WO2018068446A1

WO2018068446A1 - Tracking method, tracking device, and computer storage medium

Info

Publication number: WO2018068446A1
Application number: PCT/CN2017/072999
Authority: WO
Inventors: 陈子冲; 廖方波
Original assignee: 纳恩博（北京）科技有限公司
Priority date: 2016-10-12
Filing date: 2017-02-06
Publication date: 2018-04-19
Also published as: CN106774303B; CN106774303A

Abstract

Disclosed are a tracking method, a tracking device, and a computer storage medium, comprising: monitoring first location information of a first object; monitoring second location information of a second object in a target area; combining the first location information with the second location information, determining motion data for tracking the first object; and tracking the first object on the basis of the motion data.

Description

Tracking method and tracking device, computer storage medium

Technical field

The invention relates to an intelligent tracking technology, in particular to a tracking method and a tracking device and a computer storage medium.

Background technique

UWB (Ultra Wideband) is a wireless carrier communication technology. UWB technology can be used to achieve location tracking. Specifically, a UWB anchor node (UWB anchor) is set on the tracking robot, and a UWB beacon (UWB) is set on the target object. Tag), in this way, the tracking robot can use the UWB anchor to track the target object carrying the UWB tag in real time. During the tracking process, because there is a certain distance between the target object and the tracking robot, during the movement of the target object, obstacles may appear between the two, causing the robot to collide during the tracking process, resulting in tracking failure. Even damage tracking robots.

Summary of the invention

To solve the above technical problem, an embodiment of the present invention provides a tracking method, a tracking device, and a computer storage medium.

The tracking method provided by the embodiment of the present invention includes:

Monitoring first location information of the first object;

Monitoring second location information of the second object in the target area;

Combining the first location information with the second location information, determining to track motion data of the first object;

Tracking the first object based on the motion data.

In the embodiment of the present invention, the monitoring the second location information of the second object in the target area, include:

Monitoring the target area to obtain a first coordinate parameter set representing the position distribution of each object in the target area;

Obtaining a pose parameter of the monitoring device, and determining, according to the pose parameter, a second coordinate parameter set that represents a third object position distribution in the target area;

Obtaining first location information of the first object and boundary information, and determining a third coordinate parameter set centered on the first location information and bounded by the boundary information;

And removing the second coordinate parameter set and the third coordinate parameter set from the first coordinate parameter set to obtain a fourth coordinate parameter set in the target area that represents the second object distribution.

In the embodiment of the present invention, the monitoring the second location information of the second object in the target area further includes:

Projecting a fourth coordinate parameter set in the target area that represents the second object distribution to a coordinate system of a preset dimension, to obtain a fifth coordinate parameter set in the coordinate system of the preset dimension, where the The five-coordinate parameter set is used to represent the second location information of the second object.

In the embodiment of the present invention, the second location information of the second object in the monitoring target area includes:

Removing the third coordinate parameter set from the first coordinate parameter set to obtain a fourth coordinate parameter set in the target area that represents the second object distribution, where the fourth coordinate parameter set is used to represent the Second location information of the second object.

In the embodiment of the present invention, the combining the first location information and the second location information, Determining the tracking of the motion data of the first object, including:

Determining, according to the first location information of the first object, a first set of speed data related to tracking the first object;

Determining, according to the first location information of the first object and the second location information of the second object, a second set of speed data related to tracking the first object;

Combining the first set of velocity data, the second set of velocity data, and the second location information of the second object, determining to track motion data of the first object.

In the embodiment of the present invention, the method further includes:

When the first object is tracked according to the motion data, detecting whether an abnormal event occurs;

When an abnormal event occurs, the motion data is adjusted to be less than or equal to a preset value.

In the embodiment of the present invention, the first position information is represented by a direction angle and a distance for characterizing a position of the first object; the first group of speed data is represented by an angular velocity and a linear velocity, and is used for characterizing Tracking the speed of the first object in a state where the second object is not in the target area;

The second position information is represented by a direction angle and a distance for characterizing a position distribution of the second object within the target area; the second set of speed data is represented by angular velocity and linear velocity for characterization Tracking the speed of the first object in a state where the second object is in the target area;

Correspondingly, the determining the motion data of the first object by combining the first group of speed data, the second group of speed data, and the second position information of the second object includes:

When tracking the first object, calculating a distance between the tracking device and the second object according to a current speed of the tracking device and second position information of the second object;

Determining weights respectively corresponding to the first group of speed data and the second group of speed data according to the distance;

Importing the first set of speed data and the second set of speed data based on the determined weights The row weighting process results in the tracking device tracking the motion data of the first object.

In the embodiment of the present invention, the first position information is represented by a direction angle, an elevation angle, and a distance, and is used to represent a position of the first object; the first group of speed data passes the first dimension speed component, the second dimension a velocity component and a third dimensional velocity component are used to represent a speed of tracking the first object in a state where the second object is not in the target region;

The second position information is represented by a direction angle, an elevation angle, and a distance for characterizing a position distribution of the second object in the target area; the second set of speed data passes the first dimension speed component, and the second a dimension velocity component and a third dimension velocity component are used to represent a speed at which the first object is tracked in a state where the second object is in the target region;

And weighting the first group of speed data and the second group of speed data based on the determined weights, to obtain the tracking device tracking the motion data of the first object.

