CN115953472A - Intelligent positioning method for cargo carrying area of low-flat-bed semitrailer - Google Patents
Intelligent positioning method for cargo carrying area of low-flat-bed semitrailer Download PDFInfo
- Publication number
- CN115953472A CN115953472A CN202310233521.0A CN202310233521A CN115953472A CN 115953472 A CN115953472 A CN 115953472A CN 202310233521 A CN202310233521 A CN 202310233521A CN 115953472 A CN115953472 A CN 115953472A
- Authority
- CN
- China
- Prior art keywords
- area
- semi
- trailer
- pixel point
- semitrailer
- 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
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of image data processing, in particular to an intelligent positioning method for a cargo area of a low-flat-bed semitrailer. The method includes the steps that the optimization degree of a corresponding window area is obtained through the local smoothness of pixel points in the window area, the optimal parking area of a semi-trailer in a cargo area image is obtained according to the optimization degree, the semi-trailer area of each frame of semi-trailer image is obtained based on the gray value of the pixel points in the adjacent semi-trailer image, the real-time actual semi-trailer area in the process that the semi-trailer moves to the optimal parking area is obtained according to the characteristic points of the semi-trailer area in each frame of semi-trailer image, and the intelligent positioning of the cargo area of the semi-trailer is completed by combining the orientation direction of the optimal parking area and the orientation direction of the actual semi-trailer area. The semi-trailer moving direction adjusting device analyzes the whole process from the actual semi-trailer area to the optimal parking area, realizes flexible adjustment of the semi-trailer moving direction, and improves the accuracy of intelligent positioning of the cargo area of the low-bed semi-trailer.
Description
Technical Field
The invention relates to the technical field of image data processing, in particular to an intelligent positioning method for a cargo area of a low-bed semitrailer.
Background
When the low-flat-bed semi-trailer is loading and unloading goods, a driver is often required to select a proper position to park and then complete the loading and unloading goods, but the driver often can obtain the position information of the current semi-trailer inaccurately due to the existence of the phenomena such as sight shielding and the like, and is difficult to complete accurate parking, but the selection of the parking position not only influences the loading and unloading goods efficiency, but also influences the occurrence of safety accidents.
When the low-flat-bed semi-trailer is loaded and unloaded, accidents can be reduced at proper positions, in the process of parking the semi-trailer at the corresponding proper positions, the collected vehicle appearance data, vehicle posture positions and running track data are sent to a computer control module by the conventional method to generate a vehicle mathematical model, an ideal warehousing route of the vehicle is calculated, the ideal warehousing route of the vehicle is converted into a projection signal of an optical projection indicating module, the projection signal is projected on a windshield of the vehicle through a guide light beam through guide information in the projection signal, and the vehicle is guided to an ideal parking position based on the guide light beam pair.
Disclosure of Invention
In order to solve the problem that the low-flatbed semitrailer cannot be parked at an ideal parking position due to deviation of an ideal route, the invention aims to provide an intelligent positioning method for a cargo carrying area of the low-flatbed semitrailer, and the adopted technical scheme is as follows:
the invention provides an intelligent positioning method for a cargo carrying area of a low-bed semitrailer, which comprises the following steps:
collecting a loading area image of the unloading site to obtain a loading area gray image corresponding to the loading area image;
acquiring each window area in the gray-scale image of the cargo area by using a sliding window, taking any pixel point in the window area as an example pixel point, and calculating the local smoothness of the example pixel point according to the gray-scale value of the neighborhood pixel point in the neighborhood of the example pixel point; acquiring the preference degree of the corresponding window area based on the local smoothness of each pixel point in the window area; acquiring the preference degree of each window area, and taking the window area corresponding to the maximum preference degree as the optimal parking area of the semitrailer;
acquiring at least two continuous frames of semi-trailer images in the process that the semi-trailer moves to the optimal parking area, acquiring motion pixel points in each frame of semi-trailer image according to gray values of pixel points in adjacent semi-trailer images, and acquiring the semi-trailer area of each frame of semi-trailer image according to the motion pixel points; acquiring characteristic points of a semitrailer area in each frame of semitrailer image, and acquiring an actual semitrailer area based on the characteristic points;
and setting the optimal orientation direction of the optimal parking area, and combining the optimal orientation direction of the optimal parking area and the real-time orientation direction of the actual semitrailer area to finish the intelligent positioning of the cargo carrying area of the semitrailer.
Further, the calculating the local smoothness of the example pixel point according to the gray value of the neighborhood pixel point in the example pixel point neighborhood includes:
setting a gray difference threshold and a neighborhood with a preset size, taking neighborhood pixels in the neighborhood of the example pixel as first neighborhood pixels, respectively calculating the absolute value of a gray value difference value between each first neighborhood pixel and the example pixel as a gray difference value corresponding to the first neighborhood pixels, and taking the first neighborhood pixels with the gray difference values larger than the gray difference threshold as target pixels of the example pixel;
obtaining central pixel points corresponding to other neighborhoods adjacent to the neighborhood of the example pixel point as first pixel points, taking straight lines obtained by connecting the first pixel points with the example pixel points as first straight lines corresponding to the first pixel points, selecting the first straight lines with the straight line directions in the horizontal direction and the vertical direction as associated straight lines, and classifying the first pixel points corresponding to the associated straight lines as associated pixel points of the example pixel points;
taking any one associated pixel of the example pixels as a target associated pixel, taking a neighborhood pixel in the neighborhood of the target associated pixel as a second neighborhood pixel, and respectively calculating the absolute value of the gray value difference between each second neighborhood pixel and the target associated pixel as the gray value difference corresponding to the second neighborhood pixel;
and combining the gray difference value of each first neighborhood pixel point of the example pixel point and the gray difference value of each second neighborhood pixel point of each associated pixel point of the example pixel point to obtain the local smoothness of the example pixel point.
Further, the obtaining the local smoothness of the example pixel point includes:
obtaining the local smoothness of the example pixel point through a local smoothness formula, wherein the calculation formula of the local smoothness is as follows:
in the formula (I), the compound is shown in the specification,is an example pixel pointThe local smoothness of (a);is an exemplary pixel pointThe number of target pixel points within the neighborhood of (c),is an example pixel pointThe number of associated pixel points of (a),is the number of neighborhood pixels in the neighborhood,is an example pixel pointTo (1) aThe gray scale difference value of each pixel point in the first neighborhood,representing example pixel pointsTo (1) aThe first of each associated pixelThe gray difference value of each second neighborhood pixel point;in the form of a function of the absolute value,is a maximum function;is a natural constant.
Further, the obtaining of the preference of the corresponding window region based on the local smoothness of each pixel point in the window region includes:
acquiring a central point of a window area as a window central point, and a central point of a gray image of a cargo area as an image central point, taking Euclidean distance between the window central point and the image central point as a first central point distance, respectively calculating Euclidean distance between each pixel point and the window central point in the window area as a second central point distance of a corresponding pixel point, and selecting the maximum value of the second central point distances as a maximum central point distance;
the reciprocal of the number of the pixel points in the window area is taken as a first result, a value obtained by taking a natural constant e as a base number and the opposite number of the distance of the first central point as an index is taken as a second result, the distance of the second central point of the pixel point is taken as a numerator, the distance of the maximum central point is taken as a denominator to obtain a first ratio of the corresponding pixel point, the product of the second result, the local smoothness of the corresponding pixel point and the first ratio is taken as a third result, the sum of the third results of each pixel point in the window area is taken as a fourth result, and the product of the first result and the fourth result is taken as the preference degree of the corresponding window area.
