CN116433742A

CN116433742A - Method and device for judging rule violation of transport vehicle, electronic equipment and readable storage medium

Info

Publication number: CN116433742A
Application number: CN202111653298.2A
Authority: CN
Inventors: 张宽
Original assignee: SF Technology Co Ltd
Current assignee: SF Technology Co Ltd
Priority date: 2021-12-30
Filing date: 2021-12-30
Publication date: 2023-07-14

Abstract

The application discloses a method, a device, electronic equipment and a readable storage medium for judging violation of a transport vehicle, wherein the method comprises the following steps: acquiring a target image; extracting position information of a cargo handling vehicle and target vehicle attribute information in the target image; obtaining violation attribute information corresponding to the position information; and determining the violation judgment result of the goods handling vehicle according to the violation attribute information and the target vehicle attribute information. Therefore, according to the method for judging the violation of the carrying vehicle, on one hand, manual detection is not needed, subjective judgment is reduced while labor cost is reduced, and the accuracy of judging the violation is improved. On the other hand, different violation conditions corresponding to different positions in the field can be judged, the types of violations which can be identified are more comprehensive, the types of goods-carrying vehicles are not limited, and the method can be applied to various scenes.

Description

Method and device for judging rule violation of transport vehicle, electronic equipment and readable storage medium

Technical Field

The application relates to the technical field of logistics, in particular to a method and a device for judging violation of a carrying vehicle, electronic equipment and a readable storage medium.

Background

In the logistics industry, forklifts are an indispensable carrier. In the actual production process, in order to ensure standard operation of the forklift, relevant operation conditions of the forklift need to be supervised.

At present, a forklift is usually supervised by adopting a manual or image detection mode, but the manual supervision method greatly improves the labor cost, relies on subjective judgment of staff, is low in judgment precision, and can only judge simple illegal conditions, so that functions can be achieved incompletely. Therefore, a forklift violation judging method capable of guaranteeing low cost and detecting various violation conditions is needed.

Disclosure of Invention

The application provides a method, a device, electronic equipment and a readable storage medium for judging the violation of a transport vehicle, and aims to solve the technical problems that the current method cannot ensure low cost and can detect various violation conditions.

In a first aspect, the present application provides a method for determining a violation of a handling vehicle, including:

acquiring a target image;

extracting position information of a cargo handling vehicle and target vehicle attribute information in the target image;

obtaining violation attribute information corresponding to the position information;

And determining the violation judgment result of the goods handling vehicle according to the violation attribute information and the target vehicle attribute information.

In one possible implementation manner of the present application, the obtaining the attribute information of the violation corresponding to the location information includes:

determining a vehicle body area of the cargo handling vehicle in the target image according to the angular point positions of the first type of angular points in the position information;

determining an extension area of an accessory part on the cargo handling vehicle in the target image according to the angular point position of a second angular point in the first angular points;

determining a vehicle overall area of the cargo-handling vehicle in a target image based on the vehicle body area and the extension area;

and if the overall vehicle area is at least partially overlapped with a target warning area preset in the target image, taking the violation attribute information corresponding to the target warning area as the violation attribute information corresponding to the position information.

In one possible implementation manner of the present application, the determining, according to the corner positions of the second type of corner points in the first type of corner points, an extension area of an accessory part on the cargo handling vehicle in the target image includes:

Extracting the angular point positions of the second type of angular points in the first type of angular points;

determining the extending direction of the accessory part on the goods handling vehicle in the target image according to the angular point position of the second type of angular point;

and determining the extension area according to the area of the vehicle body area through a preset area conversion strategy.

And determining an extension area of the accessory part in the target image according to the extension area and the extension direction.

predicting the motion direction of the cargo handling vehicle in the target image according to the angular point positions of various angular points in the position information;

determining a moving target position of the cargo handling vehicle in the target image according to the moving direction and the angular point positions of the angular points of the various types;

matching the moving target position with a target warning area preset in the target image, and determining whether the target warning area is a moving target area of the goods handling vehicle;

and if the target guard area is a moving target area of the cargo handling vehicle, using the violation attribute information corresponding to the target guard area as the violation attribute information corresponding to the position information.

In one possible implementation manner of the present application, before the obtaining the attribute information of the violation corresponding to the location information, the method further includes:

extracting vehicle identity information and cargo information in the target vehicle attribute information;

and if the cargo carrying information is matched with the preset compliance cargo carrying information corresponding to the vehicle identity information, executing the step of acquiring the violation attribute information corresponding to the position information.

In one possible implementation manner of the present application, the extracting the location information of the cargo handling vehicle and the attribute information of the target vehicle in the target image includes:

inputting the target image into a preset carrying vehicle detection model to obtain position information of a cargo carrying vehicle and target vehicle attribute information;

the preset detection model of the carrying vehicle is obtained through training the following steps:

acquiring training data, wherein the training data comprises a training image and actual positions of various types of angular points in the training image;

extracting the relative distribution characteristics of the various types of angular points in the training image;

according to the relative distribution characteristics, determining angular point position characteristics of the angular points of various types in the training image;

According to the angular point position characteristics, predicting the predicted positions of the angular points of the various types;

and adjusting parameters in the initial transport vehicle detection model according to the predicted positions and the actual positions of the various types of corner points to obtain a preset transport vehicle detection model.

In one possible implementation manner of the present application, before determining the violation determination result of the cargo handling vehicle according to the violation attribute information and the target vehicle attribute information, the method further includes:

performing face recognition on the target image to determine operator information of the cargo handling vehicle;

acquiring target personnel information corresponding to target vehicle attribute information of the cargo handling vehicle;

and if the operator information is matched with the target person information, executing the step of determining the violation judgment result of the goods handling vehicle according to the violation attribute information and the target vehicle attribute information.

In a second aspect, the present application provides a handling vehicle violation determination device, including:

a first acquisition unit configured to acquire a target image;

an extracting unit for extracting position information of the cargo handling vehicle and target vehicle attribute information in the target image;

The second acquisition unit is used for acquiring the violation attribute information corresponding to the position information;

and the determining unit is used for determining the violation judgment result of the goods handling vehicle according to the violation attribute information and the target vehicle attribute information.

In one possible implementation manner of the present application, the second obtaining unit is further configured to:

In one possible implementation manner of the present application, the carrying vehicle violation judging device further includes a cargo judging unit, where the cargo judging unit is configured to:

In a possible implementation manner of the present application, the extracting unit is further configured to:

and inputting the target image into a preset carrying vehicle detection model to obtain the position information of the cargo carrying vehicle and the target vehicle attribute information.

