CN116051565A - Contact net defect target detection method and device based on structured light 3D point cloud - Google Patents
Contact net defect target detection method and device based on structured light 3D point cloud Download PDFInfo
- Publication number
- CN116051565A CN116051565A CN202310342068.7A CN202310342068A CN116051565A CN 116051565 A CN116051565 A CN 116051565A CN 202310342068 A CN202310342068 A CN 202310342068A CN 116051565 A CN116051565 A CN 116051565A
- Authority
- CN
- China
- Prior art keywords
- point cloud
- time
- layer
- layers
- frequency resource
- 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
-
- 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
- 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
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- 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
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The application provides a contact net defect target detection method and device based on structured light 3D point cloud. The method comprises the following steps: the method comprises the steps that a terminal obtains structured light 3D point cloud data of a contact net, wherein the structured light 3D point cloud data comprises N layers of point cloud patterns, N is an integer greater than 1, an ith layer of point cloud pattern in the N layers of point cloud patterns is used for representing the appearance shape structure of the contact net on an ith layer, and i is any integer from 1 to N. And the terminal sends N layers of data to the network equipment, wherein the ith layer of data in the N layers of data is carried by a time-frequency resource set corresponding to the ith layer of space domain resources in the N layers of space domain resources, and the ith layer of point cloud pattern is represented by the time-frequency position of the time-frequency resource set. Because different airspace resources can be used for layering the same time-frequency resource, the N-layer point cloud pattern is mapped to the N-layer airspace resource, and the time-frequency position of the time-frequency resource set corresponding to the airspace resource is multiplexed to implicitly represent the point cloud pattern, so that the transmission can be improved.
Description
Technical Field
The application relates to the field of overhead contact systems, in particular to an overhead contact system defect target detection method and device based on structured light 3D point cloud.
Background
Detection of structural defects by 3D structured light is currently a relatively common way. Taking the contact net as an example, the 3D structure light scanning contact net can obtain space feature points, and the shape structure obtained by externally connecting the space feature points is the shape structure of the contact net. In other words, the shape structure of the catenary can be characterized by converting the shape structure into spatial feature points through the scanning of the 3D structured light. In this way, by analyzing the space coordinates of the space feature points, whether the contact net has structural defects can be determined.
However, due to the huge number of spatial feature points obtained by 3D structured light scanning, the terminal is limited to its own capabilities, and it is generally required to transmit the coordinate parameters of these spatial feature points to a network device with a higher capability for processing, resulting in a high communication overhead.
Disclosure of Invention
The embodiment of the application provides a contact network defect target detection method and device based on structured light 3D point cloud, which are used for reducing communication overhead.
In order to achieve the above purpose, the present application adopts the following technical scheme:
in a first aspect, an embodiment of the present application provides a method for detecting a contact network defect target based on structured light 3D point cloud, where the method includes: the method comprises the steps that a terminal obtains structured light 3D point cloud data of a contact net, wherein the structured light 3D point cloud data comprises N layers of point cloud patterns, N is an integer greater than 1, an ith layer of point cloud pattern in the N layers of point cloud patterns is used for representing the appearance shape structure of the contact net on an ith layer, and i is any integer from 1 to N. And the terminal sends N layers of data to the network equipment, wherein the ith layer of data in the N layers of data is carried by a time-frequency resource set corresponding to the ith layer of space domain resources in the N layers of space domain resources, and the ith layer of point cloud pattern is represented by the time-frequency position of the time-frequency resource set.
Based on the method of the first aspect, it can be known that, because different space domain resources can be used to layer the same time-frequency resource, the N-layer point cloud patterns are mapped to the N-layer space domain resources, and the time-frequency positions of the time-frequency resource sets corresponding to the space domain resources are multiplexed to implicitly represent the point cloud patterns, so that the transmission efficiency can be improved, that is, the same time-frequency resource can be multiplexed to transmit the N-layer point cloud patterns, thereby reducing the communication overhead.
In a possible design, the ith layer of point cloud pattern includes a plurality of point cloud coordinate points, the ith layer of layer data is used for representing a spatial distance between the plurality of point cloud coordinate points, and a time-frequency position relationship between time-frequency resource blocks in the time-frequency resource set is used for representing a spatial position relationship between the plurality of point cloud coordinate points. That is, even if the time-frequency resource blocks in the time-frequency resource set are adjacent time-frequency resource blocks, the time-frequency resource blocks can be used for representing the spatial position relationship between the point cloud coordinate points through the time-frequency position relationship, so that the time-frequency resource blocks can be concentrated together, that is, no idle time-frequency resource blocks exist between the time-frequency resource blocks, and the time-frequency resource utilization rate can be improved.
Optionally, the ith layer of data is used for representing a spatial distance between each point cloud coordinate point in the plurality of point cloud coordinate points and an adjacent point cloud coordinate point, and the time-frequency position relationship between each time-frequency resource block in the time-frequency resource set and the adjacent time-frequency resource block is used for representing a spatial position relationship between the corresponding point cloud coordinate point in the plurality of point cloud coordinate points and the adjacent point cloud coordinate point.
In another possible design, the i-th layer point cloud pattern includes a plurality of point cloud coordinate points, a time-frequency distance between time-frequency resource blocks in the time-frequency resource set is used for a spatial distance between the plurality of point cloud coordinate points, and a time-frequency position relationship between the time-frequency resource blocks in the time-frequency resource set is used for a spatial position relationship between the plurality of point cloud coordinate points. That is, the point cloud pattern is completely represented by the time-frequency position of the time-frequency resource set, and at this time, the N-layer data may be data of other services, that is, the transmission of the point cloud pattern does not affect the data transmission of other services, so as to realize transmission decoupling, and the transmission is more flexible.
