Method, device and equipment for scrap pile safety detection

Abstract

The application discloses a method, device and equipment for detecting the safety of a scrap steel pile, and aims to solve the problem that the related art cannot detect the danger caused by the stacking of scrap steel. A video stream of a scrap steel stacking area is collected by a camera, image abstraction modeling is performed on the scrap steel pile in the video stream, a scrap steel pile model is obtained, then, when it is determined that the scrap steel pile model comprises a reference model for safety detection of the scrap steel pile, at least one danger coefficient for the scrap steel pile model is obtained according to a sectional image of the scrap steel pile model under at least one target visual angle and a reference image of a corresponding region of the reference model in the sectional image, finally, if it is determined that the scrap steel pile model is unsafe according to the at least one danger coefficient, an alarm is given. The embodiments of the application can detect the safety of the scrap steel pile model, if it is determined that the danger coefficient is greater than a preset threshold, it is determined that the scrap steel pile is unsafe, and an alarm is given, thereby avoiding safety accidents caused by the danger of the scrap steel pile.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent identification, and in particular to a method, device and equipment for detecting safety of scrap steel accumulation. BACKGROUND

[0002] At present, the existing technical solutions mainly realize intelligent detection and analysis and classification when scrap steel is unloaded, and realize weight and impurity deduction calculation and protection of scrap steel during unloading, and no technical solution relates to how to detect the danger caused by scrap steel stacking.

[0003] Therefore, how to solve the problem that the danger caused by scrap steel stacking cannot be detected in the related art is an issue of concern in the industry. SUMMARY

[0004] The present application aims to provide a method, device and equipment for detecting safety of scrap steel accumulation, to solve the problem that the danger caused by scrap steel stacking cannot be detected in the related art.

[0005] In a first aspect, the present application provides a method for detecting safety of scrap steel accumulation, comprising:

[0006] capturing a video stream of a scrap steel stacking area by a camera;

[0007] performing image abstraction modeling on a scrap steel pile in the video stream to obtain a scrap steel pile model;

[0008] when it is determined that the scrap steel pile model includes a reference model for safety detection of the scrap steel pile, obtaining at least one danger coefficient for the scrap steel pile model according to a cross-sectional image of the scrap steel pile model under at least one target view angle and a reference image of a corresponding area in the cross-sectional image of the reference model;

[0009] if it is determined that the scrap steel pile model is unsafe according to the at least one danger coefficient, alarming.

[0010] In a possible implementation, if it is determined that the scrap steel pile model is unsafe according to the at least one danger coefficient, the method further comprises:

[0011] if at least one danger coefficient is greater than a corresponding preset threshold value, it is determined that the scrap steel pile model is unsafe and an alarm is given.

[0012] In a possible implementation, the at least one danger coefficient for the scrap steel pile model is obtained according to a cross-sectional image of the scrap steel pile model under at least one target view angle and a reference image of a corresponding area in the cross-sectional image of the reference model, comprising:

[0013] if the reference model is a reverse triangle model, obtaining a cross-sectional image of the scrap pile model under at least one target view angle, and a reverse triangle image of a corresponding region of the reverse triangle model in the cross-sectional image;

[0014] for any of the cross-sectional images containing a reverse triangle image, obtaining a reverse triangle danger coefficient for the scrap pile model based on an angle value of a base angle of the reverse triangle image, a proportion value of a height value of a support point of the reverse triangle image and a body height value of the scrap pile model, and a scrap quality ratio of the reverse triangle model to the scrap pile model.

[0015] In a possible implementation, the obtaining of the reverse triangle danger coefficient for the scrap pile model based on the angle value of the base angle of the reverse triangle image, the proportion value of the height value of the support point of the reverse triangle image and the body height value of the scrap pile model, and the scrap quality ratio of the reverse triangle model to the scrap pile model includes:

[0016] multiplying the angle value of the base angle of the reverse triangle image by a first weight, multiplying the proportion value of the height value of the support point of the reverse triangle image and the body height value of the scrap pile model by a second weight, and multiplying the scrap quality ratio of the reverse triangle model to the scrap pile model by a third weight;

[0017] summing the obtained products to obtain the reverse triangle danger coefficient of the scrap pile model; wherein a sum of the first weight, the second weight and the third weight is a preset value.

[0018] In a possible implementation, the obtaining of the at least one danger coefficient for the scrap pile model based on the cross-sectional image of the scrap pile model under at least one target view angle, and the reference image of the corresponding region of the reference model in the cross-sectional image includes:

[0019] if the reference model is a spherical model, obtaining a cross-sectional image of the scrap pile model under at least one target view angle, and a spherical image of a corresponding region of the spherical model in the cross-sectional image;

[0020] for any of the cross-sectional images containing a spherical image, obtaining a spherical object danger coefficient for the scrap pile model based on an angle value of a base angle of the scrap pile in the cross-sectional image, a proportion value of a height value of a support point of the spherical image and a body height value of the scrap pile model, and a proportion value of a spherical area of the spherical image to an area of the cross-sectional image excluding the spherical image.

