A state recognition method

Abstract

The present invention discloses a state recognition method for recognizing the state of a dump truck carriage, which is characterized by including the following steps: obtaining a captured image in the current state; selecting a marker from the captured image; obtaining the position of the marker in the captured image; obtaining the area ratio of the marker in the captured image; judging whether the marker reaches a preset position, if so, judging whether the area ratio is greater than a first threshold, if the area of the marker is greater than the first threshold, it is determined that the dump truck carriage is in a lifting state; if the area of the marker is not greater than the first threshold, it is determined that the dump truck carriage is in a flat state; wherein, the captured image is captured by a camera module installed at the bottom of the dump truck carriage. This method is simple and effective, the feature collection is more obvious during the shooting process, and the judgment accuracy is more precise; the device based on this method has a lower cost.

Description

Technical Field

[0001] The present invention relates to the technical field of construction, and particularly to a method, device and system for identifying the state of a dump truck carriage. Background Art

[0002] The measurement work of construction waste / muck transportation is now promoted nationwide. That is, the dump truck loads soil at the construction site and unloads it at the waste dump. When loading soil, the carriage of the dump truck needs to be flat, and when unloading soil, the carriage of the dump truck needs to be lifted. It is necessary to accurately judge the flat / lifted state of the carriage to prevent accidents during the loading / unloading process, while reducing production costs and improving work efficiency.

[0003] Currently, the existing shooting module is generally installed on the top of the carriage, facing the inside of the carriage. In this way, the features are not obvious during the shooting process of the shooting module, and the accuracy is relatively low; most dump trucks also need to install a baffle to prevent the shooting module from being damaged by rain and dust, resulting in an increase in cost.

[0004] Therefore, it is an urgent problem for those skilled in the art to provide a state recognition method, device and system with more obvious features, more accurate judgment of the carriage state, and reduced costs. Summary of the Invention

[0005] The purpose of the present invention is to provide a state recognition method, which is simple and effective, with more obvious feature acquisition during the shooting process and more accurate judgment accuracy; the device based on this method has a lower cost.

[0006] Based on the above purpose, the technical solution provided by the present invention is as follows:

[0007] A state recognition method for identifying the state of a dump truck cargo box, characterized by including the following steps:

[0008] Obtain a captured image in the current state;

[0009] Select a marker from the captured image;

[0010] Obtain the position of the marker in the captured image;

[0011] Obtain the area ratio of the marker in the captured image;

[0012] Judge whether the marker reaches a preset position. If so, judge whether the area ratio is greater than a first threshold. If the area of the marker is greater than the first threshold, it is determined that the dump truck cargo box is in the lifted state; if the area of the marker is not greater than the first threshold, it is determined that the dump truck cargo box is in the flat state;

[0013] Wherein, the captured image is captured by a camera module installed at the bottom of the dump truck cargo box.

[0014] Preferably, the marker is specifically the bottom of the dump truck cargo box in the captured image.

[0015] Preferably, the preset position is specifically the position of the bottom of the dump truck cargo box in the captured image when the dump truck is in the lifted or flat state.

[0016] Preferably, obtaining the area ratio of the marker in the captured image specifically includes:

[0017] Extract the characteristic pixel points of the bottom of the dump truck cargo box in the captured image;

[0018] Obtain the specific positions where the characteristic pixel points are located;

[0019] Calculate the area ratio of the bottom of the dump truck cargo box in the captured image according to the set of specific positions of the characteristic pixel points.

[0020] Preferably, obtaining the first threshold includes the following steps:

[0021] Obtain multiple image samples of the bottom of the dump truck cargo box in the flat state;

[0022] Train the image samples to obtain the image area of the bottom of the dump truck cargo box in the flat state;

[0023] Determine the area ratio threshold of the bottom of the dump truck cargo box as the first threshold according to the image area of the bottom of the dump truck cargo box in the flat state.

[0024] Preferably, it further includes judging the magnitude relationship between the area ratio and the first threshold and the second threshold.

