SYSTEM AND METHOD FOR MEASURING WEIGHT AND BALANCE ON AN AIRCRAFT

Abstract

A system for calculating weight and distribution on an aircraft. The system includes an aircraft, at least one cabin camera configured to view the cabin of the aircraft, an image collector configured to collect images from the at least one cabin camera and a processor. The processor is configured to perform the following steps: a) detecting passengers and/or hand baggage from the images collected from the image collector, b) estimating positions of the passengers and/or hand baggage from the images collected from the image collector, and c) estimating weight of the passengers and/or hand baggage from the images collected from the image collector. The processor also calculates a real-time weight distribution of the aircraft based on the estimates provided in steps a)-c).

Claims

1. A system for calculating weight and distribution on an aircraft, the system comprising: an aircraft; at least one cabin camera configured to view the cabin of the aircraft; an image collector configured to collect images from the at least one cabin camera; and a processor configured to perform the following steps: a) detecting passengers and/or hand baggage from the images collected from the image collector; b) estimating positions of the passengers and/or hand baggage from the images collected from the image collector; c) estimating weight of the passengers and/or hand baggage from the images collected from the image collector; d) calculating a real-time weight distribution of the aircraft based on the estimates provided in steps a)-c).

2. The system of claim 1, wherein the system includes: a first module configured to determine passenger weight distribution based on the images collected from the image collector; and a second module configured to determine hand baggage weight distribution based on the images collected from the image collector.

3. The system of claim 2, further comprising a third module configured to calculate cabin weight distribution based on the data from the first and second modules.

4. The system of claim 2, wherein the first module is configured to determine biometric information of the detected passengers and wherein the passenger weight distribution is based on the biometric information, and the position, of the passenger.

5. The system of claim 3, wherein the second module is configured to determine the size and shape of detected hand baggage, and wherein the hand baggage weight distribution is based on the size and shape of the detected hand baggage, and the position, of the hand baggage.

6. The system of claim 1, wherein: the real-time weight distribution of the aircraft is determined pre-flight, during flight and/or on landing; and/or the real-time weight distribution of the aircraft is continuously updated to a pilot and/or a flight management system.

7. The system of claim 1, wherein the image collector is hardware or software.

8. A method of calculating weight distribution on an aircraft, the method comprising: collecting images from at least one cabin camera that is configured to view the cabin of the aircraft; detecting passengers and/or hand baggage from the images collected; estimating positions of the passengers and/or hand baggage from the collected images; estimating weight of the passengers and/or hand baggage from the images collected; and calculating a real-time weight distribution of the aircraft based on the estimated weight and estimated positions of the passengers and/or hand baggage.

9. The method of claim 8, wherein there is provided a first module for detecting passengers, estimating positions of the passengers, and estimating weight of the passengers.

10. The method of claim 9, wherein there is provided a second module for detecting hand baggage, estimating positions of the hand baggage, and estimating the weight of the hand baggage.

11. The method of claim 10, wherein there is provided a third module for calculating the weight distribution of the aircraft based on the data from the first and second modules.

12. The method of claim 9, wherein the first module is configured to determine biometric information of the passengers.

13. The method of claim 10, wherein the second module is configured to determine the size and shape of detected hand baggage.

14. The method of claim 8, wherein the real-time weight distribution of the aircraft is determined pre-flight, during flight and/or on landing.

15. The method of claim 8, wherein the real-time weight distribution of the aircraft is continuously updated to a pilot and/or a flight management system.

Description

BRIEF DESCRIPTION OF THE DRAWINGS

[0017] FIG. 1 shows an example of a system for calculating weight and distribution of an aircraft.

[0018] FIG. 2 shows an example of the method of using the system of FIG. 1.

[0019] FIG. 3 shows an example of passenger weight estimation with various parameters.

DETAILED DESCRIPTION

[0020] An example of a system 10 for calculating weight and distribution of an aircraft is shown in FIG. 1. The system 10 may include one or more imaging apparatus, such as a first cabin camera 100a, a second cabin camera 100b and an n.sup.th cabin camera 100n, n being any number greater than two. The amount of cabin cameras, 100a-100n, is determined by the size of the aircraft and any number that is necessary to have a field of view of the entire cabin is envisaged in the system 10. The cabin cameras 100a-100n ensure that the entire cabin is monitored for passengers and cabin baggage in order to effectively calculate the center of gravity of the aircraft by calculating the weight and distribution of the passengers and cabin baggage. The cabin cameras 100a-100n monitor the entirety of the cabin whilst grounded before take-off, during flight and on landing of the aircraft.