In a second aspect, an embodiment of the present application provides a method for detecting a contact network defect target based on a structured light 3D point cloud, where the method includes: the network equipment receives N layers of data from a terminal, wherein the structured light 3D point cloud data comprises N layers of point cloud patterns, N is an integer greater than 1, an ith layer of point cloud pattern in the N layers of point cloud patterns is used for representing the appearance shape structure of the contact net on an ith layer, i is any integer from 1 to N, the ith layer of data in the N layers of data is borne by a time-frequency resource set corresponding to the ith layer of space domain resource in the N layers of space domain resources, and the time-frequency position of the ith layer of point cloud pattern time-frequency resource set is represented. The network equipment determines N layers of point cloud patterns according to the N layers of data; and the network equipment determines whether the contact net has structural defects according to the N-layer point cloud pattern.
In one possible design, the network device determines whether the contact network has a structural defect according to the N-layer point cloud pattern, including: the network equipment fuses the N layers of point cloud patterns into one layer of target point cloud patterns; the network equipment processes the target point cloud pattern through the convolutional neural network and determines whether the catenary has structural defects. In this case, the position change of the point cloud coordinate point caused by the structural defect is represented in the image in the form of color change, so that whether the contact net has the structural defect can be accurately determined through the convolutional neural network.
Optionally, n=3, the i-th layer point cloud pattern includes a plurality of point cloud coordinate points, and the network device merges the N-layer point cloud pattern into a layer of target point cloud pattern, including: and the network equipment maps the point cloud coordinate points at the same position in the N layers of point cloud patterns into a corresponding pixel point to obtain a target point cloud pattern.
In another possible design, the determining, by the network device, whether the contact network has a structural defect according to the N-layer point cloud pattern includes: the network equipment maps the N-layer point cloud patterns into a set of target points Yun Xiangliang; the network equipment processes the target point cloud vector set through the deep neural network and determines whether the contact net has structural defects.
Optionally, the network device maps the N-layer point cloud pattern to a set of target points Yun Xiangliang, including: the network equipment maps the point cloud coordinate points at the same position in the N layers of point cloud patterns into a corresponding vector to obtain a target point cloud vector set.
In a third aspect, an embodiment of the present application provides a contact network defect target detection device based on a structured light 3D point cloud, including a module configured to execute the method described in the first aspect. For example, comprising a transceiver module and a processing module.
The processing module is used for acquiring structured light 3D point cloud data of the contact net, wherein the structured light 3D point cloud data comprises N layers of point cloud patterns, N is an integer greater than 1, and an ith layer of point cloud pattern in the N layers of point cloud patterns is used for representing the appearance shape structure of the contact net on the ith layer, and i is any integer from 1 to N. The receiving and transmitting module is used for transmitting N layers of data to the network equipment by the terminal, wherein the ith layer of data in the N layers of data is borne by a time-frequency resource set corresponding to the ith layer of airspace resource in the N layers of airspace resource, and the ith layer of point cloud pattern is represented by the time-frequency position of the time-frequency resource set.
In a possible design, the ith layer of point cloud pattern includes a plurality of point cloud coordinate points, the ith layer of layer data is used for representing a spatial distance between the plurality of point cloud coordinate points, and a time-frequency position relationship between time-frequency resource blocks in the time-frequency resource set is used for representing a spatial position relationship between the plurality of point cloud coordinate points.
Optionally, the ith layer of data is used for representing a spatial distance between each point cloud coordinate point in the plurality of point cloud coordinate points and an adjacent point cloud coordinate point, and the time-frequency position relationship between each time-frequency resource block in the time-frequency resource set and the adjacent time-frequency resource block is used for representing a spatial position relationship between the corresponding point cloud coordinate point in the plurality of point cloud coordinate points and the adjacent point cloud coordinate point.
In another possible design, the i-th layer point cloud pattern includes a plurality of point cloud coordinate points, a time-frequency distance between time-frequency resource blocks in the time-frequency resource set is used for a spatial distance between the plurality of point cloud coordinate points, and a time-frequency position relationship between the time-frequency resource blocks in the time-frequency resource set is used for a spatial position relationship between the plurality of point cloud coordinate points.
In a fourth aspect, an embodiment of the present application provides a contact network defect target detection device based on a structured light 3D point cloud, including a module for executing the method described in the second aspect. For example, comprising a transceiver module and a processing module.
The receiving and transmitting module is used for receiving N layers of data from the terminal by the network equipment, wherein the structured light 3D point cloud data comprises N layers of point cloud patterns, N is an integer greater than 1, an ith layer of point cloud pattern in the N layers of point cloud patterns is used for representing the appearance shape structure of the contact net on an ith layer, i is any integer from 1 to N, the ith layer of data in the N layers of data is borne by a time-frequency resource set corresponding to the ith layer of space domain resources in the N layers of space domain resources, and the time-frequency position of the time-frequency resource set of the ith layer of point cloud patterns is represented. The processing module is used for determining N layers of point cloud patterns according to the N layers of data by the network equipment; and the processing module is used for the network equipment to determine whether the contact net has structural defects according to the N-layer point cloud patterns.
In one possible design, the processing module is configured to integrate the N-layer point cloud patterns into one-layer target point cloud pattern by the network device; the processing module is used for processing the target point cloud pattern through the convolutional neural network by the network equipment and determining whether the contact net has a structural defect or not.
Optionally, n=3, where the ith layer of point cloud patterns include a plurality of point cloud coordinate points, and the processing module is configured to map the point cloud coordinate points at the same position in the N layer of point cloud patterns into a corresponding pixel point by using the network device, so as to obtain a target point cloud pattern.
In another possible design, the processing module is configured to map the N-layer point cloud pattern into a set of target points Yun Xiangliang by the network device; the processing module is used for the network equipment to process the target point cloud vector set through the deep neural network and determine whether the contact net has structural defects.
Optionally, the processing module is configured to map the point cloud coordinate points at the same position in the N-layer point cloud pattern into a corresponding vector by using the network device, so as to obtain a target point cloud vector set.
In a fifth aspect, embodiments of the present application provide a computer readable storage medium having program code stored thereon, which when executed by the computer, performs the method according to the first or second aspect.
