and the position information of the moving object in the image, so that the user can easily obtain the position information, and can Allows users to clearly grasp the situation of the video shooting area.

Description of drawings

In order to explain the embodiments of the present invention or the technical solutions in the prior art more clearly, the following briefly introduces the accompanying drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained according to these drawings without creative efforts. In the attached image:

1 is a flowchart (1) of a method for recognizing and locating objects within a large range of video in an embodiment of the present invention;

2 is a flowchart (2) of a method for recognizing and locating objects within a large range of video in an embodiment of the present invention;

3 is a flowchart (3) of a method for recognizing and locating objects within a large range of video in an embodiment of the present invention;

4 is a side view of a lens and a shooting range in an embodiment of the present invention;

5 is a top view of a lens and a shooting range in an embodiment of the present invention;

6 is a perspective view of a lens and a shooting range in an embodiment of the present invention;

FIG. 7 is a top view of an area where lenses are sequentially shot in an embodiment of the present invention;

8 is a top view of an effective monitoring area in an embodiment of the present invention;

Fig. 9 is the display image on the screen when the program is running in the embodiment of the present invention;

10 is an image captured by a lens in an embodiment of the present invention;

FIG. 11 is a schematic diagram of a program running and solving process in an embodiment of the present invention;

12 is a flowchart (4) of a method for identifying and locating objects within a large range of video in an embodiment of the present invention;

13 is a flowchart (5) of a method for recognizing and locating objects within a large range of video in an embodiment of the present invention;

14 is a structural block diagram (1) of a device for identifying and locating objects within a large range of video according to an embodiment of the present invention;

15 is a structural block diagram (2) of a device for recognizing and positioning objects within a large range of video according to an embodiment of the present invention;

FIG. 16 is a structural block diagram (3) of a device for recognizing and positioning objects in a large range of video according to an embodiment of the present invention.

Detailed ways

In order to make the purposes, technical solutions and advantages of the embodiments of the present invention more clearly understood, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings. Here, the exemplary embodiments of the present invention and their descriptions are used to explain the present invention, but not to limit the present invention.

FIG. 1 is a flowchart (1) of a method for identifying and locating objects in a large range of videos in an embodiment of the present invention. As shown in FIG. 1 , the method includes:

Step 101: acquire a video image;

Step 102: Identify the video image, and determine the position information (ie, pixel position) of the moving object in the image;

Step 103: Acquire state parameters of the camera device;

Step 104: Based on the state parameters and the position information of the moving object in the image, determine the position information of the moving object relative to the imaging device.

In the embodiment of the present invention, the state parameters of the imaging device include the height of the lens, the depression angle of the lens, the zoom factor of the lens (corresponding to the horizontal field of view of the lens and the vertical field of view of the lens), and the facing direction of the lens. For example, you can use DJI Jingwei M300 UAV equipped with H20T infrared lens to obtain video. You can set the flying height of the drone, that is, the height of the lens from the ground to 50 meters. The H20T lens is set to 4x zoom, and the corresponding horizontal and vertical field angles of the lens are 8 degrees and 5.6 degrees, respectively. Set the gimbal to rotate the pitch angle 8 degrees downward from the horizontal. These status parameters can be changed to set values depending on the situation. The specific side view of the lens and the shooting range for shooting video is shown in FIG. 4 , the top view of the lens and the shooting range is shown in FIG. 5 , and the oblique view of the lens and the shooting range is shown in FIG. 6 . Among them, A represents the position of the lens, and B represents the center of the shooting range of the lens. Figures 4 to 6 also describe the positional relationship between A and B.

To shoot a video under the set state parameters of the camera device, you can shoot a video as follows:

After the drone lifts off, start the infrared lens, firstly shoot the area 1, the shooting time is 2 seconds, and then rotate 8 degrees clockwise, and the rotation time is 1 second. Shoot area 2 after it is in place, shoot for 2 seconds, then rotate 8 degrees clockwise... Shoot areas 1 to 23 in this order. After shooting area 23, rotate back to area 1 counterclockwise, which takes 3 seconds. Repeat the above procedure to shoot. From the start of shooting area 1 to the rotation to area 1 ready to shoot is a large cycle, and a large cycle takes 71 seconds. Of these, 46 seconds get stabilized video for each area. FIG. 7 is a schematic diagram of each shooting area in a shooting cycle. The above time varies according to the machine parameters of different infrared lenses.

