CN-122024093-A - Weather identification method and device, aircraft and storage medium

Abstract

The invention relates to the technical field of aircraft data processing, and discloses a weather identification method, a weather identification device, an aircraft and a storage medium. The method comprises the steps of acquiring environment images acquired from at least one acquisition view angle of an aircraft, determining an image weather result according to all environment images, determining the number of point cloud noise points according to radar point cloud data of a plurality of point cloud acquisition points in a preset acquisition range when the image weather result is rainy weather or foggy weather, determining a radar weather result according to the number of point cloud noise points, and determining a flying weather identification result of the aircraft according to the image weather result and the radar weather result. According to the invention, data analysis of different processes is carried out on the environmental image data and the radar point cloud data, and the flight weather identification result is obtained through comparison and fusion of analysis results, so that multi-dimensional cross verification is realized, the environmental weather state can be identified accurately in real time, the reliability and fault tolerance of weather identification are improved, and the flight safety of an aircraft is ensured.

Inventors

• SU QINGPENG
• ZHOU XIN

Assignees

• 广东高域科技有限公司

Dates

Publication Date

20260512

Application Date

20251219

Claims (10)

1. 1. A method of weather identification, comprising: acquiring environment images acquired at least one acquisition view angle of an aircraft, and determining an image weather result according to all the environment images; when the image weather result is rainy weather or foggy weather, determining the number of point cloud noise points according to the radar point cloud data of a plurality of point cloud acquisition points in a preset acquisition range, and determining the radar weather result according to the number of point cloud noise points; and determining a flying weather identification result of the aircraft according to the image weather result and the radar weather result.
2. 2. The weather identification method as claimed in claim 1, wherein said determining an image weather result from all of said environmental images comprises: performing image recognition processing on the environment images acquired by each acquisition view angle through a preset weather classification model to obtain weather initial results of each acquisition view angle; smoothing the weather initial result and the historical weather initial result of each acquisition view angle to obtain a weather smoothing result of each acquisition view angle, wherein the historical weather initial result refers to weather initial results of the acquisition view angle at a plurality of historical moments in a preset historical time period; According to the weather smoothing result of each acquired visual angle, determining the visual angle weather result of each acquired visual angle; and determining an image weather result according to the visual angle weather results of all the acquired visual angles.
3. 3. The method of claim 2, wherein determining the perspective weather results for each of the collection perspectives based on the weather smoothing results for each of the collection perspectives comprises: For each acquisition view angle, obtaining a prediction type probability corresponding to each preset weather type in the weather smoothing result; Determining a predictive type Boolean value corresponding to each preset weather type according to the predictive type probability corresponding to each preset weather type and a preset type probability threshold; and determining the visual angle weather result of the acquisition visual angle according to the predictive type Boolean values corresponding to all the preset weather types.
4. 4. The weather identification method of claim 2, wherein the visual angle weather result comprises a predicted type boolean value corresponding to a plurality of preset weather types, the preset weather types comprising rainy weather and foggy weather; the determining the image weather result according to all the view angle weather results of the acquired view angles comprises the following steps: when the predictive type Boolean value corresponding to the rainy weather in the visual angle weather results of at least one acquired visual angle is 1, determining that the image weather result is rainy weather; and when the predicted type Boolean value corresponding to the rainy weather in all the view angle weather results of the acquired view angles is 0 and the predicted type Boolean value corresponding to the foggy weather in at least one view angle weather result of the acquired view angles is 1, determining that the image weather result is foggy weather.
5. 5. The weather identification method of claim 1, wherein the number of point cloud noise points comprises a number of interval noise points of a plurality of point cloud annular intervals; the determining the number of the point cloud noise points according to the radar point cloud data of a plurality of point cloud acquisition points in a preset acquisition range comprises the following steps: Carrying out flatness analysis on the radar point cloud data of each point cloud acquisition point and the radar point cloud data of a preset number of point cloud acquisition points adjacent to the point cloud acquisition point, and obtaining an acquisition point label of the point cloud acquisition point based on a flatness analysis result; dividing a preset acquisition range into a plurality of point cloud annular intervals based on preset interval distances, and determining the number of all the point cloud acquisition points with acquisition point labels in each point cloud annular interval as noise point labels as the interval noise point number of each point cloud annular interval.
6. 6. The method of weather identification of claim 5, wherein said determining radar weather results from said number of point cloud noise points comprises: Determining a noise number comparison value according to the point cloud noise number in the first preset distance range and the point cloud noise number in the preset acquisition range; If the noise quantity comparison value is larger than a preset comparison threshold value, determining that a radar weather result is foggy weather, and determining radar foggy weather visibility in the radar weather result according to radar point cloud data of all point cloud acquisition points of which the acquisition point labels are noise point labels; If the noise quantity comparison value is smaller than or equal to a preset comparison threshold value, determining that a radar weather result is rainy weather, and determining radar rainfall in the radar weather result according to the interval noise quantity of all the point cloud annular intervals in a second preset distance range; The radar foggy weather visibility is determined according to noise depth values of all the point cloud acquisition points of which the acquisition point tag is a noise point tag and a preset noise point fractional bit threshold, the noise depth value of each point cloud acquisition point is determined according to radar point cloud data of the point cloud acquisition point, the radar rainfall is determined according to interval rainfall of all the point cloud annular intervals, the interval rainfall of each point cloud annular interval is obtained by converting interval point cloud noise density of the point cloud annular interval, and the interval point cloud noise density of each point cloud annular interval is determined according to interval noise number and annular interval volume of the point cloud annular interval.
7. 7. The weather identification method as claimed in claim 1, wherein the determining a flying weather identification result of the aircraft based on the image weather result and the radar weather result comprises: When the image weather result and the radar weather result are both foggy weather, determining a flying weather identification result as foggy weather, and determining radar foggy weather visibility in the radar weather result as foggy weather visibility in the flying weather identification result; When the image weather result and the radar weather result are both rainy weather, determining a flying weather identification result as rainy weather, and determining a rainfall level in the flying weather identification result according to radar rainfall in the radar weather result; When the image weather result is rainy weather and the radar weather result is foggy weather, determining a flying weather identification result as rainy weather, and determining a rainfall level in the flying weather identification result as a light rain level; And when the image weather result is foggy weather and the radar weather result is rainy weather, determining the flying weather identification result as foggy weather.
8. 8. A weather identification device, comprising: The image recognition module is used for acquiring environment images acquired at least one acquisition view angle of the aircraft and determining an image weather result according to all the environment images; The radar identification module is used for determining the number of the point cloud noise points according to the radar point cloud data of a plurality of point cloud acquisition points in a preset acquisition range when the image weather result is rainy weather or foggy weather, and determining the radar weather result according to the number of the point cloud noise points; And the comparison analysis module is used for determining a flying weather identification result of the aircraft according to the image weather result and the radar weather result.
9. 9. An aircraft comprising a processor and a memory, wherein, A memory for storing a computer program; A processor for executing a program stored on a memory to implement the weather identification method of any one of claims 1-7.
10. 10. A computer-readable storage medium storing computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform the weather identification method of any of claims 1-7.

