CN111915611A - Method and device for heightening and detecting breast board of muck truck, electronic equipment and storage medium - Google Patents
Method and device for heightening and detecting breast board of muck truck, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN111915611A CN111915611A CN202010640308.8A CN202010640308A CN111915611A CN 111915611 A CN111915611 A CN 111915611A CN 202010640308 A CN202010640308 A CN 202010640308A CN 111915611 A CN111915611 A CN 111915611A
- Authority
- CN
- China
- Prior art keywords
- image
- breast board
- muck
- height
- width
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 210000000481 breast Anatomy 0.000 title claims abstract description 200
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000001514 detection method Methods 0.000 claims abstract description 69
- 230000011218 segmentation Effects 0.000 claims abstract description 56
- 239000002893 slag Substances 0.000 claims description 28
- 238000012549 training Methods 0.000 claims description 24
- 238000004891 communication Methods 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 16
- 230000008569 process Effects 0.000 claims description 14
- 238000002372 labelling Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 16
- 238000012545 processing Methods 0.000 description 8
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 230000004888 barrier function Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000006399 behavior Effects 0.000 description 3
- 230000003247 decreasing effect Effects 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
- G01B11/06—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness for measuring thickness ; e.g. of sheet material
- G01B11/0608—Height gauges
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30232—Surveillance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Image Processing (AREA)
- Apparatus For Radiation Diagnosis (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method and a device for heightening and detecting a railing panel of a muck truck, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring a first image of the muck truck; inputting the first image into a pre-trained breast board segmentation model, and determining a breast board sub-image in the first image based on the breast board segmentation model; and determining the width and the height of the breast board sub-image, and detecting whether the breast board of the muck truck is heightened according to the width and the height. The scheme provided by the embodiment of the invention does not need manual intervention, thereby greatly reducing the consumption of human resources and improving the detection efficiency. And because almost every crossing all installs image acquisition equipment, consequently can acquire the first image of the dregs car at every crossing through image acquisition equipment, and then accomplish the detection whether follow-up dregs car breast board is heightened, consequently can avoid the problem of lou examining.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a method and a device for heightening and detecting a guardrail plate of a muck truck, electronic equipment and a storage medium.
Background
Along with the rapid development of the construction industry in China, the muck truck is more and more common on the road surface, the common violation behavior of the muck truck is that the truck cargo barrier is modified and heightened, and the muck truck is seriously overloaded due to the behavior. The serious overload of the muck truck not only causes damage to the road surface, but also causes more frequent traffic accidents due to the overload, so that the discovery and the control of the overload of the muck truck are more and more important.
Whether the truck cargo barrier is modified to be heightened or not is judged, whether overload behaviors exist in the slag car or not is a common means at present, in the prior art, when the phenomenon that the cargo barrier is heightened or not exists in the slag car or not is detected, a traffic police is relied on to observe at a road junction, and whether the cargo barrier of the slag car is heightened or not is manually detected by the traffic police. The prior art has the problems that the time and the labor are consumed by the traffic police for manual detection, so that not only is great manpower resource consumed, but also if a certain intersection has no traffic police, whether a muck vehicle-mounted goods fence passing through the intersection is heightened cannot be detected, and detection omission is caused.
Disclosure of Invention
The embodiment of the invention provides a method and a device for detecting the heightening of a slag car fence, electronic equipment and a storage medium, which are used for solving the problems that a scheme for detecting the heightening of the slag car fence in the prior art is time-consuming and labor-consuming, consumes great manpower resources and is easy to cause missing detection.
The embodiment of the invention provides a heightening detection method for a breast board of a muck truck, which comprises the following steps:
acquiring a first image of the muck truck;
inputting the first image into a pre-trained breast board segmentation model, and determining a breast board sub-image in the first image based on the breast board segmentation model;
and determining the width and the height of the breast board sub-image, and detecting whether the breast board of the muck truck is heightened according to the width and the height.
Further, the obtaining a first image of a slag car includes:
and acquiring a second image containing the muck truck, inputting the second image into a pre-trained muck truck detection model, and determining a first image of the muck truck in the second image based on the muck truck detection model.
Further, said detecting whether said dregs car sideboard is heightened according to said width and height comprises:
judging whether a first ratio of the width to the height of the breast board image is smaller than a preset first threshold value or not, if so, determining that the breast board of the muck truck is heightened, and if not, determining that the breast board of the muck truck is not heightened; or judging whether a second ratio of the height to the width of the breast board sub-image is larger than a preset second threshold value, if so, determining that the breast board of the muck truck is heightened, and if not, determining that the breast board of the muck truck is not heightened.
Further, the determining the width and height of the balustrade sub-image comprises:
determining the minimum circumscribed rectangle of the breast board sub-image, taking the width of the minimum circumscribed rectangle as the width of the breast board sub-image, and taking the height of the minimum circumscribed rectangle as the height of the breast board sub-image.
