CN-121997113-A - Target identification method and system based on multi-source information fusion

CN121997113ACN 121997113 ACN121997113 ACN 121997113ACN-121997113-A

Abstract

The application provides a target identification method and system based on multi-source information fusion, and relates to the technical field of low-altitude target detection. The method comprises the steps of obtaining target radar track data, interception equipment track data and area information data, extracting first features in RCS form dimensions and second features in motion dimensions based on the target radar track data, determining spectrum interception correlation factors and area information features based on the target radar track data and interception equipment track data, carrying out feature fusion on the first features, the second features, the spectrum interception correlation factors and the area information features to obtain target features, identifying target types, and identifying target threat levels based on the target types and the target radar track data. The method is used for the target recognition process based on multi-source information fusion, and solves the technical problem that the target threat degree cannot be accurately recognized in a complex environment in the prior art.

Inventors

SHI YIREN
ZUO JINGKUN
ZHU YUE
QI LIN
CHEN LONG

Assignees

四创电子股份有限公司

Dates

Publication Date: 20260508
Application Date: 20251210

Claims (10)

1. The target identification method based on multi-source information fusion is characterized by comprising the following steps of: acquiring target radar track data, interception equipment track data and array region information data; Extracting a first feature in an RCS form dimension and extracting a second feature in a motion dimension based on the target radar track data; determining a spectrum interception correlation factor and a regional array land information characteristic based on the target radar track data and the interception equipment track data; performing feature fusion on the first feature, the second feature, the spectrum interception correlation factor and the regional array information feature to obtain a target feature, and identifying a target type; and identifying a target threat level based on the target type and the target radar track data.
2. The method for identifying a target based on multi-source information fusion according to claim 1, wherein the extracting a first feature in an RCS morphology dimension and a second feature in a motion dimension based on the target radar track data comprises: Based on target radar track data, extracting the height, speed, amplitude, azimuth width and azimuth thickness of N frames of the target radar track data and the times that a target passes through a preset event point in the RCS form dimension to construct a feature set; Based on the feature set, performing feature dimension reduction through principal component analysis to obtain a first feature; and extracting the average speed, the speed standard deviation, the course deflection standard deviation, the maneuvering factor and the oscillation frequency of the target in the motion dimension based on the target radar track data to obtain a second characteristic.
3. The method of claim 2, wherein the magnitude is obtained by dividing the original magnitude of each data point by a distance decay coefficient, the magnitude The following formula is satisfied: wherein, amp is the original amplitude of the target; Is a standardized distance; is the target distance; Is the attenuation coefficient, m is the influence factor of short and long pulse M is 0 at long pulse coverage, when In the case of a short pulse coverage area, 。
4. The multi-source information fusion-based object recognition method according to claim 2, wherein the average speed The following formula is satisfied: Wherein, the Representing the i-th frame target radar track data, The speed of the target radar track of the ith frame; the standard deviation of the speed The following formula is satisfied: Wherein, the Representing the i-th frame target radar track data, For the speed of the i-frame target radar track, Is the average speed; the heading deflection standard deviation The following formula is satisfied: Wherein, the Representing the i-th frame target radar track data, For the heading deflection standard deviation threshold value, For the i-frame target radar track heading deflection value, The course deflection mean value of the target radar track is used; The maneuver factors satisfy the following formula : Wherein, the In order to be able to achieve an average speed, The standard deviation of course deflection; The oscillation frequency The following formula is satisfied : Wherein, the And (5) indicating whether the radar track of the target unmanned aerial vehicle in the ith frame meets the vibration mode condition or not, wherein N is a sampling point.
5. The method for identifying a target based on multi-source information fusion according to claim 1, wherein the feature fusion is performed on the first feature, the second feature, the spectrum sensing correlation factor and the regional array information feature to obtain a target feature, and identifying a target type comprises: Performing feature stitching on the first feature, the second feature, the spectrum interception correlation factor and the regional array information feature to obtain a target feature; The method comprises the steps of inputting target characteristics into a trained machine learning model, and identifying target types, wherein the machine learning model is obtained through supervised training of a data set with target type labels constructed through historical data, and the target types comprise unmanned aerial vehicles, birds, planes, vehicles, flying objects and others.
6. The target recognition method based on multi-source information fusion according to claim 1, wherein the spectrum sensing factor is obtained by calculating a correlation distance and a bearing in time synchronization of sensing data and radar data; For protocol targets, the spectrum sensing correlation factor The following formula is satisfied: Wherein, the To listen to the position coordinates of the object in the data, For the position coordinates of the target in the radar data, A preset distance threshold is set; For non-protocol targets, the spectrum sensing correlation factor The following formula is satisfied: Wherein, the For the directional angle of the target in the radar data, In order to sense the directional angle of the target in the data, Is a preset direction angle threshold.
7. The method for identifying a target based on multi-source information fusion according to claim 1, wherein identifying a target threat level based on the target type and the target radar track data comprises: Determining a target threat score based on the heading, speed, and distance in the target radar track data; And matching the target threat score with the preset threat level of the target type to determine the target threat level.
8. The multi-source information fusion-based target recognition method of claim 7, wherein the target threat score The following formula is satisfied: Wherein, the For the heading threat score weight, For the speed threat score weight, The distance threat score weight, the sum of the three weights is 1; for the heading threat score, For the speed threat score to be a speed threat score, A value of 0-100 is used as a distance threat score; Is the standard value of the heading, As the standard value of the speed, Is a distance standard value; as the value of the heading, As a value of the velocity it is, Is a distance value.
9. A target recognition system based on multi-source information fusion, which is used for realizing the method of any one of claims 1-8, and is characterized by comprising a data acquisition module and electronic equipment; The data acquisition module is used for acquiring target radar track data, interception equipment track data and array region information data; The electronic equipment is used for extracting a first feature in an RCS form dimension and a second feature in a motion dimension based on the target radar track data, determining a spectrum interception correlation factor and a regional array information feature based on the target radar track data and the interception equipment track data, carrying out feature fusion on the first feature, the second feature, the spectrum interception correlation factor and the regional array information feature to obtain a target feature and identifying a target type, and identifying a target threat level based on the target type and the target radar track data.
10. The multi-source information fusion-based object recognition system of claim 9, wherein the electronic device is further configured to: Based on target radar track data, extracting the height, speed, amplitude, azimuth width and azimuth thickness of N frames of the target radar track data and the times that a target passes through a preset event point in the RCS form dimension to construct a feature set; Based on the feature set, performing feature dimension reduction through principal component analysis to obtain a first feature; and extracting the average speed, the speed standard deviation, the course deflection standard deviation, the maneuvering factor and the oscillation frequency of the target in the motion dimension based on the target radar track data to obtain a second characteristic.

