A road health drone inspection solution based on road network segmentation

Abstract

The present invention discloses a road health drone inspection scheme based on road network segmentation. First, remote sensing images are used to obtain road information in the monitoring area and create a road network. Second, road intersection nodes and road distribution information are obtained from the road network to construct an undirected Euler graph. The Fleury algorithm is then used to obtain Euler circuits in the road Euler graph, calculate the length of Euler circuits in the road network graph, and classify the road network according to the presence of Euler circuits. Finally, the working paths of each drone are divided according to the presence and length of Euler circuits, ensuring that the drones can complete the monitoring operation quickly and efficiently. This invention solves the problem of high labor costs in road pavement health monitoring. When road pavement health problems occur, timely maintenance can be carried out, alleviating inconveniences in people's daily lives and the transportation industry, and reducing the pressure on transportation departments to regulate road health. It provides guidance and basis for improving road conditions and road maintenance.

Description

Technical Field

[0001] The present invention relates to a road health status drone inspection solution based on road network segmentation, belonging to the technical fields of drone control and municipal engineering. Background Art

[0002] As an important channel for people to travel, roads bear the important tasks of carrying traffic flow and ensuring people's travel safety. Therefore, the importance of road maintenance is self-evident. Summary of the Invention

[0003] To address the aforementioned challenges of the existing technologies, this invention provides a drone-based road health inspection solution based on road network segmentation. This solution addresses the high labor costs associated with monitoring road pavement health. When road pavement health issues arise, timely maintenance can be performed, alleviating inconvenience for people's daily lives and the transportation industry, and reducing the burden on transportation authorities to oversee road health. This solution provides guidance and a basis for improving road conditions and road maintenance, and provides a scientific basis for decision-making in regional road maintenance and repair, as well as for road administration planning.

[0004] To achieve the above objectives, the present invention adopts a technical solution: a road health drone inspection solution based on road network segmentation, comprising the following steps:

[0005] S1: Obtain road information in the monitoring area through remote sensing images and create a road network;

[0006] S2: Obtain road intersection nodes and road distribution information based on the road network and construct an undirected Euler graph;

[0007] S3: Write Fleury's algorithm to obtain the Euler circuits in the road Euler graph, calculate the length of the Euler circuits in the road network graph, and classify the road network according to whether there are Euler circuits.

[0008] S4: Divide the working paths of each drone based on the existence and length of the Euler circuit to ensure that the drone can complete the monitoring task quickly and efficiently.

[0009] Furthermore, the S1 step is specifically as follows:

[0010] S11: Acquire remote sensing image data of the area to be measured, requiring the image spatial resolution to be 16m or above;

[0011] S12: Extract ROI (region of interest) samples of roads of different materials in the test area, and extract the road network from the remote sensing image through supervised classification;

[0012] S13: Construct a vector file based on the extracted road network, and annotate information such as road grade and material.

[0013] Furthermore, the S2 step is specifically as follows:

[0014] S21: Construct an undirected Euler graph to convert the road network into an undirected graph;

[0015] S22: Use the intersection nodes of roads as vertices and the road links as edges to construct an undirected graph. At the intersection nodes, create new vertices and connect roads to achieve road links. Use an adjacency matrix or adjacency table to represent the generated graph.

[0016] S23: Detecting an Euler path or Euler circuit by traversing the edges of the undirected graph, detecting an Euler path or Euler circuit, and storing the detected Euler path or Euler circuit;

[0017] Furthermore, the S3 step is specifically as follows:

[0018] S31: Initialize the Euler circuit, select any vertex in the graph as the starting point, record it as current_vertex, mark it as "visited", and define a list to save the vertex sequence of the Euler path;

[0019] S32: Determine whether it is a connected graph. If the current vertex has an unvisited neighbor, start searching from that vertex. Otherwise, put it into the Euler path sequence.

[0020] S33: Select the next node, select a next vertex next_vertex that is adjacent to current_vertex and does not belong to the Euler path, add it to the Euler path and mark it as "visited";

[0021] S34: Search the Euler circuit, starting from the initial node, continuously searching for adjacent nodes and recording them; if the next node found is the same as the starting point, continue searching from the next node of current_vertex in the Euler path, otherwise put it at the end of the Euler path;

[0022] S35: Calculate the length of the Euler circuit. By calculating the length of each edge in the Euler path, the total length of the Euler circuit can be obtained.

[0023] S36: Classify the road network by determining whether there is an Euler circuit in the Euler graph. If there is an Euler circuit, the road network is an Euler graph; otherwise, it is a non-Eulerian graph.