[0025] If the area ratio is less than the first threshold, it is determined that the dump truck cargo box is in the flat state;

[0026] If the area ratio is greater than the first threshold and less than the second threshold, it is determined that the dump truck cargo box is in the lifted state;

[0027] If the area ratio is greater than the second threshold, it is determined that the dump truck cargo box is in an abnormal state.

[0028] Preferably, before obtaining the captured image in the current state, the following steps are further included:

[0029] Obtain the current speed and position of the dump truck;

[0030] Judge whether the current position is the same as the preset position. If not, stop executing the operation of obtaining the captured image in the current state and move the dump truck to the preset position;

[0031] If they are the same, determine whether the current speed is 0. If it is not 0, stop executing the operation of acquiring the captured image in the current state and reduce the speed of the dump truck to 0.

[0032] A state recognition device includes:

[0033] A shooting module, installed at the bottom of the dump truck carriage, for acquiring an image in the current state;

[0034] A selection module, for selecting a significantly marked object in the image;

[0035] A calculation module, for calculating the area ratio of the marked object in the captured image;

[0036] A setting module, for determining and setting the area ratio threshold of the marked object as the first threshold;

[0037] A judgment module, for judging whether the position of the marked object in the captured image reaches a preset position and judging whether the area ratio of the marked object in the captured image is greater than the first threshold.

[0038] A computer storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the state recognition method as described in any one of the above.

[0039] A state recognition method provided by the present invention is used to recognize whether the dump truck cargo box is in a flat or lifted state. By acquiring a captured image of the dump truck cargo box in the current state, selecting a suitable marked object in the image, determining whether the position of the marked object in the image is at the preset position, if so, then calculating the area ratio of the marked object in the image, and judging whether the area ratio of the marked object in the image is greater than the preset first threshold, so as to determine whether the dump truck cargo box is in a flat or lifted state. For this technical solution, only a suitable marked object in the captured image in the current state needs to be selected. After confirming that the marked object is at the preset position, calculate the area ratio of the marked object in the image, and preset the first threshold, then the current state of the dump truck cargo box can be judged. The calculation process is fast and efficient, the judgment result is accurate, the construction efficiency is improved, and at the same time, the cost of the device based on this method is lower. Description of the Drawings

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required to be used in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0041] Figure 1 It is a flowchart of a state recognition method provided by the present invention;

[0042] Figure 2 It is the specific flowchart of step 4 provided by the embodiment of the present invention;

[0043] Figure 3 It is the flowchart of obtaining the first threshold provided by the embodiment of the present invention;

[0044] Figure 4 It is the specific flowchart of a state recognition method provided by the embodiment of the present invention;

[0045] Figure 5 It is the structural schematic diagram of a state recognition device provided by the embodiment of the present invention. Specific embodiments

[0046] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0047] The embodiments of the present invention are written in a progressive manner.

[0048] The embodiment of the present invention provides a state recognition method, mainly solving the technical problems in the prior art that the features are not obvious and the accuracy is low during the shooting process of the shooting module, which increases the cost.

[0049] Such as Figure 1 , a state recognition method for recognizing the state of the dump truck cargo box, including the following steps:

[0050] S1. Obtain the captured image in the current state;

[0051] S2. Select the marker from the captured image;

[0052] S3. Obtain the position of the marker in the captured image;

[0053] S4. Obtain the area ratio of the marker in the captured image;

[0054] S5. Judge whether the marker reaches the preset position. If so, S51. Judge whether the area ratio is greater than the first threshold. If the area of the marker is greater than the first threshold, it is determined that the dump truck cargo box is in the lifting state; S52. If the area of the marker is not greater than the first threshold, it is determined that the dump truck cargo box is in the flat state;

[0055] Among them, the captured image is captured by a camera module installed at the bottom of the dump truck cargo box.