Further, the method for obtaining the motion pixel points in each frame of the semi-trailer image according to the gray values of the pixel points in the adjacent semi-trailer images includes the following steps:
calculating the difference value of the gray values of the same pixel point in the adjacent semi-trailer images by using a frame difference method to serve as the gray difference value of the corresponding pixel point, setting a gray threshold, screening the pixel points of which the gray values are larger than the gray threshold in the semi-trailer images to serve as moving pixel points, acquiring the moving pixel points in each frame of semi-trailer image, acquiring at least two areas formed by the moving pixel points in the semi-trailer image, and taking the largest area as the semi-trailer area corresponding to the semi-trailer image.
Further, the acquiring of the characteristic points of the semitrailer area in each frame of semitrailer image includes:
for any semi-trailer area, taking any edge pixel point in the semi-trailer area as an example edge pixel point, acquiring an edge pixel point adjacent to the example edge pixel point as an adjacent edge pixel point of the example edge pixel point, respectively calculating an included angle between a straight line formed by each adjacent edge pixel point and the example edge pixel point and a horizontal line to obtain a first edge characteristic angle corresponding to the adjacent edge pixel point, taking the mean value of the first edge characteristic angles of all the adjacent edge pixel points as a second edge characteristic angle of the example edge pixel point, and acquiring the second edge characteristic angle of each edge pixel point;
clustering all edge pixel points of the semi-trailer area based on a second edge feature angle to obtain two categories, taking the category with more edge pixel points as a first category and the category with less edge pixel points as a second category, and respectively obtaining the second edge feature angle of the clustering center point in the first category as the category angle of the first category and taking the second edge feature angle of the clustering center point in the second category as the category angle of the second category;
and (4) combining the category angle of each category to obtain the characteristic points of the semitrailer area in each frame of semitrailer image.
Further, the obtaining of the characteristic points of the semitrailer area in each frame of semitrailer image includes:
taking any one category angle as a straight line, traversing each edge pixel point in a window area by using the straight line, acquiring an edge pixel point corresponding to a tangent line of the straight line belonging to the edge pixel point as a target edge pixel point, taking the tangent line of the target edge pixel point, selecting two tangent lines with the farthest distance as a target tangent line pair, and acquiring the target tangent line pair under each category angle; taking any pixel point in the semi-trailer area as a reference pixel point, calculating a difference value of Euclidean distances between the reference pixel point and two tangents of a target tangent pair as a first difference value, calculating a first difference value of each target tangent pair, taking the sum of all the first difference values as a second difference value of the reference pixel point, respectively obtaining a second difference value of each pixel point in the semi-trailer area, and selecting the pixel point corresponding to the minimum second difference value as a characteristic point of the semi-trailer area.
Further, the obtaining of the actual semitrailer area based on the feature points includes:
taking a semi-trailer area of any semi-trailer image as a target semi-trailer area, respectively taking the semi-trailer area of the rest semi-trailer images as remaining semi-trailer areas, sequentially carrying out shape matching on the target semi-trailer area and each remaining semi-trailer area, obtaining at least two shape similarities in the target semi-trailer area, calculating an average value of all the shape similarities as a shape similarity average value of the target semi-trailer area, obtaining the shape similarity average value of each semi-trailer area, and taking a semi-trailer image where the semi-trailer area corresponding to the maximum shape similarity average value is located as a target semi-trailer image;
the method comprises the steps of superposing feature points of a semi-trailer region in a target semi-trailer image with feature points of the semi-trailer region in each frame of remaining semi-trailer image, projecting the semi-trailer region of each frame of semi-trailer image to the semi-trailer region in the target semi-trailer image, counting the projection times of each pixel point in the semi-trailer region in the target semi-trailer image after projection, setting a projection threshold value, screening out the pixel points with the projection times being larger than or equal to the projection threshold value as actual semi-trailer pixel points, and taking the region formed by the actual semi-trailer pixel points as the actual semi-trailer region.
Further, the intelligent positioning of the cargo area of the semitrailer is completed by combining the optimal orientation direction of the optimal parking area and the real-time orientation direction of the actual semitrailer area, and comprises the following steps:
respectively acquiring a category angle and a characteristic point of a first category of an actual semitrailer area, and taking the category angle of the first category as a real-time orientation direction of the actual semitrailer area and the characteristic point as an actual central point;
the method comprises the steps of obtaining a characteristic point of an optimal parking area as an optimal central point, calculating the Euclidean distance between an actual central point and the optimal central point as the moving distance of the semi-trailer, taking the absolute value of the difference value between the real-time orientation direction and the optimal orientation direction as the orientation direction difference value of the semi-trailer, and moving the semi-trailer to the optimal parking area by using the moving distance and the orientation direction difference value.
The invention has the following beneficial effects:
in order to improve the cargo loading and unloading efficiency of the low-bed semitrailer and reduce the probability of safety accidents during cargo loading and unloading, the embodiment of the invention obtains the optimal parking position information of the low-bed semitrailer in a cargo loading area image, namely the optimal parking area of the semitrailer in the cargo loading area image, because the edge of a window area is usually the tire of the semitrailer, and the tire of the semitrailer bears the weight of the semitrailer, the smoothness of the edge of the window area is very important, so that each window area in the gray-scale image of the cargo loading area is obtained by using a sliding window, the local smoothness of pixel points in the window area is calculated, the local smoothness of the pixel points in the window area is used as an important judgment index corresponding to the preference of the window area, and the preference of each window area is obtained, when the preference of the window area is larger, the more smooth the semitrailer is in the window area, the higher the efficiency of the semitrailer in loading and unloading the position corresponding to the window area is higher, so that the window area corresponding to the maximum preference is used as the optimal parking area of the semitrailer; in order to determine the actual position of the semitrailer in the process of moving the semitrailer to the optimal parking area and acquire at least two continuous frames of semitrailer images in the whole moving process of the semitrailer, because the semitrailer moves in the whole moving process, pixel points in the semitrailer area have different gray values in adjacent semitrailer images, motion pixel points in each frame of semitrailer image need to be acquired according to the gray values of the pixel points in the adjacent semitrailer images, and then the semitrailer area of each frame of semitrailer image is acquired based on the motion pixel points; the characteristic points of the semitrailer area can represent the position of the semitrailer in the semitrailer image, so that the characteristic points of the semitrailer area in each frame of semitrailer image are obtained, and the actual semitrailer area in the moving process is obtained from the multi-frame semitrailer image based on the characteristic points; the orientation direction can reflect the position information of the semitrailer in the moving process of the semitrailer, so that the intelligent positioning of the cargo area of the semitrailer is completed by combining the optimal orientation direction of the optimal parking area and the real-time orientation direction of the actual semitrailer area; through the best parking position of acquireing the semitrailer in the cargo carrying area image to and the semitrailer is to the regional real-time actual semitrailer of the regional removal in-process of optimal parking regional, the semitrailer removes to the regional best orientation direction of optimal parking according to the regional real-time orientation direction of actual semitrailer, the semitrailer can carry out nimble adjustment based on the direction of movement of real-time orientation direction to the semitrailer under emergency, the condition that has the error when making the semitrailer arrive the optimal parking region is littleer, and then make the intelligent positioning to the cargo carrying area of low flat-bed semitrailer more accurate.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart illustrating steps of a cargo area intelligent positioning method for a low-bed semitrailer according to an embodiment of the present invention.
