WO2021232826A1

WO2021232826A1 - Wireless-positioning-technology-based method and device for controlling camera to dynamically track road target

Info

Publication number: WO2021232826A1
Application number: PCT/CN2021/070287
Authority: WO
Inventors: 刘小华; 汤夕根; 刘四奎; 唐旭栋
Original assignee: 浩鲸云计算科技股份有限公司
Priority date: 2020-05-22
Filing date: 2021-01-05
Publication date: 2021-11-25
Also published as: CN111586303A

Abstract

A wireless-positioning-technology-based method for controlling a camera to dynamically track a road target. The method comprises: determining a mutual transformation model for a visual center of gravity point of a camera and geodetic coordinates, and a correlation between a motion parameter of the camera and an element on the geodetic coordinates; and determining a target object state and a target object motion trajectory, acquiring, according to the correlation, a camera control parameter corresponding to the target object motion trajectory, and controlling, according to the parameter, the camera to track a target object. By means of the solution of the present invention, control automation of a camera is realized; and control precision is also realized in one step, and a target is precisely positioned, thereby improving the control precision and a response speed.

Description

Control method and device for camera dynamic tracking road target based on wireless positioning technology

Technical field

The invention belongs to the technical field of intelligent transportation, and specifically relates to a control method and device for a camera to dynamically track a road target based on a wireless positioning technology.

Background technique

With the continuous improvement of China's infrastructure construction level, a large number of high-definition, 360° panoramic cameras cover a wide range, so the requirements for intelligent water products for video control are greatly improved. Video control is currently mainly controlled by humans, regardless of response Ability, speed, accuracy, and intelligence are not enough.

At present, the mainstream similar product design on the market is based on video recognition technology. This technology has some shortcomings, and its use in the field of urban transportation will have greater limitations. First of all, the premise of this technical route is that the video needs to be able to see the target, and then the target identification and location tracking. Secondly, the use of this technical solution under the conditions of dark night, occlusion, light, and complex urban background will be limited. Third, it relies more on the coordination of equipment, and requires higher planning for infrastructure.

Summary of the invention

In view of the above-mentioned shortcomings of the prior art, one of the objectives of the present invention is to provide a method and device for dynamic camera control based on wireless positioning technology.

The embodiment of the invention discloses a control method for a camera to dynamically track a road target based on a wireless positioning technology, which includes: determining a mutual transformation model between the visual center of gravity of the camera and the geodetic coordinates, and the corresponding relationship between the camera motion parameters and the elements on the geodetic coordinates Confirm the state of the target object and the motion trajectory of the target object, obtain the parameters of the control camera corresponding to the motion trajectory of the target object according to the corresponding relationship, and control the camera to track the target object according to the parameters.

In a possible embodiment, determining the mutual transformation model between the visual center of gravity of the camera and the geodetic coordinates includes determining the mutual transformation model at least according to the geographic location, suspension height, tilt angle and performance parameters of the camera.

In a possible embodiment, the method further includes: performing trajectory cutting on the trajectory of the target object corresponding to the geodetic coordinates, and establishing the corresponding relationship between the trajectory and the camera control parameters.

In a possible embodiment, target object tracking includes: confirming the state of the target object according to the mobile positioning data; judging the motion trajectory of the target object, and binding the trajectory of the target object and geographic information; controlling the camera according to the elements on the geodetic coordinates The trajectory tracks the target object.

In a possible embodiment, it further includes: target occlusion analysis: using geographic information data in the geographic information system to establish an occlusion model to determine the occlusion range of the camera's field of view of the target object.

A wireless positioning technology-based camera dynamic tracking control device for road targets, including: a target object positioning module, used to determine the mutual transformation model of the camera's visual center of gravity and the geodetic coordinates, and the corresponding relationship between camera motion parameters and elements on the geodetic coordinates The target object tracking module is used to confirm the state of the target object and the motion trajectory of the target object, obtain the parameters of the control camera corresponding to the motion trajectory of the target object according to the corresponding relationship, and control the camera to track the target object according to the parameters.

In a possible embodiment, the mutual transformation model is determined according to the geographic location of the camera, the suspension height, the tilt angle, and the performance parameters of the camera.