[0021] In a possible implementation, the spherical object danger coefficient of the scrap steel pile model is obtained based on a proportion value of an angle value of a bottom corner of the scrap steel pile in the cross-section image, a height value of the support point of the spherical image, and a main body height value of the scrap steel pile model, and a proportion value of a spherical area of the spherical image and an area of the cross-section image excluding the spherical image, including:

[0022] multiplying the angle value of the bottom corner of the scrap steel pile in the cross-section image by a fourth weight, multiplying the proportion value of the height value of the support point of the spherical image and the main body height value of the scrap steel pile model by a fifth weight, and multiplying the proportion value of the spherical area of the spherical image and the area of the cross-section image excluding the spherical image by a sixth weight;

[0023] adding the obtained sums to obtain the spherical object danger coefficient of the scrap steel pile model; and wherein a sum of the fourth weight, the fifth weight, and the sixth weight is a preset value.

[0024] In a possible implementation, the method further includes:

[0025] if it is determined that the scrap steel pile model does not include the reference model, determining that the scrap steel pile model is safe.

[0026] In a second aspect, the present application provides a device for detecting safety of a scrap steel pile, the device including:

[0027] a video stream acquisition module configured to acquire a video stream of a scrap steel stacking area by using a camera;

[0028] an image abstract modeling module configured to perform image abstract modeling on the scrap steel pile in the video stream to obtain a scrap steel pile model;

[0029] a danger coefficient determination module configured to, if it is determined that the scrap steel pile model includes a reference model for detecting safety of a scrap steel pile, obtain at least one danger coefficient of the scrap steel pile model according to a cross-section image of the scrap steel pile model at at least one target view angle and a reference image of a corresponding region of the reference model in the cross-section image;

[0030] an alarm module configured to, if it is determined that the scrap steel pile model is unsafe according to the at least one danger coefficient, perform an alarm.

[0031] In a possible implementation, the alarm module is configured to:

[0032] if at least one danger coefficient is greater than a corresponding preset threshold value, it is determined that the scrap steel pile model is unsafe and an alarm is performed.

[0033] In a possible implementation, the cross-sectional images of the scrap pile model under at least one target perspective view are obtained, and the reference images of the reference model corresponding to the respective regions in the cross-sectional images are obtained, to obtain at least one risk coefficient of the scrap pile model, and the risk coefficient determination module is configured to:

[0034] If the reference model is a reverse triangular model, the cross-sectional images of the scrap pile model under at least one target perspective view are obtained, and the reverse triangular images of the reverse triangular model corresponding to the respective regions in the cross-sectional images are obtained;

[0035] For any of the cross-sectional images containing the reverse triangular images, the angle value of the base angle of the reverse triangular image, the proportion value of the height value of the support point of the reverse triangular image and the body height value of the scrap pile model, and the scrap quality ratio of the reverse triangular model and the scrap pile model are obtained to obtain the reverse triangular risk coefficient of the scrap pile model.

[0036] In a possible implementation, the cross-sectional images of the scrap pile model under at least one target perspective view are obtained, and the reference images of the reference model corresponding to the respective regions in the cross-sectional images are obtained, to obtain at least one risk coefficient of the scrap pile model, and the risk coefficient determination module is configured to:

[0037] The angle value of the base angle of the reverse triangular image is multiplied by a first weight, the proportion value of the height value of the support point of the reverse triangular image and the body height value of the scrap pile model is multiplied by a second weight, and the scrap quality ratio of the reverse triangular model and the scrap pile model is multiplied by a third weight;

[0038] The sum of the obtained respective products is taken as the reverse triangular risk coefficient of the scrap pile model; wherein the sum of the first weight, the second weight and the third weight is a preset value.

[0039] In a possible implementation, the cross-sectional images of the scrap pile model under at least one target perspective view are obtained, and the reference images of the reference model corresponding to the respective regions in the cross-sectional images are obtained, to obtain at least one risk coefficient of the scrap pile model, and the risk coefficient determination module is configured to:

[0040] If the reference model is a spherical model, the cross-sectional images of the scrap pile model under at least one target perspective view are obtained, and the spherical images of the spherical model corresponding to the respective regions in the cross-sectional images are obtained;

[0041] For any of the sectional images containing the spherical image, based on an angle value of a bottom corner of the scrap steel pile in the sectional image, a proportion value of a height value of a support point of the spherical image and a main body height value of the scrap steel pile model, and a proportion value of a spherical area of the spherical image and an area of the sectional image excluding the spherical image, a spherical article danger coefficient for the scrap steel pile model is obtained.

