CN112419790B - Airplane berth departure state detection method - Google Patents
Airplane berth departure state detection method Download PDFInfo
- Publication number
- CN112419790B CN112419790B CN202011220679.7A CN202011220679A CN112419790B CN 112419790 B CN112419790 B CN 112419790B CN 202011220679 A CN202011220679 A CN 202011220679A CN 112419790 B CN112419790 B CN 112419790B
- Authority
- CN
- China
- Prior art keywords
- aircraft
- airplane
- detecting
- aircraft nose
- bridge
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G5/00—Traffic control systems for aircraft, e.g. air-traffic control [ATC]
- G08G5/0073—Surveillance aids
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a method for detecting the departure state of an airplane berth, which comprises the following steps: acquiring parking space scene point cloud data; the method comprises the following steps of defining a corridor bridge area according to the intersection point of a stop line and a parking space central line of a model to be detected, the corridor bridge ground clearance and the aircraft body length constraint, detecting a corridor bridge and aircraft nose point cloud target in a segmentation and clustering mode in the corridor bridge area, and judging the corridor bridge connection state; detecting the aircraft nose of the aircraft at the current parking position based on a pre-trained aircraft nose detection model; detecting in real time to track the current spatial position of the aircraft nose; and calculating the ratio of the intersection part of the detection frame area of the aircraft nose and the parking space area to the aircraft nose detection frame, and if the ratio is smaller than a set threshold value, judging that the departure state of the aircraft is finished. The invention automatically acquires the departure state of the airplane position gallery bridge and the airplane, avoids the limitation of manual detection, realizes the monitoring of the whole node time period and improves the operation efficiency of the airplane position management and control system.
Description
Technical Field
The invention belongs to the technical field of airplane berth management and control, and particularly relates to a method for detecting an departure state of an airplane berth.
Background
The airport information integration system is a man-machine conversation command system which takes a laser radar and a camera as front-end sensing, realizes functions of airport monitoring, guiding, early warning and the like, and is linked with the airport information integration system. The system can effectively improve the utilization rate of the airport station resources, reduce flight delay and comprehensively improve the management level of the airport station.
In recent years, the four-type airport construction action outline printed by the civil aviation administration puts forward a requirement for ensuring low-carbon and high-efficiency operation of an airport, and the operation efficiency of an airport directly determines the operation management level of the airport by taking a station as a starting point and a stopping point of a flight plan.
The mainstream machine position management and control system in the existing market mainly only provides an airplane berth guiding function, and the machine position gallery bridge is required to be withdrawn, the airplane leaves a port and other states are required to be obtained, so that manual detection is mostly relied on, and certain limitation is realized.
Disclosure of Invention
In view of the defects of the prior art, the present invention aims to provide a method for detecting an aircraft berthing departure state, so as to automatically acquire an aircraft berth bridge and an aircraft departure state, avoid the limitation of manual detection, realize the monitoring in a full-node time period, and improve the operation efficiency of an aircraft berth management and control system.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
the invention discloses a method for detecting the departure state of an airplane berth, which comprises the following steps:
1) acquiring parking space scene point cloud data;
2) defining a corridor bridge area according to the intersection point of a stop line of a machine type to be detected and a parking space central line, the ground clearance of a corridor bridge and the length constraint of an airplane body, detecting a point cloud target of the corridor bridge and an airplane nose in a segmentation and clustering manner in the corridor bridge area, and judging the connection state of the corridor bridge;
3) detecting the aircraft nose of the aircraft at the current parking position based on a pre-trained aircraft nose detection model;
4) detecting in real time to track the current spatial position of the aircraft nose;
5) and (4) calculating the ratio of the intersection part of the detection frame area of the aircraft nose and the parking space area to the aircraft nose detection frame, if the ratio is smaller than a set threshold value, judging that the departure state of the aircraft is finished, and if the ratio is larger than or equal to the threshold value, returning to the step 4).
Further, the step 1) specifically includes: the machine position management and control system receives the departure detection instruction, starts the multi-thread laser radar to capture the laser data of the machine position scene, and analyzes and converts the laser data into point cloud format data.
