CN-121977569-A - Cabin door positioning method and device based on confidence fusion and related equipment

CN121977569ACN 121977569 ACN121977569 ACN 121977569ACN-121977569-A

Abstract

The disclosure provides a cabin door positioning method and device based on confidence fusion and related equipment, and relates to the technical field of cabin door positioning. The method comprises the steps of obtaining movement information of a boarding bridge and environment information of an environment where the boarding bridge is located, determining a plurality of confidences according to the movement information and/or the environment information, fusing the confidences to obtain comprehensive confidences, and obtaining cabin door feature point coordinate information based on first coordinate information and/or second coordinate information according to a decision mechanism set by combining the comprehensive confidences, wherein the first coordinate information is cabin door feature point coordinate information obtained through a visual odometer, and the second coordinate information is cabin door feature point coordinate information obtained based on a cabin door identification model. The method and the device can retain the advantages of accurately predicting the cabin door coordinate information by the model and estimating the cabin door coordinate in real time by visual tracking, quickly obtain more accurate cabin door coordinate information and give consideration to accuracy and high efficiency.

Inventors

HUANG XIANGYE
DENG LAN
Xu Chuixiao
LI SHIPENG
LIN RUIBIAO
TANG YAN
LEI ANLIANG

Assignees

深圳中集天达空港设备有限公司
中国国际海运集装箱(集团)股份有限公司

Dates

Publication Date: 20260505
Application Date: 20260204

Claims (13)

1. The cabin door positioning method based on confidence fusion is characterized by comprising the following steps of: acquiring motion information of a boarding bridge and environment information of an environment where the boarding bridge is located; determining a plurality of confidence parameters according to the motion information and/or the environment information; fusing the confidence parameters to obtain comprehensive confidence; And according to the comprehensive confidence and a set decision mechanism, acquiring cabin door characteristic point coordinate information based on first coordinate information and/or second coordinate information, wherein the first coordinate information is cabin door characteristic point coordinate information acquired through a visual odometer, and the second coordinate information is cabin door characteristic point coordinate information acquired based on a cabin door identification model.
2. The cabin door positioning method based on confidence fusion according to claim 1, wherein the obtaining cabin door feature point coordinate information based on the first coordinate information and/or the second coordinate information according to the comprehensive confidence in combination with the set decision mechanism comprises: If the comprehensive confidence coefficient is smaller than a first threshold value, the second coordinate information is directly determined to be cabin door feature point coordinate information; if the comprehensive confidence coefficient is larger than a second threshold value, the first coordinate information is directly determined to be cabin door feature point coordinate information, and the second threshold value is larger than the first threshold value; and if the comprehensive confidence coefficient is larger than or equal to a first threshold value and smaller than or equal to a second threshold value, fusing the first coordinate information and the second coordinate information to obtain the cabin door feature point coordinate information.
3. The cabin door positioning method based on confidence fusion according to claim 2, wherein the fusing the first coordinate information and the second coordinate information to obtain cabin door feature point coordinate information comprises: determining first weight information and second weight information, wherein the first weight information is weight information corresponding to the first coordinate information, and the second coordinate information is weight information corresponding to the second coordinate information; and carrying out weighted summation on the first coordinate information and the second coordinate information according to the first weight information and the second weight information to obtain the fused cabin door characteristic point coordinate information.
4. A door positioning method based on confidence fusion according to claim 3, wherein the first coordinate information and the second coordinate information are weighted and summed by the following formula: ; ; Wherein, the Representing the coordinate information of the feature points of the cabin door after fusion; representing second coordinate information; representing first coordinate information; Fusion weights representing the second coordinate information; fusion weights representing the first coordinate information; Representing the integrated confidence; and a coefficient is represented, and the value is 0-1.
5. A door positioning method based on confidence fusion according to claim 3, wherein the first coordinate information and the second coordinate information are weighted and summed by the following formula: ; ; Wherein, the Representing the coordinate information of the feature points of the fused cabin door; Representing cabin door characteristic point coordinate information, namely second coordinate information, obtained based on a cabin door identification model; The method comprises the steps of representing cabin door characteristic point coordinate information obtained through a visual odometer, namely first coordinate information; An evaluation score representing the model predictive result; an evaluation score representing the visual tracking result; Representing the evaluation score corresponding to the coordinate fusion.
6. The confidence fusion-based door positioning method according to claim 1, further comprising: acquiring a camera rotation matrix and a camera translation vector of a current frame cabin door image; and determining the coordinate information of the cabin door feature points in the current frame cabin door image according to the camera rotation matrix and the camera translation vector of the current frame cabin door image, the coordinate information of the cabin door feature points in the reference frame cabin door image, and the camera rotation matrix and the camera translation vector of the reference frame cabin door image, so as to obtain the first coordinate information.
7. The door positioning method based on confidence fusion according to any one of claims 1 to 6, wherein the plurality of confidence parameters comprises at least one of spatial consistency confidence, texture clarity confidence, historical accuracy confidence, environmental adaptability confidence, binocular matching confidence.
8. The door positioning method based on confidence fusion according to claim 7, wherein the comprehensive confidence is calculated by the following formula: ; Wherein, the Representing the integrated confidence; representing spatial consistency confidence; Representing texture clarity confidence; Representing historical accuracy confidence; Representing an environmental suitability confidence level; Representing confidence of binocular matching; fusion weights representing spatial consistency confidence; fusion weights representing texture sharpness confidence; Fusion weights representing historical accuracy confidence; Fusion weights representing the confidence of environmental suitability; and fusion weights representing confidence of binocular matching.
9. The door positioning method based on confidence fusion according to claim 8, wherein the spatial consistency confidence is calculated by the following formula Texture definition confidence Confidence of historical accuracy Environmental suitability confidence Confidence of binocular matching : ; ; ; ; ; Wherein, the Represent the first Pose information of the frame; represent the first Pose information of the frame; Representing a scale parameter; Representing an image For reflecting edge texture information of the image; representing the maximum value of the image gradient; Representing norms of the image gradient matrix; A frame number representing a sliding window; A frame number representing the current frame; representing a frame number within the sliding window; represent the first Frame tracking to obtain cabin door characteristic point coordinate information; represent the first Cabin door characteristic point coordinate information of frame reference; representing the intensity of the rain and fog environment; represent the first A feature point set of a frame binocular system; represent the first A feature point set of a frame binocular system; Representing the cross-over ratio.
10. Cabin door positioner based on confidence fuses, characterized by comprising: The data acquisition module is used for acquiring the motion information of the boarding bridge and the environment information of the environment where the boarding bridge is located; The confidence coefficient determining module is used for determining a plurality of confidence coefficient parameters according to the motion information and/or the environment information; the confidence coefficient fusion module is used for fusing the plurality of confidence coefficient parameters to obtain comprehensive confidence coefficient; The cabin door coordinate information determining module is used for obtaining cabin door characteristic point coordinate information based on first coordinate information and/or second coordinate information according to the comprehensive confidence degree combined with a set decision mechanism, wherein the first coordinate information is cabin door characteristic point coordinate information obtained through a visual odometer, and the second coordinate information is cabin door characteristic point coordinate information obtained based on a cabin door identification model.
11. An electronic device, comprising: processor, and A memory for storing executable instructions of the processor; wherein the processor is configured to perform the confidence fusion based door positioning method of any of claims 1 to 9 via execution of the executable instructions.
12. A computer readable storage medium having stored thereon a computer program, which when executed by a processor implements the confidence fusion based door positioning method of any of claims 1 to 9.
13. A computer program product comprising a computer program or instructions, characterized in that the computer program or instructions, when executed by a processor, implements the confidence fusion based door positioning method of any of claims 1 to 9.