The tracking device provided by the embodiment of the present invention includes:

a first monitoring unit configured to monitor first location information of the first object;

a second monitoring unit configured to monitor second location information of the second object in the target area;

a processing unit, configured to combine the first location information and the second location information to determine to track motion data of the first object;

And a driving unit configured to track the first object according to the motion data.

In the embodiment of the present invention, the second monitoring unit is further configured to: monitor the target area, and obtain a first coordinate parameter set that represents a position distribution of each object in the target area; Determining, according to the pose parameter, a second coordinate parameter set that represents a third object position distribution in the target area; acquiring first position information and boundary information of the first object, and determining Determining, by the first location information, a third coordinate parameter set bounded by the boundary information; removing the second coordinate parameter set and the third coordinate parameter set from the first coordinate parameter set, A fourth set of coordinate parameters characterizing the second object distribution within the target region is obtained.

In the embodiment of the present invention, the second monitoring unit is further configured to: project a fourth coordinate parameter set in the target area that represents the distribution of the second object into a coordinate system of a preset dimension, to obtain the a fifth coordinate parameter set in a coordinate system of the preset dimension, wherein the fifth coordinate parameter set is used to represent second position information of the second object.

In the embodiment of the present invention, the second monitoring unit is further configured to: monitor the target area, obtain a first coordinate parameter set that represents a position distribution of each object in the target area; and acquire first position information of the first object. And determining, by the boundary information, a third coordinate parameter set centered on the first location information and bounded by the boundary information; removing the third coordinate parameter set from the first coordinate parameter set to obtain A fourth coordinate parameter set in the target area that represents the distribution of the second object, the fourth coordinate parameter set being used to represent second location information of the second object.

In the embodiment of the present invention, the processing unit is further configured to: determine, according to the first location information of the first object, a first group of speed data related to tracking the first object; according to the first object Determining, by the first location information and the second location information of the second object, a second set of speed data related to tracking the first object; combining the first set of speed data, the second set of speed data, and Determining the motion data of the first object by using the second location information of the second object.

In the embodiment of the present invention, the device further includes:

An abnormality detecting unit configured to check when the first object is tracked according to the motion data Measure whether an abnormal event has occurred;

The processing unit is further configured to adjust the motion data to be less than or equal to a preset value when an abnormal event occurs.

Correspondingly, the processing unit is further configured to: when tracking the first object, calculate the tracking device and the second object according to a current speed of the tracking device and second position information of the second object a distance between the first set of speed data and the second set of speed data, respectively, based on the distance; the first set of speed data and the second set of speeds based on the determined weights The data is weighted to obtain the tracking device tracking the motion data of the first object.

The computer storage medium provided by the embodiment of the present invention stores a computer program configured to execute the above tracking method.

In the technical solution of the embodiment of the present invention, the first location information of the first object is monitored; the second location information of the second object in the target area is monitored; and the first location information and the second location information are combined to determine Tracking motion data of the first object; tracking the first object based on the motion data. Through the implementation of the embodiment of the present invention, the tracking device detects the second object (also referred to as an obstacle) in the target area while tracking the first object, and simultaneously realizes tracking of the target and avoiding obstacles, thereby greatly reducing The possibility of collision with obstacles during the tracking process protects the tracking device.

DRAWINGS

1 is a schematic flowchart 1 of a tracking method according to an embodiment of the present invention;

2 is a second schematic flowchart of a tracking method according to an embodiment of the present invention;

3 is a schematic diagram 1 of a scenario according to an embodiment of the present invention;

4 is a schematic diagram 1 of information fusion according to an embodiment of the present invention;

FIG. 5 is a schematic flowchart 3 of a tracking method according to an embodiment of the present invention;

FIG. 6 is a second schematic diagram of a scenario according to an embodiment of the present invention;

FIG. 7 is a schematic diagram 2 of information fusion according to an embodiment of the present invention;

FIG. 8 is a schematic structural diagram of a tracking device according to an embodiment of the present invention.

detailed description

The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

FIG. 1 is a schematic flowchart 1 of a tracking method according to an embodiment of the present invention. The tracking method in this example is applied to a tracking device. As shown in FIG. 1 , the tracking method includes the following steps:

Step 101: Monitor first location information of the first object.

In the embodiment of the present invention, the tracking device includes two types of sensors, wherein the first type of sensors are used to monitor first position information of the first object, and the second type of sensors are used to monitor second position information of the second object in the target area. .

In an embodiment, the first type of sensor may be a UWB anchor. Correspondingly, the first object needs to carry a UWB tag, and the tracking device locates the UWB tag carried by the first object by using the UWB anchor to obtain the first position of the first object. information.

In the above solution, the UWB anchor is usually composed of two or more UWB communication nodes, and the UWB tag is composed of another UWB communication node, and the UWB tag is determined relative to the UWB by using the principle of time-of-flight (TOF) and triangulation. The position information of the anchor, that is, the first position information of the first object.