Further, the training process of the breast board segmentation model comprises the following steps:
aiming at a third image of each slag car in a first sample set, inputting the third image and a first annotation image corresponding to the third image into the breast board segmentation model, and training the breast board segmentation model; and the first annotation image is annotated with the position information of the template image in the third image.
Further, the training process of the detection model of the slag car comprises the following steps:
inputting the fourth image and a second labeling image corresponding to the fourth image into the muck car detection model aiming at each fourth image in a second sample set, and training the muck car detection model; and the second annotation image is annotated with the position information of the muck truck image in the fourth image.
On the other hand, the embodiment of the invention provides a device for heightening and detecting a railing panel of a muck truck, which comprises:
the acquiring module is used for acquiring a first image of the muck truck;
the determining module is used for inputting the first image into a pre-trained breast board segmentation model and determining a breast board sub-image in the first image based on the breast board segmentation model;
and the detection module is used for determining the width and the height of the breast board sub-image and detecting whether the breast board of the muck truck is heightened or not according to the width and the height.
Further, the obtaining module is specifically configured to obtain a second image including the muck car, input the second image into a pre-trained muck car detection model, and determine, based on the muck car detection model, a first image of the muck car in the second image.
Further, the detection module is specifically configured to determine whether a first ratio of the width to the height of the breast board sub-image is smaller than a preset first threshold, determine that the breast board of the muck truck is heightened if the first ratio is smaller than the preset first threshold, and determine that the breast board of the muck truck is not heightened if the first ratio is not larger than the preset first threshold; or judging whether a second ratio of the height to the width of the breast board sub-image is larger than a preset second threshold value, if so, determining that the breast board of the muck truck is heightened, and if not, determining that the breast board of the muck truck is not heightened.
Further, the detection module is specifically configured to determine a minimum circumscribed rectangle of the balustrade sub-image, use a width of the minimum circumscribed rectangle as a width of the balustrade sub-image, and use a height of the minimum circumscribed rectangle as a height of the balustrade sub-image.
Further, the apparatus further comprises:
the first training module is used for inputting a third image and a first marked image corresponding to the third image into the breast board segmentation model aiming at the third image of each muck truck in the first sample set, and training the breast board segmentation model; and the first annotation image is annotated with the position information of the template image in the third image.
Further, the apparatus further comprises:
the second training module is used for inputting the fourth image and a second labeled image corresponding to the fourth image into the muck car detection model aiming at each fourth image in the second sample set and training the muck car detection model; and the second annotation image is annotated with the position information of the muck truck image in the fourth image.
On the other hand, the embodiment of the invention provides electronic equipment, which comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory complete mutual communication through the communication bus;
a memory for storing a computer program;
a processor for implementing any of the above method steps when executing a program stored in the memory.
In another aspect, an embodiment of the present invention provides a computer-readable storage medium, in which a computer program is stored, and the computer program, when executed by a processor, implements the method steps of any one of the above.
The embodiment of the invention provides a method and a device for heightening and detecting a railing panel of a muck truck, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring a first image of the muck truck; inputting the first image into a pre-trained breast board segmentation model, and determining a breast board sub-image in the first image based on the breast board segmentation model; and determining the width and the height of the breast board sub-image, and detecting whether the breast board of the muck truck is heightened according to the width and the height.
In the embodiment of the invention, the electronic equipment acquires the first image of the muck truck, determines the breast board sub-image in the first image based on the breast board segmentation model trained in advance, and then judges whether the breast board of the muck truck is heightened according to the width and the height of the breast board sub-image. The scheme provided by the embodiment of the invention does not need manual intervention, thereby greatly reducing the consumption of human resources and improving the detection efficiency. And because almost every crossing all installs image acquisition equipment, consequently can acquire the first image of the dregs car at every crossing through image acquisition equipment, and then accomplish the detection whether follow-up dregs car breast board is heightened, consequently can avoid the problem of lou examining.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic view of a heightening detection process of a breast board of a muck truck provided in embodiment 1 of the present invention;
fig. 2 is a schematic diagram of a second image provided in embodiment 2 of the present invention;
fig. 3 is a schematic diagram of a first image provided in embodiment 2 of the present invention;
FIG. 4 is a schematic view of a balustrade sub-image provided in embodiment 2 of the present invention;
FIG. 5 is a schematic diagram of determining a minimum bounding rectangle of a balustrade sub-image according to embodiment 4 of the present invention;
fig. 6 is a schematic view of a heightening detection process of a breast board of a muck truck provided in embodiment 5 of the present invention;
fig. 7 is a schematic structural view of a device for detecting the heightening of a balustrade of a muck truck provided in embodiment 6 of the present invention;
fig. 8 is a schematic structural diagram of an electronic device according to embodiment 7 of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the attached drawings, and it should be understood that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example 1:
fig. 1 is a schematic view of a heightening detection process of a breast board of a muck truck, which is provided by an embodiment of the present invention, and the process includes the following steps:
s101: a first image of a muck truck is acquired.
