CN115346168A

CN115346168A - Cargo compartment luggage carrying monitoring method and device based on artificial intelligence, electronic equipment and medium

Info

Publication number: CN115346168A
Application number: CN202210938266.5A
Authority: CN
Inventors: 上峰; 马维兵; 张宇光; 周煊; 黄海练; 陈沛亮; 岑智明
Original assignee: Guangzhou Civil Aviation Information Technology Co ltd
Current assignee: Guangzhou Civil Aviation Information Technology Co ltd
Priority date: 2022-08-05
Filing date: 2022-08-05
Publication date: 2022-11-15

Abstract

The invention is applicable to the technical field of airport luggage monitoring, and discloses a cargo compartment luggage carrying monitoring method and device based on artificial intelligence, an electronic device and a medium, which specifically comprise the following steps: receiving video information shot by a camera arranged in an abdominal cabin; performing feature recognition on the monitored image information according to a preset monitoring model to determine the characteristics of the luggage in the monitored image information and current position information corresponding to the characteristics of the luggage; comparing the current position information with the luggage position information of the appointed frame monitoring image to determine the moving distance of the corresponding luggage; and matching the moving distance of the luggage with a preset early warning rule to judge whether the violation behavior exists. According to the cargo compartment luggage carrying monitoring device based on artificial intelligence, the luggage displacement distance is used as a defining means for violently carrying luggage, so that more accurate luggage carrying monitoring can be effectively realized, the accuracy of video monitoring is improved, and the manual monitoring investment is reduced.

Description

Cargo compartment luggage carrying monitoring method and device based on artificial intelligence, electronic equipment and medium

Technical Field

Cargo compartment luggage carrying monitoring method and device based on artificial intelligence, electronic equipment and medium.

Background

In recent years, the occurrence frequency and the damage risk of the cargo hold damage unsafe events are obviously increased, and great potential safety hazards are brought to flight operation. The key reason causing multiple damage events of the cargo hold is that the cargo hold is closed, no monitoring equipment is provided, the loading and unloading operation in the cargo hold is difficult to monitor, and the pursuit of responsibility exists in dispute.

The existing video monitoring mainly has the following problems: 1. the video monitoring is mainly stored on line, an effective supervision platform is lacked, and the flight monitoring coverage rate cannot be managed; 2. the video monitoring is mainly supervised by manual spot check and after-event evidence obtaining, and the problem that a large number of flight loading and unloading monitoring cannot be effectively utilized exists.

Chinese patent publication No. CN107358194B discloses a method for judging violence sorting express delivery based on computer vision, which adopts a deep learning method, and uses a YOLO convolutional neural network to perform sample set training to obtain a model with express delivery identification capability, i.e. a package identification model, for identifying each video frame, and then based on the coordinates of the package image obtained by identification, according to the real-time change of the coordinates of the package image, judges whether the package belongs to a violence sorting behavior. The letter sorting of this patent only is to the express delivery of the same type, can't distinguish to the parcel, and the distance change degree should not be the same around the parcel of difference.

Disclosure of Invention

The invention aims to overcome the defects of the prior art and provide a cargo compartment baggage handling monitoring method, a cargo compartment baggage handling monitoring device, electronic equipment and a cargo compartment baggage handling monitoring medium based on artificial intelligence.

In order to achieve the above object, a first aspect of the embodiments of the present invention discloses a cargo compartment baggage handling monitoring method based on artificial intelligence, which includes: receiving video information shot by a camera arranged in an abdominal cabin, wherein the video information comprises multi-frame monitoring image information;

performing feature recognition on the monitoring image information according to a preset monitoring model to determine the characteristics of the luggage in the monitoring image information and current position information corresponding to the characteristics of the luggage;

comparing the current position information with the luggage position information of the appointed frame monitoring image to determine the moving distance of the corresponding luggage;

performing character recognition on a region of the baggage to determine baggage tag information, the baggage tag information including fragile items and general items;

matching the moving distance of the luggage with a preset early warning rule to judge whether the illegal action exists, and matching the first judgment distance according to the preset early warning rule to judge whether the illegal action exists or not when the luggage tag information is detected to be a fragile article; when the luggage tag information is detected to be a common article, matching a second judgment distance according to a preset early warning rule to judge whether an illegal action exists or not; and if the illegal behavior exists, early warning reminding is carried out, and data storage is carried out on the monitoring image information of the corresponding frame.