In the embodiment of the present invention, the first object refers to an object to be tracked.

Step 102: Monitor second location information of the second object in the target area.

In the embodiment of the present invention, the second location information of the second object in the target area is monitored by the second type of sensor.

In an embodiment, the second type of sensor may be a 3D camera, and the third position image of the second image in the target area may be obtained by performing a three-dimensional image acquisition on the target area by using the 3D camera. Here, the 3D camera obtains positional information of each object in the camera field of view (corresponding to the target area) with respect to the 3D camera by means of structured light technology, or TOF technology, or binocular vision. Take For example, TOF technology is a two-way ranging technology that measures the distance between nodes by using the time between the two asynchronous transceivers.

In another embodiment, the second type of sensor may be a Lidar (LiDAR) sensor, and the distance information of the surrounding object relative to the sensor is obtained by laser scanning.

In the embodiment of the present invention, the second object refers to an obstacle with respect to the first object. When tracking the first object, you need to avoid the second object and avoid collision with the second object.

In an embodiment, the tracking device may be a ground robot. Since the ground robot can only move on the two-dimensional ground, the first position information of the first object and the second position information of the second object are represented in the two-dimensional space. . For example, when the two-dimensional space is represented by a polar coordinate system, the first position information of the first object is represented by the direction angle θ and the distance d, and the position of the first object in the two-dimensional space is represented by (d, θ) . The second position information of the second object is represented by a direction angle θ' and a distance d', and the position of the second object in the two-dimensional space is represented by (d', θ'), and all the second objects in the target area are The second position information of the objects is gathered together to form a two-dimensional obstacle avoidance map M.

In another embodiment, the tracking device may be a drone, and the first position information of the first object and the second position information of the second object are represented in the three-dimensional space because the drone can move in the three-dimensional space. For example, when the three-dimensional space is represented by a polar coordinate system, the first position information of the first object passes the direction angle θ, the elevation angle

And the distance d is expressed by

Characterizing the position of the first object in three-dimensional space. The second position information of the second object passes through the direction angle θ', the elevation angle

And distance d' to indicate, pass

Characterizing the position of the second object in the three-dimensional space, and combining the second position information of all the second objects in the target area to form a three-dimensional obstacle avoidance map M.

Step 103: Combine the first location information with the second location information, determine to track motion data of the first object, and track the first object according to the motion data.

In the embodiment of the present invention, determining, according to the first location information of the first object, a first group of speed data related to tracking the first object; and according to the first location information of the first object Second location information of the second object, determining a second set of speed data associated with tracking the first object; combining the first set of speed data, the second set of speed data, and the second object The second location information determines that the motion data of the first object is tracked.

Specifically, 1) the tracking device has a proportional-integral-derivative (PID) module, the input of the PID module is first position information of the first object, and the output is the first tracking device tracking the first object without an obstacle Group speed data. 2) The tracking device further has an obstacle avoidance module, wherein the input of the obstacle avoidance module is an obstacle avoidance map M formed based on the second position information of the second object and the first position information of the first object, and the output is the second group of speed data, Here, the second set of speed data is selected from all possible motion trajectories according to the motion model of the tracking device to avoid the second object and as close as possible to the velocity data of the first object. 3) The tracking device further has an information fusion module, wherein the input of the information fusion module is the first group of speed data, the second group of speed data, and the obstacle avoidance map M formed based on the second position information of the second object, and the output of the information fusion module It is the final motion data of the tracking device. Here, the first group of speed data and the second group of speed data are merged based on the obstacle avoidance map M, and the fusion is based on: predicting the tracking device and the second object in the obstacle avoidance map M according to the current motion data of the tracking device. The distance between the tracking device and the second object is greater, the greater the weight of the first set of speed data; conversely, the smaller the distance between the tracking device and the second object, the second set of speed data The greater the weight. Finally, the first set of velocity data and the second set of velocity numbers are weighted based on the respective weights, that is, the motion data of the first object is obtained.

In the embodiment of the present invention, when the first object is tracked according to the motion data, it is detected whether an abnormal event occurs; when an abnormal event occurs, the motion data is adjusted to be less than or equal to a preset value. In an embodiment, the preset value is zero. At this time, if the tracking device is at risk of falling or colliding, the brake logic is forcibly activated to ensure the safety of the tracking device.

2 is a schematic flowchart 2 of a tracking method according to an embodiment of the present invention. The tracking method in this example is applied to a ground robot. As shown in FIG. 2, the tracking method includes the following steps:

Step 201: Monitor first location information of the first object.

In the embodiment of the present invention, the ground robot includes two types of sensors, wherein the first type of sensors are used to monitor first position information of the first object, and the second type of sensors are used to monitor second position information of the second object in the target area. .

In an embodiment, the first type of sensor may be a UWB anchor. Correspondingly, the first object needs to carry the UWB tag, and the ground robot locates the UWB tag carried by the first object by using the UWB anchor to obtain the first position of the first object. information.

In the embodiment of the present invention, the first position information is represented by a direction angle θ and a distance d, and the position of the first object is represented by (d, θ).

Step 202: Monitor the target area to obtain a first coordinate parameter set in the target area that represents the location distribution of each object.