The method for heightening and detecting the railing panel of the muck truck provided by the embodiment of the invention is applied to electronic equipment, and the electronic equipment can be equipment such as a PC (personal computer), a tablet personal computer and the like, and can also be image acquisition equipment. The image acquisition device is arranged at the roadside or the bayonet and is used for acquiring the vehicle tail image of the slag vehicle, wherein the first image of the slag vehicle in the embodiment of the invention is the vehicle tail image of the slag vehicle. If the electronic equipment is image acquisition equipment, the image acquisition equipment directly carries out the subsequent step of detecting whether the breast board of the muck truck is heightened after acquiring the first image of the muck truck. If the electronic equipment is a PC, a tablet personal computer and the like, the image acquisition equipment transmits the first image to the electronic equipment after acquiring the first image of the muck car, and the electronic equipment processes the first image to realize the detection of whether the fence plate of the muck car is heightened.
The embodiment of the invention is based on the rear scene of the standard traffic electric police car, and the vertical position of the running car is relatively fixed in the picture when the running car is captured by the image acquisition equipment, so that the situations of serious perspective distortion of the car, incomplete car and the like can be avoided. Therefore, whether the side plates are heightened or not is judged by calculating the related information of the rear side plates of the muck truck in an image processing mode.
S102: inputting the first image into a pre-trained breast board segmentation model, and determining a breast board sub-image in the first image based on the breast board segmentation model.
The electronic equipment stores a hurdle board segmentation model which is trained in advance, and the hurdle board segmentation model is used for processing an input image to obtain a hurdle board sub-image. After the electronic equipment acquires the first image of the muck truck, inputting the first image into a hurdle board segmentation model which is trained in advance, and determining a hurdle board image in the first image based on the hurdle board segmentation model.
S103: and judging whether the ratio of the width to the height of the breast board image is smaller than a preset threshold value, if so, determining that the breast board of the muck truck is heightened, and if not, determining that the breast board of the muck truck is not heightened.
After the electronic equipment determines the breast board subimage in the first image, the width and the height of the breast board subimage are determined, and whether the breast board of the muck truck is heightened is detected according to the width and the height. The electronic equipment can pre-store a width range interval and a height range interval, wherein the width range interval and the height range interval are used for representing the width of the non-heightened sideboard, and the range interval to which the height belongs is the range interval. After the electronic equipment determines the width and the height of the breast board image, the width and the height are proportionally amplified or reduced, the adjusted width belongs to a width range interval, at the moment, whether the adjusted height belongs to a height range interval or not is judged, if yes, the breast board of the muck truck is determined not to be heightened, and if not, the breast board of the muck truck is determined not to be heightened.
In the embodiment of the invention, the electronic equipment acquires the first image of the muck truck, determines the breast board sub-image in the first image based on the breast board segmentation model trained in advance, and then judges whether the breast board of the muck truck is heightened according to the width and the height of the breast board sub-image. The scheme provided by the embodiment of the invention does not need manual intervention, thereby greatly reducing the consumption of human resources and improving the detection efficiency. And because almost every crossing all installs image acquisition equipment, consequently can acquire the first image of the dregs car at every crossing through image acquisition equipment, and then accomplish the detection whether follow-up dregs car breast board is heightened, consequently can avoid the problem of lou examining.
Example 2:
the image acquired by the image acquisition device is generally a whole frame of scene image including a muck truck, and in order to accurately determine the breast board sub-image, a first image of the muck truck is generally determined in the whole frame of scene image. In order to accurately acquire the first image of the slag car, on the basis of the above embodiment, in an embodiment of the present invention, the acquiring the first image of the slag car includes:
and acquiring a second image containing the muck truck, inputting the second image into a pre-trained muck truck detection model, and determining a first image of the muck truck in the second image based on the muck truck detection model.
The method comprises the steps that a pre-trained muck car detection model is stored in the electronic equipment, and the muck car detection model is used for segmenting an image of a muck car from a whole frame of scene image. After the image acquisition equipment acquires the whole frame of scene image containing the muck truck, namely the second image containing the muck truck in the embodiment of the invention, the second image is input into a pre-trained muck truck detection model, and the first image of the muck truck in the second image is determined based on the muck truck detection model.
Fig. 2 is a schematic diagram of a second image provided in an embodiment of the present invention, where after the second image is input into the muck car detection model, a result output by the muck car detection model is shown in fig. 3, and fig. 3 is a schematic diagram of a first image provided in an embodiment of the present invention. The first image is input into the hurdle board segmentation model which is trained in advance, the output result of the hurdle board segmentation model is shown in fig. 4, and fig. 4 is a schematic diagram of a hurdle board sub-image provided by the embodiment of the invention.
In the embodiment of the invention, the second image containing the muck car is obtained, the second image is input into a pre-trained muck car detection model, and the first image of the muck car in the second image is determined based on the muck car detection model. Facilitating subsequent determination of a balustrade image in the first image.
