Unmanned vehicle target attribute identification method for dynamic target in field environment

Abstract

The invention relates to an unmanned vehicle target attribute identification method for a dynamic target in a field environment, belongs to the technical field of unmanned vehicle situation awareness, and solves the problems that unmanned vehicle identification is difficult to adapt to the dynamic target and the identification accuracy is insufficient due to time delay in the prior art. Collecting situation information in real time and sending the situation information to the unmanned vehicle; the unmanned vehicle receives the situation information, forms situation points based on the situation information and the receiving time, and generates a situation sequence for all situation points of the same target in a preset time period; acquiring investigation information of a reconnaissance target; judging whether the quantity of situation points in the situation sequence of each target meets a preset condition or not, performing trajectory prediction on each target based on the situation sequence of the target when the preset condition is met, obtaining a prediction coordinate of each target at a reconnaissance moment, matching the prediction coordinate with the reconnaissance coordinate to obtain a matched prediction coordinate, and performing trajectory prediction on each target according to the matched prediction coordinate. And taking the attribute information of the target corresponding to the matched prediction coordinate as the attribute information of the reconnaissance target.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned vehicle situational awareness, and in particular to a method for unmanned vehicle target attribute recognition of dynamic targets in a field environment. Background Art

[0002] With the rapid development of unmanned vehicle technology, its applications in various fields are becoming increasingly widespread. Traditional methods for unmanned vehicle target attribute recognition primarily rely on capturing target images and then identifying them to determine their attributes. However, in complex outdoor environments, unmanned vehicles struggle to effectively capture target images. Furthermore, the unpredictable nature of the field environment makes it difficult to rely on unmanned vehicle-generated imagery for target recognition.

[0003] This problem can be solved by remotely collecting target information and sending it to an unmanned vehicle. Existing technology remotely collects situational information, including target coordinates and attributes, in real time and sends it to the unmanned vehicle. The unmanned vehicle then analyzes and compares this situational information with the target information it has detected.

[0004] However, existing technologies have significant limitations in practical applications. For one thing, they primarily target static targets and are difficult to adapt to the dynamic nature of targets in field environments. Furthermore, time delays are inevitable during the updating and delivery of command information. This results in a certain amount of error between the target information actually detected by the unmanned vehicle and the received situational target information, which in turn reduces the accuracy of target attribute recognition. Summary of the Invention

[0005] In view of the above analysis, an embodiment of the present invention aims to provide a method for unmanned vehicle target attribute recognition of dynamic targets in a field environment, so as to solve the problem that existing unmanned vehicle recognition is difficult to adapt to dynamic targets and has time delays resulting in insufficient recognition accuracy.

[0006] On the one hand, an embodiment of the present invention provides a method for identifying target attributes of an unmanned vehicle for a dynamic target in a field environment, the method comprising:

[0007] The command and control terminal collects situation information in real time and sends it to the unmanned vehicle. The situation information includes the coordinates and attribute information of each target;

[0008] The unmanned vehicle receives situation information, forms situation points based on the situation information and the time of reception, and generates a situation sequence from all situation points of the same target within a preset time period;

[0009] After the unmanned vehicle detects any target, it obtains the detection information of the detected target, and the detection information includes the detection coordinates and detection time;

[0010] Determine whether the number of situation points in the situation sequence of each target meets the preset conditions. If the preset conditions are met, predict the trajectory of each target based on the situation sequence of the target to obtain the predicted coordinates of each target at the time of reconnaissance.

[0011] The predicted coordinates of all targets at the reconnaissance moment are matched with the reconnaissance coordinates to obtain matched predicted coordinates, and the attribute information of the target corresponding to the matched predicted coordinates is used as the attribute information of the reconnaissance target.

[0012] As a further improvement of the present application, the preset condition is: the number of situation points in the situation sequence of the target is greater than or equal to the situation point threshold;

[0013] If the preset conditions are not met, the coordinates of the last situation point in each target situation sequence are used as the predicted coordinates of the target at the reconnaissance moment.