In a possible embodiment, the method further includes: performing trajectory cutting on the trajectory of the target object corresponding to the geodetic coordinates, and establishing the corresponding relationship between the trajectory and the camera control parameter.

In a possible embodiment, target object tracking is also used to: confirm the state of the target object according to the mobile positioning data; determine the motion trajectory of the target object, and bind the trajectory of the target object with geographic information; control the camera according to the geodetic coordinates The element trajectory tracks the target object.

In a possible embodiment, it further includes: a target occlusion analysis module, configured to use geographic information data in the geographic information system to establish an occlusion model to determine the occlusion range of the camera's field of view of the target object.

A computer storage medium that stores a computer program, and when the computer program is executed, the method described above is implemented.

Compared with the prior art, the present invention has the following beneficial effects:

The solution of the invention realizes that the computer replaces the manual to complete most of the control scenes of the camera, and realizes the control automation of the camera. At the same time, the precise control is achieved in one step, the target is accurately positioned, and the control accuracy and response speed are improved. In addition, the control scheme further improves the intelligent level of camera control.

Description of the drawings

FIG. 1 is a flow chart of a control method for a camera to dynamically track a road target based on a wireless positioning technology according to an embodiment of the present invention;

2 is a schematic diagram of the principle of a camera according to an embodiment of the present invention;

FIG. 3 is a schematic diagram of a focal length field of view of a camera according to an embodiment of the present invention;

4 is a schematic diagram of the focusing principle of a camera according to an embodiment of the present invention;

FIG. 5 is a schematic diagram of occlusion analysis according to an embodiment of the present invention;

Fig. 6 is a schematic diagram of camera occlusion analysis according to an embodiment of the present invention;

Fig. 7 is a schematic structural diagram of a camera control device according to an embodiment of the present invention.

Detailed ways

In order to facilitate the understanding of those skilled in the art, the present invention will be further described below in conjunction with the embodiments and the accompanying drawings, and the content mentioned in the embodiments does not limit the present invention.

This solution is based on the detection of the target's azimuth, and the moving state and position of the target are judged through the mobile positioning data. The position expression of the mobile positioning data is a geographic information system. To realize the dynamic tracking of the target object by the camera, there must be a technology that can detect the target. The trajectory of the object on the geographic information system is reversely mapped to the video. When the two trajectories are synchronized, the re-engraving of the trajectory can be completed through the camera control technology, and the camera can track the target object.

Referring to Fig. 1, it specifically shows a control method for a camera based on wireless positioning technology to dynamically track a road target, including:

S101: Determine the mutual transformation model between the visual center of gravity of the camera and the geodetic coordinates, and the corresponding relationship between the camera motion parameters and the elements on the geodetic coordinates.

In the traffic management business, the main focus is on roads similar to cities and incidents that occur on the roads. Therefore, the camera field of view that meets the actual requirements of the traffic management business should be able to lock the elements on the road at all times.

Usually the focal length range of the camera is like this. As shown in Figure 2, the dots in the figure represent the camera. When the focal length of the first 100 meters on the road is a reasonable focal length, and 200 meters on the road, the same focal length will be very uncomfortable, because the object is far away from the pupil. As the distance becomes shorter, the object will be particularly large. On the contrary, it will be very small, so it is very important to choose a reasonable focal length.

The usual method of using a smart camera to observe the target is: 1. Choose a suitable camera, this camera is not "close", but "you can see the target." 2. When turning the camera, the camera can always adjust the angle and focal length reasonably, so that the target has been focused on the target on the "road". Referring to Figure 3, black expresses the position of the camera. The surrounding squares express the intensity of the field of vision at different locations. The larger the value, the better the field of view, the smaller the value, the worse the field of view.

Based on the above-mentioned camera vision principle, the mutual transformation model of the camera's visual center of gravity and the geodetic coordinates is established. Specifically, the mutual conversion model can be determined according to the geographic location, suspension height, tilt angle of the camera, and performance parameters of the camera.

The camera is aimed at the target, and the steps to control the camera rotation accordingly, refer to Figure 4:

Step 1: Rotate left and right horizontally to adjust to the position of the long dotted line, see 1 in Figure 4.