In one possible implementation manner of the present application, the device for determining a violation of a handling vehicle further includes a face recognition unit, where the face recognition unit is configured to:

In a third aspect, the present application also provides an electronic device, the electronic device including a processor, a memory, and a computer program stored in the memory and executable on the processor, the processor executing steps in any of the handling vehicle violation determination methods provided herein when invoking the computer program in the memory.

In a fourth aspect, the present application further provides a readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of any of the handling vehicle violation determination methods provided herein.

In summary, the method for determining the rule violation of the carrying vehicle provided by the application comprises the following steps: acquiring a target image; extracting position information of a cargo handling vehicle and target vehicle attribute information in the target image; obtaining violation attribute information corresponding to the position information; and determining the violation judgment result of the goods handling vehicle according to the violation attribute information and the target vehicle attribute information. Therefore, according to the method for judging the violation of the carrying vehicle, on one hand, manual detection is not needed, subjective judgment is reduced while labor cost is reduced, and the accuracy of judging the violation is improved. On the other hand, different violation conditions corresponding to different positions in the field can be judged, the types of violations which can be identified are more comprehensive, the types of goods-carrying vehicles are not limited, and the method can be applied to various scenes.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly introduced below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 is a schematic structural diagram of an information acquisition model provided in an embodiment of the present application;

fig. 2 is an application scenario schematic diagram of a method for determining rule violations of a handling vehicle according to an embodiment of the present application;

FIG. 3 is a schematic flow chart of a method for determining a violation of a handling vehicle according to an embodiment of the present disclosure;

FIG. 4 is a schematic flow chart of obtaining attribute information of violations provided in an embodiment of the present application;

FIG. 5 is an image schematic of a cargo-handling vehicle provided in an embodiment of the present application;

FIG. 6 is a schematic diagram of another process for obtaining attribute information of violations provided in embodiments of the present application;

FIG. 7 is a schematic flow chart of determining whether a cargo handling vehicle is illicitly loaded as provided in an embodiment of the present application;

FIG. 8 is a flow diagram of model training provided in an embodiment of the present application;

FIG. 9 is a schematic illustration of a modular structure provided in an embodiment of the present application;

FIG. 10 is a schematic view of an embodiment of a handling vehicle violation judging device provided in an embodiment of the present application;

fig. 11 is a schematic structural diagram of an embodiment of an electronic device provided in an embodiment of the present application.

Detailed Description

The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by those skilled in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.

In the description of the embodiments of the present application, it should be understood that the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or an implicit indication of the number of features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more of the described features. In the description of the embodiments of the present application, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.

The following description is presented to enable any person skilled in the art to make and use the application. In the following description, details are set forth for purposes of explanation. It will be apparent to one of ordinary skill in the art that the present application may be practiced without these specific details. In other instances, well-known processes have not been described in detail in order to avoid unnecessarily obscuring descriptions of the embodiments of the present application. Thus, the present application is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed in the embodiments of the present application.

The embodiment of the application provides a method and device for judging violation of a transport vehicle, electronic equipment and a readable storage medium. The handling vehicle violation judging device may be integrated in an electronic device, and the electronic device may be a server or a terminal.

The execution main body of the method for determining the rule violation of the handling vehicle in the embodiment of the application may be the handling vehicle rule violation determination device provided in the embodiment of the application, or different types of electronic devices such as a server device, a physical host or a User Equipment (UE) integrated with the handling vehicle rule violation determination device, where the handling vehicle rule violation determination device may be implemented in a hardware or software manner, and the UE may specifically be a terminal device such as a smart phone, a tablet computer, a notebook computer, a palm computer, a desktop computer or a personal digital assistant (Personal Digital Assistant, PDA).

The electronic device may be operated in a single operation mode, or may also be operated in a device cluster mode.

First, an information acquisition model that can be used to acquire information of a cargo-handling vehicle is described, and referring to fig. 1, the information acquisition model 100 in fig. 1 includes:

The preprocessing layer 101 is composed of a convolutional neural Network 1011 (Convolutional Neural Networks, CNN) and a Residual Network 1012 (Residual Network), the convolutional neural Network 1011 is used for performing convolutional processing on an input image so as to realize functions of pooling, denoising and the like, and the Residual Network 1012 is used for improving the calculation speed of the convolutional neural Network.

The first feature extraction layer 102 may be formed of an hourglass network (hourglass network) that may extract features of different scales by up-sampling and down-sampling multiple times, and fuse the features of each scale to obtain a thermodynamic diagram, which is input to the second feature extraction layer 103.

The second feature extraction layer 103 may be formed of an hourglass network, and may extract features from an input thermodynamic diagram and output the extracted features.

The position prediction layer 104 may be configured by a full connection layer (fully connected layers, FC), and predicts based on the output of the second feature extraction layer 103, thereby obtaining position information of the cargo-handling vehicle, and the position prediction layer 104 may perform multi-classification prediction.

The attribute prediction layer 105 may be configured by a full-link layer, and may predict the target vehicle attribute information of the cargo-handling vehicle based on the output of the second feature extraction layer 103, and the attribute prediction layer 105 may perform multi-classification prediction.

Wherein, the position prediction layer 104 and the attribute prediction layer 105 may be prediction layers capable of implementing multi-classification prediction.

It can be seen that the above-described information acquisition model 100 can acquire the position information of the cargo-handling vehicle and the target-vehicle attribute information simultaneously by one model, reduces the number of models to be called when determining violations, greatly reduces the calculation amount because of the same feature (output of the second feature extraction layer 103) when predicting the position information and the target-vehicle attribute information, and avoids prediction differences due to the difference in the extracted features when employing a plurality of models.

Referring to fig. 2, fig. 2 is a schematic view of a scenario of a system for determining a violation of a handling vehicle according to an embodiment of the present application. The system for determining the violation of the handling vehicle may include an electronic device 200, and the electronic device 200 is integrated with a device for determining the violation of the handling vehicle.

In addition, as shown in fig. 2, the handling vehicle violation determination system may further include a memory 201 for storing data, such as storing image data.

It should be noted that, the schematic view of the scenario of the system for determining the violation of the handling vehicle shown in fig. 2 is only an example, and the system for determining the violation of the handling vehicle and the scenario described in the embodiments of the present application are for more clearly describing the technical solution of the embodiments of the present application, and do not constitute a limitation on the technical solution provided in the embodiments of the present application, and as one of ordinary skill in the art can know, along with the evolution of the system for determining the violation of the handling vehicle and the appearance of a new service scenario, the technical solution provided in the embodiments of the present invention is equally applicable to similar technical problems.