In the embodiment of the present invention, the second location information of the second object in the target area is monitored by the second type of sensor. In an embodiment, the second type of sensor is a 3D camera, and the third position image of the second image in the target area is obtained by performing a three-dimensional image acquisition on the target area by using the 3D camera. In another embodiment, the second type of sensor is a LiDAR sensor, and the distance information of the surrounding object relative to the sensor is obtained by laser scanning.

In the specific implementation, the target area needs to be monitored first, and a first coordinate parameter set representing the position distribution of each object in the target area is obtained. Specifically, the ground robot obtains a three-dimensional spatial distribution O _A ={o _i :(x _i , y _i , z _i )} of all visible obstacles in the target area from the second type of sensor.

Step 203: Acquire a pose parameter of the monitoring device, and determine, according to the pose parameter, a second coordinate parameter set that represents a third object position distribution in the target area.

In the embodiment of the present invention, since the ground robot moves on the ground, it is necessary to calculate the three-dimensional position of the ground according to the posture of the ground robot and the height of the second type of sensor installation (that is, the second coordinate parameter set of the third object position). And remove the ground position from the obstacle distribution O _A to obtain an obstacle distribution O _B without the ground.

Step 204: Acquire first location information of the first object and boundary information, and determine a third coordinate parameter set centered on the first location information and bound by the boundary information.

Specifically, referring to FIG. 3, according to the first position information (d, θ) of the first object relative to the robot, and the boundary information of the first object known in advance, that is, the 3D bounding box size, the characterization can be determined. The third coordinate parameter set of the spatial distribution of the first object removes all obstacles in the 3D bounding box centered on the first position from the obstacle distribution O _B to obtain a final obstacle distribution O _c .

Step 205: Removing the second coordinate parameter set and the third coordinate parameter set from the first coordinate parameter set to obtain a fourth coordinate parameter set in the target area that represents the second object distribution.

Specifically, the ground position is first removed from the obstacle distribution O _A to obtain an obstacle distribution O _B without the ground; then, all obstacles in the 3D bounding box centered on the first object are removed from the obstacle distribution O _B The final obstacle distribution O _{c is obtained} .

Step 206: Projecting a fourth coordinate parameter set in the target area that represents the second object distribution to a coordinate system of a preset dimension, and obtaining a fifth coordinate parameter set in the coordinate system of the preset dimension. The fifth coordinate parameter set is used to represent second location information of the second object.

In the embodiment of the present invention, since the ground robot moves in a two-dimensional space, it is necessary to The fourth set of coordinate parameters is projected into the two-dimensional coordinate system, such that the obtained second position information can be represented by a direction angle and a distance in the two-dimensional polar coordinates for characterizing the second object in the target area Location distribution.

Specifically, the obstacle distribution O _{c is} projected onto a horizontal plane (ie, the ground) to obtain a two-dimensional partial obstacle avoidance map M, and the obstacle avoidance map M includes second position information of each second object.

Step 207: Determine, according to the first location information of the first object, a first set of speed data related to tracking the first object.

In the embodiment of the present invention, the first set of speed data is represented by an angular velocity and a linear velocity for characterizing the speed of tracking the first object in a state where the second object is not in the target region.

In the embodiment of the present invention, the ground robot has a local motion controller, and the local motion controller includes: a PID module, an obstacle avoidance module, and an information fusion module.

Specifically, the input of the PID module is first position information (d, θ) of the first object, and the output is that the ground robot tracks the first set of velocity data (v ₁ , ω ₁ ) of the first object without an obstacle. .

Step 208: Determine, according to the first location information of the first object and the second location information of the second object, a second set of speed data related to tracking the first object.

In the embodiment of the present invention, the second set of speed data is represented by an angular velocity and a linear velocity for characterizing the speed of tracking the first object in a state where the second object is in the target region.

Specifically, the input of the obstacle avoidance module is an obstacle avoidance map M formed based on the second position information of the second object and the first position information (d, θ) of the first object, and the output is the second set of speed data (v ₂ , ω ₂ ), here, the second set of speed data is based on the motion model of the ground robot, and selects the speed data that avoids the second object from all possible motion trajectories and is as close as possible to the first object.

Step 209: Determine, according to the first group of speed data, the second group of speed data, and the second position information of the second object, tracking motion data of the first object; The motion data tracks the first object.

In the embodiment of the present invention, when the first object is tracked, the distance between the ground robot and the second object is calculated according to the current speed of the ground robot and the second position information of the second object; Determining a weight corresponding to the first group of speed data and the second group of speed data respectively; performing weighting processing on the first group of speed data and the second group of speed data based on the determined weights The ground robot tracks motion data of the first object.