[0021] As shown in FIG. 1, system 10 may include an imaging collector 110 that collects the images from the cabin cameras 100a-100n. The imaging collector 110 may be hardware and/or software within the system 10. For example, the image collector 110 may be hardware, as an independent device, or software, running either in an independent processor or a processor within the system, as mentioned below. When the cabin cameras 100a-100n are in operation (e.g., before take-off, in flight and/or on landing), it is envisaged that the imaging collector 110 continuously receives real-time images from the cabin cameras 100a-100n. The images are then fed to a processor (not shown) and the processor may include a first module 120 and a second module 130. The first module 120 is a passenger weight distribution module. The first module 120 determines passenger weight distribution by reviewing the images collected by the imaging collector 110 in order to detect the passengers within the cabin, estimate the passenger positions and to estimate the weight of the passengers. As an example, a first cabin camera may be located to view rows 1-15 on an aircraft, and a second cabin camera may be located to view rows 16-30. As passengers enter the field of view, the image collector 110 collects the images from the first and second cabin cameras. The first module 120 then detects passengers from the images collected from the image collector 110, determines the passenger positions and calculates an estimated weight of the passengers for both sections of the aircraft (e.g., rows 1-15 and rows 16-30). Of course, there may be more than 30 rows of seats and the amount of images collected will depend on the amount of cabin cameras that enable a full view of the passenger cabin.

[0022] In the instance where there are overlapping passengers, the system 10 compensates for this by comparing the estimated positions of the passengers in the cabin. When the position of the passengers in the cabin is estimated from the cabin cameras 100a-100n, the same position of the same passengers can be recognised by the system 10 in the cabin, and compensations can be made in order to remove the overlapping image of the passenger. This therefore results in an adjustment to compensate for overlapping passengers within the view of the cabin cameras 100a-100n.

[0023] As mentioned, the first module 120 can detect passenger objects in the images collected by the image collector 110. An object detection model, such as MobileNet SSD could be used, as an example. Of course, other detection models could be used. Once the passenger has been detected by the first module 120, the position of the passenger can be estimated. As the position of the cameras, and the layout of the cabin, is known by the processor, the first module 120 can match detected passengers to the position of the cabin (e.g. specific seats). On take-off and landing, the passengers are located in their seats, and, therefore, a static frame image process may be used to determine the position of the passengers at their seats via pixel association. It may be necessary to also know the passenger positions during flight—i.e., to compute the passenger locations all the time. If the position of passengers is to be detected continuously (e.g. during flight), a dynamic algorithm may be used in order to detect the passengers and update as the passengers move around the cabin.

[0024] The first module 120 can then estimate the passenger weight. In order to do this, the first module 120 may determine some biometric information from the images collected by the image collector 110. As an example, the first module 120 may be able to determine whether a detected passenger is an adult or a child, and estimate a weight based on the determination. Other additional examples, that may be used in conjunction, could be height estimation via pixel detection, or otherwise; complexion estimation via posture detection; weight estimation based on face landmark extraction; clothing weight estimation based on skin detection, which consists of assessing the amount of skin that is detected for each passenger by the first module 120. Based on one or more of these estimation techniques, the first module 120 can then provide an estimation of the weights of the passengers and their positions.

[0025] The second module 130 can detect hand baggage objects in the images collected by the image collector 110. As mentioned above, and as an example, an object detection model, such as MobileNet SSD be used. Of course, other detection models could be used. Once the hand baggage has been detected by the second module 130, the position of the hand baggage can be estimated. As the position of the cameras, and the layout of the cabin, is known by the processor, the second module 130 can match detected hand baggage to the position of the cabin (e.g. the position in the overhead locker, or under the seat in front of their seat). On take-off and landing, the passengers are located in their seats, and, usually, the hand baggage is placed under the seat in front of them or in the overhead locker. Therefore, hand baggage positions may be gathered statically or dynamically. In the static approach, the cabin cameras 100a-100n have the overhead lockers in full view and a static frame image process may be used to determine the position of the hand baggage via pixel association. If the position of hand baggage is to be detected continuously (e.g. during flight), a dynamic algorithm may be used in order to detect the hand baggage and update once the hand baggage has been stored.