Further, the step 2) specifically includes:
21) processing scene point cloud data by adopting a straight-through filtering algorithm according to the intersection point of the stop line of the machine type to be detected and the center line of the parking space, the ground clearance of the corridor bridge and the constraint parameters of the length of the airplane body so as to filter out the spatial position area of the corridor bridge;
22) dividing gallery bridge space point cloud data according to the precision value of the spacing distance between the gallery bridge and the aircraft at the connection position when the gallery bridge is in a set critical disconnection state and by combining the normal vector included angle of each area surface;
23) clustering the point cloud data of each part, and detecting and extracting the aircraft nose and the gallery bridge target;
24) and calculating the space distance between the aircraft nose and the gallery bridge target to judge the gallery bridge connection state.
Further, the step 3) specifically includes:
31) acquiring airplane data of various airplane types of the station, and carrying out sample labeling and sample label adding on an airplane nose;
32) cutting, zooming and rotating the marked sample to enhance image data;
33) extracting HAAR characteristics of the data-enhanced sample, and training based on an enhanced learning (adaboost) algorithm to obtain an aircraft nose detection model;
34) and detecting the aircraft nose of the aircraft at the current parking position by using a pre-trained aircraft nose detection model.
Further, the step 4) specifically includes: and continuously detecting according to the motion state of the airplane at the parking position in the video by the aid of a Kalman filtering algorithm to track the spatial position of the nose of the airplane.
The invention has the beneficial effects that:
the invention expands the function of the airport management and control system, integrates the sensing capability of the laser radar and the camera, improves the operating efficiency of the airport apron and ensures the safety of the airport apron.
Drawings
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a schematic diagram of a cloud of points in a corridor bridge space area according to the present invention;
FIG. 3 is a schematic diagram of a point cloud of a corridor bridge broken state in the invention;
FIG. 4 is a schematic view of IOU computation;
FIG. 5a is a view of an aircraft in port according to the present invention;
FIG. 5b is a diagram of the departure state of the aircraft according to the present invention.
Detailed Description
In order to facilitate understanding of those skilled in the art, the present invention will be further described with reference to the following examples and drawings, which are not intended to limit the present invention.
Referring to fig. 1, the method for detecting the departure state of the airplane berth according to the present invention includes the following steps:
step S1: the airport terminal management and control system receives the departure instruction, turns on the multi-thread laser radar to obtain airport terminal scene laser data, and analyzes and converts the laser data into point cloud format data;
step S2: according to the stop line of waiting to detect the model and the nodical, corridor bridge terrain clearance, the aircraft fuselage length constraint of stand central line of aircraft and demarcate corridor bridge region, and in the region cluster detects out corridor bridge and aircraft connection part, judges corridor bridge connection state, include:
s21: by utilizing the intersection point of the stop line and the central line, the height of the corridor bridge and the length constraint of the airplane body, the scene point cloud data are directly filtered in the direction X, Z, Y respectively to filter out the spatial position area of the corridor bridge, and the method is shown in figure 2 so as to simplify the data and reduce the interference;
s22: traversing the gallery bridge space point cloud data according to a set precision value in the x direction, dividing the gallery bridge space point cloud data into sub-regions with different height values, and calculating an included angle between normal vectors of each region surface and comparing the included angle with a set threshold value to combine the sub-regions;
s23: processing each segmented point cloud region data by using an Euclidean clustering algorithm, adaptively adjusting a clustering coefficient according to the position of the aircraft stop line, and detecting the point cloud targets of the aircraft nose and the corridor bridge by combining the respective geometrical characteristics of the aircraft nose and the corridor bridge;
s24: and (3) calculating the space distance between the machine head point cloud target and the gallery bridge point cloud target, and judging that the gallery bridge is disconnected when the distance is greater than a set experience threshold, wherein fig. 3 is a point cloud schematic diagram of a gallery bridge disconnected state.