Example 3:
in order to make it more accurate to detect whether the slag car sideboard is heightened, on the basis of the above embodiments, in an embodiment of the present invention, the detecting whether the slag car sideboard is heightened according to the width and the height includes:
judging whether a first ratio of the width to the height of the breast board image is smaller than a preset first threshold value or not, if so, determining that the breast board of the muck truck is heightened, and if not, determining that the breast board of the muck truck is not heightened; or judging whether a second ratio of the height to the width of the breast board sub-image is larger than a preset second threshold value, if so, determining that the breast board of the muck truck is heightened, and if not, determining that the breast board of the muck truck is not heightened.
After the electronic equipment determines the breast board subimage in the first image, the width and the height of the breast board subimage are determined, a first ratio of the width and the height of the breast board subimage is calculated, and whether the breast board of the slag car is heightened is judged according to the first ratio. The electronic equipment stores a preset first threshold value, wherein the preset first threshold value is determined according to the reference width and the reference height of the breast board in the slag car with the breast board not heightened, that is, the electronic equipment acquires the reference width and the reference height of the breast board in the slag car with the breast board not heightened in advance, and calculates the ratio of the reference width to the reference height as the preset first threshold value. Or calculating the ratio of the reference width to the reference height, and increasing or decreasing the ratio by a smaller parameter value as a preset first threshold value.
For this reason, the ratio of the width to the height of the sub-images of the raised breast board to the sub-images of the non-raised breast board is different, and in the embodiment of the invention, whether the breast board of the slag discharging cart is raised or not can be detected according to the first ratio of the width to the height of the sub-images of the breast board. Specifically, whether a first ratio of the width to the height of the breast board image is smaller than a preset first threshold value or not is judged, if yes, the breast board of the muck truck is heightened, and if not, the breast board of the muck truck is not heightened.
Or after the electronic equipment determines the breast board sub-image in the first image, the width and the height of the breast board sub-image are determined, a second ratio of the height to the width of the breast board sub-image is calculated, and whether the breast board of the muck truck is heightened or not is judged according to the second ratio. The electronic equipment stores a preset second threshold value, and the preset second threshold value is the ratio of the reference height to the reference width of the breast board in the residue soil truck with the breast board not heightened. Or calculating the ratio of the reference height and the reference width, and increasing or decreasing the ratio by a smaller parameter value as a preset second threshold value. And judging whether a second ratio of the height to the width of the breast board sub-image is larger than a preset second threshold value, if so, determining that the breast board of the muck truck is heightened, and if not, determining that the breast board of the muck truck is not heightened.
In the embodiment of the invention, whether the slag car breast board is heightened is detected according to the first ratio of the width to the height of the breast board sub-image or the second ratio of the height to the width of the breast board sub-image. Therefore, whether the breast board of the muck truck is heightened or not can be detected more accurately.
Example 4:
the first image is input into the hurdle board segmentation model which is trained in advance, and the hurdle board sub-images output by the hurdle board segmentation model may have irregular shapes, which can also be seen from fig. 4. In order to make the determination of the width and the height of the balustrade sub-image more accurate, on the basis of the above embodiments, in an embodiment of the present invention, the determining the width and the height of the balustrade sub-image includes:
determining the minimum circumscribed rectangle of the breast board sub-image, taking the width of the minimum circumscribed rectangle as the width of the breast board sub-image, and taking the height of the minimum circumscribed rectangle as the height of the breast board sub-image.
After determining a breast board sub-image in a first image by the electronic device based on a breast board segmentation model, determining a minimum circumscribed rectangle of the breast board sub-image, taking the width of the minimum circumscribed rectangle as the width of the breast board sub-image, and taking the height of the minimum circumscribed rectangle as the height of the breast board sub-image. Fig. 5 is a schematic diagram of determining a minimum bounding rectangle of a sideboard sub-image according to an embodiment of the present invention, and it can be seen from fig. 5 that determining the width and height of the sideboard sub-image based on the minimum bounding rectangle is more accurate.
Example 5:
in an embodiment of the present invention, a training process of the balustrade segmentation model includes:
aiming at a third image of each slag car in a first sample set, inputting the third image and a first annotation image corresponding to the third image into the breast board segmentation model, and training the breast board segmentation model; and the first annotation image is annotated with the position information of the template image in the third image.
The electronic device stores a first sample set, wherein the first sample set comprises a third image of each slag car, and the third image of each slag car comprises a third image of a slag car with a heightened breast board and a third image of a slag car without a heightened breast board. And saving a corresponding first annotation image for each third image, wherein the first annotation image is annotated with the position information of the template image in the third image. And the electronic equipment inputs each third image in the first sample set and the first marked image corresponding to each third image into the breast board segmentation model to finish the training of the breast board segmentation model.