Drawings
FIG. 1 is a schematic diagram of a processing system according to an embodiment of the present disclosure;
fig. 2 is a flowchart of a contact network defect target detection method based on structured light 3D point cloud according to an embodiment of the present application;
FIG. 3 is a layered scene diagram;
FIG. 4 is a schematic diagram showing a relationship between a point cloud coordinate point and an RE;
FIG. 5 is a second schematic diagram of the relationship between the point cloud coordinate points and RE;
fig. 6 is a schematic structural diagram one of a contact net defect target detection device based on structured light 3D point cloud according to an embodiment of the present application;
fig. 7 is a schematic structural diagram two of a contact network defect target detection device based on structured light 3D point cloud according to an embodiment of the present application.
Detailed Description
The technical solutions in the present application will be described below with reference to the accompanying drawings.
Referring to fig. 1, an embodiment of the present application provides a processing system, which may include: a terminal and a network device.
The terminal is a terminal which is accessed to the processing system and has a communication function or a chip system which can be arranged on the terminal. The terminal device may also be referred to as a User Equipment (UE), an access terminal, a subscriber unit, a subscriber station, a mobile station, a remote terminal, a mobile device, a user terminal, a wireless communication device, a user agent, or a user device. The terminal device in the embodiment of the present application may be a mobile phone (mobile phone), a tablet computer (Pad), a computer with a wireless transceiving function, a Virtual Reality (VR) terminal device, an augmented reality (augmented reality, AR) terminal device, a wireless terminal in industrial control (industrial control), a wireless terminal in unmanned driving (self driving), a wireless terminal in remote medical (remote medical), a wireless terminal in smart grid (smart grid), a wireless terminal in transportation security (transportation safety), a wireless terminal in smart city (smart city), a wireless terminal in smart home (smart home), a vehicle-mounted terminal, an RSU with a terminal function, or the like.
The network device may be a device having communication and processing functions located on the network side of the processing system or may be a chip or a chip system provided on the device. The network device may be a server or a server cluster, and the server or the server cluster may be an entity device or may be a virtualized device, which is not limited thereto.
The interaction between the terminal and the network device in the processing system will be described in detail with reference to the method.
Referring to fig. 2, an embodiment of the present application provides a contact network defect target detection method based on structured light 3D point cloud. The method may be applicable to communication between a terminal and a network device. The method comprises the following steps:
s201, the terminal acquires structured light 3D point cloud data of the contact network.
The structured light 3D point cloud data comprises N layers of point cloud patterns, N is an integer greater than 1, and an ith layer of point cloud pattern in the N layers of point cloud patterns is used for representing the appearance shape structure of the contact net on the ith layer, wherein i is any integer from 1 to N. For example, the i-th layer point cloud pattern may include a plurality of point cloud coordinate points obtained by scanning the contact network through the structured light 3D. The plurality of point cloud coordinate points can be understood as coordinate points covered on the surface of the appearance shape structure of the ith layer, and the obtained external connection shape is the appearance shape structure of the ith layer by externally connecting the plurality of point cloud coordinate points. That is, the terminal scans the contact net through the structured light 3D contact net, and a point cloud coordinate point set for representing the complete appearance shape structure of the contact net can be obtained. The terminal can be used for layering the structure of the contact network, for example, the terminal is divided into M layers, M is an integer greater than or equal to N, and a plurality of point cloud coordinate points on each layer of structure are one layer of point cloud patterns.
For example, as shown in fig. 3, assume: the longitudinal width of the contact net is 21 centimeters (cm), the contact net can be layered in the longitudinal direction by taking 1cm as a unit, namely the contact net can be cut into 21 pieces in the longitudinal direction, the thickness of each piece of structure is 1cm, and each piece of structure is only the structure of the outer surface of the contact net. And a plurality of point cloud coordinate points covered on each structure are a layer of point cloud pattern.
S202, the terminal sends N layers of data to the network equipment. The network device receives N-layer data from the terminal.
The ith layer data in the N layers of data is carried by a time-frequency resource set corresponding to the ith layer of airspace resource in the N layers of airspace resources. The ith layer point cloud pattern can be represented by the time-frequency position of the time-frequency resource set corresponding to the ith layer airspace resource, that is, the ith layer point cloud pattern is transmitted by multiplexing the time-frequency position of the time-frequency resource set corresponding to the ith layer airspace resource.
It will be appreciated that the catenary actually has M layers of point cloud patterns, with N layers of point cloud patterns being at least part of the M layers of point cloud patterns. Since the size of N depends on the number of spatial resources that the terminal can use, and is therefore limited by the number of spatial resources, the terminal can only acquire and transmit at least part of the point cloud pattern, and the rest can still be transmitted in a similar manner.
Continuing the example above: in the case where the overhead line system is cut into 21 pieces in the longitudinal direction, the point cloud pattern also has 21 layers, i.e., m=21. If n=3, the terminal may repeat S201-S202 7 times to achieve full transmission of the 21-layer point cloud pattern to the network device.
In one possible design, the ith layer of data is used for representing the spatial distance between the plurality of point cloud coordinate points, and the time-frequency position relationship between the time-frequency resource blocks in the time-frequency resource set is used for representing the spatial position relationship between the plurality of point cloud coordinate points. For example, the ith layer of data is used for representing a spatial distance between each point cloud coordinate point in the plurality of point cloud coordinate points and an adjacent point cloud coordinate point, and a time-frequency position relationship between each time-frequency resource block in the time-frequency resource set and an adjacent time-frequency resource block is used for representing a spatial position relationship between a corresponding point cloud coordinate point in the plurality of point cloud coordinate points and an adjacent point cloud coordinate point. The time-frequency resource block may be one or more Resource Elements (REs), or may be one or more Resource Blocks (RBs).
That is, even if the time-frequency resource blocks in the time-frequency resource set are adjacent time-frequency resource blocks, the time-frequency resource blocks can be used for representing the spatial position relationship between the point cloud coordinate points through the time-frequency position relationship, so that the time-frequency resource blocks can be concentrated together, that is, no idle time-frequency resource blocks exist between the time-frequency resource blocks, and the time-frequency resource utilization rate can be improved.