[0024] Furthermore, the S4 step is specifically as follows:

[0025] S41: For road networks with Euler loops: evenly distribute the UAVs to each flight based on the length of the Euler loop;

[0026] S42: For a road network with a non-Eulerian circuit: repeat the S3 operation to obtain a branched Eulerian circuit;

[0027] S43: Plan the trajectory of the UAV according to the assigned monitoring task;

[0028] S44: The drone is equipped with a five-directional camera module for monitoring, ensuring that a single flight can record complete road conditions and improve monitoring efficiency;

[0029] S45: Data is uploaded to the cloud, reminding relevant units to promptly determine the health of the road and perform maintenance based on the actual situation.

[0030] The beneficial effects of this invention are: it solves the problem of high labor costs associated with monitoring road pavement health. When road pavement health issues arise, timely maintenance can be performed, alleviating inconvenience in people's daily lives and the transportation industry, and reducing the pressure on transportation departments to regulate road health. It also provides guidance and a basis for improving road conditions and road maintenance, and provides a scientific basis for decision-making in regional road maintenance and repair, as well as for road administration planning. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 is a flow chart of an embodiment of the present invention;

[0032] Figure 2 This is a graph showing the result of searching for an Euler circuit based on a road network according to an embodiment of the present invention; DETAILED DESCRIPTION

[0033] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. However, it should be understood that the specific embodiments described herein are only used to illustrate the present invention and are not intended to limit the scope of the present invention.

[0034] Unless otherwise defined, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention pertains. The terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0035] like Figure 1 、 Figure 2 As shown in the figure, a road health drone inspection solution based on road network segmentation includes the following steps:

[0036] S1: Obtain road information in the monitoring area through remote sensing images and create a road network;

[0037] S11: Acquire remote sensing image data of the area to be measured, requiring the image spatial resolution to be 16m or above;

[0038] S12: Extract ROI (region of interest) samples of roads of different materials in the test area, and extract the road network from the remote sensing image through supervised classification;

[0039] S13: construct a vector file based on the extracted road network, and annotate information such as road grade and material;

[0040] S2: Obtain road intersection nodes and road distribution information based on the road network and construct an undirected Euler graph;

[0041] S21: Construct an undirected Euler graph. Convert the road network into an undirected graph;

[0042] S22: Construct an undirected graph using road intersections as vertices and road links as edges. At intersections, create new vertices and connect roads to them, thus achieving road links. Use an adjacency matrix or adjacency list to represent the resulting graph.

[0043] S23: Detecting an Euler path or Euler circuit. Detecting an Euler path or Euler circuit by traversing the edges of the undirected graph and storing the detected Euler path or Euler circuit.

[0044] S3: Write Fleury's algorithm to obtain the Euler circuits in the road Euler graph, calculate the length of the Euler circuits in the road network graph, and classify the road network according to whether there are Euler circuits.

[0045] S31: Initialize the Euler circuit. Select any vertex in the graph as the starting point, record it as current_vertex, mark it as "visited", and define a list to save the vertex sequence of the Euler path;

[0046] S32: Determine whether the graph is connected. If the current vertex has unvisited neighbors, start searching from that vertex; otherwise, put it into the Euler path sequence.

[0047] S33: Select the next node. Select a next vertex next_vertex that is adjacent to current_vertex and does not belong to the Euler path, add it to the Euler path and mark it as "visited";

[0048] S34: Search for the Euler circuit. Starting from the initial node, continuously search for adjacent nodes and record them. If the next node found is the same as the starting point, continue searching from the next node of current_vertex in the Euler path, otherwise put it at the end of the Euler path;

[0049] S35: Calculate the length of the Euler circuit. By calculating the length of each edge in the Euler path, the total length of the Euler circuit can be obtained;

[0050] S36: Classify the road network by judging whether there is an Euler loop in the Euler graph. If there is an Euler loop, the road network is an Euler graph, otherwise it is a non-Eulerian graph.

[0051] S4: Divide the working paths of each drone based on the existence and length of the Euler loop to ensure that the drone can complete the monitoring task quickly and efficiently;

[0052] S41: For road networks with Euler loops: evenly distribute the UAVs to each flight based on the length of the Euler loop;

[0053] S42: For a road network with a non-Eulerian circuit: repeat the S3 operation to obtain a branched Eulerian circuit.