In the embodiment of the invention, the training process of the detection model of the muck car comprises the following steps:
inputting the fourth image and a second labeling image corresponding to the fourth image into the muck car detection model aiming at each fourth image in a second sample set, and training the muck car detection model; and the second annotation image is annotated with the position information of the muck truck image in the fourth image.
The electronic equipment stores a second sample set, wherein the second sample set comprises each fourth image, and each fourth image is an entire frame of scene image containing the muck truck. And storing a second annotation image corresponding to each fourth image, wherein the second annotation image is marked with the position information of the muck car image in the fourth image. And the electronic equipment inputs each fourth image in the second sample set and the second marked image corresponding to each fourth image into the muck car detection model to finish the training of the muck car detection model.
Fig. 6 is a schematic view of a heightening detection process of a breast board of a muck truck, which is provided by an embodiment of the present invention, and the process includes the following steps:
s201: and acquiring a second image containing the muck truck, inputting the second image into a pre-trained muck truck detection model, and determining a first image of the muck truck in the second image based on the muck truck detection model.
S202: inputting the first image into a pre-trained breast board segmentation model, and determining a breast board sub-image in the first image based on the breast board segmentation model.
S203: determining the minimum circumscribed rectangle of the breast board sub-image, taking the width of the minimum circumscribed rectangle as the width of the breast board sub-image, and taking the height of the minimum circumscribed rectangle as the height of the breast board sub-image.
S204: judging whether a first ratio of the width to the height of the breast board image is smaller than a preset first threshold value or not, if so, determining that the breast board of the muck truck is heightened, and if not, determining that the breast board of the muck truck is not heightened; or judging whether a second ratio of the height to the width of the breast board sub-image is larger than a preset second threshold value, if so, determining that the breast board of the muck truck is heightened, and if not, determining that the breast board of the muck truck is not heightened.
Example 6:
fig. 7 is a schematic structural view of a device for heightening and detecting a fence plate of a muck truck, provided in an embodiment of the present invention, where the device includes:
an acquisition module 61 for acquiring a first image of the muck truck;
a determining module 62, configured to input the first image into a hurdle board segmentation model which is trained in advance, and determine a hurdle board sub-image in the first image based on the hurdle board segmentation model;
and the detection module 63 is used for determining the width and the height of the breast board sub-image and detecting whether the breast board of the slag car is heightened or not according to the width and the height.
The obtaining module 61 is specifically configured to obtain a second image including the muck car, input the second image into a pre-trained muck car detection model, and determine, based on the muck car detection model, a first image of the muck car in the second image.
The detection module 63 is specifically configured to determine whether a first ratio of the width to the height of the breast board sub-image is smaller than a preset first threshold, determine that the breast board of the muck truck is heightened if the first ratio is smaller than the preset first threshold, and determine that the breast board of the muck truck is not heightened if the first ratio is not larger than the preset first threshold; or judging whether a second ratio of the height to the width of the breast board sub-image is larger than a preset second threshold value, if so, determining that the breast board of the muck truck is heightened, and if not, determining that the breast board of the muck truck is not heightened.
The detection module 63 is specifically configured to determine a minimum circumscribed rectangle of the balustrade sub-image, use the width of the minimum circumscribed rectangle as the width of the balustrade sub-image, and use the height of the minimum circumscribed rectangle as the height of the balustrade sub-image.
The device further comprises:
a first training module 64, configured to input, for a third image of each muck truck in the first sample set, the third image and a first labeled image corresponding to the third image into the breast board segmentation model, and train the breast board segmentation model; and the first annotation image is annotated with the position information of the template image in the third image.
The device further comprises:
a second training module 65, configured to input, for each fourth image in the second sample set, the fourth image and a second labeled image corresponding to the fourth image into the muck truck detection model, and train the muck truck detection model; and the second annotation image is annotated with the position information of the muck truck image in the fourth image.
Example 7:
on the basis of the foregoing embodiments, an embodiment of the present invention further provides an electronic device, as shown in fig. 8, including: the system comprises a processor 301, a communication interface 302, a memory 303 and a communication bus 304, wherein the processor 301, the communication interface 302 and the memory 303 complete mutual communication through the communication bus 304;
the memory 303 has stored therein a computer program which, when executed by the processor 301, causes the processor 301 to perform the steps of:
acquiring a first image of the muck truck;
inputting the first image into a pre-trained breast board segmentation model, and determining a breast board sub-image in the first image based on the breast board segmentation model;
and determining the width and the height of the breast board sub-image, and detecting whether the breast board of the muck truck is heightened according to the width and the height.
Based on the same inventive concept, the embodiment of the invention also provides the electronic equipment, and as the principle of solving the problems of the electronic equipment is similar to the method for detecting the heightening of the guardrail of the muck truck, the implementation of the electronic equipment can refer to the implementation of the method, and repeated parts are not described again.
The electronic device provided by the embodiment of the invention can be a desktop computer, a portable computer, a smart phone, a tablet computer, a Personal Digital Assistant (PDA), a network side device and the like.