Detailed Description
To further illustrate the technical means and effects of the present invention for achieving the predetermined purpose, the following detailed description of the method for intelligently positioning the cargo carrying area of the low-flatbed semi-trailer according to the present invention will be given with reference to the accompanying drawings and preferred embodiments. In the following description, the different references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The specific scenes aimed at by the invention are as follows: when the low-bed semitrailer unloads, the intelligent positioning of the cargo carrying area needs to be completed.
The specific scheme of the intelligent positioning method for the cargo area of the low-bed semitrailer provided by the invention is specifically described below by combining the accompanying drawings.
Referring to fig. 1, a flowchart of steps of a cargo area intelligent positioning method for a low-bed semitrailer according to an embodiment of the present invention is shown, where the method includes:
step S1: and collecting the loading area image of the unloading site to obtain a loading area gray level image corresponding to the loading area image.
The method comprises the steps of collecting a cargo area image shot by a monitoring camera installed in a cargo unloading site, wherein the cargo area image is an image of a final position to be parked of the low-flat-bed semi-trailer, the cargo area image is an RGB (red, green and blue) image, and the cargo area image is subjected to gray processing to obtain a gray image of the cargo area.
It should be noted that the present invention selects a weighted graying method to perform graying processing on the cargo area image, and the specific method is not described here and is a technical means well known to those skilled in the art.
Step S2: acquiring each window area in the gray-scale image of the cargo area by using a sliding window, taking any pixel point in the window area as an example pixel point, and calculating the local smoothness of the example pixel point according to the gray-scale value of the neighborhood pixel point in the neighborhood of the example pixel point; acquiring the preference degree of the corresponding window area based on the local smoothness of each pixel point in the window area; and acquiring the preference degree of each window area, and taking the window area corresponding to the maximum preference degree as the optimal parking area of the semitrailer.
Firstly, the cargo area image is analyzed to obtain the optimal parking area of the semi-trailer in the cargo area image, so that when the semi-trailer is used for loading and unloading cargos at the optimal parking position, the cargo loading and unloading efficiency of the semi-trailer can be improved, and the probability of safety accidents during loading and unloading cargos is reduced; secondly, analyzing the image of the semi-trailer in the process of moving the semi-trailer to the optimal parking area so as to obtain the real-time position of the semi-trailer in the moving process, namely the actual semi-trailer area; and then the semi-trailer is controlled to be parked through the orientation direction of the actual semi-trailer area and the orientation direction of the optimal parking area, so that the intelligent positioning of the semi-trailer loading area is completed.
Determining the length of the low-flat-bed semi-trailer area in the cargo area image according to the priori knowledgeWith a width ofThe size of the window of the sliding window is set to beUsing window sizes ofThe sliding window obtains a window area in the image of the cargo area, and the sliding step length of the window area isAnd analyzing each window area obtained by traversing the images of the cargo area by the sliding window, and acquiring the corresponding preference degree of each window area as the loading and unloading cargo parking position of the semitrailer.
Preferably, the length of the low-flat-bed semi-trailer area in the schemeTaking an empirical value of 200, the width of the low-bed semitrailer areaTaking the empirical value of 100, step size of window region slidingTakes an empirical value of 10.
Because the edge in the window region is the tire of semitrailer usually, and the tire of semitrailer carries out the bearing to the semitrailer, the smoothness in the edge in the window region is very important, so utilize the sliding window to obtain every window region in the grey scale image of cargo carrying area to calculate the local smoothness of every pixel in the window region. The method for acquiring the local smoothness of the pixel point comprises the following steps:
firstly, any pixel point in a window area is taken as an example pixel point, and a target pixel point in the neighborhood of the example pixel point is obtained according to the gray value of the neighborhood pixel point in the neighborhood of the example pixel point and the gray value of the example pixel point. The specific method for acquiring the target pixel point in the neighborhood of the example pixel point comprises the following steps: setting a gray difference threshold and a neighborhood with a preset size, taking neighborhood pixels in the neighborhood of the example pixel as first neighborhood pixels, respectively calculating the absolute value of a gray value difference value between each first neighborhood pixel and the example pixel as a gray difference value corresponding to the first neighborhood pixels, and taking the first neighborhood pixels with the gray difference values larger than the gray difference threshold as target pixels of the example pixel.
As an example, any one pixel point in the window area is taken as an example pixel pointSetting the size of the neighborhood of any one pixel point toObtaining example pixel pointsThe neighborhood pixel points in the neighborhood are taken as first neighborhood pixel points, and the gray difference value corresponding to each first neighborhood pixel point is respectively calculatedWherein, in the process,representing example pixel pointsIs in the neighborhood ofThe gray scale difference value of each pixel point in the first neighborhood,representing example pixel pointsIn the neighborhood of (1)The gray value of the pixel point of the first neighborhood,representing example pixelsSet a gray difference thresholdWhen it comes toThe gray level difference value of the first neighborhood pixel point is larger than the gray level difference threshold valueWhen it is going toA first neighborDomain pixel as an example pixelThe target pixel points in the neighborhood of (2) and counting the example pixel pointsThe number of target pixel points in the neighborhood is。
Preferably, the gray difference threshold value in the schemeTaking the empirical value of 15, the size of the neighborhoodTake the empirical value 3 x 3.
And secondly, acquiring the associated pixel points of the example pixel points according to the neighborhood of the pixel points and the neighborhood of the example pixel points and the angle of a straight line obtained by connecting the pixel points and the example pixel points. The specific method for acquiring the associated pixel point of the example pixel point comprises the following steps: the method comprises the steps of obtaining central pixel points corresponding to other neighborhoods adjacent to neighborhoods of example pixel points as first pixel points, taking straight lines obtained by connecting the first pixel points and the example pixel points as first straight lines corresponding to the first pixel points, selecting the first straight lines with the straight line directions in the horizontal direction and the vertical direction as association straight lines, and classifying the first pixel points corresponding to the association straight lines as association pixel points of the example pixel points.