[0014] As a further improvement of the present application, matching the predicted coordinates of all targets at the reconnaissance moment with the reconnaissance coordinates includes:

[0015] Calculating the distance between the predicted coordinates of all targets at the time of reconnaissance and the reconnaissance coordinates;

[0016] The target with the shortest distance between the predicted coordinates at the reconnaissance moment and the reconnaissance coordinates is taken as the matching target.

[0017] As a further improvement of the present application, the attribute information of the reconnaissance target determined based on the matching result includes:

[0018] The attribute information of the matching target is assigned to the reconnaissance target, thereby obtaining the attribute information of the reconnaissance target.

[0019] As a further improvement of the present application, if the number of situation points in the situation sequence of the target meets a preset threshold, the trajectory of the target is predicted using the Kalman filter algorithm to obtain the predicted coordinates of the target at the time of reconnaissance, which specifically includes the following steps:

[0020] Input all situation points of the situation sequence of the target that is greater than or equal to the situation point threshold into the initial Kalman filter model, and update the Kalman gain of the initial Kalman filter model based on the situation sequence to obtain the final Kalman model;

[0021] The situation information of the last situation point in the situation sequence and the time interval between the reception time and the reconnaissance time of the last situation point are input into the final Kalman model to obtain the coordinates of the target at the reconnaissance time.

[0022] As a further improvement of the present application, the Kalman gain of the initial Kalman filter model is updated based on the situation sequence to obtain the final Kalman model, which includes:

[0023] Starting from the second situation point, perform the following operations on each situation point in the situation sequence:

[0024] The coordinates of the situation point at the previous moment and the reception time are input into the Kalman filter model to calculate the coordinate estimate at the current moment;

[0025] Taking the coordinates of the situation point at the current moment as coordinate observation values, and updating the Kalman gain based on the coordinate observation values and the coordinate estimation value;

[0026] The last updated Kalman gain is used as the final gain of the Kalman filter model to obtain the final Kalman model.

[0027] As a further improvement of the present application, the situation information of the last situation point in the situation sequence and the time interval between the reception time and the reconnaissance time of the last situation point are input into the final Kalman model, and the coordinates of the target at the reconnaissance time are obtained as shown in the following formula:

[0028] X=x f +k·v f ·Δt1·cosθ f

[0029] Y=y f +k·v f ·Δt1·sinθ f

[0030] Among them, X and Y are the coordinates of the target at the time of reconnaissance, x f 、y f is the coordinate of the last situation point, v f is the target speed at the last situation point receiving moment, θ f is the steering angle at the moment of receiving the last situation point, Δt is the time interval between the moment of receiving the last situation point and the reconnaissance moment, and k is the Kalman gain.

[0031] As a further improvement of the present application, the target speed at the moment of receiving the last situation point is expressed as follows:

[0032]

[0033] Among them, v x,f is the x-axis component of the target velocity at the moment of receiving the last situation point, v y,f is the y-axis component of the target velocity at the moment of receiving the last situation point, Δt2 is the time interval between the last situation point and the previous situation point, x f-1 、y f-1 The coordinates of the last situation point at the previous moment;

[0034] The steering angle at the moment of receiving the last situation point is as follows:

[0035]

[0036] As a further improvement of the present application, the situation point coordinates in the situation sequence are longitude and latitude coordinates; before the Kalman gain of the initial Kalman filter model is updated based on the situation sequence to obtain the final Kalman model, the method further includes:

[0037] Convert the coordinates of the situation points in the situation sequence into rectangular coordinates.

[0038] As a further improvement of the present application, the situation point threshold is 10.

[0039] Compared with the prior art, the present invention can achieve at least one of the following beneficial effects:

[0040] 1. The present invention receives situation information sent by the command and control end through an unmanned vehicle and establishes a situation sequence. It uses the Kalman filter algorithm to predict the trajectory of the target and matches it with the reconnaissance coordinates at the time of reconnaissance. It can accurately identify the attribute information of dynamic targets, fully consider the dynamic characteristics of the target, and improve the accuracy of target attribute recognition through prediction and matching.