Referring to FIG. 4, the input of the information fusion module is a first set of velocity data (v ₁ , ω ₁ ), a second set of velocity data (v ₂ , ω ₂ ), and an obstacle avoidance based on the second location information of the second object. Map M, the output of the information fusion module is the final motion data (v ₃ , ω ₃ ) of the ground robot. Here, the first set of velocity data and the second set of velocity data are merged based on the obstacle avoidance map M, and the fusion is based on: predicting in the obstacle avoidance map M according to the current motion data (v ₀ , ω ₀ ) of the ground robot The distance d _c between the ground robot and the second object, the greater the distance d _c between the ground robot and the second object, the greater the weight of the first set of velocity data (v ₁ , ω ₁ ); otherwise, the ground robot The smaller the distance d _c between the second object and the second object, the greater the weight of the second set of velocity data (v ₂ , ω ₂ ). Finally, the first set of velocity data (v ₁ , ω ₁ ) and the second set of velocity numbers (v ₂ , ω ₂ ) are weighted based on the respective weights, that is, the motion data of the first object is obtained.

In the embodiment of the present invention, when the first object is tracked according to the motion data, it is detected whether an abnormal event occurs; when an abnormal event occurs, the motion data is adjusted to be less than or equal to a preset value. In an embodiment, the preset value is zero. At this time, once the ground robot has a risk of falling or colliding, the brake logic is forcibly activated to ensure the safety of the ground robot.

FIG. 5 is a schematic flowchart of a tracking method according to an embodiment of the present invention. The tracking method in this example is applied to a drone. As shown in FIG. 5, the tracking method includes the following steps:

Step 501: Monitor first location information of the first object.

In the embodiment of the present invention, the drone includes two types of sensors, wherein the first type of sensor is used for The first location information of the first object is monitored, and the second type of sensor is used to monitor the second location information of the second object in the target area.

In an embodiment, the first type of sensor is a UWB anchor. Correspondingly, the first object needs to carry a UWB tag, and the UWB anchors the UWB tag carried by the first object by using the UWB anchor to obtain the first position of the first object. information.

In the embodiment of the present invention, the first position information passes the direction angle θ and the elevation angle

And the distance d is expressed by

Characterizing the location of the first object.

Step 502: Monitor the target area to obtain a first coordinate parameter set in the target area that represents the location distribution of each object.

In the specific implementation, the target area needs to be monitored first, and a first coordinate parameter set representing the position distribution of each object in the target area is obtained. Specifically, the drone obtains a three-dimensional spatial distribution of all visual obstacles within the target area from the second type of sensor O _A = {o _i :(x _i , y _i , z _i )}.

Step 503: Acquire first location information of the first object and boundary information, and determine The first location information is a center and the third coordinate parameter set bounded by the boundary information is bounded.

Specifically, referring to FIG. 6, the first position information of the first object relative to the robot

And the boundary information of the first object known in advance, that is, the 3D bounding box size, the third coordinate parameter set representing the spatial distribution of the first object can be determined, and the first distribution is removed from the obstacle distribution O _A All obstacles in the 3D bounding box centered at the location, resulting in the final obstacle distribution O _B .

Step 504: Removing the third coordinate parameter set from the first coordinate parameter set, and obtaining a fourth coordinate parameter set in the target area that represents the second object distribution, where the fourth coordinate parameter set is used Representing second location information of the second object.

In particular, the distribution of the obstacle O is removed from _A to all the obstacles in the first object-centric 3D bounding box, to obtain the final distribution of the obstacle O _{_B,} O _B is the three-dimensional map of obstacle avoidance, obstacle avoidance map O _B includes second location information for each of the second objects.

Step 505: Determine, according to the first location information of the first object, a first set of speed data related to tracking the first object.

In the embodiment of the present invention, the first set of velocity data is represented by a first dimension velocity component, a second dimension velocity component, and a third dimension velocity component, and is used to represent tracking in a state where the second object is not in the target region. The speed of the first object.

In the embodiment of the present invention, the drone has a local motion controller, and the local motion controller includes: a PID module, an obstacle avoidance module, and an information fusion module.

Specifically, the input of the PID module is the first location information of the first object.

The output is that the drone tracks the first set of velocity data (α ₁ , β ₁ , γ ₁ ) of the first object without obstacles.

In the embodiment of the present invention, the velocity data is velocity data in a three-dimensional space, wherein the first dimension velocity component is a velocity component of the drone rotating around the x-axis (ie, the roll axis), and the second dimension velocity component is an unmanned The velocity component of the machine rotating around the y-axis (that is, the pitch axis), the third-dimensional velocity component It is the velocity component of the drone that rotates around the z-axis (that is, the yaw axis).

Step 506: Determine, according to the first location information of the first object and the second location information of the second object, a second set of speed data related to tracking the first object.

In the embodiment of the present invention, the second set of velocity data is represented by a first dimension velocity component, a second dimension velocity component, and a third dimension velocity component, and is used to represent that the second object is tracked in the target region. The speed of the first object.

Specifically, the input of the obstacle avoidance module is an obstacle avoidance map O _B formed based on the second position information of the second object and the first position information of the first object

The output is a second set of velocity data (α ₂ , β ₂ , γ ₂ ), where the second set of velocity data is selected from all possible motion trajectories to avoid the second object according to the motion model of the drone, and Try to be close to the speed data of the first object.

Step 507: Combine the first group of speed data, the second group of speed data, and the second position information of the second object to determine that the motion data of the first object is tracked; and track the tracking according to the motion data. Said the first object.