And finally, combining the target pixel point and the associated pixel point of the example pixel point to acquire the local smoothness of the example pixel point, specifically comprising the following steps: taking any one associated pixel point of the example pixel points as a target associated pixel point, taking a neighborhood pixel point in the neighborhood of the target associated pixel point as a second neighborhood pixel point, and respectively calculating the absolute value of the gray value difference between each second neighborhood pixel point and the target associated pixel point as the gray value difference value corresponding to the second neighborhood pixel point; and combining the gray difference value of each first neighborhood pixel point of the example pixel point and the gray difference value of each second neighborhood pixel point of each associated pixel point of the example pixel point to obtain the local smoothness of the example pixel point.
The local smoothness of the example pixel point is obtained through a local smoothness formula, and the calculation formula of the local smoothness is as follows:
in the formula (I), the compound is shown in the specification,is an example pixel pointThe local smoothness of (a);is an example pixel pointThe number of target pixel points within the neighborhood of (c),is an exemplary pixel pointThe number of associated pixel points of (a),is the number of neighborhood pixels in the neighborhood,is an example pixel pointTo (1) aThe gray scale difference value of each pixel point in the first neighborhood,representing example pixelsTo (1) aThe first of each associated pixelThe gray difference value of each second neighborhood pixel point;in the form of a function of the absolute value,is a maximum function;are natural constants.
It should be noted that, when the gray scale difference value of the first neighborhood pixel is larger, the example pixel is caused to have a larger gray scale difference valueNumber of target pixels in the neighborhood of (2)The more, the example pixel pointsThe more uneven the field position in the corresponding cargo area image, the more smooth the example pixel points are shownLocal smoothness ofThe smaller; when a pixel point is instantiatedFirst neighborhood pixel point in neighborhood and example pixel pointThe difference value of the gray level difference value between the pixels of the second neighborhood in the neighborhood of the associated pixelThe smaller, the more representative an example pixel pointWeight of gray level difference value ofThe smaller, the example pixel pointLocal smoothness ofThe larger the pixel points, the more the pixel points are in the cargo area imageThe smoother the corresponding site position is in fact, the better the loading and unloading effect of the semitrailer at that position.
Neighborhood size of pixel spotTaking an empirical valueTime, number of neighborhood pixels in neighborhoodIs 8.
And based on the calculation formula of the local smoothness, acquiring the local smoothness of each pixel point in each window region.
The distance between the window central point and the image central point can reflect the distance between the window area and the central position of the cargo area image, the information of the central position of the cargo area image is accurate, the distance between the pixel point in the window area and the window central point can reflect the importance of the pixel point in the window area, and the closer the pixel point is to the central position of the window area, the more accurate the information reflected by the pixel point is, so that the accuracy of the preference degree of the window area can be improved.
The distance between the center point of the window and the center point of the image and the distance between each pixel point in the window area and the center point of the window are basic indexes of the optimization degree of the window area, and the specific acquisition method of the indexes comprises the following steps: the method comprises the steps of obtaining a center point of a window area as a window center point, obtaining a center point of a gray image of a cargo area as an image center point, taking Euclidean distance between the window center point and the image center point as a first center point distance, respectively calculating Euclidean distance between each pixel point and the window center point in the window area as a second center point distance of corresponding pixel points, and selecting the maximum value in the second center point distances as the maximum center point distance.
It should be noted that, the method for acquiring the central point of the window area and the central point of the grayscale image of the cargo area is similar to the method for acquiring the central point of the rectangle, and the specific method is not described herein and is a technical means well known to those skilled in the art.
Taking the reciprocal of the number of the pixel points in the window area as a first result, taking a value obtained by taking a natural constant e as a base number and the opposite number of the distance of the first central point as an index as a second result, taking the distance of the second central point of the pixel points as a numerator and the distance of the maximum central point as a denominator to obtain a first ratio of the corresponding pixel points, taking the product of the second result, the local smoothness of the corresponding pixel points and the first ratio as a third result, taking the sum of the third results of each pixel point in the window area as a fourth result, and taking the product of the first result and the fourth result as the preference degree of the corresponding window area.
As an example, the distance between the first center point and the second center point of the window region is combined, the local smoothness of the pixel points in the window region is taken as an important judgment index of the preference of the window region, the preference of each window region is obtained, and then the preference of the window region is obtainedThe calculation formula of (a) is as follows:
in the formula (I), the compound is shown in the specification,the number of pixels in the window area is,is the window center pointAnd the center point of the imageA first center point distance therebetween,is in the window regionA pixel point and a window center pointA second center point distance therebetween,is the maximum center point distance in the window area,is shown asLocal smoothness of individual pixel points;is a natural constant.
It should be noted that, because the information of the central position of the image of the cargo area is relatively rich and accurate, when the distance of the first central point of the window area is larger than the distance of the second central point of the window areaThe smaller the window area is, the closer the window area is to the central position of the image of the cargo area, and the information of the semitrailer in the window area is more accurate, so the optimization degree of the window areaThe larger;indicating the use of first in the window areaObtaining the second central point distance of each pixel pointLocal smoothness weight of individual pixel point, whenLocal smoothness of each pixel pointThe larger, theThe greater the local smoothness weight of each pixel point, the greater the local smoothness weight of each pixel point in the window area, the greater the preference degree of the window area, the greater the internal smoothness of the window area is indicated, namely, the smoother the window area is, the better the effect of the semitrailer when the semitrailer is parked and loads and unloads goods at the position of the window area is, and the lower the possibility of accidents is.
The scheme is based on the corresponding preference degree of each window areaThe sliding step length is adaptively adjusted, and the sliding step length of the window area isTo a first orderTaking a window area as an example, obtain the firstPreference of individual window regionsSliding window by step lengthAfter sliding to obtainA window region, obtainPreference of individual window regionsObtaining step size update indexThe method for obtaining the step length updating index comprises(ii) a When step size updates the indexIf the value is greater than 0, the window is slid towards the window area corresponding to the local maximum preference degree, in order to ensure that the finally obtained area is accurate enough, the step length is updated,,which represents the step size after the update,indicates that the value in parentheses is rounded down; when step size updates the indexWhen it is equal to 0, step sizeKeeping the same; when step size updates the indexLess than 0, indicating that the window is sliding awayThe window area corresponding to the maximum local preference degree, at this time, the step size should be updated for improving the efficiency,(ii) a Therefore, efficient and accurate traversal of the images of the cargo area is achieved, and compared with a traditional method that a sliding window slides in the images only according to a set fixed step length, the method has the advantages that excessive window areas are obtained when the sliding window traverses the images in the fixed step length, and resource waste is caused.
The sliding window traverses the images of the cargo area based on the step length after the self-adaptive adjustment to obtain a plurality of window areas, the preference degree of each window area is obtained, and the window area corresponding to the maximum preference degree is used as the optimal parking area of the semitrailer.
And step S3: acquiring at least two continuous frames of semi-trailer images in the process that the semi-trailer moves to the optimal parking area, acquiring motion pixel points in each frame of semi-trailer image according to gray values of pixel points in adjacent semi-trailer images, and acquiring the semi-trailer area of each frame of semi-trailer image according to the motion pixel points; and acquiring the characteristic points of the semitrailer area in each frame of semitrailer image, and acquiring the actual semitrailer area based on the characteristic points.