[0042] In a possible implementation, the obtaining the spherical article danger coefficient for the scrap steel pile model based on the angle value of the bottom corner of the scrap steel pile in the sectional image, the proportion value of the height value of the support point of the spherical image and the main body height value of the scrap steel pile model, and the proportion value of the spherical area of the spherical image and the area of the sectional image excluding the spherical image is performed by the danger coefficient determining module configured to:

[0043] multiplying the angle value of the bottom corner of the scrap steel pile in the sectional image by a fourth weight, multiplying the proportion value of the height value of the support point of the spherical image and the main body height value of the scrap steel pile model by a fifth weight, and multiplying the proportion value of the spherical area of the spherical image and the area of the sectional image excluding the spherical image by a sixth weight;

[0044] obtaining a sum of the respective products as the spherical article danger coefficient for the scrap steel pile model; and wherein a sum of the fourth weight, the fifth weight and the sixth weight is a preset value.

[0045] In a possible implementation, the apparatus further includes:

[0046] a safety determining module configured to determine that the scrap steel pile model is safe if it is determined that the scrap steel pile model does not contain the reference model.

[0047] In a third aspect, the present application provides an electronic device, including:

[0048] a memory configured to store executable instructions of the processor;

[0049] a processor configured to execute the executable instructions to implement the method for detecting safety of a scrap steel pile according to any of the first aspect.

[0050] In a fourth aspect, the present application provides a computer readable storage medium, when instructions in the computer readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform the method for detecting safety of a scrap steel pile according to any of the first aspect.

[0051] In a fifth aspect, the present application provides a computer program product, including a computer program:

[0052] The computer program, when executed by a processor, implements the method for detecting the safety of a scrap steel pile as in any one of the first aspects above.

[0053] The embodiments of the present application bring at least the following beneficial effects:

[0054] In the embodiments of the present application, the safety of the scrap steel pile model can be detected, and if it is determined that the risk coefficient is greater than the preset threshold, it is determined that the scrap steel pile is unsafe, and an alarm is given, the risk caused by the scrap steel pile can be detected, and safety accidents caused by the risk of the scrap steel pile can be avoided, and safety production can be ensured.

[0055] Other features and advantages of the present application will be described in the following description, and some will become apparent from the description, or will be learned through implementation of the present application. The purpose and other advantages of the present application can be achieved and obtained through the structure specifically pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF DRAWINGS

[0056] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiments of the present application will be briefly introduced below. Obviously, the drawings introduced below are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor on the basis of these drawings.

[0057] Figure 1 The overall flowchart of the method for detecting the safety of a scrap steel pile provided by the embodiments of the present application is shown in the figure.

[0058] Figure 2 The flowchart of step 103 provided by the embodiments of the present application is shown in the figure.

[0059] Figure 3 The flowchart of step 202 provided by the embodiments of the present application is shown in the figure.

[0060] Figure 4 The schematic diagram of the cross-sectional image of the scrap steel pile model including the inverted triangular model provided by the embodiments of the present application is shown in the figure.

[0061] Figure 5 Another flowchart of step 103 provided by the embodiments of the present application is shown in the figure.

[0062] Figure 6 The flowchart of step 502 provided by the embodiments of the present application is shown in the figure.

[0063] Figure 7 The schematic diagram of the cross-sectional image of the scrap steel pile model including the spherical model provided by the embodiments of the present application is shown in the figure.

[0064] Figure 8A schematic diagram of the structure of a device for safety detection of scrap steel accumulation provided in an embodiment of the present application;

[0065] Figure 9 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0066] To make the purpose, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Among them, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0067] Moreover, in the description of the embodiments of the present application, unless otherwise specified, “ / ” means or, for example, A / B can mean A or B; “and / or” in the text is merely a description of the association relationship of associated objects, indicating that three relationships may exist, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, “multiple” refers to two or more than two.

[0068] In the following, the terms "first" and "second" are used for descriptive purposes only and should not be understood to imply or suggest relative importance or implicitly indicate the number of the technical features indicated. Therefore, features defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of this application, unless otherwise specified, "plurality" means two or more.

[0069] Related art discloses a scrap steel storage and corrosion prevention device comprising at least three triangular pyramid-shaped components, each of which has a horizontally arranged bottom surface, two vertically arranged connecting surfaces, and an inclined bearing surface. One of the connecting surfaces of two adjacent components is mated and abutted, and at least three components are abutted in sequence to form a tapered structure with a cross-section that gradually decreases from bottom to top. Each component's bearing surface is provided with a plurality of parallel water guide grooves, each of which extends to the bottom surface at its lower end. In this related art, scrap steel is stacked on the tapered structure formed by the abutment of at least three components, which prevents the scrap steel from contacting the ground. At the same time, water guide grooves are provided on the bearing surfaces of the components to divert rainwater away, preventing water accumulation on the tapered structure and ensuring that the scrap steel is in a dry environment, which helps reduce the corrosion rate of the scrap steel.