Next, a method for determining a violation of a handling vehicle provided in an embodiment of the present application will be described, in which an electronic device is used as an execution body, and in order to simplify and facilitate description, the execution body is omitted in a subsequent method embodiment, and the determining of a violation of a handling vehicle includes: acquiring a target image; extracting position information of a cargo handling vehicle and target vehicle attribute information in the target image; obtaining violation attribute information corresponding to the position information; and determining the violation judgment result of the goods handling vehicle according to the violation attribute information and the target vehicle attribute information.

Referring to fig. 3, fig. 3 is a schematic flow chart of a method for determining a violation of a handling vehicle according to an embodiment of the present application. It should be noted that although a logical order is illustrated in the flowchart, in some cases, the steps illustrated or described may be performed in an order different from that herein, and hereinafter, for convenience of explanation, it is considered that only one cargo-moving vehicle is included in the target image if not specifically stated, but the number of cargo-moving vehicles in the target image cannot be regarded as a limitation of the present application. The method for determining the violation of the carrying vehicle specifically comprises the following steps 301 to 304, wherein:

301. A target image is acquired.

The target image is an image including a cargo handling vehicle to be subjected to violation judgment, and the cargo handling vehicle refers to various wheeled handling vehicles for handling, stacking and short-distance transportation of cargoes, for example, a forklift used for handling packages in the express logistics industry is a cargo handling vehicle.

The method for acquiring the target image is not limited, and the target device may be acquired by a video camera, a still camera, or the like. For example, when judging whether the forklift in the warehouse is illegal, the forklift in the warehouse can be photographed through a camera pre-installed in the warehouse to obtain a target image.

In some embodiments, a certain preprocessing may be performed on the image acquired by the image acquisition device, so as to obtain a target image with clear image content. For example, the image acquired by the image acquisition apparatus may be subjected to preprocessing such as contrast enhancement, denoising, and the like to obtain a target image.

302. And extracting the position information of the cargo handling vehicle and the attribute information of the target vehicle in the target image.

The position information includes the position of the cargo-moving vehicle in the target image. For example, an image coordinate system may be established in the target image, and coordinates of the cargo handling vehicle in the image coordinate system may be used as position information of the cargo handling vehicle. For ease of understanding, the following specific examples illustrate how to establish an image coordinate system in a target image: assuming that coordinate axes in the image coordinate system are an X-axis and a Y-axis, an image midpoint of the target image may be taken as a coordinate origin, an arbitrary direction in the target image may be taken as a positive direction of the X-axis in the image coordinate system, and the positive direction of the Y-axis in the image coordinate system may be determined according to the positive direction of the X-axis that has been determined, so as to establish the image coordinate system. After determining the image coordinate system, coordinates of the cargo-handling vehicle in the image coordinate system may be acquired to obtain the location information.

In some embodiments, the coordinates of the midpoint of the corresponding region of the cargo-handling vehicle in the target image in the image coordinate system may be used as the location information for the cargo-handling vehicle. For example, when the region corresponding to the cargo-handling vehicle in the target image is a square region and the coordinate range corresponding to the square region in the image coordinate system is x e [4,8], y e [4,8], the coordinates (6, 6) may be used as the position information of the cargo-handling vehicle.

The target vehicle attribute information refers to vehicle attribute information of the cargo-handling vehicle in the target image, which may include one or more information. For example, the vehicle attribute information may include at least one of cargo information of the cargo handling vehicle, which refers to cargo type information corresponding to a cargo type that the cargo handling vehicle is currently handling, and vehicle identity information, which refers to vehicle type information corresponding to the cargo handling vehicle, which refers to whether the cargo handling vehicle is currently carrying cargo.

There are various corresponding classification methods for the cargo type information and the vehicle type information. For example, as for the cargo type information, the cargo may be classified according to the volume size of the cargo, for example, may be classified as large cargo, medium cargo, small cargo, and the like. In addition, the goods may be classified according to the purpose of the goods, for example, furniture, food, electronic products, and the like. The vehicle type information may be classified according to the cargo carrying capacity of the cargo carrying vehicle, and may be classified into, for example, a large-sized carrier vehicle, a medium-sized carrier vehicle, and a small-sized carrier vehicle (when the cargo carrying vehicle is a forklift, the vehicle corresponds to a large-sized forklift, a medium-sized forklift, and a small-sized forklift). Alternatively, the goods may be classified according to the type of the target goods to be carried by the goods carrying vehicle, and may be classified into, for example, for carrying furniture, for carrying food, for carrying electronic products, and the like.

In some embodiments, the location information of the cargo-handling vehicle and the target vehicle attribute information in the target image may be extracted by the information acquisition model 100 of FIG. 1. Specifically, the target image may be input into the information acquisition model 100, and after being processed by the preprocessing layer 101, the image features in the target image are extracted by the first feature extraction layer 102 and the second feature extraction layer 103, and the position information of the cargo handling vehicle and the target vehicle attribute information in the target image are predicted by the position prediction layer 104 and the attribute prediction layer 105, respectively.

303. And obtaining the violation attribute information corresponding to the position information.

The violation attribute information is determination reference information for determining whether the cargo-handling vehicle is out of order, and includes vehicle attribute information determined to be out of order, so that it can be understood as vehicle attribute information that indicates that the cargo-handling vehicle in the target image is out of order, that is, that the vehicle is parked out of order, that the vehicle is traveling out of order, and so on, when the target vehicle attribute information matches the violation attribute information corresponding to the position information. For example, the violation attribute information corresponding to the location information may be violation attribute information corresponding to a vehicle forbidden area matched with the location information, where the vehicle forbidden area refers to an area where danger may occur when the cargo handling vehicle enters, and the location information matched with the vehicle forbidden area refers to an image location corresponding to the location information included in the corresponding area of the vehicle forbidden area in the target image. It will be appreciated that since different vehicle entry regions may be associated with different offending attribute information, when the location information matches different vehicle entry regions, the corresponding offending attribute information may also be different.

For ease of understanding, the following specific examples are set forth: assuming that the cargo handling vehicle in the target image is a forklift, when the position information of the forklift in the target image is matched with the large forklift forbidden area, namely, the forklift enters the large forklift forbidden area, the illegal attribute information corresponding to the position information is illegal attribute information corresponding to the large forklift forbidden area, and it can be understood that the illegal attribute information contains the type information of the large forklift, and if the forklift entering the large forklift forbidden area is the large forklift, the target vehicle attribute information is matched with the illegal attribute information, and the forklift illegal is judged. Or when the position information of the forklift in the target image is matched with the 'cargo vehicle forbidden area', namely, the forklift enters the 'cargo vehicle forbidden area', the illegal attribute information corresponding to the position information is the illegal attribute information corresponding to the 'cargo vehicle forbidden area', and it can be understood that the illegal attribute information contains cargo information of the 'forklift carrying goods', and if the forklift entering the 'cargo vehicle forbidden area' carries goods, the target vehicle attribute information is matched with the illegal attribute information, and the forklift illegal is judged.