[0056] A state recognition method provided by the present invention is used to recognize whether the cargo box of a dump truck is in a flat state or a lifted state. By acquiring an image taken in the current state of the cargo box of the dump truck, a suitable marker is selected in the image, and it is determined whether the position of the marker in the image is at a preset position. If so, the area ratio of the marker in the image is calculated, and it is determined whether the area ratio of the marker in the image is greater than a preset first threshold, so as to determine whether the cargo box of the dump truck is in a flat state or a lifted state. In this technical solution, only a suitable marker in the image taken in the current state needs to be selected. After confirming that the marker is at the preset position, the area ratio of the marker in the image is calculated, and the first threshold is preset, then the current state of the cargo box of the dump truck can be judged. The calculation process is fast and efficient, the judgment result is accurate, the construction efficiency is improved, and at the same time, the cost of the device based on this method is lower.

[0057] Preferably, the marker is specifically the bottom of the cargo box of the dump truck in the taken image.

[0058] In the actual application process, the bottom of the cargo box of the dump truck is selected as the marker. In the images taken by the shooting module in the flat state and the lifted state of the dump truck, the bottom of the cargo box of the dump truck is easy to obtain in the image and convenient for calculation.

[0059] Preferably, the preset position is specifically the position where the bottom of the cargo box of the dump truck is located in the taken image when the dump truck is in the lifted or flat state.

[0060] In the actual application process, when the dump truck is in the lifted or flat state, according to the previously taken image samples, the position of the bottom of the cargo box of the dump truck in them is determined.

[0061] Preferably, step S4 is specifically as follows:

[0062] A1. Extract the characteristic pixel points of the bottom of the cargo box of the dump truck in the taken image;

[0063] A2. Obtain the specific positions where the characteristic pixel points are located;

[0064] A3. Calculate the area ratio of the bottom of the cargo box of the dump truck in the taken image according to the set of specific positions of the characteristic pixel points.

[0065] In the actual application process, a part with a more obvious color difference at the bottom of the cargo box of the dump truck can be selected as the characteristic pixel points according to needs; determine the specific positions of the characteristic pixel points in the 3D view; according to the positions of the characteristic pixel points in the 3D view, calculate the area of the bottom of the cargo box of the dump truck, and divide the area by the area of the taken image to obtain the area ratio.

[0066] Preferably, obtaining the first threshold includes the following steps:

[0067] B1. Obtain multiple image samples of the bottom of the cargo box of the dump truck in the flat state;

[0068] B2. Train the image samples to obtain the image area of the bottom of the dump truck box in the flat state;

[0069] B3. Determine the threshold of the area ratio of the bottom of the dump truck box as the first threshold according to the image area of the bottom of the dump truck box in the flat state.

[0070] In the actual application process, obtain multiple image samples of the dump truck in the flat state, use AI technology to train the image samples multiple times, obtain the image area of the bottom of the dump truck in the flat state, and determine the threshold of the area ratio of the bottom of the dump truck box as the first threshold according to the image area of the bottom of the dump truck box in the flat state. It should be noted that due to reasons such as vehicles and road conditions, the image area of the bottom of the dump truck box may change. To better understand this solution, for example: in this embodiment, the image area of the bottom of the dump truck box in the flat state accounts for 0-5% of the captured image area, that is, 5% is used as the first threshold. When the area ratio of the bottom image of the dump truck box exceeds 5%, it should be determined that the dump truck is in the lifting state.

[0071] Preferably, it further includes S6. Judge the size relationship between the area ratio and the first threshold and the second threshold.

[0072] If the area ratio is less than the first threshold, it is determined that the dump truck box is in the flat state;

[0073] If the area ratio is greater than the first threshold and less than the second threshold, it is determined that the dump truck box is in the lifting state;

[0074] If the area ratio is greater than the second threshold, it is determined that the dump truck box is in an abnormal state.