In an embodiment of the present invention, as shown in Figure 12, step 104 determines the position information of the moving object relative to the camera device based on the state parameter and the position information of the moving object in the image, specifically including:

Step 1041: Match the corresponding coordinate database according to the height of the lens, the depression angle of the lens and the zoom factor of the lens;

Step 1042: According to the position information of the moving object in the image, match the position of the moving object relative to the facing direction of the lens from the corresponding coordinate database;

Step 1043: Determine the position of the moving object relative to the imaging device according to the facing direction of the lens and the position of the matched moving object relative to the facing direction of the lens.

The polar coordinate database is taken as an example for description below.

For the lens of a certain type in the computer, corresponding to the height of the lens, the depression angle of the lens, and the zoom factor, the polar coordinate database of the moving object corresponding to the pixel point (that is, the position information) relative to the facing direction of the lens is obtained through the preliminary measurement. The polar axis of this polar coordinate system is the positive direction of the Y axis, and the positive direction of the angle is the clockwise direction. The database contains polar coordinate data of the moving object photographed in the image corresponding to each pixel point relative to the facing direction of the lens. Among them, the azimuth angle is defined as a negative value on the left side of the lens axis, and a positive value is defined on the right side of the lens axis, which is represented by α; the distance is represented by L. For different lens heights, lens depression angles, and zoom ratios, different databases are obtained. This set of databases is stored in a computer. That is to say, when using a lens of the same specification, the lens height, the angle of depression under the lens, and the zoom factor are the same as the three parameters in the measurement. Then, in use, the polar coordinate data of the moving object corresponding to the pixel point relative to the facing direction of the lens is the same as the polar coordinate data of the moving object corresponding to the pixel point relative to the facing direction of the lens during measurement.

When in use, the height of the lens, the depression angle of the lens, and the zoom factor are sent back to the computer during the identification and positioning process. First match to the corresponding polar coordinate database. Then, the corresponding (L, α) is obtained by matching in the corresponding polar coordinate database. The computer obtains the facing direction β of the lens when the moving target is captured. Calculate the azimuth angle γ of the moving object relative to the lens, γ=α+β. Thereby, the polar coordinate position (L, γ) of the moving object relative to the lens is obtained.

In an embodiment of the present invention, as shown in FIG. 2 , the method further includes:

Step 105: obtain the latitude and longitude coordinates of the camera device;

Step 106: Determine the longitude and latitude coordinates of the moving object based on the longitude and latitude coordinates of the camera device and the position information of the moving object relative to the camera device.

In this embodiment of the present invention, as shown in FIG. 13 , step 106 determines the longitude and latitude coordinates of the moving object based on the longitude and latitude coordinates of the camera device and the position information of the moving object relative to the camera device, including:

Step 1061: Convert the polar coordinate position of the moving object relative to the imaging device into the rectangular coordinate position of the moving object relative to the imaging device;

Step 1062: Determine the longitude and latitude coordinates of the moving object based on the longitude and latitude coordinates of the camera device and the rectangular coordinate position of the moving object relative to the camera device.

Specifically, the computer converts the polar coordinate position (L, γ) of the moving object relative to the lens into a rectangular coordinate position (x, y) through the coordinate transformation formula x=L·sinγ, y=L·cosγ.

The computer obtains the latitude and longitude coordinates (A, B) returned by the camera device. According to the rectangular coordinate position of the moving object relative to the lens, the latitude and longitude coordinates (C, D) of the moving object are calculated by the formula C=A+x/(cos B·111120), D=B+y/111120.

In this embodiment of the present invention, as shown in FIG. 3 , the method further includes:

Step 201: Obtain the latitude and longitude coordinates of the existing object;

Step 202: Compare the latitude and longitude coordinates of the moving object with the latitude and longitude coordinates of the existing object, and differentiate the moving objects based on the comparison result.