Preferably, the performing feature recognition on the monitoring image information according to a preset monitoring model to determine the characteristics of the baggage in the monitoring image information and the current position information corresponding to the characteristics of the baggage includes:

performing feature recognition on the monitoring image information according to a preset monitoring model to determine pixel points covered by luggage features in the monitoring image information;

the central point of the pixel point covered by the luggage is used as the current position information of the luggage, and the current position information comprises a transverse direction position and a longitudinal direction position.

Preferably, before the performing feature recognition on the monitoring image information according to a preset monitoring model to determine a pixel point covered by a baggage feature in the monitoring image information, the method further includes:

when the luggage is detected to be in contact with the corresponding contact surface, the characteristic recognition is started to be executed.

Preferably, the monitoring image information includes conveyor belt information, baggage information, ground information, and personnel information.

Preferably, after receiving the video information captured by the camera installed in the abdominal compartment, the method further includes:

identifying and positioning personnel in the monitoring image information according to a preset personnel model to determine personnel characteristic information;

performing action recognition on the personnel characteristic information according to a preset personnel action model to determine the action state of the corresponding personnel;

and determining whether the illegal action exists in the personnel according to the action state, and if the illegal action exists, performing early warning reminding and intercepting a corresponding image picture.

The second aspect of the embodiment of the invention discloses a cargo compartment luggage carrying and monitoring device based on artificial intelligence, which comprises:

preferably, the receiving module: the system comprises a video acquisition module, a video processing module and a monitoring module, wherein the video acquisition module is used for acquiring video information shot by a camera arranged in an abdominal compartment, and the video information comprises multi-frame monitoring image information;

a feature identification module: the monitoring image information is subjected to feature recognition according to a preset monitoring model so as to determine luggage information in the monitoring image information and current position information corresponding to the luggage information;

a distance acquisition module: the luggage position information is used for comparing the current position information with the luggage position information of the appointed frame monitoring image so as to determine the moving distance of the corresponding luggage;

the early warning module: and the early warning module is used for matching the moving distance of the luggage with a preset early warning rule to judge whether an illegal action exists, and if the illegal action exists, the early warning module carries out early warning reminding and carries out data storage on the corresponding frame of monitoring image information.

A third aspect of an embodiment of the present invention discloses an electronic device, including: a memory storing executable program code; a processor coupled with the memory; the processor calls the executable program code stored in the memory for executing the artificial intelligence-based cargo compartment baggage handling monitoring method disclosed by the first aspect of the embodiment of the invention.

In a fourth aspect of the embodiments of the present invention, a computer-readable storage medium is disclosed, which stores a computer program, where the computer program enables a computer to execute the artificial intelligence based cargo compartment baggage handling monitoring method disclosed in the first aspect of the embodiments of the present invention.

Compared with the prior art, the cargo compartment luggage carrying monitoring method and device based on artificial intelligence, the electronic equipment and the medium have the beneficial effects that:

1. through adopting luggage displacement distance to come the means of injecing as violence transport luggage, it can effectively realize more accurate luggage transport monitoring to promote video monitoring's accuracy, reduce artifical monitoring and drop into.

2. Whether the type of the luggage is a fragile article or a general article is distinguished by identifying the scratchy information of the luggage, and different judgment rules are adopted for the fragile article and the general article so as to better adapt to different luggage.

3. The presence or absence of violent conveyance is realized by the action of shooting the personnel information.

The features and advantages of the present invention will be described in detail by embodiments in conjunction with the accompanying drawings.

Drawings

Fig. 1 is a schematic flow chart of a cargo compartment baggage handling monitoring method based on artificial intelligence, which is disclosed by an embodiment of the invention.

Fig. 2 is a schematic diagram of a specific process of distance detection according to an embodiment of the present invention.

Fig. 3 is a schematic flow chart of the person identification disclosed in the embodiment of the present invention.

FIG. 4 is an illustration of an image taken of a cargo space as disclosed in an embodiment of the present invention.

Fig. 5 is a schematic structural diagram of a cargo compartment baggage handling monitoring device based on artificial intelligence according to an embodiment of the present invention.

Fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.

Wherein:

21-a receiving module; 2-a feature recognition module; 3-a distance acquisition module; 4-early warning module; 510-a memory; 520-a processor.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.