In some embodiments, the vehicle forbidden areas may be pre-corresponding to the illegal attribute information according to the condition of the stacked goods in the vehicle forbidden areas, for example, the illegal attribute information corresponding to the vehicle forbidden areas may be manually set according to the type of the stacked goods, when the stacked goods in the vehicle forbidden areas are inflammable and explosive, the large truck may be set as the illegal attribute information of the vehicle forbidden areas, so as to avoid explosion or combustion of the stacked goods when the large truck enters the vehicle forbidden areas to rollover.

The information included in the attribute information may be one kind or plural kinds. For example, the violation attribute information may include one of cargo information and vehicle identity information, or may include both cargo information and vehicle identity information. For example, when the vehicle forbidden area is a "large forklift forbidden area" or a "cargo vehicle forbidden area", the corresponding violation attribute information is vehicle identity information and cargo information, respectively. For example, when the target vehicle forbidden region is a cargo large forklift forbidden region, the corresponding illegal attribute information comprises vehicle identity information and cargo information.

304. And determining the violation judgment result of the goods handling vehicle according to the violation attribute information and the target vehicle attribute information.

For example, the violation attribute information may be matched with the target vehicle attribute information to determine a violation determination of the cargo-handling vehicle. If the violation attribute information is the same as the target vehicle attribute information, a cargo handling vehicle violation may be determined. For ease of understanding, the following specific examples are set forth: assuming that the cargo handling vehicle in the target image is a forklift, when the violation attribute information corresponding to the position information of the forklift in the target image is the violation attribute information corresponding to the large forklift forbidden area, namely the violation attribute information contains the type information of the large forklift, if the forklift in the target image is the large forklift, the forklift can be judged to be illegal. For example, when the violation attribute information corresponding to the position information of the forklift in the target image is the violation attribute information corresponding to the forbidden region of the truck, that is, the violation attribute information includes the cargo information of the forklift carrying cargo, if the forklift carrying cargo, the forklift can be judged to be illegal.

If a cargo handling vehicle violation is determined, a prompt may be sent to alert. For example, at least one of the prompt categories of audible prompts, text prompts, flashing prompts, etc. may be issued by a target terminal such as a smart phone, tablet computer, video matrix, monitoring platform, vehicle-mounted device, etc. to prompt a worker for a cargo handling vehicle violation.

In summary, the method for determining the rule violation of the handling vehicle provided in the embodiment of the present application includes: acquiring a target image; extracting position information of a cargo handling vehicle and target vehicle attribute information in the target image; obtaining violation attribute information corresponding to the position information; and determining the violation judgment result of the goods handling vehicle according to the violation attribute information and the target vehicle attribute information. Therefore, according to the method for judging the violation of the carrying vehicle, on one hand, manual detection is not needed, subjective judgment is reduced while labor cost is reduced, and the accuracy of judging the violation is improved. On the other hand, different violation conditions corresponding to different positions in the field can be judged, the types of violations which can be identified are more comprehensive, the types of goods-carrying vehicles are not limited, and the method can be applied to various scenes.

In some embodiments, to improve the accuracy of extracting the location information, the location of the vehicle body of the cargo handling vehicle in the target graphic may be extracted to obtain the location information. The reasons are as follows: the cargo-handling vehicle may include a series of functional components in addition to the vehicle body. For example, in addition to a vehicle body to which main components such as a steering wheel, a control chip, an engine, and a tire are attached, functional components such as a fork are attached, and these functional components are difficult to accurately recognize by an image due to inconspicuous feature points, similar colors to background colors, and the like, so that a result obtained by extracting the position of the vehicle body is more accurate. In order to obtain the violation attribute information, the functional components in the target image can be obtained by detecting the vehicle body in the target image and then extending according to a preset proportion so as to determine the whole cargo handling vehicle in the target image. The following provides a method for acquiring the attribute information of the violation in this case, referring to fig. 4, at this time, the acquiring the attribute information of the violation corresponding to the location information includes:

401. and determining a vehicle body area of the cargo handling vehicle in the target image according to the angular point positions of the first type of angular points in the position information.

The first type of corner points refer to corner points of the vehicle body in the target image. For convenience of understanding, taking fig. 5 as an example of the first type of corner points, referring to fig. 5, the forklift 500 is composed of the vehicle body 501 and the fork 502, so in fig. 5, the first type of corner points refer to corner points 5011, 5012, 5013 and 5014, and the vehicle body region refers to a region surrounded by corner points 5011, 5012, 5013 and 5014 connected in this order.

In some embodiments, an image coordinate system may be first established in the target image, and then coordinates of the first type of corner in the image coordinate system are taken as corner positions of the first type of corner.

The embodiment of the application may obtain the position information through the preset information acquisition model 100 in fig. 1, at this time, the corner points of the vehicle body in the training image may be labeled during training, and the initial information acquisition model 100 is trained through the labeled training image, so as to obtain the preset information acquisition model 100, and the corner point positions of the corner points of each first type may be extracted through the position prediction layer 104 therein.

402. And determining the extension area of the accessory part on the goods handling vehicle in the target image according to the angular point position of the second angular point in the first angular point.

In some embodiments, the second type of corner point may refer to a corner point of the first type that is closest to a feature of the cargo handling vehicle in the target image. Continuing with the description of fig. 5, among the corner points 5011, 5012, 5013, and 5014 of fig. 5, the corner points 5011 and 5012 are closest to the fork 502, and thus, in fig. 5, the second type of corner points are the corner points 5011 and 5012.

If the position information of the cargo handling vehicle in the target image is obtained through the preset information acquisition model 100 in fig. 1, different labels can be labeled on each type of corner points included in the first type of corner points in the training image when the initial information acquisition model 100 is trained, and then the corner point position of the second type of corner points in the target image can be determined through the preset information acquisition model 100 when the target image is processed. Taking the training image as an example of fig. 5, in the training stage, the corner 5011 and the corner 5012 can be marked as the second type corner, the corner 5013 and the corner 5014 can be marked as the third type corner, the third type corner refers to all the corners except the second type corner in the first type corner, then the initial information acquisition model 100 is trained through the marked training image, and the preset information acquisition model 100 is obtained, wherein the position prediction layer 104 can realize the multi-classification function, and the position prediction layer 104 can extract the corner positions of all types of corners in the target image, namely the corner positions of all the second type corners and the corner positions of all the third type corners.