Specifically, it is to obtain the latitude and longitude coordinates returned by a moving object, and compare them with the latitude and longitude coordinates of the moving object calculated in step 106. If two of the coordinates of the latitude and longitude are the same, it means that the moving object that returns the coordinates of latitude and longitude is recognized by the camera. The moving object that calculates the latitude and longitude is the same moving object.

In this embodiment of the present invention, step 202 distinguishes the moving objects based on the comparison result, including:

Based on the comparison results, different annotation forms are used to distinguish moving objects.

Specifically, different labeling forms may be, for example, different colors, underlines in different formats, and the like.

Specifically, when using different colors to distinguish:

If the two latitude and longitude coordinate values are consistent, the first color is used to mark the position of the moving object on the display screen;

If all the two latitude and longitude coordinate values are inconsistent, the second color is used to mark the position of the moving object on the display screen.

The method for recognizing and locating objects in a large range of video proposed by the present invention will be described below by taking an example.

Embodiment 1

Use DJI Jingwei M300 UAV equipped with H20T infrared lens to obtain video. The flying height of the drone is 50 meters above the ground. The H20T lens is set to 4x zoom, and the corresponding horizontal and vertical field angles of the lens are 8 degrees and 5.6 degrees, respectively. Set the gimbal to rotate the pitch angle 8 degrees downward from the horizontal. A stands for the lens position, and B stands for the center of the shot range of the lens. The positional relationship between the two is shown in Figure 4, Figure 5, and Figure 6. The range taken is a trapezoid with an upper base of 37 meters, a lower base of 77 meters and a height of 287 meters. The horizontal distance from the center of the ground shot by the lens to the lens is 356 meters, of which the farthest shooting distance is 549 meters, and the closest shooting distance is 262 meters.

Set the infrared lens to be activated after the drone takes off, first to shoot area 1, the shooting time is 2 seconds, and then rotate 8 degrees clockwise, and the rotation time is 1 second. After it is in place, shoot zone 2, shoot for 2 seconds, and then rotate 8 degrees clockwise... Shoot zones 1 to 23 in this order. After shooting area 23, rotate back to area 1 counterclockwise, which takes 3 seconds. Repeat the above procedure to shoot. From the start of shooting area 1 to the rotation to area 1 ready to shoot is a large cycle, and a large cycle takes 71 seconds. Of these, 46 seconds get stabilized video for each area. FIG. 7 is a schematic diagram of each shooting area in a shooting cycle. The whole video is transmitted to the computer in real time, and the present invention processes the video. In the input interface, the user enters the following parameters: the drone is the lens height of 50 meters, the drone is the longitude and latitude of the lens A (XXX.5000000E, XXX.5000000N), the gimbal pitch angle is horizontally down 8 degrees, and the zoom factor is 4 times. The direction the camera is facing is transmitted back by the drone in real time.

Assuming that the present invention is used to monitor the national border, the schematic diagram of each shooting area shown in FIG. 8 can be obtained, wherein MN is the border, the north is the outside, and the south is the inside. As the target moves from north to south, it will pass through the shaded area shown in Figure 8. The target needs to pass at least 287 meters to pass through the shadow area. If a person tries to cross the border from north to south, the speed of movement is 6 km/h, which is 100 meters in 1 minute. Then the person appears in the shooting area at least 2 times during a large cycle. That is to say, a drone and a computer can use the present invention to monitor the 936-meter national border.

Step (1) When the lens is rotated to the 10th position, a moving object P appears in the captured image, the moving object P is identified, and the pixel position of P in the image is (-240PX, +156PX). As shown in Figure 10.

Step (2) Select the lens height of 50 meters, the lower lens depression angle of 8 degrees, and the zoom factor of 4 times. In a set of databases, a database with three parameters corresponding to the lens height of 50 meters, the lower lens depression angle of 8 degrees, and the zoom factor of 4 times is matched. Then match in this database to obtain the polar coordinate position (453.4m, -3.0°) of the moving object P relative to the direction facing the lens.

In step (3), the facing direction -16° when the lens captures the point P is retrieved, and the polar coordinate position (453.4m, -19.0°) of the lens corresponding to the moving object P is calculated.