It should be noted that the terms "first", "second", "third", "fourth", etc. in the description and claims of the present invention are used for distinguishing different objects, and are not used for describing a specific order. The terms "comprises," "comprising," and any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

The existing video monitoring mainly has the following problems: 1. the video monitoring is mainly stored on line, an effective supervision platform is lacked, and the flight monitoring coverage rate cannot be managed; 2. the video monitoring is mainly supervised by manual spot check and after-event evidence obtaining, and the problem that a large number of flight loading and unloading monitoring cannot be effectively utilized exists. The embodiment of the invention discloses a cargo compartment luggage carrying monitoring method and device based on artificial intelligence, electronic equipment and a storage medium.

Example one

Referring to fig. 1, fig. 1 is a schematic flow chart of a cargo compartment baggage handling monitoring method based on artificial intelligence according to an embodiment of the present invention. The execution main body of the method described in the embodiment of the present invention is an execution main body composed of software or/and hardware, and the execution main body may receive related information in a wired or/and wireless manner and may send a certain instruction. Of course, it may also have certain processing and storage functions. The execution body may control a plurality of devices, such as a remote physical server or a cloud server and related software, or may be a local host or a server and related software for performing related operations on a device installed somewhere. In some scenarios, multiple storage devices may also be controlled, which may be co-located with the device or located in a different location. As shown in fig. 1, the cargo compartment baggage handling monitoring method based on artificial intelligence comprises the following steps:

s101: receiving video information shot by a camera arranged in an abdominal cabin, wherein the video information comprises multi-frame monitoring image information;

extracting at least 2 frames of key frame images at intervals of preset time according to the acquired video; the preset time is 1 second. The part is mainly a basic part for subsequent judgment, if no video image is acquired, the content of the video image cannot be analyzed, and the subsequent content can be compared by acquiring the corresponding video and the video image directly; however, the feature recognition can be better performed by acquiring the video and extracting the key frame, because if the picture is directly acquired, there may be some blurred scenes in the captured picture, which is not favorable for recognition, and such a situation can be effectively avoided by acquiring the key frame in the video. After the video information is acquired, the data selection is also carried out on the key frames, so that the subsequent image identification processing can be more efficient.

S102: performing feature recognition on the monitoring image information according to a preset monitoring model to determine the characteristics of the luggage in the monitoring image information and current position information corresponding to the characteristics of the luggage;

more preferably, fig. 2 is a schematic diagram of a specific process of distance detection disclosed in an embodiment of the present invention, and as shown in fig. 2, the performing feature identification on the monitored image information according to a preset monitoring model to determine a feature of baggage in the monitored image information and current position information corresponding to the feature of baggage includes:

s1021: when the luggage is detected to be in contact with the corresponding contact surface, starting to execute the next step;

s1022: performing feature recognition on the monitoring image information according to a preset monitoring model to determine pixel points covered by luggage features in the monitoring image information;

s1023: the central point of the pixel point covered by the luggage is used as the current position information of the luggage, and the current position information comprises a transverse direction position and a longitudinal direction position.

In the step, mainly for acquiring the corresponding luggage position, in the embodiment of the invention, firstly, the behavior of violently loading and unloading the goods is defined, and in the embodiment of the invention, the judgment is carried out by adopting the goods displacement distance; because the cargo is judged to have the possibility of being violently loaded and unloaded when the moving distance of the cargo exceeds the set distance, the loading and unloading behaviors can be defined more intuitively through the mode.

The contact surface may be a ground contact surface or a conveyor contact surface, and the purpose of this is to be used as a basis for image acquisition, and when contact is detected, the moving distance of the baggage on the contact surface is acquired and calculated, and the subsequent specified frame is a picture image when the baggage is in contact with the conveyor or when the baggage is relatively still with the conveyor.

When the distance judgment is carried out, two distance judgment forms of positions are provided, wherein one is the distance in the transverse direction, and the other is the distance in the longitudinal direction; the distance setting mode in different directions is different.

S103: comparing the current position information with the luggage position information of the appointed frame monitoring image to determine the moving distance of the corresponding luggage;

when the method is specifically implemented, the moving distance needs to be judged, and the distance information cannot be judged from one image alone; therefore, how to calculate the corresponding moving distance needs to be defined, and the accuracy of result judgment can be further improved by defining the appropriate moving distance as an auxiliary parameter for judgment. The subsequent determination is made by comparing the positional deviation of the baggage in the two images as the moving distance.