Acquire the continuous multiframe semitrailer image that the semitrailer removed the process to the optimal region of parking, and then acquire the semitrailer region of these semitrailer images respectively, it is regional that every frame semitrailer image obtains a semitrailer, because the position of semitrailer in the regional characteristic point of semitrailer can characterize the semitrailer image, so acquire the characteristic point in every semitrailer region, further based on the regional characteristic point acquisition of semitrailer remove the real-time position of in-process, actual semitrailer is regional promptly.
Acquiring continuous multi-frame images in the process that the semi-trailer moves to the optimal parking area, performing graying processing on the images respectively through a weight graying method to obtain corresponding semi-trailer images, acquiring the semi-trailer area of the semi-trailer images, and preparing for obtaining characteristic points representing the position of the semi-trailer in the semi-trailer images subsequently. The method for acquiring the semitrailer area of the semitrailer image is as follows: calculating the difference value of the gray values of the same pixel point in the adjacent semi-trailer images by using a frame difference method to serve as the gray difference value of the corresponding pixel point, setting a gray threshold, screening the pixel points of which the gray values are larger than the gray threshold in the semi-trailer images to serve as moving pixel points, acquiring the moving pixel points in each frame of semi-trailer image, acquiring at least two areas formed by the moving pixel points in the semi-trailer image, and taking the largest area as the semi-trailer area corresponding to the semi-trailer image.
As an example, a semitrailer image is analyzed using a frame difference method to obtain a semitrailer imageTaking a semi-trailer image as an exampleThe image of the semitrailer in the next frame isGet the semitrailer imageAny one pixel point in (1) is a pixel pointFinding out semi-trailer imagePixel point inOn the semitrailer imageThe corresponding pixel point in (1) isTo connect the pixel pointsGray value and pixel point ofOf the gray value ofThe absolute value of the difference between the two is used as a pixel pointCalculating the semitrailer image according to the gray difference valueSetting the gray threshold value asThe gray level difference value is larger than the gray level threshold valueThe pixel points are used as images of the semitrailerThe gray level difference value is less than or equal to the gray level threshold valueThe pixel points are used as images of the semitrailerStationary pixel points of (2), semitrailer imagesThe method is characterized in that a plurality of regions formed by moving pixel points may exist, and the largest region is taken as a semi-trailer image due to the possible interference of other non-semi-trailer moving objectsThere is one semi-trailer area in each semi-trailer image.
Because the semi-trailer area obtained by the method is the approximate range of the semi-trailer, the semi-trailer area is not accurate enough, if the semi-trailer is positioned by directly using the information of the semi-trailer area, the cargo loading and unloading efficiency of the semi-trailer can be reduced, safety accidents occur in the cargo loading and unloading process, so that characteristic points of the semi-trailer area need to be obtained, and the semi-trailer area which is more accurate in the semi-trailer image is obtained based on the characteristic points. The method for acquiring the characteristic points of the semitrailer area comprises the following steps:
firstly, a second edge characteristic angle of each edge pixel point in the semi-trailer area is obtained. The specific method for acquiring the second edge characteristic angle of the edge pixel point comprises the following steps: for any semi-trailer area, taking any edge pixel point in the semi-trailer area as an example edge pixel point, acquiring an edge pixel point adjacent to the example edge pixel point as an adjacent edge pixel point of the example edge pixel point, respectively calculating an included angle between a straight line formed by each adjacent edge pixel point and the example edge pixel point and a horizontal line to obtain a first edge feature angle corresponding to the adjacent edge pixel point, taking the mean value of the first edge feature angles of all the adjacent edge pixel points as a second edge feature angle of the example edge pixel point, and acquiring a second edge feature angle of each edge pixel point.
Secondly, taking the difference value of the second edge characteristic angle of the edge pixel point as distance measurement, using a K-means clustering algorithm to the edge pixel point,and dividing the edge pixel points into two categories, and respectively obtaining the category angles of the two categories. The specific acquisition method of the category angle of the category comprises the following steps: clustering all edge pixel points of the semi-trailer area based on a second edge feature angle to obtain two categories, taking the category with a large number of edge pixel points as a first category and the category with a small number of edge pixel points as a second category, and respectively obtaining the second edge feature angle of a clustering center point in the first category as the category angle of the first category and the second edge feature angle of the clustering center point in the second category as the category angle of the second category; and (4) combining the category angle of each category to obtain the characteristic points of the semitrailer area in each frame of semitrailer image.
It should be noted that, the invention selects a K-means clustering algorithm to perform clustering analysis on the edge pixel point values, and a specific method is not described here and is a technical means well known to those skilled in the art.
And finally, acquiring two tangent lines of the semi-trailer area according to the category angle, and acquiring the characteristic points of the semi-trailer area based on the Euclidean distance from the pixel points in the semi-trailer area to the two tangent lines. The specific acquisition method of the characteristic points of the semitrailer area comprises the following steps: taking any one category angle as a straight line, traversing each edge pixel point in a window area by the straight line, obtaining an edge pixel point corresponding to a tangent line of the straight line belonging to the edge pixel point as a target edge pixel point, taking the tangent line of the target edge pixel point, selecting two tangent lines with the farthest distance as a target tangent line pair, and obtaining a target tangent line pair under each category angle; taking any pixel point in the semi-trailer area as a reference pixel point, calculating a difference value between the reference pixel point and two tangent lines of a target tangent line pair to be used as a first difference value, calculating a first difference value of each target tangent line pair, taking the sum of all the first difference values as a second difference value of the reference pixel point, respectively obtaining the second difference value of each pixel point in the semi-trailer area, and selecting the pixel point corresponding to the minimum second difference value as a characteristic point of the semi-trailer area.
According to the method for acquiring the characteristic points of the semitrailer area, the characteristic points of the semitrailer area of each frame of semitrailer image are acquired, and the actual semitrailer area is acquired based on the characteristic points of each semitrailer area.
Firstly, a target semi-trailer image is selected according to the shape similarity of the semi-trailer area. The specific acquisition method of the target semitrailer image comprises the following steps: the method comprises the steps of taking a semi-trailer area of any one semi-trailer image as a target semi-trailer area, taking the semi-trailer area of the rest semi-trailer image as a residual semi-trailer area, sequentially carrying out shape matching on the target semi-trailer area and each residual semi-trailer area, obtaining at least two shape similarities in the target semi-trailer area, calculating an average value of all the shape similarities as a shape similarity average value of the target semi-trailer area, obtaining the shape similarity average value of each semi-trailer area, and taking a semi-trailer image where the semi-trailer area corresponding to the maximum shape similarity average value is located as a target semi-trailer image.
It should be noted that, the shape context matching algorithm of the present invention performs shape similarity matching on semi-trailer regions, and a specific method is not described herein and is well known to those skilled in the art.