Description

Weather identification method and device, aircraft and storage medium Technical Field The invention relates to the technical field of aircraft data processing, in particular to a weather identification method and device, an aircraft and a storage medium. Background The aircraft is easily influenced by weather changes in the low-altitude airspace flight process, particularly in a rainy and foggy weather, water drops in the air can reduce the visibility, so that the visual field and the obstacle detection capability of the aircraft are influenced. In the prior art, the aircraft carries out weather identification based on images acquired by the visual sensors, the definition of the images is greatly influenced by severe weather such as rain and fog, and the image transmission communication link is limited, so that the reliability of the weather identification method based on a single visual sensor is insufficient, and the identification accuracy under the condition of severe weather is reduced. Disclosure of Invention Based on the foregoing, it is necessary to provide a weather identification method, apparatus, aircraft and storage medium, so as to solve the problems of insufficient reliability and low accuracy of the existing weather identification. A weather identification method, comprising: acquiring environment images acquired at least one acquisition view angle of an aircraft, and determining an image weather result according to all the environment images; when the image weather result is rainy weather or foggy weather, determining the number of point cloud noise points according to the radar point cloud data of a plurality of point cloud acquisition points in a preset acquisition range, and determining the radar weather result according to the number of point cloud noise points; and determining a flying weather identification result of the aircraft according to the image weather result and the radar weather result. A weather identification device, comprising: The image recognition module is used for acquiring environment images acquired at least one acquisition view angle of the aircraft and determining an image weather result according to all the environment images; The radar identification module is used for determining the number of the point cloud noise points according to the radar point cloud data of a plurality of point cloud acquisition points in a preset acquisition range when the image weather result is rainy weather or foggy weather, and determining the radar weather result according to the number of the point cloud noise points; And the comparison analysis module is used for determining a flying weather identification result of the aircraft according to the image weather result and the radar weather result. An aircraft comprising a processor and a memory, wherein, A memory for storing a computer program; and the processor is used for executing the program stored in the memory to realize the weather identification method. A computer-readable storage medium storing computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform a weather identification method as described above. According to the weather identification method, the weather identification device, the aircraft and the storage medium, the environment images acquired from at least one acquisition view angle of the aircraft are acquired, the image weather results are determined according to all the environment images, when the image weather results are rainy weather or foggy weather, the number of point cloud noise points is determined according to radar point cloud data of a plurality of point cloud acquisition points in a preset acquisition range, the radar weather results are determined according to the number of the point cloud noise points, and the flying weather identification result of the aircraft is determined according to the image weather results and the radar weather results. The invention combines the image sensor and the radar sensor to collect the environmental data together for weather identification, thereby avoiding the problem of insufficient reliability of weather identification of a single sensor. Meanwhile, the invention carries out data analysis of different processes on the environmental image data and the radar point cloud data based on a redundancy mechanism, and obtains the flying weather identification result through comparison and fusion of analysis results, thereby realizing multi-dimensional cross verification, being capable of accurately identifying the environmental weather state in real time, improving the reliability and fault tolerance of weather identification and ensuring the flying safety of the aircraft. Drawings In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments of the present invention will be briefly described below