[0070] In the scrap steel stacking scenario, there is no technical solution regarding how to detect the hazards caused by scrap steel stacking.

[0071] Therefore, the application provides a method, device and equipment for detecting the safety of a scrap steel pile to solve the problem that the safety of a scrap steel pile cannot be detected in the prior art.

[0072] The application concept of the application can be summarized as follows: a video stream of a scrap steel stacking area is collected by a camera, a scrap steel pile in the video stream is modeled by image abstraction to obtain a scrap steel pile model, then, when it is determined that the scrap steel pile model includes a reference model for safety detection of the scrap steel pile, at least one risk coefficient for the scrap steel pile model is obtained according to a cross-sectional image of the scrap steel pile model at at least one target view angle and a reference image of a corresponding region of the reference model in the cross-sectional image, and finally, when it is determined that the scrap steel pile model is unsafe according to the at least one risk coefficient, an alarm is given. The embodiments of the application can detect the safety of a scrap steel pile by safety detection of the scrap steel pile model, determine that the scrap steel pile is unsafe and give an alarm when it is determined that the risk coefficient is greater than a preset threshold, detect the danger caused by the stacking of the scrap steel pile, avoid safety accidents caused by the danger of the scrap steel pile, and ensure the safety of the stacking of the scrap steel pile and safe production.

[0073] After introducing the main inventive idea of the embodiments of the application, the application scenarios to which the technical solutions of the embodiments of the application can be applied are briefly introduced as follows. It should be noted that the following introduction of the application scenarios is only used to illustrate the embodiments of the application but not to limit the embodiments of the application. In actual implementation, the technical solutions provided by the embodiments of the application can be flexibly applied according to actual needs.

[0074] In order to facilitate understanding of the method for detecting the safety of a scrap steel pile provided by the embodiments of the application, the following further describes the method with reference to the accompanying drawings.

[0075] In a possible implementation, the application provides a method for detecting the safety of a scrap steel pile, and a schematic diagram of the overall process of the method is shown in FIG. 1. Figure 1 As shown in FIG. 1, the method includes the following steps.

[0076] In step 101, a video stream of a scrap steel stacking area is collected by a camera.

[0077] In a possible implementation, the embodiments of the application erect four ball cameras in the area where the scrap steel is stacked, set the preset points of the cameras to stay for 5 minutes each, so that the four ball cameras can cover the full scene of the scrap steel pile, and after the video stream of the scrap steel stacking area is collected, the ball cameras are connected to a central intelligent analysis server, and the video streams of the four ball cameras are pulled for intelligent analysis, including the establishment of the scrap steel pile model and the determination of the risk coefficient in the subsequent steps.

[0078] In step 102, a scrap steel pile in the video stream is modeled by image abstraction to obtain a scrap steel pile model.

[0079] In a possible implementation, the image abstract modeling is performed according to video streams captured by four ball cameras, and the scrap pile model obtained by the application is a three-dimensional model.

[0080] In step 103, when it is determined that the scrap pile model comprises a reference model for safety detection of the scrap pile, at least one risk coefficient for the scrap pile model is obtained according to a cross-sectional image of the scrap pile model at at least one target view angle and a reference image of a corresponding region of the reference model in the cross-sectional image.

[0081] In a possible implementation, the scrap pile model obtained by the embodiments of the application is not a completely regular three-dimensional model, but is determined according to the actual stacking condition of the scrap pile. If it is determined that the scrap pile model comprises a reference model for safety detection of the scrap pile, the reference model is a model of a preset shape or a preset form for safety detection of the scrap pile, including an inverted triangular model and a spherical model. For the above two reference models, step 103 in the embodiments of the application can be implemented as the following steps:

[0082] I. The reference model is an inverted triangular model

[0083] In a possible implementation, a flowchart of step 103 is shown in Figure 2 , which includes the following contents:

[0084] In step 201, if the reference model is an inverted triangular model, a cross-sectional image of the scrap pile model at at least one target view angle and an inverted triangular image of a corresponding region of the inverted triangular model in the cross-sectional image are obtained.

[0085] In step 202, for any cross-sectional image containing an inverted triangular image, an inverted triangular risk coefficient for the scrap pile model is obtained based on an angle value of a base angle of the inverted triangular image, a proportion value of a height value of a support point of the inverted triangular image and a main body height value of the scrap pile model, and a scrap steel quality ratio of the inverted triangular model to the scrap pile model.