Description

Cabin door positioning method and device based on confidence fusion and related equipment Technical Field The disclosure relates to the technical field of cabin door positioning, in particular to a cabin door positioning method and device based on confidence fusion and related equipment. Background The boarding bridge is used for connecting a boarding gate of a terminal building with a cabin door of an airplane, is special docking equipment for serving the airplane, and can provide a safe and efficient passage for personnel/goods. During the operation of the boarding bridge docking the door, it is necessary to quickly and accurately locate the position of the door so that the boarding bridge is automatically docked with the door. The cabin door positioning method provided in the related art has the problem that real-time performance and positioning accuracy are difficult to achieve. It should be noted that the information disclosed in the above background section is only for enhancing understanding of the background of the present disclosure and thus may include information that does not constitute prior art known to those of ordinary skill in the art. Disclosure of Invention The disclosure provides a cabin door positioning method, a cabin door positioning device and related equipment based on confidence fusion, which at least overcome the technical problems that the cabin door positioning method provided in the related technology is difficult to achieve real-time performance and positioning accuracy. Other features and advantages of the present disclosure will be apparent from the following detailed description, or may be learned in part by the practice of the disclosure. According to one aspect of the disclosure, a cabin door positioning method based on confidence coefficient fusion is provided, and the cabin door positioning method comprises the steps of obtaining motion information of a boarding bridge and environment information of the environment where the boarding bridge is located, determining a plurality of confidence coefficient parameters according to the motion information and/or the environment information, fusing the confidence coefficient parameters to obtain comprehensive confidence coefficient, and obtaining cabin door feature point coordinate information based on first coordinate information and/or second coordinate information according to a decision mechanism set by combining the comprehensive confidence coefficient, wherein the first coordinate information is cabin door feature point coordinate information obtained through a visual odometer, and the second coordinate information is cabin door feature point coordinate information obtained based on a cabin door recognition model. In some embodiments, the cabin door feature point coordinate information is obtained based on the first coordinate information and/or the second coordinate information according to the set decision mechanism combined with the comprehensive confidence coefficient, and the method comprises the steps of directly determining the second coordinate information as fused cabin door feature point coordinate information if the comprehensive confidence coefficient is smaller than a first threshold value, directly determining the first coordinate information as fused cabin door feature point coordinate information if the comprehensive confidence coefficient is larger than the first threshold value, wherein the second threshold value is larger than the first threshold value, and fusing the first coordinate information and the second coordinate information to obtain fused cabin door feature point coordinate information if the comprehensive confidence coefficient is larger than or equal to the first threshold value and smaller than or equal to the second threshold value. In some embodiments, fusing the first coordinate information and the second coordinate information to obtain fused cabin door feature point coordinate information includes determining first weight information and second weight information, wherein the first weight information is weight information corresponding to the first coordinate information, the second coordinate information is weight information corresponding to the second coordinate information, and weighting and summing the first coordinate information and the second coordinate information according to the first weight information and the second weight information to obtain fused cabin door feature point coordinate information. In some embodiments, the first coordinate information and the second coordinate information are weighted summed by the following formula:; Wherein, the method comprises the steps of, Representing the coordinate information of the feature points of the cabin door after fusion; representing second coordinate information; representing first coordinate information; Fusion weights representing the second coordinate information; fusion weights representing the first coordinate info