The communication bus mentioned in the electronic device may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.
The communication interface 302 is used for communication between the above-described electronic apparatus and other apparatuses.
The Memory may include a Random Access Memory (RAM) or a Non-Volatile Memory (NVM), such as at least one disk Memory. Alternatively, the memory may be at least one memory device located remotely from the processor.
The Processor may be a general-purpose Processor, including a central processing unit, a Network Processor (NP), and the like; but may also be a Digital Signal Processor (DSP), an application specific integrated circuit, a field programmable gate array or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or the like.
When the processor executes the program stored in the memory in the embodiment of the invention, the first image of the muck car is acquired; inputting the first image into a pre-trained breast board segmentation model, and determining a breast board sub-image in the first image based on the breast board segmentation model; and determining the width and the height of the breast board sub-image, and detecting whether the breast board of the muck truck is heightened according to the width and the height.
In the embodiment of the invention, the electronic equipment acquires the first image of the muck truck, determines the breast board sub-image in the first image based on the breast board segmentation model trained in advance, and then judges whether the breast board of the muck truck is heightened according to the width and the height of the breast board sub-image. The scheme provided by the embodiment of the invention does not need manual intervention, thereby greatly reducing the consumption of human resources and improving the detection efficiency. And because almost every crossing all installs image acquisition equipment, consequently can acquire the first image of the dregs car at every crossing through image acquisition equipment, and then accomplish the detection whether follow-up dregs car breast board is heightened, consequently can avoid the problem of lou examining.
Example 8:
on the basis of the foregoing embodiments, an embodiment of the present invention further provides a computer storage readable storage medium, in which a computer program executable by an electronic device is stored, and when the program is run on the electronic device, the electronic device is caused to execute the following steps:
acquiring a first image of the muck truck;
inputting the first image into a pre-trained breast board segmentation model, and determining a breast board sub-image in the first image based on the breast board segmentation model;
and determining the width and the height of the breast board sub-image, and detecting whether the breast board of the muck truck is heightened according to the width and the height.
Based on the same inventive concept, the embodiment of the present invention further provides a computer-readable storage medium, and since the principle of solving the problem when the processor executes the computer program stored in the computer-readable storage medium is similar to the method for detecting raised height of the balustrade of the muck vehicle, the implementation of the computer program stored in the computer-readable storage medium by the processor may refer to the implementation of the method, and repeated details are omitted.
The computer readable storage medium may be any available medium or data storage device that can be accessed by a processor in an electronic device, including but not limited to magnetic memory such as floppy disks, hard disks, magnetic tape, magneto-optical disks (MOs), etc., optical memory such as CDs, DVDs, BDs, HVDs, etc., and semiconductor memory such as ROMs, EPROMs, EEPROMs, non-volatile memory (NAND FLASH), Solid State Disks (SSDs), etc.
In a computer-readable storage medium provided in an embodiment of the present invention, there is stored a computer program that, when executed by a processor, enables obtaining a first image of a muck car; inputting the first image into a pre-trained breast board segmentation model, and determining a breast board sub-image in the first image based on the breast board segmentation model; and determining the width and the height of the breast board sub-image, and detecting whether the breast board of the muck truck is heightened according to the width and the height.
In the embodiment of the invention, the electronic equipment acquires the first image of the muck truck, determines the breast board sub-image in the first image based on the breast board segmentation model trained in advance, and then judges whether the breast board of the muck truck is heightened according to the width and the height of the breast board sub-image. The scheme provided by the embodiment of the invention does not need manual intervention, thereby greatly reducing the consumption of human resources and improving the detection efficiency. And because almost every crossing all installs image acquisition equipment, consequently can acquire the first image of the dregs car at every crossing through image acquisition equipment, and then accomplish the detection whether follow-up dregs car breast board is heightened, consequently can avoid the problem of lou examining.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may 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 instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may 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 flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (14)
1. A heightening detection method for a breast board of a muck truck is characterized by comprising the following steps:
acquiring a first image of the muck truck;
inputting the first image into a pre-trained breast board segmentation model, and determining a breast board sub-image in the first image based on the breast board segmentation model;
and determining the width and the height of the breast board sub-image, and detecting whether the breast board of the muck truck is heightened according to the width and the height.
2. The method of claim 1, wherein the obtaining a first image of a muck car comprises:
and acquiring a second image containing the muck truck, inputting the second image into a pre-trained muck truck detection model, and determining a first image of the muck truck in the second image based on the muck truck detection model.
3. The method of claim 1, wherein said detecting whether said slag car fence is raised based on said width and height comprises:
judging whether a first ratio of the width to the height of the breast board image is smaller than a preset first threshold value or not, if so, determining that the breast board of the muck truck is heightened, and if not, determining that the breast board of the muck truck is not heightened; or judging whether a second ratio of the height to the width of the breast board sub-image is larger than a preset second threshold value, if so, determining that the breast board of the muck truck is heightened, and if not, determining that the breast board of the muck truck is not heightened.