[0086] In a possible implementation, a flowchart of step 202 is shown in Figure 3 , which includes the following contents:

[0087] In step 301, the angle value of the base angle of the inverted triangular image is multiplied by a first weight, the proportion value of the height value of the support point of the inverted triangular image and the main body height value of the scrap pile model is multiplied by a second weight, and the scrap steel type ratio of the inverted triangular model to the scrap pile model is multiplied by a third weight.

[0088] In step 302, the sum of the obtained products is used as the inverted triangle risk coefficient of the scrap steel pile model; wherein the sum of the first weight, the second weight and the third weight is a preset value.

[0089] For example, Figure 4 The figure shows a cross-sectional image of a scrap steel pile model including an inverted triangle model, wherein both inverted 1 and inverted 2 are inverted triangle models. The above step 202 can be implemented as the following formula (1). The embodiment of the present application uses the following formula (1) to determine the inverted triangle hazard coefficient for the scrap steel pile model:

[0090]

[0091] Here, P1 represents the weight of the trigonometric function sinθ applied to the angle θ of the inverted triangle image's base angle (i.e., the first weight). P2 represents the weight of the ratio of the height h2 of the inverted triangle image's support point to the main height h of the scrap pile model (i.e., the second weight). P3 represents the weight of the scrap mass ratio between the inverted triangle model and the scrap pile model (i.e., the third weight). The sum of these three weights equals 1. The formula normalizes the base angle, height ratio, and scrap mass ratio of the inverted triangle image, ensuring that all values ​​are between 0 and 1. The system considers 90 degrees to be the most dangerous angle for weight bearing; in terms of height, the system considers higher heights to be more dangerous; and in terms of mass, the system considers a larger proportion of heavy steel in the inverted triangle model to be more dangerous. The β risk coefficient ranges from 0 to 1, with higher values ​​indicating a higher risk. The system sets a threshold, typically 80%, and issues an alarm if the β value exceeds this preset threshold.

[0092] 2. The reference model is a spherical model

[0093] In a possible implementation, the flowchart of step 103 is as follows: Figure 5 As shown, including the following:

[0094] In step 501, if the reference model is a spherical model, a cross-sectional image of the scrap steel pile model at at least one target viewing angle and a spherical image of the spherical model in a region corresponding to the cross-sectional image are obtained.

[0095] In step 502, for any cross-sectional image containing a spherical image, a spherical object hazard factor for the scrap steel pile model is obtained based on the angle value of the bottom angle of the scrap steel pile in the cross-sectional image, the ratio of the height value of the support point of the spherical image to the main body height value of the scrap steel pile model, and the ratio of the spherical area of ​​the spherical image to the area of ​​the cross-sectional image minus the spherical image.

[0096] In a possible implementation, the flowchart of step 502 is as follows: Figure 6 As shown, including the following:

[0097] In step 601, the angle value of the bottom angle of the scrap pile in the cross-sectional image is multiplied by the fourth weight, the ratio value of the height value of the support point of the spherical image and the main body height value of the scrap pile model is multiplied by the fifth weight, and the ratio value of the spherical area of ​​the spherical image and the area of ​​the cross-sectional image minus the spherical image is multiplied by the sixth weight.

[0098] In step 602, the sum of the obtained products is used as the spherical object hazard coefficient of the scrap steel pile model; wherein the sum of the fourth weight, the fifth weight and the sixth weight is a preset value.

[0099] For example, Figure 7 The figure shows a cross-sectional image of a scrap steel pile model including a spherical model, wherein S1 is a spherical model. The above step 502 can be implemented as the following formula (2). That is, the embodiment of the present application uses the following formula (2) to determine the spherical object hazard factor for the scrap steel pile model:

[0100]

[0101] P4 represents the weight of the trigonometric function sinθ applied to the angle θ of the scrap pile's base in the cross-sectional image, representing the fourth weight. P5 represents the weight of the ratio of the spherical image's support point h2 to the main height h of the scrap pile model, representing the fifth weight. P6 represents the weight of the ratio of the spherical area S2 of the spherical image to the area S of the cross-sectional image minus the spherical image, representing the sixth weight. The sum of these three weights equals 1. The formula normalizes the base angle, height ratio, and scrap mass ratio of the inverted triangle image, ensuring that all values ​​are between 0 and 1. The system considers 90 degrees to be the most dangerous angle for weight bearing; the system considers higher heights to be more dangerous; and the system considers a larger proportion of heavy steel in the inverted triangle model to be more dangerous. The β risk coefficient ranges from 0 to 1, with higher values ​​indicating a higher risk. The system sets a threshold, typically 80%, and issues an alarm if the β value exceeds this threshold.