S104: and matching the moving distance of the luggage with a preset early warning rule to judge whether an illegal action exists, if so, carrying out early warning reminding, and carrying out data storage on the corresponding frame of monitoring image information.

Specifically, when the distance from the article to the original contact point (starting point) to the new contact point (end point) is detected to be greater than 50cm, the corresponding article can be judged to be loaded and unloaded violently; because the normal lowering of the item does not cause the item to slip that long; when the article slides that far, it can be determined that there is a possibility that it is loaded and unloaded violently.

More preferably, after the central point of the pixel point where the baggage is located is used as the current position information of the baggage, the method further includes:

character recognition is performed on a region of the baggage to determine baggage tag information, the baggage tag information including fragile items and general items.

In the actual use process, different objects have different moving distances, and when the encountered objects are fragile objects such as glass bottles, the situation is not met if the objects are required to have the same moving distance with the general luggage object; because the fragile article is easier to be damaged in the moving process due to the property of the fragile article, the customer benefit is influenced; therefore, it is necessary to distinguish them when carrying out the implementation. Whether the luggage tag is a fragile article or not is determined by identifying the luggage tag, and the luggage tag and the fragile article are matched with different judgment distances.

More preferably, matching the moving distance of the luggage with a preset early warning rule to determine whether an illegal action exists includes:

when the luggage tag information is detected to be a fragile article, matching according to a preset early warning rule and a first judgment distance to judge whether an illegal action exists or not;

and when the luggage tag information is detected to be a common article, matching a second judgment distance according to a preset early warning rule to judge whether the illegal behavior exists or not.

More preferably, the monitoring image information includes conveyor belt information, baggage information, ground information, and personnel information. The secondary identification determination is made by determining the positional distance between the baggage and each component.

If the luggage or the package is pasted with a fragile label, the distance from the fragile object to the new contact point (terminal point) is more than or equal to 30cm after the fragile object is separated from the original contact point (starting point); the distance from the original contact point (initial point) to the new contact point (terminal point) of the common article is more than or equal to 50cm; the articles fall off the conveyor belt, and the vertical distance between the articles and the contact surface of the placing position is more than or equal to 30cm. The aviation goods comprise two types of goods, namely heavy goods such as a trunk and a carton and light goods such as general packages (woven bags and the like), violent loading and unloading behaviors are slightly different, the violent loading and unloading of the heavy goods have 3 illegal actions of throwing, throwing and replaying, and the violent loading and unloading of the light goods have 4 illegal actions of throwing, throwing and replaying, and the scheme can monitor the illegal actions.

The violent loading and unloading behaviors are respectively described aiming at two types of articles, namely a luggage case and a common package.

The loading and unloading scene of the luggage case and the violent loading and unloading of the luggage case have the following 3 scenes:

first, suitcase throwing scenario: the staff throw away the suitcase with strength, the displacement between the floor point and the original point of the suitcase is too large (the general article is more than or equal to 50cm, and the fragile article is more than or equal to 30 cm), or the suitcase drops after being thrown to the conveyor belt (the vertical distance is more than or equal to 30 cm); when the specific detection is carried out, the positions of the luggage, the conveyor belt and the ground are required to be detected; judging whether the problem of violent loading and unloading exists or not by detecting the moving distance of the luggage on the conveyor belt or on the ground;

second, a suitcase throwing scene: the employee drops the suitcase from top to bottom onto the conveyor belt, the suitcase produces a large displacement (generally, the article is more than or equal to 50cm, the fragile article is more than or equal to 30 cm) at the floor point, or drops from the conveyor belt to the ground (the vertical distance is more than or equal to 30 cm),

third, replay suitcase scenario: the scene is mainly that the employees put the trunk hard to the conveyor belt or place the trunk from a higher position to a lower position so that the trunk slides greatly or falls on the ground directly (the general goods are more than or equal to 50cm, the fragile goods are more than or equal to 30cm, and the vertical distance is more than or equal to 30 cm)