Step S3: the aircraft nose of the aircraft at the current parking position is detected based on the aircraft nose detection model trained in advance, and the method comprises the following steps:
s31: acquiring airplane data of various airplane types of the station, and carrying out sample labeling and sample label adding on an airplane nose;
s32: data enhancement such as cutting, zooming, rotating and the like is carried out on the marked sample so as to improve the robustness of the detection algorithm;
s33: extracting HAAR characteristics of the data-enhanced sample, and training based on an adaboost algorithm to obtain an aircraft nose detection model;
s34: and detecting the airplane by using the trained airplane nose detection model, and screening out the nose of the airplane at the current stand based on hough circle detection.
Step S4: and the spatial position of the aircraft nose is continuously detected and tracked by combining Kalman filtering according to the interframe relation of the aircraft at the parking position in the video, so that the stability of the detection algorithm is improved.
Step S5: calculating a ratio IOU of a cross part of a detection frame area of a nose and a stand area of the aircraft to a detection frame of the aircraft nose, and judging that the departure state of the aircraft is finished when the ratio is smaller than a set empirical threshold, wherein FIG. 4 is a calculation example of an IOU value, and FIGS. 5a and 5b are schematic diagrams of the departure state and the on-port state of the aircraft respectively.
While the invention has been described in terms of its preferred embodiments, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention.
Claims (3)
1. An aircraft berthing departure state detection method is characterized by comprising the following steps:
1) acquiring parking space scene point cloud data;
2) defining a corridor bridge area according to the intersection point of a stop line of a machine type to be detected and a parking space central line, the ground clearance of a corridor bridge and the length constraint of an airplane body, detecting a point cloud target of the corridor bridge and an airplane nose in a segmentation and clustering manner in the corridor bridge area, and judging the connection state of the corridor bridge;
3) detecting the aircraft nose of the aircraft at the current parking position based on a pre-trained aircraft nose detection model;
4) detecting in real time to track the current spatial position of the aircraft nose;
5) calculating the ratio of the intersection part of the detection frame area of the aircraft nose and the parking space area to the aircraft nose detection frame, if the ratio is smaller than a set threshold value, judging that the departure state of the aircraft is finished, and if the ratio is larger than or equal to the threshold value, returning to the step 4);
the step 2) specifically comprises the following steps:
21) processing scene point cloud data by adopting a straight-through filtering algorithm according to the intersection point of the stop line of the machine type to be detected and the center line of the parking space, the ground clearance of the corridor bridge and the constraint parameters of the length of the airplane body so as to filter out the spatial position area of the corridor bridge;
22) dividing gallery bridge space point cloud data according to the precision value of the spacing distance between the gallery bridge and the aircraft at the connection position when the gallery bridge is in a set critical disconnection state and by combining the normal vector included angle of each area surface;
23) clustering the point cloud data of each part, and detecting and extracting the aircraft nose and the gallery bridge target;
24) calculating the space distance between the aircraft nose and the gallery bridge target to judge the gallery bridge connection state;
the step 3) specifically comprises the following steps:
31) acquiring airplane data of various airplane types of the station, and carrying out sample labeling and sample label adding on an airplane nose;
32) cutting, zooming and rotating the marked sample to enhance image data;
33) extracting HAAR characteristics of the data-enhanced sample and training based on an enhanced learning algorithm to obtain an aircraft nose detection model;
34) and detecting the aircraft nose of the aircraft at the current parking position by using a pre-trained aircraft nose detection model.
2. The method for detecting the departure state of an aircraft from a berth as claimed in claim 1, wherein the step 1) comprises: the machine position management and control system receives the departure detection instruction, starts the multi-thread laser radar to capture the laser data of the machine position scene, and analyzes and converts the laser data into point cloud format data.