[0102] In step 104, if the scrap steel pile model is determined to be unsafe based on at least one risk factor, an alarm is issued.

[0103] It should be noted that, considering that the scrap steel pile model contains more than one reference model, such as Figure 3 The scrap steel pile model includes two inverted triangle models. If at least one risk factor is greater than the corresponding preset threshold, that is, at least one risk factor among multiple risk factors is greater than the corresponding preset threshold, the scrap steel pile model is determined to be unsafe and an alarm is issued.

[0104] In another possible implementation, if the scrap pile model does not include the reference model, i.e., the scrap pile model does not include the inverted triangular model or the spherical model, the scrap pile model is determined to be safe.

[0105] In summary, the embodiments of the present application can detect the safety of the scrap pile by performing safety detection on the scrap pile model. If the dangerous coefficient is greater than the preset threshold, the scrap pile is determined to be unsafe, and an alarm is performed. The embodiments of the present application can detect the danger caused by the scrap pile, avoid safety accidents caused by the danger of the scrap pile, and ensure safe production.

[0106] Based on the same inventive concept, the embodiments of the present application also provide a device for detecting the safety of a scrap pile, as shown in Figure 8 The device 800 includes:

[0107] A video stream acquisition module 801 is configured to acquire a video stream of a scrap pile area by a camera.

[0108] An image abstract modeling module 802 is configured to perform image abstract modeling on the scrap pile in the video stream to obtain a scrap pile model.

[0109] A dangerous coefficient determination module 803 is configured to, when it is determined that the scrap pile model includes a reference model for safety detection of the scrap pile, obtain at least one dangerous coefficient for the scrap pile model according to a cross-sectional image of the scrap pile model at at least one target view angle and a reference image of a corresponding region of the reference model in the cross-sectional image.

[0110] An alarm module 804 is configured to, if it is determined that the scrap pile model is unsafe according to the at least one dangerous coefficient, perform an alarm.

[0111] In a possible implementation, the alarm module is configured to:

[0112] If at least one dangerous coefficient is greater than a corresponding preset threshold, the scrap pile model is determined to be unsafe and an alarm is performed.

[0113] In a possible implementation, the dangerous coefficient determination module is configured to:

[0114] If the reference model is an inverted triangular model, the cross-sectional image of the scrap pile model at at least one target view angle and an inverted triangular image of a corresponding region of the inverted triangular model in the cross-sectional image are obtained.

[0115] For any of the cross-section images containing the inverted triangle image, based on an angle value of a bottom angle of the inverted triangle image, a proportion value of a height value of a support point of the inverted triangle image and a body height value of the scrap pile model, and a scrap mass ratio of the inverted triangle model to the scrap pile model, an inverted triangle danger coefficient for the scrap pile model is obtained.

[0116] In a possible implementation, the obtaining the inverted triangle danger coefficient for the scrap pile model based on the angle value of the bottom angle of the inverted triangle image, the proportion value of the height value of the support point of the inverted triangle image and the body height value of the scrap pile model, and the scrap mass ratio of the inverted triangle model to the scrap pile model, the danger coefficient determining module is configured to:

[0117] multiply the angle value of the bottom angle of the inverted triangle image by a first weight, multiply the proportion value of the height value of the support point of the inverted triangle image and the body height value of the scrap pile model by a second weight, and multiply the scrap mass ratio of the inverted triangle model to the scrap pile model by a third weight;

[0118] sum the obtained products to obtain the inverted triangle danger coefficient for the scrap pile model; wherein a sum of the first weight, the second weight and the third weight is a preset value.

[0119] In a possible implementation, the obtaining the at least one danger coefficient for the scrap pile model according to the cross-section image of the scrap pile model at the at least one target view angle and the reference image of the reference model corresponding to the corresponding region in the cross-section image, the danger coefficient determining module is configured to:

[0120] if the reference model is a spherical model, obtaining the cross-section image of the scrap pile model at the at least one target view angle and the spherical image of the spherical model corresponding to the corresponding region in the cross-section image;

[0121] For any of the cross-section images containing the spherical image, based on an angle value of a bottom angle of the scrap pile in the cross-section image, a proportion value of a height value of a support point of the spherical image and a body height value of the scrap pile model, and a proportion value of a spherical area of the spherical image to an area of the cross-section image excluding the spherical image, a spherical object danger coefficient for the scrap pile model is obtained.

[0122] In a possible implementation, the method further includes: performing a ratio of an angle value of a bottom corner of the scrap steel pile in the cross-section image, a height value of the support point of the spherical image, and a main body height value of the scrap steel pile model, and a ratio of a spherical area of the spherical image to an area of the cross-section image excluding the spherical image, to obtain a spherical object danger coefficient of the scrap steel pile model; and determining, by the danger coefficient determining module, the spherical object danger coefficient of the scrap steel pile model according to the ratio.