Then, the characteristic points are used as projection basis, the projection times of pixel points in the semitrailer area are calculated, and the projection threshold is set to beAccording to the number of projections and the projection thresholdAnd acquiring an actual semitrailer area. The specific acquisition method of the actual semitrailer area comprises the following steps: the semitrailer image processing method based on the image projection comprises the steps of superposing the characteristic points of a semitrailer area in a target semitrailer image with the characteristic points of the semitrailer area with each frame of semitrailer image with the characteristic points of a semitrailer area in the remaining frame of semitrailer image, projecting the semitrailer area of each frame of semitrailer image to the semitrailer area in the target semitrailer image, counting the projection times of each pixel point in the semitrailer area in the projected target semitrailer image, setting a projection threshold value, screening out the pixel points with the projection times larger than or equal to the projection threshold value as actual semitrailer pixel points, and taking the area formed by the actual semitrailer pixel points as the actual semitrailer area.
Therefore, the semi-trailer is analyzed to the optimal parking area to move the semi-trailer image, and the real-time position information of the semi-trailer in the moving process, namely the actual semi-trailer area, is obtained.
And step S4: and setting the optimal orientation direction of the optimal parking area, and combining the optimal orientation direction of the optimal parking area and the real-time orientation direction of the actual semi-trailer area to finish the intelligent positioning of the cargo area of the semi-trailer.
And the control of the semi-trailer is finished according to the difference between the optimal parking area of the semi-trailer and the real-time actual semi-trailer area, so that the intelligent positioning of the semi-trailer is finished.
Firstly, the real-time orientation direction and the actual center point of the actual semitrailer area are obtained according to the step S3. The method for acquiring the real-time orientation and the actual central point of the semitrailer comprises the following steps: and respectively acquiring a category angle and a characteristic point of a first category of the actual semitrailer area, and taking the category angle of the first category as the real-time orientation direction of the actual semitrailer area and the characteristic point as an actual central point.
The method for moving the semitrailer to the optimal parking area comprises the following steps: the method comprises the steps of obtaining a characteristic point of an optimal parking area as an optimal central point, calculating a Euclidean distance between an actual central point and the optimal central point as a moving distance of the semitrailer, taking an absolute value of a difference value between a real-time orientation direction and the optimal orientation direction as an orientation direction difference value of the semitrailer, and moving the semitrailer to the optimal parking area by using the moving distance and the orientation direction difference value. The method for acquiring the characteristic points of the optimal parking area is the same as the method for acquiring the characteristic points of the semitrailer area.
Preferably, the optimal orientation direction defaults to being vertically up in the cargo area image, taking the empirical value of 90 °.
And the semitrailer control system moves the semitrailer on the basis of the moving distance and the difference value of the orientation direction, and adjusts the moving direction of the semitrailer, and when the moving distance and the difference value of the orientation direction are both 0 or tend to 0, the semitrailer is indicated to have successfully moved to the optimal parking area.
According to the semi-trailer intelligent positioning system, firstly, the images of the cargo area are analyzed in the semi-trailer control system, the acquired images of the cargo area are transmitted to the semi-trailer control system through the wireless transmission module to be analyzed, the optimal parking area position information of the semi-trailer is obtained, the real-time semi-trailer images in the semi-trailer moving process are analyzed, the actual semi-trailer area position information of the semi-trailer is obtained, the semi-trailer parking is controlled in real time through the semi-trailer control system, and therefore the intelligent positioning of the semi-trailer is completed.
It should be noted that: the precedence order of the above embodiments of the present invention is only for description, and does not represent the merits of the embodiments. The processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that are within the spirit of the present invention are intended to be included therein.
Claims (9)
1. The intelligent positioning method for the cargo carrying area of the low-flat-bed semi-trailer is characterized by comprising the following steps:
collecting a loading area image of the unloading site to obtain a loading area gray image corresponding to the loading area image;
acquiring each window area in the gray-scale image of the cargo area by using a sliding window, taking any pixel point in the window area as an example pixel point, and calculating the local smoothness of the example pixel point according to the gray-scale value of the neighborhood pixel point in the neighborhood of the example pixel point; acquiring the preference degree of the corresponding window area based on the local smoothness of each pixel point in the window area; acquiring the preference degree of each window area, and taking the window area corresponding to the maximum preference degree as the optimal parking area of the semitrailer;
acquiring at least two continuous frames of semi-trailer images in the process that the semi-trailer moves to the optimal parking area, acquiring motion pixel points in each frame of semi-trailer image according to gray values of pixel points in adjacent semi-trailer images, and acquiring the semi-trailer area of each frame of semi-trailer image according to the motion pixel points; acquiring characteristic points of a semitrailer area in each frame of semitrailer image, and acquiring an actual semitrailer area based on the characteristic points;
and setting the optimal orientation direction of the optimal parking area, and combining the optimal orientation direction of the optimal parking area and the real-time orientation direction of the actual semitrailer area to finish the intelligent positioning of the cargo carrying area of the semitrailer.
2. The method as claimed in claim 1, wherein the calculating of the local smoothness of the example pixel points according to the gray values of the neighborhood pixel points in the neighborhood of the example pixel points comprises:
setting a gray difference threshold and a neighborhood with a preset size, taking neighborhood pixels in the neighborhood of the example pixel as first neighborhood pixels, respectively calculating the absolute value of a gray value difference value between each first neighborhood pixel and the example pixel as a gray difference value corresponding to the first neighborhood pixels, and taking the first neighborhood pixels with the gray difference values larger than the gray difference threshold as target pixels of the example pixel;
obtaining central pixel points corresponding to other neighborhoods adjacent to the neighborhood of the example pixel point as first pixel points, taking straight lines obtained by connecting the first pixel points with the example pixel points as first straight lines corresponding to the first pixel points, selecting the first straight lines with the straight line directions in the horizontal direction and the vertical direction as associated straight lines, and classifying the first pixel points corresponding to the associated straight lines as associated pixel points of the example pixel points;
taking any one associated pixel point of the example pixel points as a target associated pixel point, taking a neighborhood pixel point in the neighborhood of the target associated pixel point as a second neighborhood pixel point, and respectively calculating the absolute value of the gray value difference between each second neighborhood pixel point and the target associated pixel point as the gray value difference value corresponding to the second neighborhood pixel point;
and combining the gray difference value of each first neighborhood pixel point of the example pixel point and the gray difference value of each second neighborhood pixel point of each associated pixel point of the example pixel point to obtain the local smoothness of the example pixel point.
3. The method as claimed in claim 2, wherein the obtaining of the local smoothness of the sample pixel point comprises:
obtaining the local smoothness of the example pixel point through a local smoothness formula, wherein the calculation formula of the local smoothness is as follows:
in the formula (I), the compound is shown in the specification,is an example pixel pointThe local smoothness of (a);is an example pixel pointThe number of target pixel points within the neighborhood of (c),is an example pixel pointThe number of associated pixel points of (a),is the number of neighborhood pixels in the neighborhood,is an example pixel pointTo (1) aThe gray difference value of each first neighborhood pixel point,representing example pixel pointsTo (1)The first of each associated pixelThe gray difference value of each second neighborhood pixel point;in the form of a function of the absolute value,is a maximum function;is a natural constant.