[0075] In the actual application process, a second threshold is set. Both the second threshold and the first threshold are the area ratios of the bottom image of the dump truck box in the captured image. Similarly, the second threshold is obtained by the same method as obtaining the first threshold. To better understand this solution, for example: in this embodiment, the image area of the bottom of the dump truck box in different degrees of lifting states accounts for 5-90% of the captured image area, that is, 90% is used as the second threshold. When the area ratio of the bottom of the dump truck box is less than 5%, the dump truck is in the flat state; when the area ratio of the bottom of the dump truck box is between 5%-90%, the dump truck is in the lifting state; when the area ratio of the bottom of the dump truck box is greater than 90%, the dump truck is in an abnormal state.

[0076] Preferably, before step S1, the following steps are further included:

[0077] Obtain the current speed and position of the dump truck;

[0078] Judge whether the current position is the same as the preset position. If not, stop executing to obtain the captured image in the current state and move the dump truck to the preset position;

[0079] If they are the same, determine whether the current speed is 0. If it is not 0, stop executing the acquisition of the captured image in the current state and reduce the speed of the dump truck to 0.

[0080] In the actual application process, before identifying the state of the dump truck compartment, it is also necessary to judge the current speed and position of the dump truck. The dump truck should be parked at a preset soil unloading or loading position, and the speed should be 0 at this time; only then can the state identification of the dump truck compartment be carried out. Therefore, judge whether the position of the dump truck is the same as the preset position. If it is different, move the dump truck to the preset position. If it is the same, execute the compartment state identification; similarly, judge whether the speed of the dump truck is 0. If it is not 0, reduce the speed of the dump truck to 0. If it is 0, execute the compartment state identification.

[0081] A state identification device, including,

[0082] A shooting module, installed at the bottom of the dump truck compartment, for acquiring an image in the current state;

[0083] A selection module, for selecting a marker with obvious pixel points in the image;

[0084] A calculation module, for calculating the area ratio of the marker in the captured image;

[0085] A setting module, for determining and setting the area ratio threshold of the marker as the first threshold;

[0086] A judgment module, for judging whether the position of the marker in the captured image reaches the preset position and judging whether the area ratio of the marker in the captured image is greater than the first threshold.

[0087] In the actual application process, the shooting module acquires an image in the current state. The shooting direction of this image can be selected according to actual needs. For example, the shooting direction can be the same as the direction faced by the rearview mirror of the dump truck to capture the image of the bottom of the dump truck compartment; or the shooting direction is opposite to the direction faced by the rearview mirror of the dump truck to capture the image of the back of the cab. After determining the position of the marker in the image, the selection module selects a specific marker in the image. The calculation module calculates the area ratio of the marker in the image, sets the area ratio threshold of the marker as the first threshold according to the area ratio, and judges whether the area ratio is greater than the first threshold through the judgment module as a condition for identifying the lifted or flat state of the dump truck compartment.

[0088] A computer storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the state identification method as described in any of the above.

[0089] The above computer storage medium provided in this embodiment, since it can execute and implement the foregoing state identification method, can achieve the same technical effects as the foregoing method embodiment.

[0090] In the embodiments provided in the present application, it should be understood that the disclosed methods and devices can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of modules is only a logical function division. In actual implementation, there may be other division methods. For example, multiple modules or components can be combined, or can be integrated into another system, or some features can be ignored, or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed with each other can be through some interfaces, and the indirect coupling or communication connection of devices or modules can be electrical, mechanical, or other forms.

[0091] In addition, in each embodiment of the present invention, each functional module can be all integrated in one processor, or each module can be separately used as a device alone, or two or more modules can be integrated in one device; each functional module in each embodiment of the present invention can be implemented in the form of hardware, or can be implemented in the form of hardware plus software functional units.

[0092] Those of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments can be completed through program instructions and related hardware. The foregoing program instructions can be stored in a computer-readable storage medium. When the program instructions are executed, they execute the steps including the above method embodiments; and the foregoing storage media include: various media that can store program codes such as removable storage devices, read-only memories (ROMs), magnetic disks, or optical discs.