Step 2: Adjust the vertical angle. Adjust the length of the long dotted line to the length of the short dotted line. Refer to 2 in Figure 4.

The third step: adjust the focus, adjust the imaging size of the target object to an appropriate size, see 3 in Figure 4.

Step 4: Make fine adjustments and adjust the target to position 4.

The above 4 steps can be divided into 4 steps to be completed separately, or can be completed directly in one action. The above method provides the logic that 4 actions are directly completed in one action.

The logic of controlling the camera is directly bound to the elements on the geographic information, and the objects appearing on the geographic information, as long as there is a camera supported by the light mirror product around, the above-mentioned focusing operation can be completed with a single head shake. The movement trajectory of the object is reflected on the map. To achieve complete synchronization between the trajectory of the map and the trajectory of the video, the movement of the object on the map needs to be completely synchronized with the corresponding camera control logic. In this way, whether you click on the map or move naturally, the camera can accurately track and capture.

Specifically, the method of directly binding the control camera logic and the elements on the geographic information is: cutting the trajectory of the elements on the geodetic coordinates, and establishing the corresponding relationship between the trajectory and the camera angle, focal length, zoom, and pitch.

S102: Confirm the state of the target object and the motion trajectory of the target object, obtain a parameter for controlling the camera corresponding to the motion trajectory of the target object according to the foregoing corresponding relationship, and control the camera to track the target object according to the parameter.

Target object tracking includes: confirming the state of the target object according to the mobile positioning data; judging the movement trajectory of the target object, and binding the trajectory of the target object and geographic information according to the aforementioned corresponding relationship; controlling the camera to track the target object according to the element trajectory in the geodetic coordinates .

Specifically, according to the mobile positioning data and the shape of the road itself, the driving state of the target object is judged, and the target object is bound to the trajectory of geographic information, and the trajectory of the target object is represented by the geographic information.

Target tracking includes three parts: confirming target status, confirming target trajectory and calculating camera parameters.

Specifically, confirming the target state includes judging that the target object is moving at a constant speed, accelerating, decelerating, standing still, maneuvering quickly, and walking slowly. These states are used to predict the position of the target in the next 5 seconds. The data of a single GPS includes the plane positioning, altitude, and direction angle on the map. Since the main goal of traffic is to drive in the framework of "roads", multiple GPS data sorted by time expresses the trajectory of objects.

Confirming the target trajectory includes predicting the trajectory of the target when the positioning signal upload interval exceeds 1 second, and then converting the displacement (S), velocity (V), and time (T) of its movement according to the angle. The following needs to be met The formula:

S=VT, the size of S is used to determine the moving state of the target. For example, when the target displacement is greater than the expected displacement, the target object is in an accelerating state, when the target displacement is less than the expected displacement, the target object is in a decelerating state, and the target displacement is equal to the expected displacement when S=0. The object is at rest, etc.

In one embodiment, the status and motion shutdown of the target object can be acquired through the global positioning system, so as to accurately determine the position of the target object.

Finally, the camera control parameters are calculated according to the aforementioned corresponding relationship. After confirming the future position of the target object, the camera is used to scan the target motion trajectory. The whole process is carried out in a continuous correction process. Specifically, the movement of the camera is controlled according to the aforementioned corresponding relationship and the trajectory element of the target object in the geodetic coordinates.

In order to ensure the simplicity of the camera movement, this component also adds anti-shake capability, which is mainly used to prevent the random movement of the target in a small area from causing the camera to shake tracking.

In an embodiment, the foregoing method further includes: using geographic information data in the geographic information system to establish an occlusion model, and determine the occlusion range of the camera's field of view of the target object.

Specifically, a two-point-one-line occlusion model can be established using geographic information data to determine the occlusion range of the field of view of each camera for different elements.

Referring to Figure 5, in traffic management, the main objects that need to be observed are people, cars, and accidents that occur on the road. These objects are very easy to be obscured by buildings and trees on the road, resulting in objects that can be seen in theory but in fact invisible, then the camera may need to be replaced if necessary, or the position of the object after being obscured may be prompted.

In Figure 6, before the camera has undergone special processing, the target of its field of view is the dashed part of the above figure. However, due to the slope of the road, the target will be completely lost. Therefore, an algorithm is required to convert the elements of the slope to the angle and focal length to reach the black solid line.