[0123] multiplying the angle value of the bottom corner of the scrap steel pile in the cross-section image by a fourth weight, multiplying the ratio of the height value of the support point of the spherical image and the main body height value of the scrap steel pile model by a fifth weight, and multiplying the ratio of the spherical area of the spherical image to the area of the cross-section image excluding the spherical image by a sixth weight;

[0124] adding the obtained respective sums to obtain the spherical object danger coefficient of the scrap steel pile model; and wherein a sum of the fourth weight, the fifth weight, and the sixth weight is a preset value.

[0125] In a possible implementation, the apparatus further includes:

[0126] a safety determining module configured to determine that the scrap steel pile model is safe if it is determined that the scrap steel pile model does not contain the reference model.

[0127] The electronic device 130 according to this embodiment of the present application will be described below with reference to Figure 9 FIG. 1. Figure 9 The electronic device 130 shown is merely an example and should not be taken as limiting the functionality or applicability of the embodiments of the present application.

[0128] As shown in Figure 9 FIG. 1, the electronic device 130 is in the form of a general electronic device. The components of the electronic device 130 can include, but are not limited to, the at least one processor 131 described above, the at least one memory 132 described above, and a bus 133 connecting different system components, including the memory 132 and the processor 131.

[0129] The bus 133 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a processor or local bus using any of a variety of bus structures, such as 32-bit bus, 64-bit bus, or 128-bit bus, using any of a variety of bus architectures.

[0130] The memory 132 can include a readable medium in the form of volatile memory, such as a random access memory (RAM) 1321 and / or a cache memory 1322, and can further include a read-only memory (ROM) 1323.

[0131] The storage 132 can also include a number of program modules 1324 that are stored in the memory 132, including but not limited to an operating system, one or more application programs, other program modules, program data, and a component of a web environment, each of which or a combination thereof, can include implementation of a network environment.

[0132] The electronic device 130 can also communicate with one or more external devices 134 such as a keyboard or pointing device, and can communicate with one or more devices that enable a user to interact with the electronic device 130 and / or any devices (e.g., a router, a modem, etc.) that enable the electronic device 130 to communicate with one or more other electronic devices. Such communication can occur via an input / output (I / O) interface 135. Still yet, the electronic device 130 can communicate with one or more networks, such as a local area network (LAN), a wide area network (WAN), and / or the Internet, through a network adapter 136. As depicted, the network adapter 136 communicates with the other components of the electronic device 130 via the bus 133. It should be appreciated that the network adapter 136 and / or the bus 133 can be implemented using one or more types of communication media, such as IO ports, serial ports, USB ports, PCMCIA slots, wireless networking components, and / or the like.

[0133] In exemplary embodiments, the present application also provides a computer readable storage medium including instructions, such as the memory 132 including instructions, which can be executed by the processor 131 of the electronic device 130 to complete the method of the scrap steel accumulation safety detection described above. Optionally, the computer readable storage medium can be a non-transitory computer readable storage medium, such as a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, and an optical data storage device, etc.

[0134] In exemplary embodiments, the present application also provides a computer program product including a computer program, which is executed by the processor 131 to implement the method of the scrap steel accumulation safety detection provided by the present application.

[0135] Those skilled in the art will appreciate that embodiments of the present application can be supplied as a method, a system, or a computer program product. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer usable program code.

[0136] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 one or more flow or blocks

[0137] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 one or more flow or blocks

[0138] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 one or more flow or blocks

[0139] Obviously, numerous modifications and variations of the present application are possible in light of the above teachings. It is therefore to be understood that within the scope of the appended claims and their equivalents, the application can be practiced otherwise than as specifically described.

Claims

1. A method for safety detection of scrap steel accumulation, characterized in that: The method comprises: Use cameras to collect video streams of the scrap steel stacking area; Performing image abstraction modeling on the scrap steel pile in the video stream to obtain a scrap steel pile model; When it is determined that the scrap steel pile model includes a reference model for safety inspection of the scrap steel pile, if the reference model is an inverted triangle model, a cross-sectional image of the scrap steel pile model at at least one target viewing angle and an inverted triangle image of a corresponding area of ​​the inverted triangle model in the cross-sectional image are obtained; for any cross-sectional image including an inverted triangle image, an inverted triangle hazard factor for the scrap steel pile model is obtained based on an angle value of a base angle of the inverted triangle image, a height value of a support point of the inverted triangle image and a ratio of a main body height value of the scrap steel pile model, and a scrap steel mass ratio between the inverted triangle model and the scrap steel pile model; If the reference model is a spherical model, a cross-sectional image of the scrap pile model at at least one target viewing angle and a spherical image of the spherical model in a region corresponding to the cross-sectional image are obtained; for any cross-sectional image containing a spherical image, a spherical object hazard factor for the scrap pile model is obtained based on an angle value of a bottom angle of the scrap pile in the cross-sectional image, a ratio of a height value of a support point of the spherical image to a main body height value of the scrap pile model, and a ratio of a spherical area of ​​the spherical image to an area of ​​the cross-sectional image excluding the spherical image; If it is determined that the scrap steel pile model is unsafe according to at least one risk factor, an alarm is issued.