For example, as shown in fig. 4, 4 point cloud coordinate points in the same layer are a point cloud coordinate point a, a point cloud coordinate point B, a point cloud coordinate point C, and a point cloud coordinate point D, respectively. The spatial position relationship between the 4 point cloud coordinate points can be represented by the time-frequency position relationship between 4 adjacent REs. The data carried by the RE1 can represent the distance between the point cloud coordinate point A and the point cloud coordinate point B, and the spatial position relationship between the point cloud coordinate point A and the point cloud coordinate point B, namely, the left side of the point cloud coordinate point A and the Yu Dianyun coordinate point B, can be represented by the time domain position relationship between the RE1 and the RE2, namely, the RE1 is positioned before the RE 2. The data carried by the RE2 can represent the distance between the point cloud coordinate point B and the point cloud coordinate point C, and the spatial position relationship between the point cloud coordinate point B and the point cloud coordinate point C, namely, the position above the point cloud coordinate point B and the position above the point cloud coordinate point Yu Dianyun coordinate point C, can be represented by the frequency domain position relationship between the RE2 and the RE3, namely, the frequency point of the RE2 is higher than the frequency point of the RE 3. The data carried by the RE3 can represent the distance between the point cloud coordinate point C and the point cloud coordinate point D, and the spatial position relationship between the point cloud coordinate point C and the point cloud coordinate point D, namely, the right side of the point cloud coordinate point C and the point cloud coordinate point Yu Dianyun coordinate point D, can be represented by the time domain position relationship between the RE3 and the RE4, namely, the RE3 is positioned behind the RE 4. The data carried by the RE4 can represent the distance between the point cloud coordinate point D and the point cloud coordinate point A, and the spatial position relationship between the point cloud coordinate point D and the point cloud coordinate point A, namely, the position below the point cloud coordinate point D, yu Dianyun coordinate point A, can be represented by the frequency domain position relationship between the RE4 and the RE1, namely, the frequency point of the RE1 is higher than the frequency point of the RE 4.
Of course, all distances can be carried by one RE, for example, the data carried by RE1 can represent the distances between the point cloud coordinate point a and the point cloud coordinate point B, the point cloud coordinate point C and the point cloud coordinate point D, respectively, and at this time, REs 2-4 can be used for carrying data of other services.
In another possible design, the i-th layer point cloud pattern includes a plurality of point cloud coordinate points, a time-frequency distance between time-frequency resource blocks in the time-frequency resource set is used for a spatial distance between the plurality of point cloud coordinate points, and a time-frequency position relationship between the time-frequency resource blocks in the time-frequency resource set is used for a spatial position relationship between the plurality of point cloud coordinate points. That is, the point cloud pattern is completely represented by the time-frequency position of the time-frequency resource set, and at this time, the N-layer data may be data of other services, that is, the transmission of the point cloud pattern does not affect the data transmission of other services, so as to realize transmission decoupling, and the transmission is more flexible.
For example, as shown in fig. 5, 4 point cloud coordinate points in the same layer are a point cloud coordinate point a, a point cloud coordinate point B, a point cloud coordinate point C, and a point cloud coordinate point D, respectively. The spatial position relationship and the spatial distance between the 4 point cloud coordinate points can be represented by the time-frequency position relationship and the time-frequency distance between the 4 REs. The spatial position relationship between the point cloud coordinate point A and the point cloud coordinate point B is the time-frequency position relationship between RE1 and RE 2. The spatial distance relation between the point cloud coordinate point A and the point cloud coordinate point B is the time-frequency distance between RE1 and RE2, such as the center point of RE1 to the center point of RE 2. The spatial position relationship between the point cloud coordinate point B and the point cloud coordinate point C is the time-frequency position relationship between RE2 and RE 3. The spatial distance relation between the point cloud coordinate point B and the point cloud coordinate point C is the time-frequency distance between RE2 and RE3, such as the center point of RE2 to the center point of RE 3. The spatial position relationship between the point cloud coordinate point C and the point cloud coordinate point D is the time-frequency position relationship between RE3 and RE 4. The spatial distance relation between the point cloud coordinate point C and the point cloud coordinate point D is the time-frequency distance between RE3 and RE4, such as the center point of RE3 to the center point of RE 4. The spatial position relationship between the point cloud coordinate point D and the point cloud coordinate point A is the time-frequency position relationship between RE4 and RE 1. The spatial distance relation between the point cloud coordinate point D and the point cloud coordinate point A is the time-frequency distance between RE4 and RE1, such as the center point of RE4 to the center point of RE 1.
And S203, the network equipment determines N layers of point cloud patterns according to the N layers of data.
The network device determines an N-layer point cloud pattern according to a time-frequency position relation which can be based on a time-frequency resource set and the spatial distance between the i-th layer data used for representing a plurality of point cloud coordinate points. Or, the network device determines the N-layer point cloud patterns only according to the time-frequency position relation which can be based on the time-frequency resource set.
S204, the network equipment determines whether the contact net has structural defects according to the N-layer point cloud patterns.
In one possible design, the network device may integrate the N-layer point cloud pattern into one-layer target point cloud pattern. For example, n=3, the network device maps the point cloud coordinate points at the same position in the N-layer point cloud pattern to a corresponding pixel point, so as to obtain the target point cloud pattern. For example, for the same position W1 in the N-layer point cloud pattern: if there is no point cloud coordinate point at the position W1, the RGB values of the pixel point corresponding to the position W1 are respectively preset to 0. If the position W1 has the point cloud coordinate point of the 1 st layer, the R value of the pixel point corresponding to the position W1 is preset to 100, and the rest GB values are preset to 0 respectively. If the position W1 has the point cloud coordinate point of the 2 nd layer, the G value of the pixel point corresponding to the position W1 is preset to 100, and the rest RB values are preset to 0 respectively. If the position W1 has the point cloud coordinate point of the 3 rd layer, the B value of the pixel point corresponding to the position W1 is preset to 100, and the rest RG values are preset to 0 respectively. If there is a point cloud coordinate point of the 1 st-2 nd layer at the position W1, the RG value of the pixel point corresponding to the position W1 is preset to 100, and the rest B values are preset to 0. If the position W1 has the 2-3 layer point cloud coordinate points, presetting the GB value of the pixel point corresponding to the position W1 to be 100, and presetting the rest R values to be 0. If there are point cloud coordinate points of the 1 st and 3 rd layers at the position W1, the R and B values of the pixel point corresponding to the position W1 are preset to 100, and the rest G values are preset to 0. And if the position W1 is provided with the point cloud coordinate points of the 1 st layer to the 3 rd layer, presetting the RGB value of the pixel point corresponding to the position W1 to be 100.
Thus, the network equipment can process the target point cloud pattern through the convolutional neural network to determine whether the catenary has structural defects. In this case, the position change of the point cloud coordinate point caused by the structural defect is represented in the image in the form of color change, so that whether the contact net has the structural defect can be accurately determined through the convolutional neural network.
In another possible design, the network device may map the N-layer point cloud pattern to a set of target point cloud vectors. For example, the network device may map the point cloud coordinate points at the same position in the N-layer point cloud pattern to a corresponding vector, that is, coordinates of the point cloud coordinate points at the same position, to obtain a set of target point cloud vectors, that is, a set of multiple coordinates. The network equipment can process the target point cloud vector set through the deep neural network to determine whether the catenary has structural defects.
In summary, since different space domain resources can be used to layer the same time-frequency resource, the N-layer point cloud patterns are mapped to the N-layer space domain resources, and the time-frequency positions of the time-frequency resource sets corresponding to the space domain resources are multiplexed to implicitly represent the point cloud patterns, so that the transmission efficiency can be improved, that is, the same time-frequency resource can be multiplexed to transmit the N-layer point cloud patterns, so that the communication overhead can be reduced.
Referring to fig. 6, in this embodiment, there is further provided a contact network defect target detection device 600 based on a structured light 3D point cloud, where the contact network defect target detection device based on the structured light 3D point cloud includes: a transceiver module 601 and a processing module 602.
In a possible embodiment, the apparatus 600 may be adapted to the above-mentioned terminal, and perform the above-mentioned functions of the terminal.
For example, the processing module 602 is configured to obtain structured light 3D point cloud data of the catenary, where the structured light 3D point cloud data includes N layers of point cloud patterns, N is an integer greater than 1, and an ith layer of point cloud pattern in the N layers of point cloud patterns is used to characterize an appearance shape structure of the catenary on the ith layer, and i is any integer from 1 to N. And the transceiver module 601 is configured to send N layers of data to the network device, where the i-th layer of data in the N layers of data is carried by a time-frequency resource set corresponding to the i-th layer of space domain resources in the N layers of space domain resources, and the i-th layer point cloud pattern is represented by a time-frequency position of the time-frequency resource set.
In a possible design, the ith layer of point cloud pattern includes a plurality of point cloud coordinate points, the ith layer of layer data is used for representing a spatial distance between the plurality of point cloud coordinate points, and a time-frequency position relationship between time-frequency resource blocks in the time-frequency resource set is used for representing a spatial position relationship between the plurality of point cloud coordinate points.
Optionally, the ith layer of data is used for representing a spatial distance between each point cloud coordinate point in the plurality of point cloud coordinate points and an adjacent point cloud coordinate point, and the time-frequency position relationship between each time-frequency resource block in the time-frequency resource set and the adjacent time-frequency resource block is used for representing a spatial position relationship between the corresponding point cloud coordinate point in the plurality of point cloud coordinate points and the adjacent point cloud coordinate point.
In another possible design, the i-th layer point cloud pattern includes a plurality of point cloud coordinate points, a time-frequency distance between time-frequency resource blocks in the time-frequency resource set is used for a spatial distance between the plurality of point cloud coordinate points, and a time-frequency position relationship between the time-frequency resource blocks in the time-frequency resource set is used for a spatial position relationship between the plurality of point cloud coordinate points.
In another possible embodiment, the apparatus 600 may be adapted to the network device described above, and perform the functions of the network device described above.
The transceiver module 601 is configured to receive N layers of data from a terminal by using a network device, where the structured light 3D point cloud data includes N layers of point cloud patterns, N is an integer greater than 1, an ith layer of point cloud pattern in the N layers of point cloud patterns is used to characterize an appearance shape structure of a catenary on an ith layer, i is any integer from 1 to N, the ith layer of data in the N layers of data is carried by a time-frequency resource set corresponding to the ith layer of airspace resource in the N layers of airspace resources, and a time-frequency position of the ith layer of point cloud pattern time-frequency resource set is characterized. The processing module 602 is configured to determine an N-layer point cloud pattern according to the N-layer data by using the network device; and the processing module 602 is used for determining whether the overhead line system has structural defects according to the N-layer point cloud pattern by the network equipment.
In a possible design, the processing module 602 is configured to integrate the N-layer point cloud patterns into one-layer point cloud pattern by the network device; and the processing module 602 is used for the network equipment to process the target point cloud pattern through the convolutional neural network and determine whether the catenary has structural defects.
Optionally, n=3, where the i-th layer point cloud pattern includes a plurality of point cloud coordinate points, and the processing module 602 is configured to map the point cloud coordinate points at the same position in the N-layer point cloud pattern to a corresponding pixel point by using the network device, so as to obtain the target point cloud pattern.
In another possible design, the processing module 602 is configured to map the N-layer point cloud pattern into the set of target points Yun Xiangliang by the network device; the processing module 602 is configured to process, by using the network device, the set of cloud vectors of the target point through the deep neural network, and determine whether the catenary has a structural defect.
Optionally, the processing module 602 is configured to map the point cloud coordinate points at the same position in the N-layer point cloud pattern to a corresponding vector by using the network device, so as to obtain a target point cloud vector set.
The following describes, in detail, each component of the contact net defect target detection device 700 based on the structured light 3D point cloud with reference to fig. 7:
the processor 701 is a control center of the apparatus 700, and may be one processor or a collective term of a plurality of processing elements. For example, the processor 701 is one or more central processing units (central processing unit, CPU), but may also be an integrated circuit (application specific integrated circuit, ASIC), or one or more integrated circuits configured to implement embodiments of the present application, such as: one or more microprocessors (digital signal processor, DSPs), or one or more field programmable gate arrays (field programmable gate array, FPGAs).