The occlusion analysis is to map the parameters of the road, the occlusion in the facility, and the road surface illumination in the geographical information to the data of the geographical information according to the above requirements. The specific principle is to establish a spatial connection between the camera and the target object. If the spatial connection intersects with any spatial element, it is determined that the target is occluded.

In one embodiment, the result of the camera tracking the movement trajectory of the target object is displayed through the front-end interface.

The embodiment of the present invention also discloses a control device for a camera to dynamically track a road target based on a wireless positioning technology, including: a target object positioning module 10 for determining the mutual transformation model of the camera's visual center of gravity and the geodetic coordinates and camera motion parameters Correspondence with elements on the geodetic coordinates; target object tracking module 20, used to confirm the state of the target object and the target object motion trajectory, obtain the parameters of the control camera corresponding to the target object motion trajectory according to the corresponding relationship, and according to the parameters Control the camera to track the target object.

The embodiment mode of the present invention corresponds to the foregoing method embodiment, and the specific content can refer to the method embodiment.

In the several embodiments provided in this application, it should be understood that the disclosed device and method may be implemented in other ways. For example, the above-described embodiments are only illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into Another system, or some features can be ignored, or not implemented.

The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of the embodiments of the present invention.

In addition, the functional units in the various embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or software functional unit.

There are many specific applications of the present invention. The above are only the preferred embodiments of the present invention. It should be pointed out that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements can be made. These Improvements should also be regarded as the protection scope of the present invention.

Claims

A control method for a camera to dynamically track a road target based on wireless positioning technology, which is characterized in that:

Obtain the mutual transformation model of the camera's visual center of gravity and the geodetic coordinates, and the corresponding relationship between the camera motion parameters and the elements on the geodetic coordinates;

The state of the target object and the motion trajectory of the target object are acquired, the parameters for controlling the camera corresponding to the motion trajectory of the target object are acquired according to the corresponding relationship, and the camera is controlled to track the target object according to the parameters.
The method according to claim 1, wherein obtaining the mutual transformation model between the visual center of gravity of the camera and the geodetic coordinates comprises: determining the mutual transformation model at least according to the geographic location, suspension height, tilt angle and performance parameters of the camera.
3. The method according to claim 2, further comprising: performing trajectory cutting on the trajectory of the target object corresponding to the geodetic coordinates, and establishing the corresponding relationship between the trajectory and the camera control parameters.
The method of claim 1, further comprising: confirming the state of the target object according to the mobile positioning data; judging the trajectory of the target object, and binding the trajectory of the target object and geographic information; The trajectory of the element tracks the target object.
The method according to claim 1, further comprising: using geographic information data in the geographic information system to establish an occlusion model to determine the occlusion range of the camera's field of view of the target object.
A control device for a camera to dynamically track a road target based on wireless positioning technology, which is characterized in that it includes:

The target object positioning module is used to determine the mutual transformation model of the camera's visual center of gravity and the geodetic coordinates, and the corresponding relationship between the camera motion parameters and the elements on the geodetic coordinates;

The target object tracking module is used to confirm the state of the target object and the motion trajectory of the target object, obtain the parameters for controlling the camera corresponding to the motion trajectory of the target object according to the corresponding relationship, and control the camera to track the target object according to the parameters.
7. The control device according to claim 6, wherein the target object positioning module is further used to determine the mutual transformation model according to the geographic location, suspension height, tilt angle of the camera, and performance parameters of the camera.
7. The control device according to claim 7, wherein the target object positioning module is further configured to: perform a trajectory cutting on the trajectory of the target object corresponding to the geodetic coordinates, and establish the corresponding relationship between the trajectory and the camera control parameters.
The control device according to claim 6, wherein the target object tracking is further used for: confirming the state of the target object according to the mobile positioning data; judging the trajectory of the target object, and binding the trajectory of the target object and geographic information; and controlling The camera tracks the target object according to the element trajectory on the geodetic coordinates.
7. The control device according to claim 6, further comprising: a target occlusion analysis module, configured to use geographic information data in the geographic information system to establish an occlusion model to determine the occlusion range of the camera's field of view of the target object.