The following 4 scenes exist for violent handling of general packages:

first, a parcel-throwing scene: the staff throw the parcel out with the hand, and the parcel falls to a far place (generally, the article is more than or equal to 50cm, and the fragile article is more than or equal to 10 cm) on the conveyer belt after flying for a certain distance in the air, or falls from the conveyer belt (the vertical distance is more than or equal to 30 cm); that is, when the specific position is judged, the flying time of the parcel in the air can be judged, and whether the article is loaded or unloaded violently can be determined by judging the flying time of the parcel in the air;

second, parcel-throwing scenario: the staff throw the parcel out with strength (mostly small parcels), the goods fall to a far place of the conveyor belt (the general goods are more than or equal to 50cm, and the fragile goods are more than or equal to 30 cm), or the goods fall after throwing the parcel to the conveyor belt (the vertical distance is more than or equal to 30 cm);

third, a parcel-falling scene: the staff drop the packages to the conveyor belt from top to bottom, and the packages generate large displacement (generally, the objects are more than or equal to 50cm, and the fragile objects are more than or equal to 30 cm) on the floor point or drop to the ground from the conveyor belt (the vertical distance is more than or equal to 30 cm);

fourth, replay scenario of parcels: the staff puts the parcel effort on the conveyer belt again, makes the parcel produce great slip or directly drop ground (general article is more than or equal to 50cm, fragile article is more than or equal to 30cm, vertical distance is more than or equal to 30 cm).

The scenes which are violently loaded and unloaded in the actual process are collected into distance judgment in various modes, so that the judgment of the complex scene becomes simpler; under the condition of not wasting resources, the accuracy of judgment is effectively improved.

In specific implementation, both parties are required to determine POC test data (a normal loading and unloading video of abdominal cargos and an illegal loading and unloading video sample of the abdominal cargos) and a data returning scheme in future formal use, and a 4G returning or offline file importing mode is adopted.

In addition to the distance judgment mode, a personnel behavior identification mode can be adopted for further identification judgment; namely, the personnel action recognition and the distance judgment are combined to realize more accurate recognition control; more preferably, fig. 3 is a schematic diagram of a specific flow of person identification disclosed in the embodiment of the present invention, and as shown in fig. 3, after receiving video information captured by a camera disposed in an abdominal compartment, the method further includes:

s1011: identifying and positioning personnel in the monitoring image information according to a preset personnel model to determine personnel characteristic information;

s1012: performing action recognition on the personnel characteristic information according to a preset personnel action model to determine the action state of the corresponding personnel;

s1013: and determining whether the illegal action exists in the personnel according to the action state, and if so, carrying out early warning reminding and intercepting a corresponding image picture.

The computer vision-based abnormal loading behavior in the embodiment of the invention is identified and a large amount of model training is carried out. After the abnormal behavior action is defined, the scheme adopts an abnormal behavior recognition algorithm based on computer vision. The method comprises the steps of firstly obtaining a characteristic vector of an abnormal loading and unloading behavior, selecting the position change condition, time and behavior change angle of a job behavior characteristic point, and effectively extracting the collected job image behavior characteristics, thereby establishing an abnormal behavior identification characteristic vector database. And comparing the abnormal behavior characteristics in the database with the target characteristics so as to finish the identification of the abnormal loading and unloading behaviors. Whether the abnormal loading behavior exists is judged by identifying the action of specific personnel, when the abnormal loading behavior is identified, early warning is carried out, more diversified combination judgment can be realized through various types of combination, and the accuracy of prediction is improved.

When video acquisition is performed by using a fisheye camera in the subsequent image acquisition, corresponding fisheye images need to be used in model training, fig. 4 is a diagram of images shot by a cargo hold disclosed in the embodiment of the invention, and as shown in fig. 4, the fisheye images are shot and have certain distortion, so that if the images are used for subsequent recognition, the same pattern needs to be used for recognition in the training.

In the embodiment of the invention, the statistical form can be output at intervals of preset time, and the statistical form analysis comprises operation flight list coverage rate statistical display, AI analysis alarm prompt, alarm snapshot picture call display, daily safe operation data analysis, operation standard management and the like.

The application of the violence sorting identification analysis algorithm in the embodiment of the invention to the abdominal compartment monitoring can assist in realizing an automatic and intelligent passenger plane abdominal compartment loading monitoring rod. Meanwhile, the algorithm is not only applied to the abdominal cabin, but also applied to the whole transportation process of goods, luggage and mails of the flight. The existing monitoring video is used as a training sample, an abdominal cabin monitoring algorithm is combined, the algorithm is combined with the realization of a video monitoring platform, intelligent violent sorting identification can be realized on the whole transportation process, the cost of manual monitoring is reduced, and the monitoring accuracy is improved.