3. The method for detecting the departure state of an aircraft from a berth as claimed in claim 1, wherein the step 4) comprises: and continuously detecting according to the motion state of the airplane at the parking position in the video by the aid of a Kalman filtering algorithm to track the spatial position of the nose of the airplane.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011220679.7A CN112419790B (en) | 2020-11-05 | 2020-11-05 | Airplane berth departure state detection method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011220679.7A CN112419790B (en) | 2020-11-05 | 2020-11-05 | Airplane berth departure state detection method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112419790A CN112419790A (en) | 2021-02-26 |
CN112419790B true CN112419790B (en) | 2022-05-10 |
Family
ID=74827546
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011220679.7A Active CN112419790B (en) | 2020-11-05 | 2020-11-05 | Airplane berth departure state detection method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112419790B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113011335A (en) * | 2021-03-19 | 2021-06-22 | 捻果科技(深圳)有限公司 | Automatic identification method for corridor bridge approach connection aircraft in civil aviation airport flight area |
CN114155490B (en) * | 2021-12-08 | 2024-02-27 | 北京航易智汇科技有限公司 | Airport airplane berth warning lamp safety control system and method |
CN117789486B (en) * | 2024-02-28 | 2024-05-10 | 南京莱斯信息技术股份有限公司 | Monitoring system and method for right turn stop of intersection of large-sized vehicle |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
AU2015252745A1 (en) * | 2014-04-28 | 2016-12-01 | Windbidco Pty Ltd | Method and system for detecting aircraft induced wake turbulence |
CN105336221B (en) * | 2014-08-01 | 2017-12-08 | 深圳中集天达空港设备有限公司 | A kind of real-time capturing method and system of docking aircraft |
CN107886260B (en) * | 2017-12-28 | 2021-11-02 | 南京航空航天大学 | Parking space allocation method based on robustness allocation model |
CN109859532A (en) * | 2019-02-28 | 2019-06-07 | 深圳市北斗智能科技有限公司 | A kind of the break indices method and relevant apparatus of multi-constraint condition |
CN110579771A (en) * | 2019-09-12 | 2019-12-17 | 南京莱斯信息技术股份有限公司 | Airplane berth guiding method based on laser point cloud |
CN111857168A (en) * | 2020-07-03 | 2020-10-30 | 北京二郎神科技有限公司 | Unmanned aerial vehicle positioning method and device and unmanned aerial vehicle parking attitude adjusting method and device |
-
2020
- 2020-11-05 CN CN202011220679.7A patent/CN112419790B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN112419790A (en) | 2021-02-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112419790B (en) | Airplane berth departure state detection method | |
CN104794731B (en) | Multi-target detection tracking for ball machine control strategy | |
Narote et al. | A review of recent advances in lane detection and departure warning system | |
CN108230254B (en) | Automatic detection method for high-speed traffic full lane line capable of self-adapting scene switching | |
WO2020001223A1 (en) | Method and device for traffic signal detection and intelligent driving, vehicle, and electronic device | |
CN103903019A (en) | Automatic generating method for multi-lane vehicle track space-time diagram | |
CN110619276B (en) | Anomaly and violence detection system and method based on unmanned aerial vehicle mobile monitoring | |
CN110782673A (en) | Vehicle violation identification and detection system based on unmanned aerial vehicle shooting cloud computing | |
CN113093772B (en) | Method for accurately landing hangar of unmanned aerial vehicle | |
CN102043964A (en) | Tracking algorithm and tracking system for taking-off and landing of aircraft based on tripod head and camera head | |
CN110579771A (en) | Airplane berth guiding method based on laser point cloud | |
CN110320531A (en) | Obstacle recognition method, map creating method and device based on laser radar | |
KR101840167B1 (en) | System and method for interworking with target interest through handover between multiple cameras in cloud | |
CN113014866B (en) | Airport low-altitude bird activity monitoring and risk alarming system | |
CN103065325A (en) | Target tracking method based on color distance of multicolors and image dividing and aggregating | |
US9950812B2 (en) | System and method for airside activity management using video analytics | |
CN114415171A (en) | Automobile travelable area detection method based on 4D millimeter wave radar | |
CN114926422A (en) | Method and system for detecting boarding and alighting passenger flow | |
CN103679128A (en) | Anti-cloud-interference airplane target detection method | |
Dolph et al. | Sense and avoid for small unmanned aircraft systems | |
US11314974B2 (en) | Detecting debris in a vehicle path | |
CN113194249A (en) | Moving object real-time tracking system and method based on camera | |
Qiu et al. | Intelligent highway lane center identification from surveillance camera video | |
CN113391642B (en) | Unmanned aerial vehicle autonomous obstacle avoidance method and system based on monocular vision | |
CN106327921A (en) | Undercarriage safety monitoring method based on course line and visible data fusion |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |