CN111369556B - Contact net detection method and system - Google Patents
Contact net detection method and system Download PDFInfo
- Publication number
- CN111369556B CN111369556B CN202010205617.2A CN202010205617A CN111369556B CN 111369556 B CN111369556 B CN 111369556B CN 202010205617 A CN202010205617 A CN 202010205617A CN 111369556 B CN111369556 B CN 111369556B
- Authority
- CN
- China
- Prior art keywords
- image
- feature
- gray
- preset
- processing device
- 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.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 63
- 238000012545 processing Methods 0.000 claims abstract description 109
- 238000000034 method Methods 0.000 claims abstract description 32
- 239000013589 supplement Substances 0.000 claims abstract description 14
- 238000004422 calculation algorithm Methods 0.000 claims description 44
- 238000006243 chemical reaction Methods 0.000 claims description 21
- 238000003708 edge detection Methods 0.000 claims description 20
- 239000000284 extract Substances 0.000 claims description 18
- 238000001914 filtration Methods 0.000 claims description 6
- 230000001502 supplementing effect Effects 0.000 claims 8
- 238000003384 imaging method Methods 0.000 description 7
- 230000003137 locomotive effect Effects 0.000 description 7
- 230000000153 supplemental effect Effects 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 230000002452 interceptive effect Effects 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000004873 anchoring Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- 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
- G01B11/002—Measuring arrangements characterised by the use of optical techniques for measuring two or more coordinates
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The application relates to a contact net detection method and system. The contact net detecting system includes: detect car body, supplementary light source, image processing device, install at the lifter that detects car body top, set up rotatory cloud platform on the lifter, install the image sensor on rotatory cloud platform: the image sensor collects images of contact points between the contact net and the pantograph on the detection vehicle body and sends the images to the image processing device; the image processing device judges whether the image gray value of the image is in a preset image gray range; if the image gray value is larger than the upper threshold value in the preset image gray range, controlling the lifting rod to adjust the height of the image sensor and controlling the rotary cradle head to adjust the photographing angle of the image sensor until the image sensor collects the image gray value of the image which is smaller than the upper threshold value; if the image gray value is smaller than the lower threshold value in the preset image gray range, controlling the supplementary light source to supplement light to the image sensor, and adopting the method to ensure the image gray.
Description
Technical Field
The application relates to the technical field of overhead contact systems, in particular to a method and a system for detecting overhead contact systems.
Background
With the development of electrified railway technology, an electric locomotive obtains electric energy from a contact net through a pantograph arranged at the top of the locomotive, and then the electric locomotive runs at a high speed by utilizing the electric energy. The advantages and disadvantages of the contact network performance are directly related to the speed of the operation of the electric locomotive, and even the contact network can influence the operation safety of the electric locomotive, so that the contact network needs to be detected in real time. The traditional contact net detection technology is used for carrying a camera by a technician to shoot through manual detection, and then calculating geometric parameters of the contact net according to the obtained picture.
However, the electric locomotive runs at a high speed, and the measurement position and the shooting angle determined manually in the traditional measurement technology are easy to cause too high or too low image gray level due to the influence of illumination and noise, so that the electric locomotive cannot be used in the later parameter measurement and calculation, and therefore, a contact net detection method is needed.
Disclosure of Invention
Based on the above, it is necessary to provide a contact net detection method and system for the above technical problems.
In a first aspect, there is provided a catenary detection method, the method being applied to a catenary detection system, the catenary detection system comprising: the detection vehicle comprises a detection vehicle body, a supplementary light source, an image processing device, a lifting rod arranged at the top of the detection vehicle body, a rotary tripod head arranged on the lifting rod and an image sensor arranged on the rotary tripod head, wherein the method comprises the following steps:
the image sensor acquires an image of a contact point between the contact net and the pantograph on the detection vehicle body and sends the image to the image processing device;
the image processing device judges whether the image gray value of the image is in a preset image gray range;
if the image gray value of the image is larger than the upper threshold value in the preset image gray range, controlling the lifting rod to adjust the height of the image sensor and controlling the rotary cradle head to adjust the photographing angle of the image sensor until the image gray value of the image acquired by the image sensor is smaller than the upper threshold value;
and if the image gray level value of the image is smaller than the lower threshold value in the preset image gray level range, controlling the supplementary light source to supplement light to the image sensor.
As an alternative embodiment, the method further comprises: and if the image gray value of the image is within the preset image gray range, maintaining the photographing angle of the image sensor.
As an alternative embodiment, the method further comprises:
the image processing device acquires a characteristic gray level threshold value and a characteristic pixel threshold value of a target characteristic in a characteristic database, and extracts the target characteristic contained in the image according to the characteristic gray level threshold value, the characteristic pixel threshold value, the preset characteristic quantity and an edge detection algorithm;
and determining the image coordinate value of the target feature according to a two-dimensional image coordinate system, and obtaining the space coordinate value of the target feature through a preset coordinate conversion algorithm.
As an optional implementation manner, the determining the image coordinate value of the target feature according to the two-dimensional image coordinate system, and obtaining the space coordinate value of the target feature through a preset coordinate conversion algorithm includes:
the image processing device acquires feature points in the target feature, obtains the image coordinate values corresponding to the feature points based on the two-dimensional image coordinate system, and determines the space coordinate values of the feature points as the space coordinate values of the target feature according to the image coordinate values, a preset scale factor, a horizontal focal length and a vertical focal length of an image sensor, a coordinate axis offset factor and the preset coordinate conversion algorithm.
As an alternative embodiment, the method further comprises:
the image processing device carries out median filtering processing on the image according to the gray information of the image and a preset maximum inter-class variance algorithm, and eliminates noise points in the image to obtain a denoised image;
the image processing device obtains a feature gray level threshold and a feature pixel threshold of a target feature in a feature database, and extracts the target feature contained in the image according to the feature gray level threshold, the feature pixel threshold, a preset feature quantity and an edge detection algorithm, wherein the image processing device comprises the following steps:
the image processing device acquires a characteristic gray level threshold and a characteristic pixel threshold of the target characteristic from a characteristic database, and extracts the target characteristic contained in the denoised image according to the characteristic gray level threshold, the characteristic pixel threshold, the preset characteristic quantity and an edge detection algorithm.
In a second aspect, there is provided a catenary detection system, the catenary detection system comprising: the detecting vehicle comprises a detecting vehicle body, a supplementary light source, an image processing device, a lifting rod arranged at the top of the detecting vehicle body, a rotary cradle head arranged on the lifting rod and an image sensor arranged on the rotary cradle head;
the image sensor is used for collecting an image of a contact point between the contact net and the pantograph on the detection vehicle body and sending the image to the image processing device;
the image processing device is used for judging whether the image gray value of the image is in a preset image gray range or not;
if the image gray value of the image is larger than the upper threshold value in the preset image gray range, the image processing device is used for controlling the lifting rod to adjust the height of the image sensor and controlling the rotary holder to adjust the photographing angle of the image sensor until the image gray value of the image acquired by the image sensor is smaller than the upper threshold value;
and if the image gray level value of the image is smaller than the lower threshold value in the preset image gray level range, controlling the supplementary light source to supplement light to the image sensor.
As an optional implementation manner, the image processing device is further configured to maintain the photographing angle of the image sensor if the image gray level value of the image is within the preset image gray level range.
As an optional implementation manner, the image processing device is further configured to obtain a feature gray level threshold and a feature pixel threshold of a target feature in a feature database, and extract the target feature contained in the image according to the feature gray level threshold, the feature pixel threshold, a preset feature quantity and an edge detection algorithm;
and determining the image coordinate value of the target feature according to a two-dimensional image coordinate system, and obtaining the space coordinate value of the target feature through a preset coordinate conversion algorithm.
As an optional implementation manner, the image processing device is further configured to obtain a feature point in the target feature, obtain the image coordinate value corresponding to the feature point based on the two-dimensional image coordinate system, and determine a spatial coordinate value of the feature point as a spatial coordinate value of the target feature according to the image coordinate value, a preset scale factor, a horizontal focal length and a vertical focal length of an image sensor, a coordinate axis offset factor, and the preset coordinate conversion algorithm.
As an optional implementation manner, the image processing device is configured to perform median filtering processing on the image according to gray information of the image and a preset maximum inter-class variance algorithm, and remove noise points in the image to obtain a denoised image; the image processing device is configured to obtain a feature gray level threshold and a feature pixel threshold of a target feature in a feature database, and extract the target feature included in the image according to the feature gray level threshold, the feature pixel threshold, a preset feature quantity and an edge detection algorithm, where the image processing device includes:
the image processing device is further used for acquiring a characteristic gray level threshold and a characteristic pixel threshold of the target characteristic from a characteristic database, and extracting the target characteristic contained in the denoised image according to the characteristic gray level threshold, the characteristic pixel threshold, the preset characteristic quantity and an edge detection algorithm.
The embodiment of the application provides a contact net detection method and a contact net detection system, wherein the contact net detection system comprises: the detection vehicle body, the supplementary light source, the image processing device, install at the lifter that detects vehicle body top, set up rotatory cloud platform on the lifter and install the image sensor on rotatory cloud platform, the method includes: the image sensor collects images of contact points between the contact net and the pantograph on the detection vehicle body and sends the images to the image processing device; the image processing device judges whether the image gray value of the image is in a preset image gray range; if the image gray value of the image is larger than the upper threshold value in the preset image gray range, controlling the lifting rod to adjust the height of the image sensor and controlling the rotary holder to adjust the photographing angle of the image sensor until the image gray value of the image acquired by the image sensor is smaller than the upper threshold value; and if the image gray value of the image is smaller than the lower threshold value in the preset image gray range, controlling the supplementary light source to supplement light to the image sensor. By adopting the method, high-quality contact net images can be obtained, so that the contact net can be conveniently detected.
Drawings
Fig. 1 is a schematic flow chart of a method for detecting a contact net according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of a contact net detection system provided in an embodiment of the present application;
fig. 3 is a schematic view of an imaging angle of an image sensor according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
The application provides a contact net detection method which can be applied to a contact net detection system, wherein the contact net detection system comprises: the device comprises a detection vehicle body, a supplementary light source, an image processing device, a lifting rod arranged at the top of the detection vehicle body, a rotary cradle head arranged on the lifting rod and an image sensor arranged on the rotary cradle head, wherein the image sensor collects images of contact points between a contact net and a pantograph on the detection vehicle body and sends the images to the image processing device; the image processing device judges whether the image gray value of the image is in a preset image gray range; if the image gray value of the image is larger than the upper threshold value in the preset image gray range, controlling the lifting rod to adjust the height of the image sensor and controlling the rotary holder to adjust the photographing angle of the image sensor until the image gray value of the image acquired by the image sensor is smaller than the upper threshold value; and if the image gray value of the image is smaller than the lower threshold value in the preset image gray range, controlling the supplementary light source to supplement light to the image sensor.
In one embodiment, as shown in fig. 1, there is provided a catenary detection method, which is applied to a catenary detection system, wherein the catenary detection system includes: the detection vehicle body, the supplementary light source, the image processing device, the lifting rod installed at the top of the detection vehicle body, the rotary cradle head arranged on the lifting rod and the image sensor installed on the rotary cradle head, the specific processing procedure of the method is as follows:
step 101, an image sensor collects an image of a contact point between the contact net and the pantograph on the detection vehicle body, and sends the image to an image processing device.
In implementation, the image sensor is installed on a rotary tripod head, and a lifting rod is arranged below the rotary tripod head, as shown in fig. 2, two image sensors (an image sensor A1 and an image sensor A2) can be arranged on the detection vehicle body, and the image sensor can acquire images of contact points between the contact net and the pantograph on the detection vehicle body in real time under the high-speed running state of the detection vehicle. The image sensor may then transmit the image to the image processing device via the smart meter transmission channel, but is not limited to.
In step 102, the image processing apparatus determines whether the image gray value of the image is within a preset image gray range.
In practice, the image processing device acquires a preset image gray scale range V after receiving the image sent by the image sensor min ,V max ]And judging whether the image gray scale of the image is within the preset image gray scale range, wherein the image gray scale range V min ,V max ]Is formed by an image gray upper limit threshold V max And an image gray-level lower threshold V min And a gray scale interval is enclosed. Specifically, the image sensor A1 forms an image with an image gray scale of [ P ] 1min ,P 1max ]Wherein P is 1max Is the maximum gray value, P, in the image formed by A1 1min Is the minimum gray value in the image formed by A1. Similarly, the image sensor A2 forms an image having an image gray scale of [ P ] 2min ,P 2max ]Wherein P is 2max Is the maximum gray value in the image formed by A2, P 2min Is the minimum gray value in the image formed by A2. The image processing device compares the gray scale range of the formed image with the preset image gray scale range to judge whether the image gray scale of the image meets the requirement。
Step 103, if the image gray value of the image is greater than the upper threshold in the preset image gray range, controlling the lifting rod to adjust the height of the image sensor and controlling the rotary holder to adjust the photographing angle of the image sensor until the image gray value of the image acquired by the image sensor is less than the upper threshold.
In implementation, if the image gray value of the image is greater than the upper threshold in the preset image gray range, the image sensor controls the lifting rod to adjust the height of the image sensor and controls the rotary holder to adjust the photographing angle of the image sensor until the image gray value of the image acquired by the image sensor is less than the upper threshold, that is, the image gray is satisfied within the preset gray range.
Alternatively, two cases can be distinguished: in the first case, the image sensor A1 performs clear imaging (meets the gray scale requirement), and the gray scale value of the image sensor A2 is greater than the upper threshold in the preset gray scale range of the image, resulting in failure of imaging. I.e. the image sensor A1 is clearly imaged,image sensor A2 fails to image, and maximum gray value P of image formed by A2 2max Is larger than a preset upper limit threshold V of image gray level max I.e. P 2max >V max . The image processing device controls the image sensor A2 to adjust, and the image processing device can adjust the photographing height of the lifting rod of the image sensor A2 according to the lifting rod height and the photographing angle of the image sensor A1 as references, and coordinate with controlling the rotating cradle head on the lifting rod to adjust the photographing angle until the image gray scale range of the image formed by the image sensor A2 is within the preset image gray scale range. In addition, the imaging failure of the image sensor A1, the clear imaging of the image sensor A2 is similar to the first case, and the embodiments of the present application will not be repeated separately.
In the second case, the image gray values of the image sensor A1 and the image sensor A2 are both greater than the upper threshold in the preset image gray range, resulting in failure of imaging. V (V) max <P 2max ；V max <P 1max And the image processing device respectively controls the lifting rods of the A1 and the A2 and the corresponding rotary holder, and adjusts the height and the photographing angle of the image sensor until the image gray value of the image formed by the image sensor meets the preset image gray range. Preferably, in order to adjust the height and photographing angle of the image sensor more quickly, an image sensor can be selected as an initial adjustment standard for adjustment, and then, the image sensor is adjusted for a second time. Specifically, first, the image processing apparatus compares the maximum gray values of the images formed by A1 and A2, if P 1max >P 2max The image processing device adjusts the height of the lifting rod of the image sensor A1 by taking the height of the lifting rod of the image sensor A2 as a reference, then the image processing device respectively controls the rotation holders of the image sensor A1 and the image sensor A2, adjusts the photographing angle until the image gray scale range of one of the image sensors is within the preset image gray scale range, and then the operation of the first case is executed.
And 104, controlling a supplementary light source to supplement light to the image sensor if the image gray value of the image is smaller than a lower threshold value in a preset image gray range.
In an implementation, if the image gray value of the image is smaller than a lower threshold in a preset image gray range, the image processing device controls the supplementary light source to supplement light to the image sensor. Specifically, taking the image sensor A1 as an example, if the minimum gray value P among the gray values of the image sensor A1 1min Less than a lower threshold V in a preset image gray scale range min The image processing device controls the supplemental light source to supplement light, and preferably, the supplemental light intensity can be preset as a slight supplemental light. If the maximum gray value P among the image gray values of the image sensor A1 1max Less than a lower threshold V in a preset image gray scale range min The image processing apparatus controls the supplemental light source to supplement light thereto, and preferably, the supplemental light intensity may be set to be highly supplemental light. The processing procedure of the image processing apparatus for imaging the image sensor A2 is similar to that of the image sensor A1, and the embodiments of the present application will not be repeated.
As an alternative embodiment, if the image gray value of the image is within the preset image gray range, the photographing angle of the image sensor is maintained.
In practice, if the image gray value of the image sensor is within a preset image gray range, that is,the image processing device controls the photographing angle of the image sensor to be unchanged, and continuous photographing is performed.
As an optional implementation manner, the image processing device acquires a feature gray level threshold and a feature pixel threshold of the target feature in the feature database, and extracts the target feature contained in the image according to the feature gray level threshold, the feature pixel threshold, the preset feature quantity and the edge detection algorithm. According to a two-dimensional image coordinate system, determining image coordinate values of target features, and obtaining space coordinate values of the target features through a preset coordinate conversion algorithm, wherein the specific processing process is as follows:
in implementation, the image processing device acquires a feature gray level threshold and a feature pixel threshold of a target feature in the feature database, extracts the feature gray level threshold and the feature pixel threshold from the image, and then extracts the target feature according to a preset feature quantity, namely an edge detection algorithm. Specifically, the image formed by the image sensor may include a carrier rope, a contact line, a central anchoring rope, and the like, and if a technician presets the contact line as a target feature, the image processing device selects a contact line gray threshold value and a feature pixel threshold value in a feature database, and extracts the contact line in the image according to an edge detection algorithm (that is, edge detection is performed according to the shape and the size of a gray gradient), so as to obtain the target feature. Then, the image processing device determines the position coordinates of the target feature in the plane coordinate system of the formed image, and obtains the space coordinate value of the target feature through a preset coordinate conversion algorithm, so that the geometric parameters of the contact network can be measured and calculated according to the space coordinate value, and the detection of the contact network is completed.
Alternatively, the image processing device may also acquire the gray threshold and the pixel threshold of the interfering object from the feature database, and then the image processing device rejects the interfering object in the image to obtain the target feature.
Optionally, before extracting the target feature, denoising the image, that is, the image processing device performs median filtering processing on the image according to gray information of the image and a preset maximum inter-class variance algorithm, so as to remove noise points in the image and obtain a denoised image; then, the image processing device extracts the target features, namely, the image processing device acquires the feature gray level threshold and the feature pixel threshold of the target features in the feature database, and extracts the target features contained in the denoised image according to the feature gray level threshold, the feature pixel threshold, the preset feature quantity and the edge detection algorithm.
As an optional implementation manner, according to a two-dimensional image coordinate system, determining an image coordinate value of a target feature, and obtaining a space coordinate value of the target feature through a preset coordinate conversion algorithm, wherein the specific processing procedure is as follows:
the image processing device acquires feature points in the target feature to obtain image coordinate values corresponding to the feature points based on the two-dimensional image coordinate system, and determines the space coordinate values of the feature points as the space coordinate values of the target feature according to the image coordinate values, a preset scale factor, a horizontal focal length and a vertical focal length of the image sensor, a coordinate axis offset factor and a preset coordinate conversion algorithm.
In implementation, the image processing device correspondingly acquires the image formed by the A1 and the image formed by the A2, and then processes the image formed by each image sensor, as shown in fig. 3, to obtain the image coordinate values of the feature points, and further obtain the space coordinate values according to the image coordinates, the preset scale factors, the parameters such as the horizontal focal length and the vertical focal length of the image sensor, the coordinate axis offset factors and the preset coordinate conversion algorithm. Specifically, the image processing apparatus determines the intersection point (e.g., point M in fig. 3) of the contact line of the contact net and the inspection vehicle pantograph in the image as the feature point of the extracted target feature (contact line), and then based on the resultThe two-dimensional image coordinate system of the image (the coordinate system is in units of image pixels), and the image coordinate value of the feature point M is determined, for example, the coordinate origin O of the two-dimensional coordinate system of the image formed by the image sensor A1 1 Is (u) 01 ,v 01 ) The coordinate of M point is M 1 (u 1 ,v 1 ) Two-dimensional coordinate system origin of coordinates O of image formed by image sensor A2 2 Is (u) 02 ,v 02 ) The coordinate of M point is M 2 (u 2 ,v 2 ) Then, the image processing apparatus calculates spatial coordinate values of the intersection point M in relation to the three-dimensional spatial coordinate system of the image sensors A1 and A2, respectively, according to a preset coordinate conversion algorithm. The three-dimensional space coordinate system of the setpoint M with respect to the image sensor A1 (e.g., O in fig. 3 1 x c1 y c1 Coordinate system) is (x) c1 ,y c1 ,z c1 ) The method comprises the steps of carrying out a first treatment on the surface of the The three-dimensional space coordinate system of the setpoint M with respect to the image sensor A2 (e.g., O in fig. 3 2 x c2 y c2 Coordinate system) is (x) c2 ,y c2 ,z c2 ). The conversion relationship between the two-dimensional image coordinate system and the three-dimensional space coordinate system of the feature points in the image sensor A1 and the image sensor A2 is as follows (1), (2):
wherein ρ is 1 Is the scale factor of the image sensor A1 ρ 2 Is the scale factor of the image sensor A2; alpha 1 、β 1 A horizontal focal length and a vertical focal length of the image sensor A1; alpha 2 、β 2 A horizontal focal length and a vertical focal length of the image sensor A2; c 1 Is coordinate axis offset factor, c in two-dimensional image coordinate system corresponding to image sensor A1 2 Is a coordinate axis offset factor in a two-dimensional image coordinate system corresponding to the image sensor A2.
Then, for the image formed by the image sensor A1, the specific processing procedure of determining the spatial coordinate value of the intersection point M in the three-dimensional coordinate system by the image processing device according to the preset coordinate conversion algorithm is as follows:
wherein R is a rotation matrix, and T is a translation vector.
Bringing the formula (3) into the formula (2) to obtain the x-related value c1 、y c1 、z c1 As shown in equation (4). Solving to obtain the coordinate (x) of the intersection point M under the three-dimensional space coordinate system of the image sensor A1 c1 ,y c1 ,z c1 )。
Correspondingly, the processing method of the image processing device to obtain the three-dimensional space coordinate value of the intersection point M relative to the image sensor A2 is similar to the processing method of the image sensor A1, and will not be described in detail in this embodiment of the present application.
Optionally, according to the spatial coordinate value of the intersection point M obtained by the image sensor A1 under the three-dimensional spatial coordinate system and the spatial coordinate value of the intersection point M obtained by the image sensor A2 under the three-dimensional spatial coordinate system, the intersection point M may be spatially imaged, or the geometric parameters of the contact network may be measured and calculated according to the obtained spatial coordinate values, so as to detect the contact network.
As an alternative implementation manner, as shown in fig. 2, an angle sensor may be installed at the bottom of the detection vehicle body, and the image sensor corrects the coordinate offset factor in the coordinate conversion process according to the vehicle body offset angle acquired by the angle sensor, so that the image processing device is more accurate in calculating the spatial coordinate value of the feature point.
The embodiment of the application provides a contact net detection method, which is applied to a contact net detection system, wherein the contact net detection system comprises: the device comprises a detection vehicle body, a supplementary light source, an image processing device, a lifting rod arranged at the top of the detection vehicle body, a rotary cradle head arranged on the lifting rod and an image sensor arranged on the rotary cradle head, wherein the image sensor collects images of contact points between a contact net and a pantograph on the detection vehicle body and sends the images to the image processing device; the image processing device judges whether the image gray value of the image is in a preset image gray range; if the image gray value of the image is larger than the upper threshold value in the preset image gray range, controlling the lifting rod to adjust the height of the image sensor and controlling the rotary holder to adjust the photographing angle of the image sensor until the image gray value of the image acquired by the image sensor is smaller than the upper threshold value; and if the image gray value of the image is smaller than the lower threshold value in the preset image gray range, controlling the supplementary light source to supplement light to the image sensor. The method can ensure the gray level of the contact net image so as to facilitate the calculation and the test through the image.
It should be understood that, although the steps in the flowchart of fig. 1 are shown in sequence as indicated by the arrows, the steps are not necessarily performed in sequence as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in fig. 1 may include multiple sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor do the order in which the sub-steps or stages are performed necessarily performed in sequence, but may be performed alternately or alternately with at least a portion of other steps or sub-steps of other steps.
In one embodiment, there is provided a catenary detection system comprising: detect car body, supplementary light source, image processing device, install at the lifter that detects car body top, set up rotatory cloud platform on the lifter and install the image sensor on rotatory cloud platform, wherein:
the image sensor collects images of contact points between the contact net and the pantograph on the detection vehicle body, and sends the images to the image processing device.
The image processing device judges whether the image gray value of the image is in a preset image gray range.
If the image gray value of the image is larger than the upper threshold value in the preset image gray range, controlling the lifting rod to adjust the height of the image sensor and controlling the rotary holder to adjust the photographing angle of the image sensor until the image gray value of the image acquired by the image sensor is smaller than the upper threshold value.
And if the image gray value of the image is smaller than the lower threshold value in the preset image gray range, controlling the supplementary light source to supplement light to the image sensor.
As an alternative embodiment, the image processing device is further configured to maintain the photographing angle of the image sensor if the image gray value of the image is within a preset image gray range.
As an optional implementation manner, the image processing device is further configured to obtain a feature gray level threshold and a feature pixel threshold of the target feature in the feature database, and extract the target feature included in the image according to the feature gray level threshold, the feature pixel threshold, a preset feature quantity and an edge detection algorithm;
and determining the image coordinate value of the target feature according to the two-dimensional image coordinate system, and obtaining the space coordinate value of the target feature through a preset coordinate conversion algorithm.
As an optional implementation manner, the image processing device is further configured to obtain a feature point in the target feature, obtain an image coordinate value corresponding to the feature point based on the two-dimensional image coordinate system, and determine a spatial coordinate value of the feature point as a spatial coordinate value of the target feature according to the image coordinate value, a preset scale factor, a horizontal focal length and a vertical focal length of the image sensor, a coordinate axis offset factor, and a preset coordinate conversion algorithm.
As an optional implementation manner, the image processing device is used for performing median filtering processing on the image according to gray information of the image and a preset maximum inter-class variance algorithm, removing noise points in the image, and obtaining a denoised image; the image processing device is configured to obtain a feature gray level threshold and a feature pixel threshold of a target feature in a feature database, and extract the target feature included in the image according to the feature gray level threshold, the feature pixel threshold, a preset feature quantity and an edge detection algorithm, where the image processing device includes:
the image processing device is also used for acquiring the characteristic gray level threshold and the characteristic pixel threshold of the target characteristic from the characteristic database, and extracting the target characteristic contained in the denoised image according to the characteristic gray level threshold, the characteristic pixel threshold, the preset characteristic quantity and the edge detection algorithm.
For specific limitations of the contact net detection system, reference may be made to the above limitation of the contact net detection method, and the description thereof will not be repeated here. The above-mentioned various devices in the contact net detection system may be implemented in whole or in part by software, hardware, and combinations thereof.
The embodiment of the application provides a contact net detecting system, and this contact net detecting system includes: the device comprises a detection vehicle body, a supplementary light source, an image processing device, a lifting rod arranged at the top of the detection vehicle body, a rotary cradle head arranged on the lifting rod and an image sensor arranged on the rotary cradle head, wherein the image sensor collects images of contact points between a contact net and a pantograph on the detection vehicle body and sends the images to the image processing device; the image processing device judges whether the image gray value of the image is in a preset image gray range; if the image gray value of the image is larger than the upper threshold value in the preset image gray range, controlling the lifting rod to adjust the height of the image sensor and controlling the rotary holder to adjust the photographing angle of the image sensor until the image gray value of the image acquired by the image sensor is smaller than the upper threshold value; and if the image gray value of the image is smaller than the lower threshold value in the preset image gray range, controlling the supplementary light source to supplement light to the image sensor. The method can ensure the gray level of the contact net image so as to facilitate the calculation and the test through the image.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the various embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples merely represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the invention. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application is to be determined by the claims appended hereto.
Claims (10)
1. The utility model provides a contact net detection method which is characterized in that, the method is applied to contact net detecting system, contact net detecting system includes: the detection vehicle comprises a detection vehicle body, a supplementary light source, an image processing device, a lifting rod installed at the top of the detection vehicle body, a rotary cradle head arranged on the lifting rod and an image sensor installed on the rotary cradle head, wherein the method comprises the following steps:
the image sensor acquires an image of a contact point between the contact net and the pantograph on the detection vehicle body and sends the image to the image processing device;
the image processing device judges whether the image gray value of the image is in a preset image gray range;
if the image gray value of the image is larger than the upper threshold value in the preset image gray range, controlling the lifting rod to adjust the height of the image sensor and controlling the rotary cradle head to adjust the photographing angle of the image sensor until the image gray value of the image acquired by the image sensor is smaller than the upper threshold value;
if the image gray value of the image is smaller than the lower threshold value in the preset image gray range, controlling the supplementary light source to supplement light to the image sensor; when the minimum gray value in the image gray values is smaller than the lower threshold, the light supplementing intensity is light supplementing; and when the maximum gray value in the gray values of the images is smaller than the lower limit threshold, the light supplementing intensity is high light supplementing.
2. The method according to claim 1, wherein the method further comprises:
and if the image gray value of the image is within the preset image gray range, maintaining the photographing angle of the image sensor.
3. The method according to claim 1, wherein the method further comprises:
the image processing device acquires a characteristic gray level threshold value and a characteristic pixel threshold value of a target characteristic in a characteristic database, and extracts the target characteristic contained in the image according to the characteristic gray level threshold value, the characteristic pixel threshold value, the preset characteristic quantity and an edge detection algorithm;
and determining the image coordinate value of the target feature according to a two-dimensional image coordinate system, and obtaining the space coordinate value of the target feature through a preset coordinate conversion algorithm.
4. A method according to claim 3, wherein determining the image coordinate values of the target feature according to the two-dimensional image coordinate system and obtaining the space coordinate values of the target feature by a preset coordinate conversion algorithm comprises:
the image processing device acquires feature points in the target feature, obtains the image coordinate values corresponding to the feature points based on the two-dimensional image coordinate system, and determines the space coordinate values of the feature points as the space coordinate values of the target feature according to the image coordinate values, a preset scale factor, a horizontal focal length and a vertical focal length of an image sensor, a coordinate axis offset factor and the preset coordinate conversion algorithm.
5. The method according to claim 1, wherein the method further comprises:
the image processing device carries out median filtering processing on the image according to the gray information of the image and a preset maximum inter-class variance algorithm, and eliminates noise points in the image to obtain a denoised image;
the image processing device obtains a feature gray level threshold and a feature pixel threshold of a target feature in a feature database, and extracts the target feature contained in the image according to the feature gray level threshold, the feature pixel threshold, a preset feature quantity and an edge detection algorithm, wherein the image processing device comprises the following steps:
the image processing device acquires a characteristic gray level threshold and a characteristic pixel threshold of the target characteristic from a characteristic database, and extracts the target characteristic contained in the denoised image according to the characteristic gray level threshold, the characteristic pixel threshold, the preset characteristic quantity and an edge detection algorithm.
6. A catenary detection system, the catenary detection system comprising: the detecting vehicle comprises a detecting vehicle body, a supplementary light source, an image processing device, a lifting rod arranged at the top of the detecting vehicle body, a rotary cradle head arranged on the lifting rod and an image sensor arranged on the rotary cradle head;
the image sensor is used for collecting an image of a contact point between the contact net and the pantograph on the detection vehicle body and sending the image to the image processing device;
the image processing device is used for judging whether the image gray value of the image is in a preset image gray range or not;
if the image gray value of the image is larger than the upper threshold value in the preset image gray range, the image processing device is used for controlling the lifting rod to adjust the height of the image sensor and controlling the rotary holder to adjust the photographing angle of the image sensor until the image gray value of the image acquired by the image sensor is smaller than the upper threshold value;
if the image gray value of the image is smaller than the lower threshold value in the preset image gray range, controlling the supplementary light source to supplement light to the image sensor; when the minimum gray value in the image gray values is smaller than the lower threshold, the light supplementing intensity is light supplementing; and when the maximum gray value in the gray values of the images is smaller than the lower limit threshold, the light supplementing intensity is high light supplementing.
7. The system of claim 6, wherein the image processing device is further configured to maintain the photographing angle of the image sensor if the image gray level value of the image is within the preset image gray level range.
8. The system of claim 6, wherein the image processing device is further configured to obtain a feature gray level threshold and a feature pixel threshold of a target feature in a feature database, and extract the target feature included in the image according to the feature gray level threshold, the feature pixel threshold, a preset feature number, and an edge detection algorithm;
and determining the image coordinate value of the target feature according to a two-dimensional image coordinate system, and obtaining the space coordinate value of the target feature through a preset coordinate conversion algorithm.
9. The system of claim 8, wherein the image processing device is further configured to obtain a feature point in the target feature, obtain the image coordinate value corresponding to the feature point based on the two-dimensional image coordinate system, and determine a spatial coordinate value of the feature point as a spatial coordinate value of the target feature according to the image coordinate value, a preset scale factor, a horizontal focal length and a vertical focal length of an image sensor, a coordinate axis offset factor, and the preset coordinate conversion algorithm.
10. The system according to claim 6, wherein the image processing device is configured to perform median filtering processing on the image according to gray information of the image and a preset maximum inter-class variance algorithm, and remove noise points in the image, so as to obtain a denoised image; the image processing device is configured to obtain a feature gray level threshold and a feature pixel threshold of a target feature in a feature database, and extract the target feature included in the image according to the feature gray level threshold, the feature pixel threshold, a preset feature quantity and an edge detection algorithm, where the image processing device includes:
the image processing device is further used for acquiring a characteristic gray level threshold and a characteristic pixel threshold of the target characteristic from a characteristic database, and extracting the target characteristic contained in the denoised image according to the characteristic gray level threshold, the characteristic pixel threshold, the preset characteristic quantity and an edge detection algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010205617.2A CN111369556B (en) | 2020-03-23 | 2020-03-23 | Contact net detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010205617.2A CN111369556B (en) | 2020-03-23 | 2020-03-23 | Contact net detection method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111369556A CN111369556A (en) | 2020-07-03 |
| CN111369556B true CN111369556B (en) | 2024-02-20 |
Family
ID=71206885
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010205617.2A Active CN111369556B (en) | 2020-03-23 | 2020-03-23 | Contact net detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111369556B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114216546A (en) * | 2021-12-14 | 2022-03-22 | 江苏太平洋通信科技有限公司 | Freight source overload identification management system and method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104567684A (en) * | 2015-01-20 | 2015-04-29 | 中国铁道科学研究院 | Contact network geometrical parameter detection method and device |
| CN108650495A (en) * | 2018-06-28 | 2018-10-12 | 华域视觉科技(上海)有限公司 | A kind of automobile-used panoramic looking-around system and its adaptive light compensation method |
| CN108900781A (en) * | 2018-07-26 | 2018-11-27 | 珠海格力电器股份有限公司 | Light supplement control method and device for image acquisition device and image acquisition system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8780143B2 (en) * | 2009-02-19 | 2014-07-15 | Samsung Electronics Co., Ltd | Display method and apparatus for controlling brightness of projector light source |
-
2020
- 2020-03-23 CN CN202010205617.2A patent/CN111369556B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104567684A (en) * | 2015-01-20 | 2015-04-29 | 中国铁道科学研究院 | Contact network geometrical parameter detection method and device |
| CN108650495A (en) * | 2018-06-28 | 2018-10-12 | 华域视觉科技(上海)有限公司 | A kind of automobile-used panoramic looking-around system and its adaptive light compensation method |
| CN108900781A (en) * | 2018-07-26 | 2018-11-27 | 珠海格力电器股份有限公司 | Light supplement control method and device for image acquisition device and image acquisition system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111369556A (en) | 2020-07-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10108881B2 (en) | Train type identification method and system, and security inspection method and system | |
| JP5177147B2 (en) | Imaging apparatus, imaging method, and imaging program | |
| US20160364619A1 (en) | Vehicle-Surroundings Recognition Device | |
| WO2017113805A1 (en) | Method and system for identifying train number and model, and safety check method and system | |
| JP5959073B2 (en) | Detection device, detection method, and program | |
| US20200288065A1 (en) | Target tracking method and device, movable platform, and storage medium | |
| US9135745B2 (en) | Image processing method and system using the same | |
| JP2014215877A (en) | Object detection device | |
| JP2010102572A (en) | Periphery monitoring device for vehicle | |
| CN113173502B (en) | Anticollision method and system based on laser vision fusion and deep learning | |
| CN111369556B (en) | Contact net detection method and system | |
| JP2003051017A (en) | White line detector | |
| JP5287177B2 (en) | Trolley wire wear and displacement measuring device by image processing | |
| JP2019185469A (en) | Image analysis device, method, and program | |
| CN105933611A (en) | Dynamic envelope line drawing method for preventing camera jitter in rail foreign matter invasion recognition | |
| KR20150101806A (en) | System and Method for Monitoring Around View using the Grid Pattern Automatic recognition | |
| JP2013015336A (en) | Trolley wire wear measurement apparatus by means of image processing | |
| JP2013196331A (en) | Imaging control device and program | |
| CN108831844B (en) | Method and system for detecting wafer defects | |
| CN111340765B (en) | Thermal infrared image reflection detection method based on background separation | |
| CN110322508B (en) | Auxiliary positioning method based on computer vision | |
| KR102166021B1 (en) | Apparatus and method for monitoring deflection of transmission line | |
| RU2650857C1 (en) | System for determining geometric parameters of three-dimensional objects | |
| CN103971086B (en) | Vehicle head positioning method and device | |
| CN112883789B (en) | Bowling prevention method and system based on laser vision fusion and deep learning |
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 |