According to the cargo compartment luggage carrying monitoring device based on artificial intelligence, the luggage displacement distance is used as a defining means for violently carrying luggage, so that more accurate luggage carrying monitoring can be effectively realized, the accuracy of video monitoring is improved, and the manual monitoring investment is reduced.

Example two

Referring to fig. 5, fig. 5 is a schematic structural diagram of a cargo compartment baggage handling monitoring device based on artificial intelligence according to an embodiment of the present invention. As shown in fig. 5, the artificial intelligence based cargo compartment baggage handling monitoring device may include:

the receiving module 21: the system comprises a video acquisition module, a video processing module and a monitoring module, wherein the video acquisition module is used for acquiring video information shot by a camera arranged in an abdominal compartment, and the video information comprises multi-frame monitoring image information;

the feature recognition module 22: the monitoring image information is subjected to feature recognition according to a preset monitoring model so as to determine luggage information in the monitoring image information and current position information corresponding to the luggage information;

the distance acquisition module 23: the system is used for comparing the current position information with the luggage position information of the appointed frame monitoring image to determine the moving distance of the corresponding luggage;

the early warning module 24: and the early warning module is used for matching the moving distance of the luggage with a preset early warning rule to judge whether an illegal action exists, and if the illegal action exists, the early warning module carries out early warning reminding and carries out data storage on the corresponding frame of monitoring image information.

More preferably, the performing feature recognition on the monitoring image information according to a preset monitoring model to determine the characteristics of the baggage in the monitoring image information and the current position information corresponding to the characteristics of the baggage includes:

the first detection module: the system is used for starting to execute the next step when the luggage is detected to be in contact with the corresponding contact surface;

a feature identification module: the monitoring image information is subjected to feature recognition according to a preset monitoring model so as to determine pixel points covered by luggage features in the monitoring image information;

a position determination module: the central point of the pixel point covered by the luggage is used as the current position information of the luggage, and the current position information comprises a transverse direction position and a longitudinal direction position.

More preferably, after receiving the video information captured by the camera installed in the abdominal compartment, the method further includes:

a person positioning module: the system comprises a monitoring image information acquisition module, a monitoring image information acquisition module and a monitoring image information acquisition module, wherein the monitoring image information acquisition module is used for acquiring monitoring image information;

an action recognition module: the personnel characteristic information is used for identifying the action of the personnel according to a preset personnel action model so as to determine the action state of the corresponding personnel;

and a violation judgment module: and the warning module is used for determining whether the illegal action exists in the personnel according to the action state, and when the illegal action is determined to exist, performing early warning reminding and intercepting a corresponding image picture.

According to the cargo compartment luggage carrying monitoring device based on artificial intelligence, the luggage displacement distance is used as a defining means for violently carrying luggage, so that more accurate luggage carrying monitoring can be effectively realized, the accuracy of video monitoring is improved, and the manual monitoring investment is reduced. At present, the problem of high misjudgment rate exists only in single judgment through the movement of the displacement of the luggage, and the accuracy is higher after the two modes are combined.

EXAMPLE III

Referring to fig. 6, fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the disclosure. The electronic device may be a computer, a server, or the like, and may also be an intelligent device such as a mobile phone, a tablet computer, a monitoring terminal, or the like, and an image acquisition device having a processing function. As shown in fig. 6, the electronic device may include:

a memory 510 storing executable program code;

a processor 520 coupled to the memory 510;

the processor 520 calls the executable program code stored in the memory 510 to perform some or all of the steps of the artificial intelligence based cargo space baggage handling monitoring method according to the first embodiment.

The embodiment of the invention discloses a computer readable storage medium which stores a computer program, wherein the computer program enables a computer to execute part or all of the steps in the artificial intelligence based cargo compartment baggage handling monitoring method in the first embodiment.

The embodiment of the invention also discloses a computer program product, wherein when the computer program product runs on a computer, the computer is enabled to execute part or all of the steps in the artificial intelligence-based cargo compartment baggage handling monitoring method in the first embodiment.

The embodiment of the invention also discloses an application publishing platform, wherein the application publishing platform is used for publishing the computer program product, and when the computer program product runs on a computer, the computer is enabled to execute part or all of the steps in the cargo compartment baggage handling monitoring method based on artificial intelligence in the first embodiment.