2. The method according to claim 1, characterized in that If it is determined that the scrap steel pile model is unsafe according to the at least one risk factor, an alarm is issued, including: If at least one risk factor is greater than a corresponding preset threshold, the scrap steel pile model is determined to be unsafe and an alarm is issued.

3. The method according to claim 1, characterized in that The method of obtaining an inverted triangle hazard coefficient for the scrap steel pile model based on an angle value of a base angle of the inverted triangle image, a ratio value of a height value of a support point of the inverted triangle image to a main body height value of the scrap steel pile model, and a scrap steel mass ratio between the inverted triangle model and the scrap steel pile model includes: Multiplying the angle value of the base angle of the inverted triangle image by a first weight, multiplying the ratio of the height value of the support point of the inverted triangle image to the main height value of the scrap pile model by a second weight, and multiplying the scrap steel type ratio between the inverted triangle model and the scrap steel pile model by a third weight; The sum of the obtained products is used as the inverted triangle hazard coefficient of the scrap steel pile model; wherein the sum of the first weight, the second weight and the third weight is a preset value.

4. The method according to claim 1, wherein Obtaining a spherical object risk factor for the scrap steel pile model based on an angle value of a bottom angle of the scrap steel pile in the cross-sectional image, a ratio value of a height value of a support point of the spherical image to a main body height value of the scrap steel pile model, and a ratio value of a spherical area of ​​the spherical image to an area of ​​the cross-sectional image excluding the spherical image, includes: multiplying a fourth weight by an angle value of a bottom angle of the scrap pile in the cross-sectional image, multiplying a fifth weight by a ratio of a height value of a support point of the spherical image to a main body height value of the scrap pile model, and multiplying a sixth weight by a ratio of a spherical area of ​​the spherical image to an area of ​​the cross-sectional image excluding the spherical image; The sum of the obtained values ​​is used as the spherical object hazard coefficient of the scrap steel pile model; wherein the sum of the fourth weight, the fifth weight and the sixth weight is a preset value.

5. The method according to any one of claims 1 to 4, characterized in that The method further comprises: If it is determined that the scrap steel pile model does not include the reference model, the scrap steel pile model is determined to be safe.

6. A device for safety detection of scrap steel accumulation, characterized in that: The device comprises: A video stream acquisition module is configured to acquire a video stream of the scrap steel stacking area through a camera; an image abstract modeling module configured to perform image abstract modeling on the scrap steel pile in the video stream to obtain a scrap steel pile model; a hazard factor determination module configured to, upon determining that the scrap steel pile model includes a reference model for safety detection of the scrap steel pile, obtain a cross-sectional image of the scrap steel pile model at at least one target viewing angle and an inverted triangle image of a corresponding area of ​​the inverted triangle model in the cross-sectional image if the reference model is an inverted triangle model; and for any cross-sectional image including an inverted triangle image, obtain an inverted triangle hazard factor for the scrap steel pile model based on an angle value of a base angle of the inverted triangle image, a ratio of a height value of a support point of the inverted triangle image to a height value of a main body of the scrap steel pile model, and a scrap steel mass ratio between the inverted triangle model and the scrap steel pile model; If the reference model is a spherical model, a cross-sectional image of the scrap pile model at at least one target viewing angle and a spherical image of the spherical model in a region corresponding to the cross-sectional image are obtained; for any cross-sectional image containing a spherical image, a spherical object hazard factor for the scrap pile model is obtained based on an angle value of a bottom angle of the scrap pile in the cross-sectional image, a ratio of a height value of a support point of the spherical image to a main body height value of the scrap pile model, and a ratio of a spherical area of ​​the spherical image to an area of ​​the cross-sectional image excluding the spherical image; The alarm module is configured to generate an alarm if it is determined that the scrap steel pile model is unsafe according to at least one risk factor.

7. An electronic device, characterized in that: include: a memory for storing executable instructions for the processor; A processor is used to execute the executable instructions to implement the method for safety detection of scrap steel accumulation as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the method for safety detection of scrap steel accumulation as described in any one of claims 1 to 5.

Images