[0041] 2. Based on the situation sequence, this invention effectively solves the problem of mismatch between situation target information and actual reconnaissance target information caused by time delay by introducing preset conditions and situation point thresholds. When the number of situation points does not meet the preset conditions, the coordinates of the last situation point are used as the predicted coordinates, reducing the impact of time delay on target attribute recognition. When the number of situation points in the target's situation sequence meets the preset conditions, the Kalman filter algorithm is used for trajectory prediction. By converting the situation point coordinates in the situation sequence into rectangular coordinates, the prediction accuracy of the Kalman filter model is further improved.

[0042] In the present invention, the above-mentioned technical solutions can be combined with each other to achieve more preferred combinations. Other features and advantages of the present invention will be described in the following description, and some advantages will become apparent from the description or be learned through practice of the present invention. The objectives and other advantages of the present invention can be realized and obtained through the contents particularly pointed out in the description and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The accompanying drawings are only used for the purpose of illustrating specific embodiments and are not to be considered as limiting the present invention. Throughout the drawings, the same reference symbols denote the same components.

[0044] Figure 1 A flowchart of a method for identifying target attributes of an unmanned vehicle for dynamic targets in a field environment is provided in accordance with one embodiment of the present invention. DETAILED DESCRIPTION

[0045] The preferred embodiments of the present invention are described in detail below with reference to the accompanying drawings, wherein the accompanying drawings constitute a part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention and are not intended to limit the present invention.

[0046] A specific embodiment of the present invention discloses a method for identifying target attributes of an unmanned vehicle for dynamic targets in a field environment, such as Figure 1 shown.

[0047] A method for identifying target attributes of an unmanned vehicle for a dynamic target in a field environment, the method comprising:

[0048] Step 101: The command and control terminal collects situation information in real time and sends it to the unmanned vehicle. The situation information includes the coordinates and attribute information of each target.

[0049] The command and control terminal refers to a remote control center located outside the unmanned vehicle. It integrates data from various sources, such as satellites, radar, cameras, and infrared detectors. Situational information includes the coordinates and attribute information of each target. Coordinates are longitude and latitude coordinates, while attribute information includes the target type and characteristics. Types include vehicles, personnel, and aircraft, while characteristics include size, color, and friend-or-foe information. Attribute information can be obtained through satellite remote sensing or radar technology, such as imaging ground targets with high-resolution optical cameras. By analyzing these images, the target's appearance characteristics, such as shape, size, and color, can be extracted. Situational information is transmitted to the unmanned vehicle via a wireless communication network.

[0050] In step 102, the unmanned vehicle receives situation information, forms situation points based on the situation information and the receiving time, and generates a situation sequence for all situation points of the same target within a preset time period.

[0051] The preset time period is a pre-set time window, such as 10 seconds to 5 minutes, that limits the time range of situation points. After receiving situation information, the unmanned vehicle generates a situation point based on this information and the time of receipt. All situation points for the same target within the preset time period are combined to form a situation sequence.

[0052] Step 103: After the unmanned vehicle detects any target, it obtains the detection information of the detected target, and the detection information includes the detection coordinates and the detection time.

[0053] An unmanned vehicle detects moving objects in the environment using its onboard sensors, such as cameras, radar, or lidar. After detecting a target, the vehicle determines its position using its GPS or inertial navigation system. Radar range and angle data are used to calculate the target's polar coordinates relative to the vehicle. This coordinate conversion is then performed to determine the target's reconnaissance coordinates. The reconnaissance time is the moment the vehicle detects the target.

[0054] Step 104 determines whether the number of situation points in each target's situation sequence meets a preset condition. If the preset condition is met, trajectory prediction is performed for each target based on the target's situation sequence to obtain the predicted coordinates of each target at the time of reconnaissance. The preset condition is that the number of situation points in the target's situation sequence is greater than or equal to a situation point threshold.

[0055] When the number of situation points is greater than or equal to the situation point threshold, trajectory prediction is performed for each target based on its situation sequence. If the number of situation points is less than the situation point threshold, the coordinates of the last situation point in each target's situation sequence are used as the predicted coordinates of the target at the time of reconnaissance. The situation point threshold is 10, meaning the default condition is that the number of situation points in the situation sequence is greater than or equal to 10.