4. The method of claim 1, wherein the determining the width and height of the balustrade sub-image comprises:
determining the minimum circumscribed rectangle of the breast board sub-image, taking the width of the minimum circumscribed rectangle as the width of the breast board sub-image, and taking the height of the minimum circumscribed rectangle as the height of the breast board sub-image.
5. The method of claim 1, wherein the training process of the balustrade segmentation model comprises:
aiming at a third image of each slag car in a first sample set, inputting the third image and a first annotation image corresponding to the third image into the breast board segmentation model, and training the breast board segmentation model; and the first annotation image is annotated with the position information of the template image in the third image.
6. The method of claim 2, wherein the training process of the muck car detection model comprises:
inputting the fourth image and a second labeling image corresponding to the fourth image into the muck car detection model aiming at each fourth image in a second sample set, and training the muck car detection model; and the second annotation image is annotated with the position information of the muck truck image in the fourth image.
7. The utility model provides a detection device is increased to dregs car breast board which characterized in that, the device includes:
the acquiring module is used for acquiring a first image of the muck truck;
the determining module is used for inputting the first image into a pre-trained breast board segmentation model and determining a breast board sub-image in the first image based on the breast board segmentation model;
and the detection module is used for determining the width and the height of the breast board sub-image and detecting whether the breast board of the muck truck is heightened or not according to the width and the height.
8. The apparatus of claim 7, wherein the acquisition module is specifically configured to acquire a second image including the muck car, input the second image into a pre-trained muck car detection model, and determine the first image of the muck car in the second image based on the muck car detection model.
9. The device according to claim 7, wherein the detection module is specifically configured to determine whether a first ratio of the width to the height of the balustrade image is smaller than a preset first threshold, if so, determine that the balustrade of the muck car is raised, and if not, determine that the balustrade of the muck car is not raised; or judging whether a second ratio of the height to the width of the breast board sub-image is larger than a preset second threshold value, if so, determining that the breast board of the muck truck is heightened, and if not, determining that the breast board of the muck truck is not heightened.
10. The apparatus according to claim 7, wherein the detection module is specifically configured to determine a minimum bounding rectangle of the balustrade sub-image, use a width of the minimum bounding rectangle as a width of the balustrade sub-image, and use a height of the minimum bounding rectangle as a height of the balustrade sub-image.
11. The apparatus of claim 7, wherein the apparatus further comprises:
the first training module is used for inputting a third image and a first marked image corresponding to the third image into the breast board segmentation model aiming at the third image of each muck truck in the first sample set, and training the breast board segmentation model; and the first annotation image is annotated with the position information of the template image in the third image.
12. The apparatus of claim 8, wherein the apparatus further comprises:
the second training module is used for inputting the fourth image and a second labeled image corresponding to the fourth image into the muck car detection model aiming at each fourth image in the second sample set and training the muck car detection model; and the second annotation image is annotated with the position information of the muck truck image in the fourth image.
13. An electronic device is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor and the communication interface are used for realizing mutual communication by the memory through the communication bus;
a memory for storing a computer program;
a processor for implementing the method steps of any one of claims 1 to 6 when executing a program stored in the memory.
14. A computer-readable storage medium, characterized in that a computer program is stored in the computer-readable storage medium, which computer program, when being executed by a processor, carries out the method steps of any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010640308.8A CN111915611B (en) | 2020-07-06 | 2020-07-06 | Method and device for heightening detection of road surface fence, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010640308.8A CN111915611B (en) | 2020-07-06 | 2020-07-06 | Method and device for heightening detection of road surface fence, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111915611A true CN111915611A (en) | 2020-11-10 |
| CN111915611B CN111915611B (en) | 2024-08-27 |
Family
ID=73227413
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010640308.8A Active CN111915611B (en) | 2020-07-06 | 2020-07-06 | Method and device for heightening detection of road surface fence, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111915611B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112730166A (en) * | 2020-12-31 | 2021-04-30 | 北京佳华智联科技有限公司 | Detection method, device and detection device for measure for inhibiting atmospheric particulate matter emission |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102411767A (en) * | 2011-11-25 | 2012-04-11 | 中科怡海高新技术发展江苏股份公司 | Construction site intelligent monitoring system and method based on internet of things |