Description

Target identification method and system based on multi-source information fusion Technical Field The application relates to the technical field of low-altitude target detection, in particular to a target identification method and system based on multi-source information fusion. Background With the continuous increase of the low-altitude activity density, various low-speed targets and airspace targets are increasingly complex in number, type and behavior mode, and higher recognition and safety management pressures are brought to a monitoring system. In practical application, the motion behavior of the target is changeable, radar observation characteristics are easily influenced by factors such as environment, topography, equipment performance and the like, so that the state of the target is unstable and uncertain, often only basic attribute judgment can be carried out on the target, and potential dangerous degrees are difficult to accurately distinguish according to the actual behavior characteristics and airspace situation of the target, so that whether the target possibly forms a threat is difficult to timely and accurately evaluate in a complex scene. Therefore, how to accurately identify the threat level of the target in a complex environment is a problem to be solved in the related art. Disclosure of Invention The application provides a target identification method and a target identification system based on multi-source information fusion, which solve the technical problem that the prior art cannot accurately identify the threat degree of a target in a complex environment. In order to achieve the above purpose, the application adopts the following technical scheme: The method comprises the steps of obtaining target radar track data, interception equipment track data and array region information data, extracting first features in RCS form dimensions and second features in motion dimensions based on the target radar track data, determining spectrum interception correlation factors and area array region information features based on the target radar track data and the interception equipment track data, carrying out feature fusion on the first features, the second features, the spectrum interception correlation factors and the area array region information features to obtain target features, identifying target types, and identifying target threat levels based on the target types and the target radar track data. With reference to the first aspect, in one possible implementation manner, extracting the first feature in the RCS form dimension and the second feature in the motion dimension based on the target radar track data includes extracting the height, the speed, the amplitude, the azimuth width, the azimuth thickness of the N frames of the target radar track data and the number of times that the target passes through the preset event point in the RCS form dimension based on the target radar track data, constructing a feature set, performing feature dimension reduction by principal component analysis based on the feature set to obtain the first feature, and extracting the average speed, the speed standard deviation, the heading deflection standard deviation, the maneuvering factor and the oscillation frequency of the target in the motion dimension based on the target radar track data to obtain the second feature. In one possible implementation, the amplitude is obtained by dividing the original amplitude of each data point by the distance decay coefficient, the amplitudeThe following formula is satisfied: wherein, amp is the original amplitude of the target; Is a standardized distance; is the target distance; Is the attenuation coefficient, m is the influence factor of short and long pulse M is 0 at long pulse coverage, whenIn the case of a short pulse coverage area,。 In one possible implementation, the average speedThe following formula is satisfied: Wherein, the Representing the i-th frame target radar track data,The speed of the target radar track of the ith frame; with reference to the first aspect, in one possible implementation manner, the speed standard deviation The following formula is satisfied: Wherein, the Representing the i-th frame target radar track data,For the speed of the i-frame target radar track,Is the average speed; In one possible implementation, the heading deflection standard deviation The following formula is satisfied: Wherein, the Representing the i-th frame target radar track data,For the heading deflection standard deviation threshold value,For the i-frame target radar track heading deflection value,The course deflection mean value of the target radar track is used; in one possible implementation, the maneuver factor satisfies the following formula : Wherein, the In order to be able to achieve an average speed,The standard deviation of course deflection; In one possible implementation, the oscillation frequency The following formula is satisfied: Wherein, the And (5) ind