[0056] If the number of situation points is less than 10, in this case, due to the limited number of situation points, the accuracy of trajectory prediction through Kalman filtering is low, and the coordinates of the last situation point in each target situation sequence are used as the predicted coordinates of the target at the time of reconnaissance.

[0057] If the number of situation points in the target's situation sequence meets the preset threshold, the Kalman filter algorithm is used to predict the target's trajectory and obtain the predicted coordinates of the target at the time of reconnaissance. The specific steps include:

[0058] Step 1041: input all situation points of the situation sequence of the target that are greater than or equal to the situation point threshold into the initial Kalman filter model, and update the Kalman gain of the initial Kalman filter model based on the situation sequence to obtain a final Kalman model;

[0059] The Kalman gain of the initial Kalman filter model is updated based on the situation sequence to obtain the final Kalman model, which includes:

[0060] Starting from the second situation point, perform the following operations on each situation point in the situation sequence:

[0061] Step 10411: Input the coordinates of the situation point at the previous moment and the reception time into the Kalman filter model to calculate the coordinate estimate at the current moment;

[0062] The coordinates of the previous moment and their reception time are input into the Kalman filter model, which then calculates the current coordinate estimate. The Kalman filter model dynamically adjusts the Kalman gain parameters based on each observed coordinate estimate, allowing the model's prediction to gradually approach the target's true trajectory. Calculating the current coordinate estimate requires calculating the target's speed and steering angle at the previous moment using the coordinates of the situation points at the current and previous moments, as well as the interval between the situation points' reception times. The current coordinate estimate is calculated based on the previous speed, steering angle, reception time interval, and the current Kalman gain.

[0063] Step 10412: The coordinates of the current situation point are used as coordinate observations, and the Kalman gain is updated based on the coordinate observations and the coordinate estimates. The Kalman gain measures the impact of the difference between the observations and the estimates on the model parameters. The coordinates of the current situation point are compared with the coordinate estimates at the current moment, the difference between the two is calculated, and the Kalman gain is updated based on this difference.

[0064] The update formula of Kalman gain is:

[0065]

[0066] Δ x =x obs -x pred

[0067] Δ y =y obs -y pred

[0068] Among them, Δ x is the x-axis coordinate difference between the coordinate of the situation point at the current moment and the estimated coordinate value at the current moment, Δ y is the y-axis coordinate difference between the coordinate of the situation point at the current moment and the coordinate estimate at the current moment, α is the preset learning rate, k old is the Kalman gain of the last update, k new is the Kalman gain updated at the current moment, x pred is the estimated value of the x-axis coordinate at the current moment, y pred is the estimated value of the y-axis coordinate at the current moment, x obs is the x-axis coordinate of the situation point at the current moment, y obs is the y-axis coordinate of the situation point at the current moment.

[0069] Step 10413: Use the last updated Kalman gain as the final gain of the Kalman filter model to obtain the final Kalman model.

[0070] Step 1042: Input the situation information of the last situation point in the situation sequence and the time interval between the reception time and the reconnaissance time of the last situation point into the final Kalman model to obtain the coordinates of the target at the reconnaissance time.

[0071] The situation information of the last situation point in the situation sequence and the time interval between the reception time and the reconnaissance time of the last situation point are input into the final Kalman model to obtain the coordinates of the target at the reconnaissance time as shown in the following formula:

[0072] X=x f +k·v f ·Δt1·cosθ f

[0073] Y=y f +k·v f ·Δt1·sinθ f

[0074] Among them, X and Y are the coordinates of the target at the time of reconnaissance, x f 、y f is the coordinate of the last situation point, v f is the target speed at the last situation point receiving moment, θ f is the steering angle at the moment of receiving the last situation point, Δt1 is the time interval between the moment of receiving the last situation point and the reconnaissance moment, and k is the Kalman gain.