In various embodiments of the present invention, it should be understood that the sequence numbers of the processes do not mean the execution sequence necessarily in order, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be implemented in the form of hardware, and can also be implemented in the form of a software functional unit.

The integrated units, if implemented as software functional units and sold or used as a stand-alone product, may be stored in a computer accessible memory. Based on such understanding, the technical solution of the present invention, which is a part of or contributes to the prior art in essence, or all or part of the technical solution, can be embodied in the form of a software product, which is stored in a memory and includes several requests for causing a computer device (which may be a personal computer, a server, a network device, or the like, and may specifically be a processor in the computer device) to execute part or all of the steps of the method according to the embodiments of the present invention.

In the embodiments provided herein, it should be understood that "B corresponding to a" means that B is associated with a, from which B can be determined. It should also be understood that determining B from a does not mean determining B from a alone, but may also be determined from a and/or other information.

Those of ordinary skill in the art will appreciate that some or all of the steps in the methods of the embodiments described herein may be implemented by hardware associated with a program that may be stored in a computer-readable storage medium, including a Read-Only Memory (ROM), a Random Access Memory (RAM), a Programmable Read-Only Memory (PROM), an Erasable Programmable Read-Only Memory (EPROM), a One-time Programmable Read-Only Memory (OTPROM), an electronically Erasable Programmable Read-Only Memory (EEPROM), an optical Disc-Read-Only Memory (CD-ROM) or other storage medium capable of storing data, a magnetic tape, or any other computer-readable medium capable of carrying a computer program or computer-readable data.

The cargo compartment baggage handling monitoring method, the cargo compartment baggage handling monitoring device, the electronic device and the storage medium based on artificial intelligence disclosed by the embodiment of the invention are described in detail, a specific embodiment is applied to the method for explaining the principle and the implementation mode of the invention, and the description of the embodiment is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed, and in summary, the content of the present specification should not be construed as a limitation to the present invention.

Claims

1. A cargo compartment luggage carrying monitoring method based on artificial intelligence is characterized by comprising the following steps:

receiving video information shot by a camera arranged in an abdominal cabin, wherein the video information comprises multi-frame monitoring image information;

matching the moving distance of the luggage with a preset early warning rule to judge whether the illegal action exists, and matching the first judgment distance according to the preset early warning rule to judge whether the illegal action exists or not when the luggage tag information is detected to be a fragile article; when the luggage tag information is detected to be a common article, matching according to a preset early warning rule and a second judgment distance to judge whether an illegal action exists or not; and if the illegal behavior exists, early warning reminding is carried out, and data storage is carried out on the monitoring image information of the corresponding frame.

2. The artificial intelligence based cargo compartment baggage handling monitoring method according to claim 1, wherein the performing of feature recognition on the monitored image information according to a preset monitoring model to determine characteristics of baggage in the monitored image information and current position information corresponding to the characteristics of baggage comprises:

3. The artificial intelligence-based cargo compartment baggage handling monitoring method according to claim 2, wherein before the characteristic recognition is performed on the monitored image information according to a preset monitoring model to determine pixel points covered by the baggage characteristics in the monitored image information, the method further comprises:

4. The artificial intelligence based cargo compartment baggage handling monitoring method of claim 1, wherein the monitored image information comprises conveyor information, baggage information, ground information, and personnel information.

5. The artificial intelligence based cargo compartment baggage handling monitoring method according to claim 6, further comprising, after said receiving video information captured by a camera installed in the abdominal compartment:

6. The utility model provides a cargo hold luggage transport monitoring devices based on artificial intelligence which characterized in that includes:

a receiving module: the system comprises a video acquisition module, a video processing module and a monitoring module, wherein the video acquisition module is used for acquiring video information shot by a camera arranged in an abdominal compartment, and the video information comprises multi-frame monitoring image information;

a distance acquisition module: the system is used for comparing the current position information with the luggage position information of the appointed frame monitoring image to determine the moving distance of the corresponding luggage;

7. An electronic device, comprising: a memory storing executable program code; a processor coupled with the memory; the processor invokes the executable program code stored in the memory to perform the artificial intelligence based cargo compartment baggage handling monitoring method of any of claims 1 to 7.

8. A computer-readable storage medium storing a computer program, wherein the computer program causes a computer to execute the artificial intelligence based cargo compartment baggage handling monitoring method of any one of claims 1 to 7.