Alternatively, the processor 701 may perform various functions of the apparatus 700, such as the functions in the method shown in fig. 2 described above, by running or executing a software program stored in the memory 702, and invoking data stored in the memory 702.
In a particular implementation, the processor 701 may include one or more CPUs, such as CPU0 and CPU1 shown in FIG. 7, as an embodiment.
In a specific implementation, the apparatus 700 may also include a plurality of processors, such as the processor 701 and the processor 704 shown in fig. 7, as an embodiment. Each of these processors may be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). A processor herein may refer to one or more devices, circuits, and/or processing cores for processing data (e.g., computer program instructions).
The memory 702 is configured to store a software program for executing the present application, and the processor 701 controls the execution of the software program, and the specific implementation may refer to the above method embodiment, which is not described herein again.
Alternatively, the memory 702 may be a read-only memory (ROM) or other type of static storage device that may store static information and instructions, a random access memory (random access memory, RAM) or
Other types of dynamic storage devices, which can store information and instructions, can also be, but are not limited to, an electrically erasable programmable read-only memory (EEPROM), a compact disk read-only memory (CD-ROM) or other optical disk storage, optical disk storage (including compact disk, laser disk, optical disk, digital versatile disk, blu-ray disc, etc.), magnetic disk storage or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and capable of being accessed by a computer. The memory 702 may be integrated with the processor 701 or may exist separately and be coupled to the processor 701 through an interface circuit (not shown in fig. 7) of the apparatus 700, which is not specifically limited in this embodiment.
A transceiver 703 for communication with other devices. For example, the multi-beam based positioning device is a terminal and the transceiver 703 may be used to communicate with a network device or with another terminal.
Alternatively, the transceiver 703 may include a receiver and a transmitter (not separately shown in fig. 7). The receiver is used for realizing the receiving function, and the transmitter is used for realizing the transmitting function.
Alternatively, transceiver 703 may be integrated with processor 701 or may exist separately and be coupled to processor 701 through interface circuitry (not shown in fig. 7) of apparatus 700, as embodiments of the present application are not specifically limited.
It should be noted that the structure of the apparatus 700 shown in fig. 7 is not limited to the apparatus, and an actual apparatus 700 may include more or less components than those shown, or may combine some components, or may have different arrangements of components.
In addition, the technical effects of the apparatus 700 may refer to the technical effects of the method of the above method embodiment, which are not described herein.
It should be appreciated that the processor in embodiments of the present application may be a central processing unit (central processing unit, CPU), which may also be other general purpose processors, digital signal processors (digital signal processor, DSP), application specific integrated circuits (application specific integrated circuit, ASIC), off-the-shelf programmable gate arrays (field programmable gate array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
It should also be appreciated that the memory in embodiments of the present application may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The nonvolatile memory may be a read-only memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an electrically Erasable EPROM (EEPROM), or a flash memory. The volatile memory may be random access memory (random access memory, RAM) which acts as an external cache. By way of example but not limitation, many forms of random access memory (random access memory, RAM) are available, such as Static RAM (SRAM), dynamic Random Access Memory (DRAM), synchronous Dynamic Random Access Memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced Synchronous Dynamic Random Access Memory (ESDRAM), synchronous Link DRAM (SLDRAM), and direct memory bus RAM (DR RAM).
The above embodiments may be implemented in whole or in part by software, hardware (e.g., circuitry), firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions in accordance with the embodiments of the present application are produced in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center by wired (e.g., infrared, wireless, microwave, etc.) means. Computer readable storage media can be any available media that can be accessed by a computer or data storage devices, such as servers, data centers, etc. that contain one or more collections of available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium may be a solid state disk.
It should be understood that the term "and/or" is merely an association relationship describing the associated object, and means that three relationships may exist, for example, a and/or B may mean: there are three cases, a alone, a and B together, and B alone, wherein a, B may be singular or plural. In addition, the character "/" herein generally indicates that the associated object is an "or" relationship, but may also indicate an "and/or" relationship, and may be understood by referring to the context.
In the present application, "at least one" means one or more, and "a plurality" means two or more. "at least one of" or the like means any combination of these items, including any combination of single item(s) or plural items(s). For example, at least one (one) of a, b, or c may represent: a, b, c, a-b, a-c, b-c, or a-b-c, wherein a, b, c may be single or plural.
It should be understood that, in various embodiments of the present application, the sequence numbers of the foregoing processes do not mean the order of execution, and the order of execution of the processes should be determined by the functions and internal logic thereof, and should not constitute any limitation on the implementation process of the embodiments of the present application.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the partitioning of elements is merely a logical functional partitioning, and there may be additional partitioning in actual implementation, e.g., multiple elements or components may be combined or integrated into another system, or some feature fields may be omitted, or not implemented. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (random access memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The foregoing is merely specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think about changes or substitutions within the technical scope of the present application, and the changes or substitutions are intended to be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. The contact net defect target detection method based on the structured light 3D point cloud is characterized by comprising the following steps of:
the method comprises the steps that a terminal obtains structured light 3D point cloud data of a contact net, wherein the structured light 3D point cloud data comprises N layers of point cloud patterns, N is an integer greater than 1, an ith layer of point cloud pattern in the N layers of point cloud patterns is used for representing the appearance shape structure of the contact net on an ith layer, and i is any integer from 1 to N;
the terminal sends N layers of data to the network equipment, wherein the ith layer of data in the N layers of data is carried by a time-frequency resource set corresponding to the ith layer of airspace resource in the N layers of airspace resource, and the ith layer of point cloud pattern is represented by the time-frequency position of the time-frequency resource set.
2. The method of claim 1, wherein the i-th layer of point cloud patterns comprises a plurality of point cloud coordinate points, the i-th layer of data is used for representing spatial distances between the plurality of point cloud coordinate points, and the time-frequency positional relationship between time-frequency resource blocks in the time-frequency resource set is used for representing spatial positional relationship between the plurality of point cloud coordinate points.