4. The method as claimed in claim 1, wherein the obtaining of the preference degree of the corresponding window region based on the local smoothness of each pixel point in the window region comprises:
acquiring a central point of a window area as a window central point, and a central point of a gray image of a cargo area as an image central point, taking Euclidean distance between the window central point and the image central point as a first central point distance, respectively calculating Euclidean distance between each pixel point and the window central point in the window area as a second central point distance of a corresponding pixel point, and selecting the maximum value of the second central point distances as a maximum central point distance;
the reciprocal of the number of the pixel points in the window area is taken as a first result, a value obtained by taking a natural constant e as a base number and the opposite number of the distance of the first central point as an index is taken as a second result, the distance of the second central point of the pixel point is taken as a numerator, the distance of the maximum central point is taken as a denominator to obtain a first ratio of the corresponding pixel point, the product of the second result, the local smoothness of the corresponding pixel point and the first ratio is taken as a third result, the sum of the third results of each pixel point in the window area is taken as a fourth result, and the product of the first result and the fourth result is taken as the preference degree of the corresponding window area.
5. The method for intelligently positioning the cargo carrying area of the low-flatbed semitrailer according to claim 1, wherein the method for obtaining the motion pixel points in each frame of semitrailer image according to the gray values of the pixel points in the adjacent semitrailer images and obtaining the semitrailer area of each frame of semitrailer image according to the motion pixel points comprises the following steps:
calculating the difference value of the gray values of the same pixel point in the adjacent semi-trailer images by using a frame difference method to serve as the gray difference value of the corresponding pixel point, setting a gray threshold, screening the pixel points of which the gray values are larger than the gray threshold in the semi-trailer images to serve as moving pixel points, acquiring the moving pixel points in each frame of semi-trailer image, acquiring at least two areas formed by the moving pixel points in the semi-trailer image, and taking the largest area as the semi-trailer area corresponding to the semi-trailer image.
6. The method for intelligently positioning the cargo area of the low-flatbed semitrailer according to claim 1, wherein the step of obtaining the characteristic points of the semitrailer area in each frame of semitrailer image comprises the following steps:
for any semi-trailer area, taking any edge pixel point in the semi-trailer area as an example edge pixel point, acquiring an edge pixel point adjacent to the example edge pixel point as an adjacent edge pixel point of the example edge pixel point, respectively calculating an included angle between a straight line formed by each adjacent edge pixel point and the example edge pixel point and a horizontal line to obtain a first edge characteristic angle corresponding to the adjacent edge pixel point, taking the mean value of the first edge characteristic angles of all the adjacent edge pixel points as a second edge characteristic angle of the example edge pixel point, and acquiring the second edge characteristic angle of each edge pixel point;
clustering all edge pixel points of the semi-trailer area based on a second edge feature angle to obtain two categories, taking the category with a large number of edge pixel points as a first category and the category with a small number of edge pixel points as a second category, and respectively obtaining the second edge feature angle of a clustering center point in the first category as the category angle of the first category and the second edge feature angle of the clustering center point in the second category as the category angle of the second category;
and combining the category angle of each category to obtain the characteristic points of the semitrailer area in each frame of semitrailer image.
7. The method as claimed in claim 6, wherein the step of obtaining the characteristic points of the semitrailer area in each frame of semitrailer image comprises:
taking any one category angle as a straight line, traversing each edge pixel point in a window area by the straight line, obtaining an edge pixel point corresponding to a tangent line of the straight line belonging to the edge pixel point as a target edge pixel point, taking the tangent line of the target edge pixel point, selecting two tangent lines with the farthest distance as a target tangent line pair, and obtaining a target tangent line pair under each category angle; taking any pixel point in the semi-trailer area as a reference pixel point, calculating a difference value of Euclidean distances between the reference pixel point and two tangents of a target tangent pair as a first difference value, calculating a first difference value of each target tangent pair, taking the sum of all the first difference values as a second difference value of the reference pixel point, respectively obtaining a second difference value of each pixel point in the semi-trailer area, and selecting the pixel point corresponding to the minimum second difference value as a characteristic point of the semi-trailer area.
8. The method for intelligently positioning the cargo area of the low-flatbed semitrailer according to claim 1, wherein the obtaining the actual semitrailer area based on the characteristic points comprises:
taking a semi-trailer area of any semi-trailer image as a target semi-trailer area, respectively taking the semi-trailer area of the rest semi-trailer images as remaining semi-trailer areas, sequentially carrying out shape matching on the target semi-trailer area and each remaining semi-trailer area, obtaining at least two shape similarities in the target semi-trailer area, calculating an average value of all the shape similarities as a shape similarity average value of the target semi-trailer area, obtaining the shape similarity average value of each semi-trailer area, and taking a semi-trailer image where the semi-trailer area corresponding to the maximum shape similarity average value is located as a target semi-trailer image;
the method comprises the steps of superposing feature points of a semi-trailer region in a target semi-trailer image with feature points of the semi-trailer region in each frame of remaining semi-trailer image, projecting the semi-trailer region of each frame of semi-trailer image to the semi-trailer region in the target semi-trailer image, counting the projection times of each pixel point in the semi-trailer region in the target semi-trailer image after projection, setting a projection threshold value, screening out the pixel points with the projection times being larger than or equal to the projection threshold value as actual semi-trailer pixel points, and taking the region formed by the actual semi-trailer pixel points as the actual semi-trailer region.