Step (4) The latitude and longitude coordinates of the lens are retrieved, and the latitude and longitude of the moving object P is calculated (XXX.4980943E, XXX.5038578N).

In step (5), the position and position parameters of P are displayed on the user display screen, as shown in FIG. 9 .

The software operation logic is shown in Figure 11.

Embodiment 2

Use DJI Jingwei M300 UAV equipped with H20T infrared lens to obtain video. The flying height of the drone is 50 meters above the ground. The H20T lens is set to 4x zoom, and the corresponding horizontal and vertical field angles of the lens are 8 degrees and 5.6 degrees, respectively. Set the gimbal to rotate the pitch angle 8 degrees downward from the horizontal. In the figure, A represents the position of the lens, and B represents the center of the shooting range of the lens. The positional relationship between the two is shown in Figure 4, Figure 5, and Figure 6. The range taken is a trapezoid with an upper base of 37 meters, a lower base of 77 meters and a height of 287 meters. The horizontal distance from the center of the ground shot by the lens to the lens is 356 meters, of which the farthest shooting distance is 549 meters, and the closest shooting distance is 262 meters.

Set the infrared lens to be activated after the drone takes off, first to shoot area 1, the shooting time is 2 seconds, and then rotate 8 degrees clockwise, and the rotation time is 1 second. Shoot area 2 after it is in place, shoot for 2 seconds, then rotate 8 degrees clockwise... Shoot areas 1 to 23 in this order. After shooting area 23, rotate back to area 1 counterclockwise, which takes 3 seconds. Repeat the above procedure to shoot. From the start of shooting area 1 to the rotation to area 1 ready to shoot is a large cycle, and a large cycle takes 71 seconds. Of these, 46 seconds get stabilized video for each area. FIG. 7 is a schematic diagram of each shooting area in a shooting cycle. The whole video is transmitted to the computer in real time, and the present invention processes the video. In the input interface, the user enters the following parameters: the drone is the lens height of 50 meters, the drone is the latitude and longitude of the lens (XXX.5000000E, XXX.5000000N), the gimbal pitch angle is 8 degrees horizontally downward, and the zoom factor is 4 times, the direction the camera is facing is transmitted back by the drone in real time.

Set in this area, our personnel wear the receiver of the satellite positioning system, and send the position to the computer in real time (that is, the known latitude and longitude coordinates). When the longitude and latitude of the moving target identified in the computer are consistent with the sent back longitude and latitude, a red border will be displayed on the screen around the moving target. When the latitude and longitude of the moving target identified in the computer is inconsistent with the latitude and longitude sent back, the moving target 4 displays a blue border on the screen.

Step (1) When the lens is rotated to the 14th position, a moving object appears in the captured image, and the moving object is identified, and its pixel position in the image is C (50PX, 50PX). When the lens is rotated to the 15th position , another moving object appears in the captured image, and the moving object is identified, and its pixel position in the image is E (80PX, 80PX), as shown in Figure 10 .

Step (2) Select the lens height of 50 meters, the lower lens depression angle of 8 degrees, and the zoom factor of 4 times. In a set of databases, a database with three parameters corresponding to the lens height of 50 meters, the lower lens depression angle of 8 degrees, and the zoom factor of 4 times is matched. In this database, the polar coordinate position (382.7m, 0.6°) of the moving object C relative to the facing direction of the lens is obtained by matching, and the polar coordinate position (400.3m, 1.0°) of the moving object E relative to the facing direction of the lens is obtained by matching. .

In step (3), the facing direction 16.0° when the moving object C is captured by the lens is retrieved, and the polar coordinate position (453.4m, -19.0°) of the lens corresponding to the moving object P is calculated. The facing direction 24.0° when the moving object E is captured by the lens is retrieved, and the polar coordinate position (400.3m, 25.0°) of the lens corresponding to the moving object P is calculated.

Step (4) The latitude and longitude coordinates of the lens are retrieved, and the latitude and longitude C (XXX.5014125E, XXX.5032996N) and E (XXX.5021824E, XXX.5032643N) of the moving object are calculated respectively.