3. The method of claim 2, wherein the i-th layer data is used to characterize a spatial distance between each point cloud coordinate point of the plurality of point cloud coordinate points and an adjacent point cloud coordinate point, and wherein a time-frequency positional relationship between each time-frequency resource block and an adjacent time-frequency resource block in the set of time-frequency resources is used to characterize a spatial positional relationship between a corresponding point cloud coordinate point of the plurality of point cloud coordinate points and an adjacent point cloud coordinate point.
4. The method of claim 1, wherein the i-th layer point cloud pattern comprises a plurality of point cloud coordinate points, wherein a time-frequency distance between time-frequency resource blocks in the time-frequency resource set is used for a spatial distance between the plurality of point cloud coordinate points, and wherein a time-frequency positional relationship between time-frequency resource blocks in the time-frequency resource set is used for a spatial positional relationship between the plurality of point cloud coordinate points.
5. The contact net defect target detection method based on the structured light 3D point cloud is characterized by comprising the following steps of:
the network equipment receives N layers of data from a terminal, wherein the structured light 3D point cloud data comprises N layers of point cloud patterns, N is an integer greater than 1, an ith layer of point cloud pattern in the N layers of point cloud patterns is used for representing the appearance shape structure of the contact net on an ith layer, i is any integer from 1 to N, the ith layer of data in the N layers of data is borne by a time-frequency resource set corresponding to an ith layer of space domain resource in the N layers of space domain resources, and the ith layer of point cloud pattern is represented by the time-frequency position of the time-frequency resource set;
the network equipment determines the N layers of point cloud patterns according to the N layers of data;
and the network equipment determines whether the contact net has structural defects according to the N-layer point cloud patterns.
6. The method of claim 5, wherein the network device determining whether the catenary has a structural defect according to the N-layer point cloud pattern comprises:
the network equipment fuses the N layers of point cloud patterns into one layer of target point cloud patterns;
and the network equipment processes the target point cloud pattern through a convolutional neural network and determines whether the contact net has a structural defect.
7. The method of claim 6, wherein N = 3, the i-th layer of point cloud patterns comprise a plurality of point cloud coordinate points, the network device merging the N-layer of point cloud patterns into a layer of target point cloud patterns, comprising:
and the network equipment maps the point cloud coordinate points at the same position in the N layers of point cloud patterns into a corresponding pixel point to obtain the target point cloud pattern.
8. The method of claim 5, wherein the network device determining whether the catenary has a structural defect according to the N-layer point cloud pattern comprises:
the network device maps the N-layer point cloud pattern to a set of target points Yun Xiangliang;
the network device processes the set of target points Yun Xiangliang through a deep neural network to determine whether the catenary has structural defects.
9. The method of claim 8, wherein the network device mapping the N-layer point cloud pattern to a set of target points Yun Xiangliang comprises:
and the network equipment maps the point cloud coordinate points at the same position in the N layers of point cloud patterns into a corresponding vector to obtain the target point cloud vector set.
10. A contact net defect target detection device based on structured light 3D point cloud, characterized in that the device comprises means for performing the method according to any of the preceding claims 1-9.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310342068.7A CN116051565B (en) | 2023-04-03 | 2023-04-03 | Contact net defect target detection method and device based on structured light 3D point cloud |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310342068.7A CN116051565B (en) | 2023-04-03 | 2023-04-03 | Contact net defect target detection method and device based on structured light 3D point cloud |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116051565A true CN116051565A (en) | 2023-05-02 |
CN116051565B CN116051565B (en) | 2023-07-28 |
Family
ID=86120443
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310342068.7A Active CN116051565B (en) | 2023-04-03 | 2023-04-03 | Contact net defect target detection method and device based on structured light 3D point cloud |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116051565B (en) |
Citations (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20170066459A1 (en) * | 2015-09-03 | 2017-03-09 | Sameer Singh | Rail track asset survey system |
JP2017224935A (en) * | 2016-06-14 | 2017-12-21 | 株式会社日立ソリューションズ | Object detection/evaluation system and object detection/evaluation method |
CN109532021A (en) * | 2018-10-10 | 2019-03-29 | 浙江大学 | The molten product layer-by-layer detection method of defect of 3D printing based on the actinic abnormal point of structure |
CN109816633A (en) * | 2018-12-27 | 2019-05-28 | 大族激光科技产业集团股份有限公司 | A kind of defect monitoring method based on 3D printing system, device and terminal device |
CN110030951A (en) * | 2019-05-14 | 2019-07-19 | 武汉大学 | A kind of diversion vertical shaft defect inspection method based on three-dimensional laser scanning technique |
CN111127382A (en) * | 2018-10-15 | 2020-05-08 | 西南交通大学 | Contact net suspension assembly U-shaped ring spare cap defect detection method |
CN112581457A (en) * | 2020-12-23 | 2021-03-30 | 武汉理工大学 | Pipeline inner surface detection method and device based on three-dimensional point cloud |
CN112964172A (en) * | 2020-12-08 | 2021-06-15 | 聚时科技(上海)有限公司 | Aviation blade surface measuring method and measuring equipment based on structured light camera |
CN113393441A (en) * | 2021-06-15 | 2021-09-14 | 浙江大学 | Layered manufacturing defect detection method based on machine vision |
CN113420004A (en) * | 2021-07-02 | 2021-09-21 | 中易天建设工程技术(深圳)有限公司 | Tunnel point cloud data storage method and device, computer equipment and storage medium |
CN113630884A (en) * | 2021-08-04 | 2021-11-09 | 庞威 | Resource block adjusting method and device for side-chain communication |