[0075] The target speed at the moment of receiving the last situation point is as follows:

[0076]

[0077] Among them, v x,f is the x-axis component of the target velocity at the moment of receiving the last situation point, v y,f is the y-axis component of the target velocity at the moment of receiving the last situation point, Δt2 is the time interval between the last situation point and the previous situation point, x f-1 、y f-1 The coordinates of the last situation point at the previous moment;

[0078] The steering angle at the moment of receiving the last situation point is as follows:

[0079]

[0080] Before obtaining the final Kalman model by updating the Kalman gain of the initial Kalman filter model based on the situation sequence, the following steps are also included:

[0081] Convert the coordinates of the situation points in the situation sequence into rectangular coordinates. The coordinates of the situation points are longitude and latitude coordinates, which can be converted into plane rectangular coordinates using Mercator projection, Gauss-Krüger projection, etc.

[0082] Step 105 : Match the predicted coordinates of all targets at the reconnaissance moment with the reconnaissance coordinates to obtain matched predicted coordinates, and use the attribute information of the target corresponding to the matched predicted coordinates as the attribute information of the reconnaissance target.

[0083] Matching the predicted coordinates of all targets at the reconnaissance moment with the reconnaissance coordinates includes:

[0084] Calculating the distance between the predicted coordinates of all targets at the time of reconnaissance and the reconnaissance coordinates;

[0085] The target with the shortest distance between the predicted coordinates at the reconnaissance moment and the reconnaissance coordinates is taken as the matching target.

[0086] The spatial distance between the predicted and detected positions of all targets at the time of reconnaissance is calculated, and the target with the smallest distance is selected as the matching result. To calculate the distance, all predicted coordinates are iterated over, and the linear distance between them and the detected coordinates on the plane is calculated. The distance between the predicted and detected coordinates of the target at the time of reconnaissance is the Euclidean distance, which quantifies the spatial deviation between the predicted and actual positions. By comparing all calculated results, the corresponding target with the smallest value is selected as the matching target. If multiple targets have the same distance value, additional attributes of the targets are compared, such as the closest speed or closest direction.

[0087] The attribute information of the reconnaissance target determined based on the matching results includes:

[0088] The attribute information of the matching target is assigned to the reconnaissance target, thereby obtaining the attribute information of the reconnaissance target.

[0089] The above-mentioned embodiments of the present invention include at least the following beneficial effects: the present invention receives situation information sent by the command and control terminal through an unmanned vehicle and establishes a situation sequence, uses the Kalman filter algorithm to predict the trajectory of the target, and matches it with the reconnaissance coordinates at the time of reconnaissance, so as to accurately identify the attribute information of the dynamic target, fully consider the dynamic characteristics of the target, and improve the accuracy of target attribute recognition through prediction and matching; on the basis of the situation sequence, the present invention effectively solves the problem of mismatch between situation target information and actual reconnaissance target information caused by time delay by introducing preset conditions and situation point thresholds. When the number of situation points does not meet the preset conditions, the coordinates of the last situation point are used as the predicted coordinates, reducing the influence of time delay on target attribute recognition. When the number of situation points in the situation sequence of the target meets the preset conditions, the Kalman filter algorithm is used to predict the trajectory, and the prediction accuracy of the Kalman filter model is further improved by converting the situation point coordinates in the situation sequence into rectangular coordinates.

[0090] Those skilled in the art will appreciate that all or part of the process steps of the above-described embodiments can be implemented by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium, such as a magnetic disk, an optical disk, a read-only memory, or a random access memory.

[0091] The above description is only a preferred specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by any technician familiar with this technical field within the technical scope disclosed by the present invention should be covered by the scope of protection of the present invention.

Claims

1. A method for identifying target attributes of unmanned vehicles for dynamic targets in a field environment, characterized by: The method comprises: The command and control terminal collects situation information in real time and sends it to the unmanned vehicle. The situation information includes the coordinates and attribute information of each target; The unmanned vehicle receives situation information, forms situation points based on the situation information and the time of reception, and generates a situation sequence from all situation points of the same target within a preset time period; After the unmanned vehicle detects any target, it obtains the detection information of the detected target, and the detection information includes the detection coordinates and detection time; Determine whether the number of situation points in the situation sequence of each target meets the preset conditions. If the preset conditions are met, predict the trajectory of each target based on the situation sequence of the target to obtain the predicted coordinates of each target at the time of reconnaissance. The predicted coordinates of all targets at the reconnaissance moment are matched with the reconnaissance coordinates to obtain matched predicted coordinates, and the attribute information of the target corresponding to the matched predicted coordinates is used as the attribute information of the reconnaissance target.