Step (5) Compare the latitude and longitude coordinates returned by the receiver of our personnel satellite positioning system to distinguish different moving objects. The moving object C matches the latitude and longitude returned by our personnel, and the object E does not match the latitude and longitude returned by our personnel. Explain that the moving object C is our personnel.

Step (6) On the user display screen, the position and position parameters of C are displayed in red, and the position and position parameters of E are displayed in blue. As shown in Figure 9.

The software operation logic is shown in Figure 11.

The moving object in the above example is a single person, and in other examples, the detection of a larger range, where the moving object can also be a vehicle, etc., should also be within the protection scope of the present invention.

Embodiments of the present invention also provide a device for recognizing and locating objects in a large range of video, as described in the following embodiments. Since the principle of the device for solving the problem is similar to the method for recognizing and locating objects in a large range of videos, the implementation of the device can refer to the implementation of the method for recognizing and locating objects in a large range of videos, and the repetition will not be repeated.

FIG. 14 is a structural block diagram (1) of a device for identifying and positioning objects in a large range of video in an embodiment of the present invention. As shown in FIG. 12 , the device includes:

A video image acquisition module 02, for acquiring video images;

The video image recognition module 04 is used for recognizing the video image and determining the position information of the moving object in the image;

A state parameter acquisition module 06, used to acquire the state parameters of the camera device;

The relative position information determination module 08 of the moving object is configured to determine the position information of the moving object relative to the camera device based on the state parameter and the position information of the moving object in the image. .

In this embodiment of the present invention, as shown in FIG. 15 , the device further includes:

The latitude and longitude coordinate acquisition module 10 of the camera device is used to obtain the longitude and latitude coordinates of the camera device;

The moving object latitude and longitude coordinate determination module 12 is configured to determine the longitude and latitude coordinates of the moving object based on the longitude and latitude coordinates of the camera device and the position information of the moving object relative to the camera device.

In the embodiment of the present invention, the state parameters of the imaging device include the height of the lens, the depression angle of the lens, the zoom factor of the lens, and the facing direction of the lens.

In the embodiment of the present invention, the relative position information determination module 08 of the moving object is specifically used for:

Match the corresponding coordinate database according to the height of the lens, the depression angle under the lens and the zoom factor of the lens;

According to the position information of the moving object in the image, the position of the moving object relative to the facing direction of the lens is matched from the corresponding coordinate database;

According to the facing direction of the lens and the position of the matched moving object relative to the facing direction of the lens, the position of the moving object relative to the imaging device is determined.

In the embodiment of the present invention, the latitude and longitude coordinate determination module 12 of the moving object is specifically used for:

Convert the polar coordinate position of the moving object relative to the camera device into the rectangular coordinate position of the moving object relative to the camera device;

The latitude and longitude coordinates of the moving object are determined based on the latitude and longitude coordinates of the imaging device and the rectangular coordinate position of the moving object relative to the imaging device.

In this embodiment of the present invention, as shown in FIG. 16 , the device further includes:

The latitude and longitude coordinate obtaining module 14 of the existing object is used to obtain the latitude and longitude coordinates of the existing object;

The comparison and differentiation module 16 is configured to compare the latitude and longitude coordinates of the moving object with the latitude and longitude coordinates of the existing object, and differentiate the moving object based on the comparison result.

In the embodiment of the present invention, the comparison and differentiation module 16 is specifically used for:

If the latitude and longitude coordinates of the moving object are the same as the latitude and longitude coordinates of the existing object, use the first color to mark the position of the moving object on the display screen;

If the latitude and longitude coordinates of the moving object are different from the latitude and longitude coordinates of the existing object, a second color is used to mark the position of the moving object on the display screen.

In the embodiment of the present invention, compared with the technical solution in the prior art in which the user cannot know the position of the moving object in the video relative to the camera and the absolute position of the moving object, the moving object is determined by acquiring a video image; identifying the video image position information in the image; obtain the state parameters of the camera device; determine the position information of the moving object relative to the camera device based on the state parameters and the position information of the moving object in the image; obtain the longitude and latitude coordinates of the camera device; based on the longitude and latitude of the camera device The coordinates and the position information of the moving object relative to the camera device determine the latitude and longitude coordinates of the moving object, so that the user can easily obtain the position information, and the user can clearly grasp the situation of the video shooting area.