CN114187441A (en) * | 2021-12-08 | 2022-03-15 | 深圳市商汤科技有限公司 | Contact net part defect detection method and device, electronic equipment and storage medium |
CN114445369A (en) * | 2022-01-27 | 2022-05-06 | 成都唐源电气股份有限公司 | Contact net sectional insulator identification method and device based on 3D imaging technology |
CN114812440A (en) * | 2022-04-22 | 2022-07-29 | 国网湖北省电力有限公司十堰供电公司 | High-rise building fireproof plugging module defect detection device and method based on line structured light |
CN114881955A (en) * | 2022-04-28 | 2022-08-09 | 厦门微亚智能科技有限公司 | Slice-based annular point cloud defect extraction method and device and equipment storage medium |
CN115583030A (en) * | 2022-10-17 | 2023-01-10 | 山东大学 | Method and device for online detection of internal three-dimensional defects during component additive manufacturing |
CN115631153A (en) * | 2022-10-14 | 2023-01-20 | 佳源科技股份有限公司 | Pipe gallery visual defect detection method and system based on perception learning structure |
-
2023
- 2023-04-03 CN CN202310342068.7A patent/CN116051565B/en active Active
Patent Citations (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20170066459A1 (en) * | 2015-09-03 | 2017-03-09 | Sameer Singh | Rail track asset survey system |
JP2017224935A (en) * | 2016-06-14 | 2017-12-21 | 株式会社日立ソリューションズ | Object detection/evaluation system and object detection/evaluation method |
CN109532021A (en) * | 2018-10-10 | 2019-03-29 | 浙江大学 | The molten product layer-by-layer detection method of defect of 3D printing based on the actinic abnormal point of structure |
CN111127382A (en) * | 2018-10-15 | 2020-05-08 | 西南交通大学 | Contact net suspension assembly U-shaped ring spare cap defect detection method |
CN109816633A (en) * | 2018-12-27 | 2019-05-28 | 大族激光科技产业集团股份有限公司 | A kind of defect monitoring method based on 3D printing system, device and terminal device |
CN110030951A (en) * | 2019-05-14 | 2019-07-19 | 武汉大学 | A kind of diversion vertical shaft defect inspection method based on three-dimensional laser scanning technique |
CN112964172A (en) * | 2020-12-08 | 2021-06-15 | 聚时科技(上海)有限公司 | Aviation blade surface measuring method and measuring equipment based on structured light camera |
CN112581457A (en) * | 2020-12-23 | 2021-03-30 | 武汉理工大学 | Pipeline inner surface detection method and device based on three-dimensional point cloud |
CN113393441A (en) * | 2021-06-15 | 2021-09-14 | 浙江大学 | Layered manufacturing defect detection method based on machine vision |
CN113420004A (en) * | 2021-07-02 | 2021-09-21 | 中易天建设工程技术(深圳)有限公司 | Tunnel point cloud data storage method and device, computer equipment and storage medium |
CN113630884A (en) * | 2021-08-04 | 2021-11-09 | 庞威 | Resource block adjusting method and device for side-chain communication |
CN114187441A (en) * | 2021-12-08 | 2022-03-15 | 深圳市商汤科技有限公司 | Contact net part defect detection method and device, electronic equipment and storage medium |
CN114445369A (en) * | 2022-01-27 | 2022-05-06 | 成都唐源电气股份有限公司 | Contact net sectional insulator identification method and device based on 3D imaging technology |
CN114812440A (en) * | 2022-04-22 | 2022-07-29 | 国网湖北省电力有限公司十堰供电公司 | High-rise building fireproof plugging module defect detection device and method based on line structured light |
CN114881955A (en) * | 2022-04-28 | 2022-08-09 | 厦门微亚智能科技有限公司 | Slice-based annular point cloud defect extraction method and device and equipment storage medium |
CN115631153A (en) * | 2022-10-14 | 2023-01-20 | 佳源科技股份有限公司 | Pipe gallery visual defect detection method and system based on perception learning structure |
CN115583030A (en) * | 2022-10-17 | 2023-01-10 | 山东大学 | Method and device for online detection of internal three-dimensional defects during component additive manufacturing |
Non-Patent Citations (4)
Title |
---|
YAODONG CUI 等: "Deep Learning for Image and Point Cloud Fusion in Autonomous Driving: A Review", 《ARXIV:2004.05224V2 [CS.CV]》, pages 1 - 19 * |
ZHENCHAO OUYANG 等: "PV-EncoNet: Fast Object Detection Based on Colored Point Cloud", 《IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS》, vol. 23, no. 8, pages 12439 - 12450 * |
周新宇: "基于三维点云的铁路接触网支柱定位检测研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》, pages 033 - 206 * |
李桥: "基于三维点云辅助分析的接触网零部件故障智能识别方法研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》, pages 033 - 279 * |
Also Published As
Publication number | Publication date |
---|---|
CN116051565B (en) | 2023-07-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110990510B (en) | Three-dimensional map generation method, terminal and server | |
US11818336B2 (en) | Systems and methods for intra prediction | |
CN113692046B (en) | Label positioning method and device, computer equipment and storage medium | |
CN115915405B (en) | Control method and device for bonding wire equipment cluster | |
CN115694566B (en) | High-reliability control method and device for antioxidant silk-binding equipment | |
CN111295667A (en) | Image stereo matching method and driving assisting device | |
CN118019112A (en) | Self-organizing and cooperative method of Internet of things nodes of bonding silver wire equipment | |
CN116308066B (en) | Storage management method and device based on Internet of things | |
CN116051565B (en) | Contact net defect target detection method and device based on structured light 3D point cloud | |
CN117499979A (en) | Target detection method and device for phased array antenna | |
WO2016196404A1 (en) | Decoding of intra-predicted images | |
CN113672669B (en) | Data query method and device based on distributed storage | |
CN116109769A (en) | Three-dimensional model building method and device, electronic equipment and storage medium | |
EP4290180A1 (en) | Event location transmission method, device and system | |
CN115857836B (en) | Information storage method and device based on big data | |
CN115866062B (en) | Real-time collection and storage method and device for big data in multi-tenant architecture | |
CN113630895A (en) | Data packet transmission method and device | |
CN114980146B (en) | Beam enhancement method and device based on intelligent communication box and intelligent communication box | |
CN115017486B (en) | Service processing method and related device | |
CN111538975A (en) | Image processing method and device | |
CN115880294B (en) | Integrated processing method and system based on endoscope image | |
CN117591304B (en) | Computer vision-based high-efficiency machine room consumption control method and system | |
US20220377561A1 (en) | Distributed private location verification and enhancement | |
CN114867104B (en) | Positioning method and device based on multiple beams | |
CN117202165A (en) | Electric energy meter HPLC module with remote upgrading function and upgrading method |
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 |