In other embodiments, each corner included in the first type of corner in the training image may be labeled with a different label during the training phase. Taking fig. 5 as an example of the training image, if the corner 5011, the corner 5012, the corner 5013 and the corner 5014 are first class corners, in the training stage, the corner 5011, the corner 5012, the corner 5013 and the corner 5014 may be marked as a first class corner, a second class corner, a third class corner and a fourth class corner, respectively, and in executing step 402, the first class corner and the second class corner are used as a second class corner. In the embodiment of the application, when a new functional component is added to the cargo handling vehicle, if the cargo handling vehicle with the added functional component is required to be judged whether to violate rules, the definition logic of the second type corner point is required to be changed, so that the cargo handling vehicle is very flexible. For example, when another fork 503 is newly added to the forklift in fig. 5, the first sub-class corner, the second sub-class corner, and the third sub-class corner may be used as the second sub-class corner.

The definition of the accessory parts and the functional parts is the same, and will not be described in detail below.

The extended area refers to an area corresponding to a functional component of the cargo handling vehicle in the target image, and for example, in fig. 5, if the functional component in fig. 5 is only the fork 502, the extended area refers to an area corresponding to the fork 502. If the functional components in fig. 5 include both forks 502 and 503, the extended area refers to the area corresponding to fork 502.

In some embodiments, the extension region may be determined according to an area of the vehicle body region in the target image and a direction in which the functional component extends outward from the vehicle body. The step of determining the extension area of the accessory component on the cargo handling vehicle in the target image according to the corner positions of the second type corner in the first type corner may be implemented by the following steps:

(1) And extracting the angular point positions of the second type of angular points in the first type of angular points.

(2) And determining the extending direction of the accessory part on the goods handling vehicle in the target image according to the corner positions of the second type of corner points.

The extending direction refers to a direction in which the functional component extends outward from the vehicle body in the target image. Taking fig. 5 as an example, a method for determining the extending direction is as follows:

(2.1) assuming that the corner point 5011 and the corner point 5012 are the second type of corner points, the direction of the edge 5015 of the vehicle body 501 in the target image is first determined according to the relative position between the corner point 5011 and the corner point 5012, and the edge 5015 is the edge obtained by connecting the corner point 5011 and the corner point 5012.

(2.2) determining the direction of the edge 5015 in the target image to be directed to the normal direction outside the vehicle body 501, that is, the direction of the normal 5016 in the target image, based on the direction of the edge 5015 in the target image.

(2.3) the direction of the normal 5016 is taken as the extending direction.

(3) And determining the extension area according to the area of the vehicle body area through a preset area conversion strategy.

The extended area is the area of the new area of the target image after the vehicle body area is extended, and the extended area is the area of the corresponding area of the functional component in the target image because the purpose of extension is to obtain the corresponding area of the functional component in the target image.

The area conversion policy is a preset policy for calculating an extended area, and in some embodiments, the area conversion policy may be a formula for calculating an extended area, for example, equation (1) may be used as the area conversion policy:

S ₁ ＝S ₀ * a type son (1)

Wherein S is ₁ Is an extension area S ₀ Is the area of the vehicle body region, and a is a preset area conversion coefficient.

Since the projected area ratio on the horizontal plane between the functional parts and the vehicle body is similar for any kind of cargo-handling vehicle and the image acquisition apparatus is generally provided at the top of the field, the acquired target image can be approximately regarded as a plan view, the projected area ratios on the horizontal plane between the functional parts and the vehicle body of a plurality of cargo-handling vehicles can be calculated in advance, and the average value of the respective projected area ratios is taken as a in the equation (1), and the extended area can be calculated according to the equation (1).

(4) And determining an extension area of the accessory part in the target image according to the extension area and the extension direction.

In some embodiments, the vehicle body region may be extended in the extending direction until the extended area reaches the extended area to obtain the extended region.

In addition to the above-described manner of obtaining the extension region, the extension area may be set to a constant value, and the vehicle body region may be extended according to the extension direction and the extension area to obtain the extension region.

In other embodiments, the corner position of the second corner is taken as an extension starting point, the extension end point is determined according to the extension area in the extension direction, and the area wrapped by the second corner and the extension end point is taken as an extension area.

The method of obtaining the extension region described above cannot be regarded as a limitation of the embodiments of the present application. For example, the method of acquiring the extending direction may also be changed. For example, in the case of acquiring the extending direction as described above, the normal direction may be rotated by a predetermined angle instead of the extending direction, and the obtained direction may be used as the extending direction.

403. And determining a vehicle overall area of the cargo handling vehicle in a target image according to the vehicle body area and the extension area.

The vehicle overall area refers to an overall area corresponding to a vehicle body and functional components of the cargo handling vehicle in the target image, and the vehicle overall area can be obtained by superposing the vehicle body area and the extension area. Taking fig. 5 as an example, if the functional component is only the fork 502, the overall area of the vehicle refers to the areas of the vehicle body 501 and the fork 502 corresponding in fig. 5. If the functional components include both forks 502 and 503, the overall area of the vehicle refers to the areas of the vehicle body 501, forks 502 and forks 503 corresponding in fig. 5.

404. And if the overall vehicle area is at least partially overlapped with a target warning area preset in the target image, taking the violation attribute information corresponding to the target warning area as the violation attribute information corresponding to the position information.

The target guard region may be understood as a region corresponding to any one of the vehicle-prohibited regions described above in the target image.

If the overall vehicle area is at least partially overlapped with a target guard area preset in the target image, the condition that the cargo handling vehicle enters a target vehicle forbidden area corresponding to the target guard area is indicated, so that whether the cargo handling vehicle is allowed to enter the target vehicle forbidden area or not needs to be judged, the illegal attribute information corresponding to the target guard area, namely, the illegal attribute information corresponding to the target vehicle forbidden area, is used as the illegal attribute information corresponding to the position information, the target vehicle attribute information of the cargo handling vehicle is matched with the illegal attribute information corresponding to the target guard area, and whether the cargo handling vehicle is illegal or not is judged.