In the embodiment of the present invention, when the first object is tracked, the distance between the drone and the second object is calculated according to the current speed of the drone and the second position information of the second object; Determining weights respectively corresponding to the first group of speed data and the second group of speed data according to the distance; weighting the first group of speed data and the second group of speed data based on the determined weights Obtaining, by the drone, tracking motion data of the first object.

Referring to FIG. 7, the input of the information fusion module is a first set of velocity data (α ₁ , β ₁ , γ ₁ ), a second set of velocity data (α ₂ , β ₂ , γ ₂ ), and a second location based on the second object. The obstacle avoidance map O _B formed by the information, the output of the information fusion module is the final motion data (α ₃ , β ₃ , γ ₃ ) of the drone. Here, the first set of velocity data and the second set of velocity data are merged based on the obstacle avoidance map O _B , and the fusion is based on: avoiding the current motion data (α ₀ , β ₀ , γ ₀ ) of the drone O _B barrier predicted distance map d _c between the UAV and the second object, the greater the distance d _c between the UAV and a second object, the first set of data rate (α _{_1,} β _1, γ ₁ ) the greater the weight; conversely, the smaller the distance d _c between the drone and the second object, the greater the weight of the second set of velocity data (α ₂ , β ₂ , γ ₂ ). Finally, weighting the first set of velocity data (α ₁ , β ₁ , γ ₁ ) and the second set of velocity numbers (α ₂ , β ₂ , γ ₂ ) based on the respective weights, thereby obtaining the tracking first object Sports data.

In the embodiment of the present invention, when the first object is tracked according to the motion data, it is detected whether an abnormal event occurs; when an abnormal event occurs, the motion data is adjusted to be less than or equal to a preset value. In an embodiment, the preset value is zero. At this time, once the drone has a risk of falling or colliding, the brake logic is forcibly activated to ensure the safety of the drone.

FIG. 8 is a schematic structural diagram of a tracking device according to an embodiment of the present invention. As shown in FIG. 8, the tracking device includes:

The first monitoring unit 81 is configured to monitor first location information of the first object;

a second monitoring unit 82, configured to monitor second location information of the second object in the target area;

The processing unit 83 is configured to determine, according to the first location information and the second location information, tracking motion data of the first object;

The driving unit 84 is configured to track the first object according to the motion data.

In the embodiment of the present invention, the second monitoring unit 82 is further configured to: monitor the target area, obtain a first coordinate parameter set that represents a position distribution of each object in the target area; acquire a pose parameter of the monitoring device, according to the Determining, by the pose parameter, a second coordinate parameter set that represents a third object position distribution in the target area; acquiring first position information of the first object and boundary information, determining that the first location information is centered a third coordinate parameter set bounded by the boundary information; removing the second coordinate parameter set and the third coordinate parameter set from the first coordinate parameter set to obtain a representation in the target area A set of fourth coordinate parameters of the two object distributions.

In the embodiment of the present invention, the second monitoring unit 82 is further configured to: project a fourth coordinate parameter set in the target area that represents the distribution of the second object into a coordinate system of a preset dimension, and obtain a a fifth coordinate parameter set in a coordinate system of the preset dimension, the fifth coordinate parameter The set of numbers is used to represent the second location information of the second object.

In the embodiment of the present invention, the second monitoring unit 82 is further configured to: monitor the target area, obtain a first coordinate parameter set that represents the position distribution of each object in the target area; and acquire the first position of the first object. Determining, by the information and the boundary information, a third coordinate parameter set centered on the first location information and bounded by the boundary information; removing the third coordinate parameter set from the first coordinate parameter set, Obtaining a fourth coordinate parameter set in the target area that represents the distribution of the second object, the fourth coordinate parameter set is used to represent second location information of the second object.

In the embodiment of the present invention, the processing unit 83 is further configured to: determine, according to the first location information of the first object, a first group of speed data related to tracking the first object; according to the first object And determining, by the first location information and the second location information of the second object, a second set of speed data associated with tracking the first object; combining the first set of speed data, the second set of speed data, and The second location information of the second object determines to track motion data of the first object.

In the embodiment of the present invention, the device further includes:

The abnormality detecting unit 85 is configured to detect whether an abnormal event occurs when the first object is tracked according to the motion data;

The processing unit 83 is further configured to adjust the motion data to be less than or equal to a preset value when an abnormal event occurs.

The second position information is represented by a direction angle and a distance for characterizing a position distribution of the second object within the target area; the second set of speed data passes angular velocity and linear velocity Representing a speed for tracking the first object in a state where the second object is in the target area;

Correspondingly, the processing unit 83 is further configured to: when tracking the first object, calculate the tracking device and the second object according to a current speed of the tracking device and second position information of the second object a distance between the first set of speed data and the second set of speed data, respectively; determining, according to the determined weight, the first set of speed data and the second group The speed data is weighted to obtain the tracking device tracking the motion data of the first object.

Those skilled in the art should understand that the implementation functions of the units in the tracking device shown in FIG. 8 can be understood by referring to the related description of the foregoing tracking method.