[0054] S43: Plan the trajectory of the UAV according to the assigned monitoring task;

[0055] S44: The drone is equipped with a five-way camera module for monitoring, ensuring that a single flight can record the complete road conditions and improve monitoring efficiency

[0056] S45: Data is uploaded to the cloud to remind relevant departments to promptly judge the road health status and carry out maintenance according to the actual situation.

[0057] The present invention first obtains road information of the monitoring area through remote sensing images and creates a road network. Secondly, it obtains road intersection nodes and road distribution information based on the road network and constructs an undirected Euler graph. Thirdly, it writes the Fleury algorithm to obtain the Euler circuits in the road Euler graph, calculates the length of the Euler circuits in the road network graph, and classifies the road network according to whether there are Euler circuits. Finally, it divides the working paths of each drone according to the presence and length of the Euler circuits to ensure that the drones can complete the monitoring operation quickly and efficiently.

[0058] This invention addresses the high labor costs associated with monitoring road pavement health. When road pavement health issues arise, timely maintenance can be performed, alleviating inconvenience in people's daily lives and the transportation industry, and reducing the burden on transportation authorities to oversee road health. It provides guidance and a basis for improving road conditions and road maintenance, and offers a scientific basis for decision-making in regional road maintenance and repair, as well as for road administration planning.

[0059] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions or improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A road health drone inspection solution based on road network segmentation, characterized by: The following steps are involved: S1: Obtain road information in the monitoring area through remote sensing images and create a road network; S2: Obtain road intersection nodes and road distribution information based on the road network and construct an undirected Euler graph; S3: Write the Fleury algorithm to obtain the Eulerian circuits in the road graph, calculate the length of the Eulerian circuits in the road network graph, and classify the road network according to whether there are Eulerian circuits. S4: Divide the working paths of each drone based on the existence and length of the Euler loop to ensure that the drone can complete the monitoring task quickly and efficiently; Among them, step S4 is specifically as follows: S41: For road networks with Euler loops: evenly distribute the UAVs to each flight based on the length of the Euler loop; S42: For roads that are not Euler circuits: repeat S3 until all roads are split to obtain branch Euler circuits; S43: Plan the trajectory of the UAV according to the assigned monitoring task; S44: The drone is equipped with a five-directional camera module for monitoring, ensuring that a single flight can record complete road conditions and improve monitoring efficiency; S45: Data is uploaded to the cloud, reminding relevant units to promptly determine the health of the road and perform maintenance based on the actual situation.

2. The road health drone inspection solution based on road network segmentation according to claim 1 is characterized in that: The S1 step is specifically as follows: S11: Acquire remote sensing image data of the area to be measured, requiring the image spatial resolution to be 16m or above; S12: Extract ROI samples of roads of different materials in the test area and extract the road network from the remote sensing image through supervised classification; S13: Construct a vector file based on the extracted road network and annotate the road grade and material information.

3. The road health drone inspection solution based on road network segmentation according to claim 1 is characterized in that: The S2 step is specifically as follows: S21: Construct an undirected Euler graph to convert the road network into an undirected graph; S22: Use the intersection nodes of roads as vertices and the road links as edges to construct an undirected graph. At the intersection nodes, create new vertices and connect roads to achieve road links. Use an adjacency matrix or adjacency table to represent the generated graph. S23: Detecting an Euler path or Euler circuit by traversing the edges of the undirected graph, detecting an Euler path or Euler circuit, and storing the detected Euler path or Euler circuit.

4. The road health drone inspection solution based on road network segmentation according to claim 1 is characterized in that: The S3 step is specifically as follows: S31: Initialize the Euler circuit, select any vertex in the graph as the starting point, record it as current_vertex, mark it as "visited", and define a list to save the vertex sequence of the Euler path; S32: Determine whether it is a connected graph. If the current vertex has an unvisited neighbor, start searching from that vertex. Otherwise, put it into the Euler path sequence. S33: Select the next node, select a next vertex next_vertex that is adjacent to current_vertex and does not belong to the Euler path, add it to the Euler path and mark it as "visited"; S34: Search the Euler circuit, starting from the initial node, continuously searching for adjacent nodes and recording them; if the next node found is the same as the starting point, continue searching from the next node of current_vertex in the Euler path, otherwise put it at the end of the Euler path; S35: Calculate the length of the Euler circuit. By calculating the length of each edge in the Euler path, the total length of the Euler circuit can be obtained. S36: Classify the road network by determining whether there is an Euler circuit in the Euler graph. If there is an Euler circuit, the road network is an Euler graph; otherwise, it is a non-Eulerian graph.

Images