Further, a threshold may be preset for determining the size of the area overlapping between the overall area of the vehicle and the target guard area, and when the overlapping area is smaller than the threshold, it is indicated that the cargo handling vehicle may enter the target vehicle forbidden area only because the control of the operator is poor, and since the volume of the vehicle body entering the target vehicle forbidden area is small, even if the target vehicle attribute information of the cargo handling vehicle matches with the illegal attribute information corresponding to the target vehicle forbidden area, a safety problem does not occur, and it may be regarded that the cargo handling vehicle does not enter the target vehicle forbidden area. In contrast, when the overlapping area is greater than or equal to the threshold value, it is indicated that most of the vehicle bodies of the cargo handling vehicles have entered the target vehicle prohibited area, and at this time, the reason may not be considered to be that the control of the operator is poor, it is necessary to match the violation attribute information corresponding to the target guard area, that is, the violation attribute information corresponding to the target vehicle prohibited area, as the violation attribute information corresponding to the location information, and to determine whether the cargo handling vehicles in the target image are illegal.

In some embodiments, the movement direction of the cargo handling vehicle in the target image may be predicted according to the angular point position, and the violation attribute information corresponding to the vehicle forbidden area into which the cargo handling vehicle may enter may be used as the violation attribute information corresponding to the position information. Referring to fig. 6, at this time, the obtaining the attribute information of the violation corresponding to the location information includes:

601. and predicting the movement direction of the cargo handling vehicle in the target image according to the angular point positions of the angular points of various types in the position information.

The corner positions in step 601 include the positions of the multiple types of corner points. For example, the corner positions of the second class corner and the corner positions of the third class corner may be included, or the corner positions of the first class corner, the second class corner, the third class corner and the fourth class corner may be included, and the descriptions of the second class corner, the third class corner, the first class corner, the second class corner, the third class corner and the fourth class corner may be referred to above, which are not described in detail.

The direction of movement in step 601 refers to the potential direction of movement of the cargo-handling vehicle, i.e., the direction of movement of the cargo-handling vehicle that is likely to be next.

The movement direction may be obtained by the same method as that for obtaining the extension direction, for example, the movement direction may be obtained according to the method in the above-described step (2.1) -step (2.3).

602. And determining the moving target position of the cargo handling vehicle in the target image according to the moving direction and the angular point positions of the angular points of the various types.

In some embodiments, the angular point positions of the angular points of each type in the target image can be used as a starting point, the motion direction is used as the direction of the motion track, the motion track of the angular points of each type is obtained, and each point on the motion track can be used as the motion target position.

603. And matching the moving target position with a target warning area preset in the target image, and determining whether the target warning area is a moving target area of the goods handling vehicle.

604. And if the target guard area is a moving target area of the cargo handling vehicle, using the violation attribute information corresponding to the target guard area as the violation attribute information corresponding to the position information.

In some embodiments, it may be determined whether the position range of the target alert area in the target image includes at least one of the moving target positions, and if the position range of the target alert area in the target image includes at least one of the moving target positions, it is indicated that the target alert area is a moving target area of the cargo handling vehicle in the target image, that is, the cargo handling vehicle in the target image may drive into the target vehicle forbidden area, and at this time, it is required to match the target vehicle attribute information with the violation attribute information corresponding to the target alert area, that is, the violation attribute information corresponding to the target vehicle forbidden area, and determine whether the cargo handling vehicle in the target image may be violated.

Similarly, a threshold may be set for judging whether the reason why the target guard area is the moving target area is poor control of the operator. Reference may be made specifically to step 404, and no further description is given.

In some embodiments, it may also be determined first whether the cargo handling vehicle in the target image is carrying cargo in violation, prior to acquiring the violation attribute information. Referring to fig. 7, at this time, before the obtaining the attribute information of the violation corresponding to the location information, the method further includes:

701. and extracting vehicle identity information and cargo information in the target vehicle attribute information.

The description of the vehicle identity information and the cargo information may refer to the description of the attribute information of the target vehicle in step 302, which is not described in detail.

Referring to table 1, table 1 shows a specific case after extracting vehicle identity information and cargo information in target vehicle attribute information, where the cargo handling vehicle is a forklift:

fork truck type	Whether or not to carry cargo	Cargo type
			Small forklift	Is that	Large cargo

TABLE 1

Wherein, the fork truck type corresponds the vehicle identity information in the target vehicle attribute information, whether the cargo and the cargo type correspond to the cargo information in the target vehicle attribute information.

Referring to table 2, specific cases of another cargo handling vehicle, namely a forklift, after extracting the vehicle identity information and the cargo information in the target vehicle attribute information are shown in table 2:

fork truck type	Whether or not to carry cargo	Cargo type
			For transporting furniture	Is that	Furniture with a cover

TABLE 2

Similarly, the forklift category corresponds to the vehicle identification information in the target vehicle attribute information, and whether the load and the cargo category correspond to the load information in the target vehicle attribute information.

702. And if the cargo carrying information is matched with the preset compliance cargo carrying information corresponding to the vehicle identity information, executing the step of acquiring the violation attribute information corresponding to the position information.

The preset compliance cargo information refers to cargo information corresponding to the vehicle identity information in the target vehicle attribute information when compliance cargo is carried out. For example, the preset compliance cargo information may refer to a cargo type corresponding to the vehicle identity information in the target vehicle attribute information when the compliance cargo is carried. Different kinds of cargo handling vehicles have different cargo carrying capacities, and if the cargo currently handled by the cargo handling vehicles exceeds the corresponding cargo carrying capacity, the risk of rollover and the like may occur, so that the cargo carrying information of the different kinds of cargo handling vehicles, such as the cargo kinds and the like, capable of being handled by the different kinds of cargo handling vehicles needs to be limited in advance, that is, the corresponding preset compliance cargo carrying information is set for the different kinds of cargo handling vehicles.

For example, different preset compliance cargo information may be set according to the type of cargo handling vehicle. For example, the "small-sized cargo" may be used as preset compliance cargo information corresponding to a small-sized forklift having relatively weak cargo capacity, that is, the small-sized forklift may determine compliance of the corresponding forklift when transporting the small-sized cargo. For example, the "small cargo", "medium cargo" and "large cargo" may be used as preset compliance cargo information corresponding to a large forklift with relatively strong cargo capacity, that is, the large forklift may determine compliance of the corresponding forklift no matter what cargo is being carried, in this example, if the cargo information and the vehicle identity information of the forklift are as shown in table 1, then it may be determined that the corresponding forklift is illegal. Alternatively, "furniture" may be defined as preset compliance cargo information corresponding to a forklift of the type "for transporting furniture", that is, when the cargo transported by the forklift for transporting furniture is furniture, the corresponding forklift compliance may be determined, and in this example, if the cargo information and the vehicle identity information of the forklift are as shown in table 2, the corresponding forklift compliance may be determined.

If it is determined that the cargo-moving vehicle is compliant, the step of acquiring the violation attribute information corresponding to the location information may be performed. If a cargo handling vehicle violation is determined, a prompt may be issued to alert.