In practical applications, the first monitoring unit can be implemented by a UWB anchor, UWB. An anchor usually consists of more than two UWB communication nodes. The second monitoring unit can be implemented by a 3D camera. The drive unit can be realized by a motor. The anomaly detection unit can be implemented by a pose sensor. The processing unit can be implemented by a processor.

Embodiments of the Invention The above tracking device can also be stored in a computer readable storage medium if it is implemented in the form of a software function module and sold or used as a standalone product. Based on such understanding, the technical solution of the embodiments of the present invention may be embodied in the form of a software product in essence or in the form of a software product stored in a storage medium, including a plurality of instructions. A computer device (which may be a personal computer, server, or network device, etc.) is caused to perform all or part of the methods described in various embodiments of the present invention. The foregoing storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read only memory (ROM), a magnetic disk, or an optical disk. Thus, embodiments of the invention are not limited to any specific combination of hardware and software.

Correspondingly, an embodiment of the present invention further provides a computer storage medium, wherein a computer program is stored, and the computer program is used to execute the tracking method of the embodiment of the present invention.

While the preferred embodiments of the present invention have been disclosed for purposes of illustration, those skilled in the art will recognize that various modifications, additions and substitutions are possible, and the scope of the invention should not be limited to the embodiments described above.

Industrial applicability

The technical solution of the embodiment of the present invention monitors first location information of the first object, monitors second location information of the second object in the target area, and determines the tracking by combining the first location information and the second location information. Motion data of the first object; tracking the first object based on the motion data. The tracking device detects the second object (also called an obstacle) in the target area while tracking the first object, and at the same time realizes tracking of the target and avoiding obstacles, thereby greatly reducing the possibility of collision obstacles during the tracking process. Sexuality protects tracking devices.

Claims

A tracking method, the method comprising:

Monitoring first location information of the first object;

Monitoring second location information of the second object in the target area;

Combining the first location information with the second location information, determining to track motion data of the first object;

Tracking the first object based on the motion data.
The tracking method of claim 1, wherein the monitoring the second location information of the second object in the target area comprises:

Monitoring the target area to obtain a first coordinate parameter set representing the position distribution of each object in the target area;

Obtaining a pose parameter of the monitoring device, and determining, according to the pose parameter, a second coordinate parameter set that represents a third object position distribution in the target area;

Obtaining first location information of the first object and boundary information, and determining a third coordinate parameter set centered on the first location information and bounded by the boundary information;

And removing the second coordinate parameter set and the third coordinate parameter set from the first coordinate parameter set to obtain a fourth coordinate parameter set in the target area that represents the second object distribution.
The tracking method of claim 2, wherein the monitoring the second location information of the second object in the target area further comprises:

Projecting a fourth coordinate parameter set in the target area that represents the second object distribution to a coordinate system of a preset dimension, to obtain a fifth coordinate parameter set in the coordinate system of the preset dimension, where the The five-coordinate parameter set is used to represent the second location information of the second object.
The tracking method of claim 1, wherein the monitoring the second location information of the second object in the target area comprises:

Monitoring the target area to obtain a first coordinate parameter set representing the position distribution of each object in the target area;

Obtaining first location information of the first object and boundary information, and determining a third coordinate parameter set centered on the first location information and bounded by the boundary information;

Removing the third coordinate parameter set from the first coordinate parameter set to obtain a fourth coordinate parameter set in the target area that represents the second object distribution, where the fourth coordinate parameter set is used to represent the Second location information of the second object.
The tracking method according to claim 1, wherein the determining the motion data of the first object by combining the first location information and the second location information comprises:

Determining, according to the first location information of the first object, a first set of speed data related to tracking the first object;

Determining, according to the first location information of the first object and the second location information of the second object, a second set of speed data related to tracking the first object;

Combining the first set of velocity data, the second set of velocity data, and the second location information of the second object, determining to track motion data of the first object.
The tracking method according to claim 5, wherein the method further comprises:

When the first object is tracked according to the motion data, detecting whether an abnormal event occurs;

When an abnormal event occurs, the motion data is adjusted to be less than or equal to a preset value.
The tracking method according to claim 5, wherein

The first position information is represented by a direction angle and a distance for characterizing a position of the first object; the first set of speed data is represented by an angular velocity and a linear velocity for characterizing that the target region does not have the Tracking the speed of the first object in the state of the second object;

The second position information is represented by a direction angle and a distance for characterizing a position distribution of the second object within the target area; the second set of speed data is represented by angular velocity and linear velocity for characterization Tracking the first pair in a state where the second object is in the target area Speed of elephant

Correspondingly, the determining the motion data of the first object by combining the first group of speed data, the second group of speed data, and the second position information of the second object includes:

When tracking the first object, calculating a distance between the tracking device and the second object according to a current speed of the tracking device and second position information of the second object;

Determining weights respectively corresponding to the first group of speed data and the second group of speed data according to the distance;

And weighting the first group of speed data and the second group of speed data based on the determined weights, to obtain the tracking device tracking the motion data of the first object.
The tracking method according to claim 5, wherein

The first position information is represented by a direction angle, an elevation angle, and a distance for characterizing a position of the first object; the first set of velocity data passes the first dimension velocity component, the second dimension velocity component, and the third dimension speed a component representation for characterizing a speed of tracking the first object in a state where the second object is not in the target area;