9. The method as claimed in claim 6, wherein the intelligent positioning of the cargo area of the semitrailer in combination with the optimal orientation direction of the optimal parking area and the real-time orientation direction of the actual semitrailer area comprises:
respectively acquiring a category angle and a characteristic point of a first category of an actual semitrailer area, and taking the category angle of the first category as a real-time orientation direction of the actual semitrailer area and the characteristic point as an actual central point;
the method comprises the steps of obtaining a characteristic point of an optimal parking area as an optimal central point, calculating a Euclidean distance between an actual central point and the optimal central point as a moving distance of the semitrailer, taking an absolute value of a difference value between a real-time orientation direction and the optimal orientation direction as an orientation direction difference value of the semitrailer, and moving the semitrailer to the optimal parking area by using the moving distance and the orientation direction difference value.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310233521.0A CN115953472B (en) | 2023-03-13 | 2023-03-13 | Intelligent positioning method for cargo carrying area of low-bed semi-trailer |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310233521.0A CN115953472B (en) | 2023-03-13 | 2023-03-13 | Intelligent positioning method for cargo carrying area of low-bed semi-trailer |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115953472A true CN115953472A (en) | 2023-04-11 |
CN115953472B CN115953472B (en) | 2023-05-23 |
Family
ID=85886503
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310233521.0A Active CN115953472B (en) | 2023-03-13 | 2023-03-13 | Intelligent positioning method for cargo carrying area of low-bed semi-trailer |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115953472B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117972318A (en) * | 2024-04-02 | 2024-05-03 | 山东万洋石油科技有限公司 | Pulse waveform testing method and system for high-speed self-generating shear valve |
Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2009094681A1 (en) * | 2008-01-28 | 2009-08-06 | Tgw Mechanics Gmbh | Picking system and method for loading a load-carrying unit |
CN106022694A (en) * | 2016-05-30 | 2016-10-12 | 燕山大学 | Bulk cargo yard stacker-reclaimer positioning method based on point cloud data processing technology and system for realizing same |
CN108012325A (en) * | 2017-10-30 | 2018-05-08 | 上海神添实业有限公司 | A kind of navigation locating method based on UWB and binocular vision |
CN109829947A (en) * | 2019-02-25 | 2019-05-31 | 北京旷视科技有限公司 | Pose determines method, tray loading method, apparatus, medium and electronic equipment |
CN112379387A (en) * | 2020-11-13 | 2021-02-19 | 劢微机器人科技(深圳)有限公司 | Automatic goods location calibration method, device, equipment and storage medium |
CN113674350A (en) * | 2021-07-15 | 2021-11-19 | 浙江大华技术股份有限公司 | Parking space state detection method and device, computer equipment and storage medium |
CN114387344A (en) * | 2021-12-31 | 2022-04-22 | 深圳市镭神智能系统有限公司 | Cargo carrying tool pose detection method and device, carrying vehicle and medium |
CN114419150A (en) * | 2021-12-21 | 2022-04-29 | 未来机器人(深圳)有限公司 | Forklift goods taking method and device, computer equipment and storage medium |
CN114862226A (en) * | 2022-05-18 | 2022-08-05 | 江苏佳利达国际物流股份有限公司 | Intelligent dispatching and loading and unloading management method and system for warehouse logistics |
CN115100283A (en) * | 2022-06-24 | 2022-09-23 | 未来机器人(深圳)有限公司 | Goods placement control method and device, computer equipment and storage medium |
CN115410399A (en) * | 2022-08-09 | 2022-11-29 | 北京科技大学 | Truck parking method and device and electronic equipment |
CN115457484A (en) * | 2022-11-10 | 2022-12-09 | 梁山华鲁专用汽车制造有限公司 | Control method and device for automatic unloading of semitrailer |
DE102022120971A1 (en) * | 2021-08-24 | 2023-03-02 | Kabushiki Kaisha Toyota Jidoshokki | Fork lift truck and method of detecting the loading position for a fork lift truck |
-
2023
- 2023-03-13 CN CN202310233521.0A patent/CN115953472B/en active Active
Patent Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2009094681A1 (en) * | 2008-01-28 | 2009-08-06 | Tgw Mechanics Gmbh | Picking system and method for loading a load-carrying unit |
CN106022694A (en) * | 2016-05-30 | 2016-10-12 | 燕山大学 | Bulk cargo yard stacker-reclaimer positioning method based on point cloud data processing technology and system for realizing same |
CN108012325A (en) * | 2017-10-30 | 2018-05-08 | 上海神添实业有限公司 | A kind of navigation locating method based on UWB and binocular vision |
CN109829947A (en) * | 2019-02-25 | 2019-05-31 | 北京旷视科技有限公司 | Pose determines method, tray loading method, apparatus, medium and electronic equipment |
CN112379387A (en) * | 2020-11-13 | 2021-02-19 | 劢微机器人科技(深圳)有限公司 | Automatic goods location calibration method, device, equipment and storage medium |
CN113674350A (en) * | 2021-07-15 | 2021-11-19 | 浙江大华技术股份有限公司 | Parking space state detection method and device, computer equipment and storage medium |
DE102022120971A1 (en) * | 2021-08-24 | 2023-03-02 | Kabushiki Kaisha Toyota Jidoshokki | Fork lift truck and method of detecting the loading position for a fork lift truck |
CN114419150A (en) * | 2021-12-21 | 2022-04-29 | 未来机器人(深圳)有限公司 | Forklift goods taking method and device, computer equipment and storage medium |
CN114387344A (en) * | 2021-12-31 | 2022-04-22 | 深圳市镭神智能系统有限公司 | Cargo carrying tool pose detection method and device, carrying vehicle and medium |
CN114862226A (en) * | 2022-05-18 | 2022-08-05 | 江苏佳利达国际物流股份有限公司 | Intelligent dispatching and loading and unloading management method and system for warehouse logistics |
CN115100283A (en) * | 2022-06-24 | 2022-09-23 | 未来机器人(深圳)有限公司 | Goods placement control method and device, computer equipment and storage medium |
CN115410399A (en) * | 2022-08-09 | 2022-11-29 | 北京科技大学 | Truck parking method and device and electronic equipment |
CN115457484A (en) * | 2022-11-10 | 2022-12-09 | 梁山华鲁专用汽车制造有限公司 | Control method and device for automatic unloading of semitrailer |
Non-Patent Citations (2)
Title |
---|
FLORIAN J.: "Positioning of loading units in a transshipment yard storage area", OR SPECTRUM * |
吴海波;夏胜平;盛锋;: "基于计算机视觉的大型车辆实时定位定向技术", 计算机系统应用 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117972318A (en) * | 2024-04-02 | 2024-05-03 | 山东万洋石油科技有限公司 | Pulse waveform testing method and system for high-speed self-generating shear valve |
Also Published As
Publication number | Publication date |
---|---|
CN115953472B (en) | 2023-05-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111862157B (en) | Multi-vehicle target tracking method integrating machine vision and millimeter wave radar | |
CN107679520B (en) | Lane line visual detection method suitable for complex conditions | |
CN101334837B (en) | Multi-method integrated license plate image positioning method | |
Choi et al. | Vision-based fusion of robust lane tracking and forward vehicle detection in a real driving environment | |
CN115311277B (en) | Pit defect identification method for stainless steel product | |
CN115953472A (en) | Intelligent positioning method for cargo carrying area of low-flat-bed semitrailer | |
CN102044151A (en) | Night vehicle video detection method based on illumination visibility identification | |
CN110197494B (en) | Pantograph contact point real-time detection algorithm based on monocular infrared image | |
CN117094914B (en) | Smart city road monitoring system based on computer vision | |
CN108898132A (en) | A kind of terahertz image dangerous material recognition methods based on Shape context description | |
CN116385472B (en) | Hardware stamping part deburring effect evaluation method | |
CN115690105B (en) | Milling cutter scratch detection method based on computer vision | |
CN116012357A (en) | Automobile circular trailer hole air line defect detection method based on machine vision | |
CN116486091B (en) | Fan blade defect area rapid segmentation method and system based on artificial intelligence | |
CN115511907A (en) | Scratch detection method for LED screen | |
CN117541582B (en) | IGBT insulation quality detection method for high-frequency converter | |
CN117058111B (en) | Quality inspection method and system for automobile aluminum alloy die casting die | |
CN117542003A (en) | Freight train model judging method based on image feature analysis | |
CN115457484B (en) | Control method and device for automatic unloading of semitrailer | |
CN115100510B (en) | Tire wear degree identification method | |
CN114882387B (en) | Bearing raceway bruise identification and automatic polishing positioning method in grinding process | |
JP2008293446A (en) | Apparatus and program for identifying moving object | |
CN111881748A (en) | Lane line visual identification method and system based on VBAI platform modeling | |
CN115115629A (en) | Automobile sealing strip quality detection method based on computer vision | |
CN115294102A (en) | Stainless steel product abnormity identification method based on machine vision |
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 |