In some embodiments, the location information of the cargo handling vehicle and the target vehicle attribute information in the cargo target image may be obtained by the information acquisition model 100 in fig. 1, and at this time, the target image may be input into the information acquisition model 100 preset in fig. 1 to obtain the location information and the target vehicle attribute information. Referring to fig. 8, the preset information acquisition model 100 may be trained by:

801. and obtaining training data, wherein the training data comprises training images and actual positions of various types of angular points in the training images.

For example, a large number of images of the cargo handling vehicle may be obtained from a preset database, and a data enhancement process may be performed on a part of the images, where the format of all the images is not limited in the present application, for example, the images of the training image, the target image, etc. may be images in xml, jpg, etc. In some embodiments, a portion of the image may be randomly selected from the acquired image of the cargo-handling vehicle, the selected image may be subjected to data enhancement processing such as flipping, random cropping, color dithering, translation transformation, scale transformation, contrast transformation, noise disturbance, and the like, and the enhanced image may be normalized to obtain the training image. Then, labeling is performed on each type of corner points in the training image by means of manual labeling, machine labeling and other methods, and specific labeling methods can refer to the mode in step 402, and detailed description is omitted.

802. And extracting the relative distribution characteristics of the various types of angular points in the training image.

The relative distribution characteristics comprise information of relative position relations among various types of angular points in the training image. Illustratively, the relative distribution features of the various types of corner points in the training image may be extracted by the first feature extraction layer 102 in the initial information acquisition model 100 of fig. 1. For example, when the first feature extraction layer 102 is formed by an hourglass network, the training image processed by the preprocessing layer 101 may be up-sampled and down-sampled for multiple times, so as to extract features of different scales of each type of corner points in the training image, and then the features of different scales are fused, so that the relative distribution features of each type of corner points in the training image are obtained, and the relative distribution features may be represented by a thermodynamic diagram (Heat Map);

thermodynamic diagrams are a type of feature diagram that can characterize the distribution of objects.

803. And determining the angular point position characteristics of the angular points of each type in the training image according to the relative distribution characteristics.

The angular point position features contain the position information of various types of angular points in the training image. Illustratively, the corner position features of the various types of corners in the training image may be obtained by the second feature extraction layer 103 in the initial information acquisition model 100 of fig. 1. For example, when the second feature extraction layer 103 is formed by an hourglass network, the relative distribution features output by the first feature extraction layer 102 may be up-sampled and down-sampled multiple times to extract features of different scales of each type of corner points in the relative distribution features, and then the features of different scales are fused to obtain corner point position features of each type of corner points in the training image, and similarly, the corner point position features may also be represented in a thermodynamic diagram form.

It can be understood that, when determining the angular point position feature, the relative position relation between the various types of angular points in the relative distribution feature is considered, so that the angular point position information contained in the obtained angular point position feature is more accurate than the angular point position information obtained by other modes.

804. And predicting the predicted positions of the various types of corner points according to the corner point position characteristics.

Illustratively, the predicted positions of the various types of corner points in the training image may be predicted by the position prediction layer 104 in the initial information acquisition model 100 of fig. 1. Assuming that the corner types include the first class corner, and the first class corner further includes the first subclass corner, the second subclass corner, the third subclass corner and the fourth subclass corner, if fig. 5 is used as the training image, each prediction position condition obtained may refer to table 3:

TABLE 3 Table 3

Wherein x is ₁ ，y ₁ 、x ₂ ，y ₂ 、x ₃ ，y ₃ 、x ₄ ，y ₄ In an image coordinate system preset in a training image, coordinates corresponding to a first subclass angular point 5011, a second subclass angular point 5012, a third subclass angular point 5013 and a fourth subclass angular point 5014 are respectively provided.

805. And adjusting parameters in the initial transport vehicle detection model according to the predicted positions and the actual positions of the various types of corner points to obtain a preset transport vehicle detection model.

In the present embodiment, the handling vehicle detection model may be understood as the information acquisition model 100 in fig. 1.

Prior to performing steps 801-805, training preparation may be performed by:

(1) Building a training environment of a detection model of the transport vehicle, wherein the training environment refers to a configuration environment of the model;

(2) Constructing a transport vehicle detection model, and defining a loss function of the transport vehicle detection model, wherein the loss function can be a cross entropy loss function, a square loss function and the like;

(3) Modifying training parameter configurations, the training parameters may include training step size, training rate, and the like;

(4) And importing the pre-training weight of the transport vehicle detection model to obtain an initial transport vehicle detection model.

After the training preparation step is performed, the labeled training image can be input into an initial transport vehicle detection model for training.

In addition, the training image in step 801 may be further divided into a training image set and a test image set, the initial detection model of the transport vehicle is trained by the training image in the training image set, the trained detection model of the transport vehicle is verified by the training image in the test image set, and if the trained detection model of the transport vehicle meets a preset training termination condition, the trained detection model of the transport vehicle is used as the preset detection model of the transport vehicle.

In some embodiments, it may also be determined whether the operator of the cargo-handling vehicle corresponds to a person in the shift schedule to determine whether the cargo-handling vehicle is dedicated to a person. Illustratively, the determination may be made by:

(1) And carrying out face recognition on the target image, and determining operator information of the cargo handling vehicle, wherein the operator information comprises personnel information of personnel currently operating the cargo handling vehicle.

(2) And acquiring target personnel information corresponding to the target vehicle attribute information of the cargo handling vehicle, wherein the target personnel information can be personnel information of a predetermined compliance operator of the cargo handling vehicle in a scheduling table.

(3) And matching the operator information with the target personnel information, and if the operator information and the target personnel information are successfully matched, indicating that the special person for the goods handling vehicle is special.

The embodiment of the present application also provides a module structure that can perform the method for determining a violation of a handling vehicle, and referring to fig. 9, the module structure in fig. 9 includes a handling vehicle detection module 901, an attribute detection module 902, an image acquisition module 903, and a terminal module 904. The handling vehicle detection module 901 includes a detection data set making module 9011 and a detection model training module 9012, where the detection data set making module 9011 is configured to obtain a training image, label the training image, and divide the training image into a training image set and a test image set. The test model training module 9012 is configured to perform training preparation, construct an initial transport vehicle test model, and train the initial transport vehicle test model through the training image set and the test image set output by the test data set making module 9011, so as to obtain a preset transport vehicle test model.

The attribute detection module 902 is configured to process the target image through a preset detection model of the cargo handling vehicle, so as to determine a violation determination result of the cargo handling vehicle.

The image acquisition module 903 is used to acquire a target image.