[0026] The second module 130 can then estimate the hand baggage weight. In order to do this, the second module 130 may determine the size and shape of the hand baggage to determine an estimate of the weight. Further, the second module 130 may be able to use statistical analysis and regulations for baggage allowed in the cabin (e.g., based on the airline) and provide an average weight estimate. A computer vision algorithm could then compute the weight based on the statistical analysis and the hand baggage detected in the images. Based on one or more of these estimation techniques, the second module 130 can then provide an estimation of the weights of the hand baggage and their positions.

[0027] The data of the passenger weights and positions from the first module 120, and the data of the hand baggage weights and positions from the second module 130 is then fed to a third module 140. The third module 140 is a cabin weight distribution module. The third module 140 calculates a cabin weight distribution based on the data from the first and second modules 120, 130. The cabin weight distribution can then be used to calculate a center of gravity for the aircraft. Optionally, these values may then be fed to the Flight Management System such that the center of gravity of the aircraft may be updated, and the pilot may be informed of a change in the weight distribution. As shown in FIG. 1, the processor loops back to the image collector 110 for continuous updating throughout the flight (including on take-off and landing) such that the pilot or the Flight Management System may be updated of the weight distribution at all times.

[0028] An example of a method of using the system 10 of FIG. 1 is shown in FIG. 2. As can be seen in FIG. 2, the method may include: [0029] 201: collecting the images from the cabin cameras 100a-100n, [0030] 202: detecting hand baggage from the collection of images; [0031] 203: detecting passengers from the collection of images; [0032] 204a: estimating hand baggage positions based on the hand baggage detected; [0033] 204b: estimating hand baggage weight based on the hand baggage detected; [0034] 205a: estimating passenger positions based on the passengers detected; [0035] 205b: estimating passenger weights based on the passengers detected; [0036] 206: calculating real-time weight distribution based on the estimates in 204a, 204b, 205a and 205b; [0037] 207: optionally, sending the weight distribution calculation to the Flight Management System.

[0038] The steps above may also be repeated throughout the entire flight (including take-off and landing) for up-to-date weight distribution calculations.

[0039] An example of passenger weight estimation is shown in FIG. 3. The example shown in this figure could apply to many of the estimations discussed above in relation to FIG. 1, but in the particular example shown in FIG. 3, identification of summer or winter clothes is made to produce a weight estimate. At step 301, the images are collected from the image collector 110 (shown in FIG. 1). The processor then identifies passengers as discussed above. The processor determines if the passenger is an adult at step 302 and then determines if the passenger is wearing winter clothes after analysing the image at step 303. Calculations are used at step 304 to determine if the passenger detected is an adult. If the calculations determine that the detected passenger is not an adult, the processor moves to step 304b and determines if the passenger is wearing winter clothes. If the passenger (i.e., a child passenger) is identified to not be wearing winter clothes, the processor identifies that the passenger is wearing summer clothes at step 306b and calculates a weight estimate accordingly. If the passenger is identified as wearing winter clothes, the processor at step 306a estimates a weight based on the passenger wearing winter clothes. If the calculations determine that the detected passenger is an adult, the processor moves to step 304a and determines if the passenger is wearing winter clothes. If the passenger (i.e., an adult passenger) is identified to not be wearing winter clothes, the processor identifies that the passenger is wearing summer clothes at step 305b and calculates a weight estimate accordingly. If the passenger is identified as wearing winter clothes, the processor at step 305a estimates a weight based on the passenger wearing winter clothes. Therefore, the passengers weight, whether a child or an adult, can be estimated using the steps shown in FIG. 3.

[0040] Although identifying passengers wearing winter or summer clothes is described and shown in FIG. 3, it is envisaged that similar processes may be used to determine the height of the passenger, size and shape of the baggage etc. The passenger weight estimation may, of course, be used in conjunction with the determination of the position of the passengers and/or baggage, as discussed above.

[0041] The systems and methods described above may, therefore, be used to determine passenger and hand baggage weight distribution to provide an overall weight distribution of the aircraft. The overall weight distribution of the aircraft may then be determined in real-time before flight, during flight and during landing of the aircraft. The system and method provide an accurate weight distribution to a pilot or Flight Management System during the entire process of boarding, seating, flight, landing and disembarkation of the aircraft.

[0042] Although this disclosure has been described in terms of preferred examples, it should be understood that these examples are illustrative only and that the claims are not limited to those examples. Those skilled in the art will be able to make modifications and alternatives in view of the disclosure which are contemplated as falling within the scope of the appended claims.