The second position information is represented by a direction angle, an elevation angle, and a distance for characterizing a position distribution of the second object in the target area; the second set of speed data passes the first dimension speed component, and the second a dimension velocity component and a third dimension velocity component are used to represent a speed at which the first object is tracked in a state where the second object is in the target region;

Correspondingly, the determining the motion data of the first object by combining the first group of speed data, the second group of speed data, and the second position information of the second object includes:

When tracking the first object, calculating a distance between the tracking device and the second object according to a current speed of the tracking device and second position information of the second object;

Determining weights respectively corresponding to the first group of speed data and the second group of speed data according to the distance;

Importing the first set of speed data and the second set of speed data based on the determined weights The row weighting process results in the tracking device tracking the motion data of the first object.
A tracking device, the device comprising:

a first monitoring unit configured to monitor first location information of the first object;

a second monitoring unit configured to monitor second location information of the second object in the target area;

a processing unit, configured to combine the first location information and the second location information to determine to track motion data of the first object;

And a driving unit configured to track the first object according to the motion data.
The tracking device according to claim 9, wherein the second monitoring unit is further configured to: monitor the target area, obtain a first coordinate parameter set in the target area that represents a distribution of each object position; and acquire a bit of the monitoring device. a posture parameter, determining, according to the pose parameter, a second coordinate parameter set that represents a third object position distribution in the target area; acquiring first position information of the first object and boundary information, and determining the first a third coordinate parameter set centered on the location information and bounded by the boundary information; removing the second coordinate parameter set and the third coordinate parameter set from the first coordinate parameter set to obtain a target area Characterizing a fourth set of coordinate parameters of the second object distribution.
The tracking device according to claim 10, wherein the second monitoring unit is further configured to: project a fourth coordinate parameter set representing the second object distribution in the target area to a coordinate of a preset dimension In the system, a fifth coordinate parameter set in the coordinate system of the preset dimension is obtained, and the fifth coordinate parameter set is used to represent the second location information of the second object.
The tracking device according to claim 9, wherein the second monitoring unit is further configured to: monitor the target area, obtain a first coordinate parameter set that represents a distribution of each object position in the target area; and acquire the first Determining, by the first position information of the object and the boundary information, a third coordinate parameter set centered on the first position information and bounded by the boundary information; removing the first coordinate parameter set from the first coordinate parameter set a set of three coordinate parameters, and obtaining a fourth coordinate parameter set in the target area that represents the distribution of the second object, the fourth coordinate The parameter set is used to represent the second location information of the second object.
The tracking device according to claim 9, wherein the processing unit is further configured to: determine, according to the first location information of the first object, a first set of speed data related to tracking the first object; Determining, according to the first location information of the first object and the second location information of the second object, a second set of speed data related to tracking the first object; combining the first group of speed data, the first The two sets of speed data and the second position information of the second object determine to track the motion data of the first object.
The tracking device of claim 13, wherein the device further comprises:

An abnormality detecting unit configured to detect whether an abnormal event occurs when the first object is tracked according to the motion data;

The processing unit is further configured to adjust the motion data to be less than or equal to a preset value when an abnormal event occurs.
The tracking device according to claim 13, wherein

The first position information is represented by a direction angle and a distance for characterizing a position of the first object; the first set of speed data is represented by an angular velocity and a linear velocity for characterizing that the target region does not have the Tracking the speed of the first object in the state of the second object;

The second position information is represented by a direction angle and a distance for characterizing a position distribution of the second object within the target area; the second set of speed data is represented by angular velocity and linear velocity for characterization Tracking the speed of the first object in a state where the second object is in the target area;

Correspondingly, the processing unit is further configured to: when tracking the first object, calculate the tracking device and the second object according to a current speed of the tracking device and second position information of the second object a distance between the first set of speed data and the second set of speed data, respectively, based on the distance; the first set of speed data and the second set of speeds based on the determined weights Data is weighted to obtain the tracking device tracking the first The motion data of the object.
The tracking device according to claim 13, wherein

The first position information is represented by a direction angle, an elevation angle, and a distance for characterizing a position of the first object; the first set of velocity data passes the first dimension velocity component, the second dimension velocity component, and the third dimension speed a component representation for characterizing a speed of tracking the first object in a state where the second object is not in the target area;

The second position information is represented by a direction angle, an elevation angle, and a distance for characterizing a position distribution of the second object in the target area; the second set of speed data passes the first dimension speed component, and the second a dimension velocity component and a third dimension velocity component are used to represent a speed at which the first object is tracked in a state where the second object is in the target region;

Correspondingly, the processing unit is further configured to: when tracking the first object, calculate the tracking device and the second object according to a current speed of the tracking device and second position information of the second object a distance between the first set of speed data and the second set of speed data, respectively, based on the distance; the first set of speed data and the second set of speeds based on the determined weights The data is weighted to obtain the tracking device tracking the motion data of the first object.
A computer storage medium having stored therein computer executable instructions configured to perform the tracking method of any of claims 1-8.