2. The method according to claim 1, characterized in that The preset condition is: the number of situation points in the situation sequence of the target is greater than or equal to the situation point threshold; If the preset conditions are not met, the coordinates of the last situation point in each target situation sequence are used as the predicted coordinates of the target at the reconnaissance moment.

3. The method according to claim 1, characterized in that Matching the predicted coordinates of all targets at the reconnaissance moment with the reconnaissance coordinates includes: Calculating the distance between the predicted coordinates of all targets at the time of reconnaissance and the reconnaissance coordinates; The target with the shortest distance between the predicted coordinates at the reconnaissance moment and the reconnaissance coordinates is taken as the matching target.

4. The method according to claim 3, characterized in that The attribute information of the reconnaissance target determined based on the matching results includes: The attribute information of the matching target is assigned to the reconnaissance target, thereby obtaining the attribute information of the reconnaissance target.

5. The method according to claim 2, characterized in that If the number of situation points in the target's situation sequence meets the preset threshold, the Kalman filter algorithm is used to predict the target's trajectory and obtain the predicted coordinates of the target at the time of reconnaissance. The specific steps include: Input all situation points of the situation sequence of the target that is greater than or equal to the situation point threshold into the initial Kalman filter model, and update the Kalman gain of the initial Kalman filter model based on the situation sequence to obtain the final Kalman model; The situation information of the last situation point in the situation sequence and the time interval between the reception time and the reconnaissance time of the last situation point are input into the final Kalman model to obtain the coordinates of the target at the reconnaissance time.

6. The method according to claim 5, characterized in that The Kalman gain of the initial Kalman filter model is updated based on the situation sequence to obtain the final Kalman model, which includes: Starting from the second situation point, perform the following operations on each situation point in the situation sequence: The coordinates of the situation point at the previous moment and the reception time are input into the Kalman filter model to calculate the coordinate estimate at the current moment; Taking the coordinates of the situation point at the current moment as coordinate observation values, and updating the Kalman gain based on the coordinate observation values and the coordinate estimation value; The last updated Kalman gain is used as the final gain of the Kalman filter model to obtain the final Kalman model.

7. The method according to claim 6, characterized in that The situation information of the last situation point in the situation sequence and the time interval between the reception time and the reconnaissance time of the last situation point are input into the final Kalman model to obtain the coordinates of the target at the reconnaissance time as shown in the following formula: X=x f +k·v f ·Δt1·cosθ f Y=y f +k·v f ·Δt1·sinθ f Among them, X and Y are the coordinates of the target at the time of reconnaissance, x f 、y f is the coordinate of the last situation point, v f is the target speed at the last situation point receiving moment, θ f is the steering angle at the moment of receiving the last situation point, Δt is the time interval between the moment of receiving the last situation point and the reconnaissance moment, and k is the Kalman gain.

8. The method according to claim 7, characterized in that The target speed at the moment of receiving the last situation point is as follows: Among them, v x,f is the x-axis component of the target velocity at the moment of receiving the last situation point, v y,f is the y-axis component of the target velocity at the moment of receiving the last situation point, Δt2 is the time interval between the last situation point and the previous situation point, x f-1 、y f-1 The coordinates of the last situation point at the previous moment; The steering angle at the moment of receiving the last situation point is as follows:

9. The method according to claim 8, characterized in that The situation point coordinates in the situation sequence are longitude and latitude coordinates; before the Kalman gain of the initial Kalman filter model is updated based on the situation sequence to obtain the final Kalman model, the method further includes: Convert the coordinates of the situation points in the situation sequence into rectangular coordinates.

10. The method according to claim 2, characterized in that The situation point threshold is 10.

Images