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, etc.) 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 process and/or block in the flowchart illustrations and/or block diagrams, and combinations of processes and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to the processor of a general purpose computer, special purpose computer, embedded processor or other programmable data processing device to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing device produce Means for implementing the functions specified in a flow or flow of a flowchart and/or a block or blocks of a block diagram.

These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory result in an article of manufacture comprising instruction means, the instructions The apparatus implements the functions specified in the flow or flow of the flowcharts and/or the block or blocks of the block diagrams.

These computer program instructions can also be loaded on a computer or other programmable data processing device to cause a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process such that The instructions provide steps for implementing the functions specified in the flow or blocks of the flowcharts and/or the block or blocks of the block diagrams.

The specific embodiments described above further describe the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above-mentioned specific embodiments are only specific embodiments of the present invention, and are not intended to limit the scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

A method for identifying and locating objects in a large range of videos, characterized in that it includes:

Get video images;

Identifying the video image to determine the position information of the moving object in the image;

Get the status parameters of the camera device;

Based on the state parameters and the position information of the moving object in the image, the position information of the moving object relative to the imaging device is determined.
The method for identifying and locating objects within a large range of video as claimed in claim 1, further comprising:

Obtain the latitude and longitude coordinates of the camera device;

The latitude and longitude coordinates of the moving object are determined based on the latitude and longitude coordinates of the imaging device and the position information of the moving object relative to the imaging device.
The method for recognizing and locating objects in a large range of video according to claim 1, wherein the state parameters of the camera device include the height of the lens, the depression angle of the lens, the zoom factor of the lens and the facing direction of the lens.
The method for recognizing and locating objects within a large range of video according to claim 3, wherein, based on the state parameters and the position information of the moving object in the image, determining the position information of the moving object relative to the camera device, comprising:

Match the corresponding coordinate database according to the height of the lens, the depression angle under the lens and the zoom factor of the lens;

According to the position information of the moving object in the image, the position of the moving object relative to the facing direction of the lens is matched from the corresponding coordinate database;

The position of the moving object relative to the imaging device is determined according to the facing direction of the lens and the position of the matched moving object relative to the facing direction of the lens.
The method for recognizing and locating objects within a large range of video according to claim 2, wherein determining the latitude and longitude coordinates of the moving object based on the latitude and longitude coordinates of the camera device and the position information of the moving object relative to the camera device, comprising:

Convert the polar coordinate position of the moving object relative to the camera device into the rectangular coordinate position of the moving object relative to the camera device;

The latitude and longitude coordinates of the moving object are determined based on the latitude and longitude coordinates of the imaging device and the rectangular coordinate position of the moving object relative to the imaging device.
The method for identifying and locating objects within a large range of video as claimed in claim 2, further comprising:

Get the latitude and longitude coordinates of an existing object;

The latitude and longitude coordinates of the moving object are compared with the latitude and longitude coordinates of the existing object, and the moving objects are distinguished based on the comparison result.
The method for recognizing and locating objects in a large range of video according to claim 6, wherein the moving objects are distinguished based on the comparison result, comprising:

Based on the comparison results, different annotation forms are used to distinguish moving objects.
A device for identifying and locating objects in a large range of videos, characterized in that it includes:

A video image acquisition module for acquiring video images;

A video image recognition module, used for recognizing the video image and determining the position information of the moving object in the image;

The state parameter acquisition module is used to acquire the state parameters of the camera device;

The relative position information determination module of the moving object is configured to determine the position information of the moving object relative to the camera device based on the state parameter and the position information of the moving object in the image.
A computer device, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, when the processor executes the computer program, any one of claims 1 to 7 is implemented A method for object recognition and localization in a large range of video.
A computer-readable storage medium on which a computer program is stored, characterized in that, when the program is executed by a processor, the steps of the method for recognizing and locating objects in a large range of video according to any one of claims 1 to 7 are implemented.