The terminal module 904 is configured to send a prompt message when the cargo handling vehicle violates a rule.

In order to better implement the method for determining the rule violation of the handling vehicle in the embodiment of the present application, on the basis of the method for determining the rule violation of the handling vehicle, a device for determining the rule violation of the handling vehicle is further provided in the embodiment of the present application, as shown in fig. 10, which is a schematic structural diagram of an embodiment of the device for determining the rule violation of the handling vehicle in the embodiment of the present application, and the device 1000 for determining the rule violation of the handling vehicle includes:

a first acquisition unit 1001 for acquiring a target image;

an extracting unit 1002, configured to extract position information of a cargo handling vehicle and target vehicle attribute information in the target image;

a second obtaining unit 1003, configured to obtain violation attribute information corresponding to the location information;

a determining unit 1004, configured to determine a violation determination result of the cargo handling vehicle according to the violation attribute information and the target vehicle attribute information.

In a possible implementation manner of the present application, the second obtaining unit 1003 is further configured to:

In one possible implementation manner of the present application, the carrying vehicle violation judging device 1000 further includes a cargo judging unit 1005, where the cargo judging unit 1005 is configured to:

In one possible implementation of the present application, the extracting unit 1002 is further configured to:

In one possible implementation manner of the present application, the carrying vehicle violation judging device 1000 further includes a face recognition unit 1006, where the face recognition unit 1006 is configured to:

In the implementation, each unit may be implemented as an independent entity, or may be implemented as the same entity or several entities in any combination, and the implementation of each unit may be referred to the foregoing method embodiment, which is not described herein again.

The method for determining the rule violation of the handling vehicle in any embodiment can be executed by the device for determining the rule violation of the handling vehicle, so that the method for determining the rule violation of the handling vehicle in any embodiment of the application can achieve the beneficial effects, which are detailed in the foregoing description and are not repeated here.

In addition, in order to better implement the method for determining the rule violation of the handling vehicle in the embodiment of the present application, on the basis of the method for determining the rule violation of the handling vehicle, referring to fig. 11, fig. 11 shows a schematic structural diagram of the electronic device in the embodiment of the present application, and specifically, the electronic device provided in the embodiment of the present application includes a processor 1101, where the processor 1101 is configured to implement each step of the method for determining the rule violation of the handling vehicle in any embodiment when executing a computer program stored in a memory 1102; alternatively, the processor 1101 is configured to implement the functions of each unit in the corresponding embodiment as in fig. 10 when executing the computer program stored in the memory 1102.

By way of example, a computer program may be partitioned into one or more modules/units that are stored in the memory 1102 and executed by the processor 1101 to accomplish the embodiments of the present application. One or more of the modules/units may be a series of computer program instruction segments capable of performing particular functions to describe the execution of the computer program in a computer device.

Electronic devices may include, but are not limited to, processor 1101, memory 1102. It will be appreciated by those skilled in the art that the illustrations are merely examples of electronic devices and are not limiting of electronic devices, and may include more or fewer components than illustrated, or may combine certain components, or different components.

The processor 1101 may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like, which is a control center for an electronic device, with various interfaces and lines connecting various parts of the overall electronic device.

The memory 1102 may be used to store computer programs and/or modules, and the processor 1101 implements the various functions of the computer device by running or executing the computer programs and/or modules stored in the memory 1102 and invoking data stored in the memory 702. The memory 1102 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, application programs required for at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, video data, etc.) created according to the use of the electronic device, and the like. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, smart Media Card (SMC), secure Digital (SD) Card, flash Card (Flash Card), at least one disk storage device, flash memory device, or other volatile solid-state storage device.

It will be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process of the above-described device for determining rule violations of a handling vehicle, electronic device and corresponding units of the above-described device may refer to the description of the method for determining rule violations of a handling vehicle in any embodiment, and will not be described in detail herein.

Those of ordinary skill in the art will appreciate that all or a portion of the steps of the various methods of the above embodiments may be performed by instructions or by controlling associated hardware, which may be stored on a readable storage medium and loaded and executed by a processor.

Therefore, the embodiment of the present application provides a readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, performs the steps in the method for determining a violation of a handling vehicle in any embodiment of the present application, and specific operations may refer to the description of the method for determining a violation of a handling vehicle in any embodiment, which is not described herein again.

Wherein the readable storage medium may include: read Only Memory (ROM), random access Memory (RAM, random Access Memory), magnetic or optical disk, and the like.

The steps in the method for determining the rule violation of the handling vehicle in any embodiment of the present application may be executed due to the instructions stored in the readable storage medium, so that the beneficial effects that can be achieved by the method for determining the rule violation of the handling vehicle in any embodiment of the present application may be achieved, which are described in detail in the foregoing description and are not repeated herein.

The foregoing describes in detail a method, an apparatus, a storage medium, and an electronic device for determining rule violations of a handling vehicle according to embodiments of the present application, and specific examples are applied to describe principles and implementations of the present application, where the descriptions of the foregoing embodiments are only used to help understand the method and core ideas of the present application; meanwhile, those skilled in the art will have variations in the specific embodiments and application scope in light of the ideas of the present application, and the present description should not be construed as limiting the present application in view of the above.

Claims

1. A method of determining a violation of a handling vehicle, comprising:

acquiring a target image;

2. The method for determining a violation of a carrier vehicle according to claim 1, wherein the acquiring violation attribute information corresponding to the location information includes:

3. The method according to claim 2, wherein determining an extension area of an accessory part on the cargo handling vehicle in the target image according to a corner position of a second corner of the first corner includes:

4. The method for determining a violation of a carrier vehicle according to claim 1, wherein the acquiring violation attribute information corresponding to the location information includes:

5. The method according to claim 1, wherein before the obtaining of the violation attribute information corresponding to the location information, the method further comprises:

6. The method of claim 1, wherein the extracting the location information of the cargo handling vehicle and the target vehicle attribute information in the target image comprises:

7. The method of any one of claims 1-6, wherein prior to determining the violation determination result for the cargo handling vehicle based on the violation attribute information and the target vehicle attribute information, the method further comprises:

8. A transportation vehicle violation determination device, comprising:

a first acquisition unit configured to acquire a target image;

9. An electronic device comprising a processor, a memory and a computer program stored in the memory and executable on the processor, the processor implementing the steps in the method of determining a violation of a carrier vehicle according to any of claims 1 to 7 when the computer program is executed by the processor.

10. A readable storage medium, characterized in that the readable storage medium has stored thereon a computer program which, when executed by a processor, implements the steps of the method for determining a violation of a handling vehicle according to any of claims 1 to 7.