[0093] The above has introduced in detail a state recognition method, device, and system provided by the present invention. The above description of the disclosed embodiments enables those skilled in the art to implement or use the present invention. Various modifications to these embodiments will be obvious to those skilled in the art. The general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown herein, but will be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A state recognition method for recognizing the state of the cargo box of a dump truck, characterized in that, It includes the following steps: Obtain the current speed and position of the dump truck; Judge whether the current position is the same as the preset position. If not, stop executing the operation of obtaining the captured image in the current state and moving the dump truck to the preset position; If it is the same, judge whether the current speed is 0. If not, stop executing the operation of obtaining the captured image in the current state and reducing the speed of the dump truck to 0; Obtain the captured image in the current state; Select a marker from the captured image; Obtain the position of the marker in the captured image; Obtain the area ratio of the marker in the captured image; Judge whether the marker reaches the preset position. If so, judge whether the area ratio is greater than the first threshold. If the area of the marker is greater than the first threshold, it is determined that the cargo box of the dump truck is in the lifted state; if the area of the marker is not greater than the first threshold, it is determined that the cargo box of the dump truck is in the flat state; Among them, the captured image is captured by a camera module installed at the bottom of the cargo box of the dump truck; The marker is specifically the bottom of the cargo box of the dump truck in the captured image.

2. The state recognition method according to claim 1, wherein The preset position is specifically the position where the bottom of the cargo box of the dump truck is located in the captured image when the dump truck is in the lifted or flat state.

3. The state recognition method according to claim 2, wherein Obtaining the area ratio of the marker in the captured image specifically includes: Extract the characteristic pixel points at the bottom of the cargo box of the dump truck in the captured image; Obtain the specific positions where the characteristic pixel points are located; Calculate the area ratio of the bottom of the cargo box of the dump truck in the captured image according to the set of specific positions of the characteristic pixel points.

4. The state recognition method according to claim 3, wherein Obtaining the first threshold includes the following steps: Obtain multiple image samples of the bottom of the cargo box of the dump truck in the flat state; Train the image samples to obtain the area of the bottom of the cargo box of the dump truck in the flat state; Determine the area ratio threshold of the bottom of the cargo box of the dump truck as the first threshold according to the area of the bottom of the cargo box of the dump truck in the flat state.

5. The state recognition method according to claim 1, characterized in that It also includes judging the size relationship between the area ratio and the first threshold and the second threshold, If the area ratio is less than the first threshold, it is determined that the cargo box of the dump truck is in the flat state; If the area ratio is greater than the first threshold and less than the second threshold, it is determined that the cargo box of the dump truck is in the lifted state; If the area ratio is greater than the second threshold, it is determined that the cargo box of the dump truck is in an abnormal state.

6. A state recognition device, characterized in that, It includes, An acquisition module, used to obtain the current speed and position of the dump truck; A position module, used to judge whether the current position is the same as the preset position. If not, stop executing the operation of obtaining the captured image in the current state and moving the dump truck to the preset position; A speed module, used to judge whether the current speed is 0 when the judgment result of the position module is the same. If not, stop executing the operation of obtaining the captured image in the current state and reducing the speed of the dump truck to 0; A shooting module, installed at the bottom of the dump truck carriage, used to obtain the image in the current state; A selection module, used to select a marker with obvious pixel points in the image; A calculation module, used to calculate the area ratio of the marker in the captured image; A setting module, used to determine and set the area ratio threshold of the marker as the first threshold; A judgment module, configured to judge whether the position of the marker in the captured image reaches a preset position and judge whether the area ratio of the marker in the captured image is greater than a first threshold; Wherein, the marker is specifically the bottom of the dump truck cargo box in the captured image.

7. A computer storage medium, characterized in that, A computer program is stored on the computer storage medium, and when the computer program is executed by a processor, the state recognition method according to any one of claims 1 to 5 is implemented.

Images