| KR101422644B1 (en) * | 2014-01-28 | 2014-07-24 | 주식회사 스마트비전 | Method and system for controlling overloaded vehicle |
| CN204881524U (en) * | 2015-05-15 | 2015-12-16 | 石家庄华燕交通科技有限公司 | Boxcar breast board height detection device |
| CN105157608A (en) * | 2015-08-31 | 2015-12-16 | 浙江大华技术股份有限公司 | Detection method, apparatus, and system of oversized vehicle |
| CN106767450A (en) * | 2016-12-28 | 2017-05-31 | 重庆交通大学 | A kind of vehicle super-high ultra-wide detecting system and method demarcated based on function |
| CN108225173A (en) * | 2016-12-09 | 2018-06-29 | 西安思能网络科技有限公司 | A kind of automobile full car size measuring system |
| CN108734091A (en) * | 2018-03-30 | 2018-11-02 | 暨南大学 | Compartment anomaly detection method, computer installation and computer readable storage medium |
| CN110766039A (en) * | 2019-09-02 | 2020-02-07 | 厦门卫星定位应用股份有限公司 | Muck truck transportation state identification method, medium, equipment and muck truck |
| CN111222394A (en) * | 2019-10-16 | 2020-06-02 | 北京文安智能技术股份有限公司 | Muck truck overload detection method, device and system |
-
2020
- 2020-07-06 CN CN202010640308.8A patent/CN111915611B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102411767A (en) * | 2011-11-25 | 2012-04-11 | 中科怡海高新技术发展江苏股份公司 | Construction site intelligent monitoring system and method based on internet of things |
| KR101422644B1 (en) * | 2014-01-28 | 2014-07-24 | 주식회사 스마트비전 | Method and system for controlling overloaded vehicle |
| CN204881524U (en) * | 2015-05-15 | 2015-12-16 | 石家庄华燕交通科技有限公司 | Boxcar breast board height detection device |
| CN105157608A (en) * | 2015-08-31 | 2015-12-16 | 浙江大华技术股份有限公司 | Detection method, apparatus, and system of oversized vehicle |
| CN108225173A (en) * | 2016-12-09 | 2018-06-29 | 西安思能网络科技有限公司 | A kind of automobile full car size measuring system |
| CN106767450A (en) * | 2016-12-28 | 2017-05-31 | 重庆交通大学 | A kind of vehicle super-high ultra-wide detecting system and method demarcated based on function |
| CN108734091A (en) * | 2018-03-30 | 2018-11-02 | 暨南大学 | Compartment anomaly detection method, computer installation and computer readable storage medium |
| CN110766039A (en) * | 2019-09-02 | 2020-02-07 | 厦门卫星定位应用股份有限公司 | Muck truck transportation state identification method, medium, equipment and muck truck |
| CN111222394A (en) * | 2019-10-16 | 2020-06-02 | 北京文安智能技术股份有限公司 | Muck truck overload detection method, device and system |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112730166A (en) * | 2020-12-31 | 2021-04-30 | 北京佳华智联科技有限公司 | Detection method, device and detection device for measure for inhibiting atmospheric particulate matter emission |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111915611B (en) | 2024-08-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11455805B2 (en) | Method and apparatus for detecting parking space usage condition, electronic device, and storage medium | |
| EP3620981B1 (en) | Object detection method, device, apparatus and computer-readable storage medium | |
| CN109190488B (en) | Front vehicle door opening detection method and device based on deep learning YOLOv3 algorithm | |
| CN112330601A (en) | Parking detection method, device, equipment and medium based on fisheye camera | |
| EP3270364A2 (en) | Detection method and apparatus of a status of a parking lot and electronic equipment | |
| CN109492609B (en) | Method for detecting lane line, vehicle and computing equipment | |
| CN114565895A (en) | Security monitoring system and method based on intelligent society | |
| CN112862856A (en) | Method, device and equipment for identifying illegal vehicle and computer readable storage medium | |
| CN111626189B (en) | Road surface abnormity detection method and device, electronic equipment and storage medium | |
| CN111914671B (en) | Safety belt detection method and device, electronic equipment and storage medium | |
| CN111915611A (en) | Method and device for heightening and detecting breast board of muck truck, electronic equipment and storage medium | |
| CN111199567B (en) | Lane line drawing method, device and terminal equipment | |
| CN111191603A (en) | In-vehicle personnel identification method, device, terminal equipment and medium | |
| CN113297939B (en) | Obstacle detection method, obstacle detection system, terminal device and storage medium | |
| CN115019511A (en) | Method and device for identifying illegal lane change of motor vehicle based on automatic driving vehicle | |
| CN116863124B (en) | Vehicle attitude determination method, controller and storage medium | |
| CN112270319A (en) | Event marking method and device and electronic equipment | |
| CN114596496A (en) | Wheel state identification method and device, water spray control method and device | |
| CN114814643A (en) | AC power supply ground fault monitoring method, fire early warning system | |
| CN112200835A (en) | Traffic accident detection method and device, electronic equipment and storage medium | |
| CN114359884A (en) | License plate recognition method and device, electronic equipment and storage medium | |
| CN113111818A (en) | Vehicle lane occupation detection method, device, equipment and storage medium | |
| TWI778652B (en) | Method for calculating overlap, electronic equipment and storage medium | |
| CN114627651B (en) | Pedestrian protection early warning method and device, electronic equipment and readable storage medium | |
| CN111401824A (en) | Method and device for calculating working hours |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |