Slope geological disaster intelligent monitoring system based on thermal imaging and laser correlation linkage

Abstract

The invention provides a slope geological disaster intelligent monitoring system based on thermal imaging and laser correlation linkage, which relates to the technical field of geological disaster monitoring and comprises a laser correlation monitoring module, a thermal imaging monitoring module and a warning module. The laser correlation monitoring module is used for determining the slope disaster condition according to the laser beam on-off state between a laser transmitter and a laser receiver which are arranged on the two sides of a slope monitoring area respectively. The thermal imaging monitoring module is used for acquiring a thermal imaging image according to a thermal imager, and respectively extracting a temperature distribution gradient, a mass center moving speed and a contour form change rate of a target object in the slope monitoring area according to the thermal imaging image; inputting the temperature distribution gradient, the mass center moving speed and the contour form change rate into a support vector machine classification model to generate the object type of the target object; and the warning module is used for generating a disaster warning when the slope disaster condition is that a slope disaster occurs and the object is a disaster object. According to the invention, accurate disaster prediction can be provided.

Description

Technical Field

[0001] The present invention relates to the technical field of geological disaster monitoring, and in particular to an intelligent monitoring system for slope geological disasters based on the linkage of thermal imaging and laser beaming. Background Art

[0002] Geological disaster monitoring is of key significance to ensuring the safety of life and property, infrastructure stability and sustainable development of the ecological environment.

[0003] Related technologies for monitoring geological hazards on slopes primarily rely on a variety of methods, including surface prism measurement, GNSS displacement monitoring, vibration sensors, and tilt sensors, to achieve comprehensive monitoring and early warning of slope surface deformation. However, these methods suffer from high false alarm rates, delayed response times, and limited coverage, resulting in low geological hazard monitoring accuracy. Existing monitoring methods struggle to meet the stringent requirements for monitoring and early warning accuracy in slope geological hazard scenarios. Summary of the Invention

[0004] The problem solved by the present invention is how to improve the monitoring precision and early warning accuracy of geological disasters.

[0005] To solve the above problems, the present invention provides an intelligent monitoring system for slope geological disasters based on the linkage of thermal imaging and laser beaming, which includes a laser beaming monitoring module, a thermal imaging monitoring module and a warning module; The laser beam monitoring module is used to determine the slope disaster situation according to the on-off status of the laser beam between the laser transmitter and the laser receiver respectively set on both sides of the slope monitoring area; The thermal imaging monitoring module is configured to obtain a thermal imaging image of the slope monitoring area using a thermal imager, extract a temperature distribution gradient, a centroid movement speed, and a contour morphology change rate of a target object in the slope monitoring area based on the thermal imaging image, and input the temperature distribution gradient, the centroid movement speed, and the contour morphology change rate into a support vector machine classification model to generate an object type of the target object; The warning module is used to generate a disaster warning when the slope disaster situation is a slope disaster and the object type is a disaster body.

[0006] Optionally, the thermal imaging image includes thermal images of continuous frames, and extracting the temperature distribution gradient, center of mass moving speed, and contour morphology change rate of the target object in the slope monitoring area based on the thermal imaging image includes: Determining the temperature gradient value of each pixel point of the thermal imaging image using a gradient operator according to the temperature data of the thermal imaging image, and generating the temperature distribution gradient according to the temperature gradient value of each pixel point; Determine the target center of mass coordinates of each frame in the thermal imaging image using a center of mass calculation method, and determine the center of mass moving speed based on the time corresponding to each target center of mass coordinate and the frame number; According to the thermal imaging image, an edge detection algorithm is used to extract the target contour of the target object for each of the frames, and the contour morphology change rate is determined according to the target contour and the time corresponding to the frames.

[0007] Optionally, the object type includes the disaster object and the non-disaster object, and the inputting the temperature distribution gradient, the center of mass moving speed, and the contour morphology change rate into a support vector machine classification model to generate the object type of the target object includes: Respectively extracting the temperature feature vector of the temperature distribution gradient, the center of mass feature vector of the center of mass moving speed, and the contour feature vector of the contour morphology change rate, and inputting the temperature feature vector, the center of mass feature vector, and the contour feature vector into the support vector machine classification model; The support vector machine classification model solves the optimal hyperplane based on the constraint conditions and the objective function to generate the object category.

[0008] Optionally, the non-disaster objects include pedestrians and animals, and the thermal imaging monitoring module is further used to extract a target centroid time series of the target object according to the centroid moving speed; Determine the Euclidean distance between each target element in the target centroid time series and each known element in the known centroid time series of each known type in the known sequence set, and construct a distance matrix; Determine the minimum cumulative distance between all elements in the distance matrix according to a dynamic programming algorithm to generate a DTW distance; According to the DTW distance and preset classification requirements, the target object is classified into the pedestrian, the animal, or the disaster object.

[0009] Optionally, the warning module is further configured to send an instruction to the laser beam monitoring module to stop generating the slope disaster situation when the target object is the pedestrian or the animal and the slope disaster situation is a disaster occurring on the slope.

[0010] Optionally, the intelligent monitoring system for slope geological disasters based on the linkage of thermal imaging and laser shooting further includes an audible and visual alarm, which is used to issue a corresponding alarm according to the disaster warning.

[0011] Optionally, the intelligent monitoring system for slope geological disasters based on the linkage of thermal imaging and laser shooting also includes poles respectively arranged on both sides of the slope monitoring area, and the laser transmitter, the laser receiver and the thermal imager are respectively arranged on the poles on both sides of the slope monitoring area.

[0012] Optionally, the intelligent monitoring system for slope geological disasters based on the linkage of thermal imaging and laser shooting further includes a camera arranged on the vertical pole via a connecting arm.

[0013] Optionally, the intelligent monitoring system for slope geological disasters based on the linkage of thermal imaging and laser shooting also includes a power distribution data transceiver box arranged on the vertical pole, and the power distribution data transceiver box is communicatively connected to the laser transmitter, the laser receiver, the thermal imager and the sound and light alarm respectively.

[0014] Optionally, the intelligent monitoring system for slope geological disasters based on the linkage of thermal imaging and laser shooting also includes a renewable energy power generation device arranged at the top of the vertical pole through an equipment bracket, and the renewable energy power generation device is electrically connected to the laser transmitter, the laser receiver, the thermal imager, the camera and the power distribution data transceiver box respectively.

[0015] The beneficial effects of the intelligent monitoring system for slope geological disasters based on thermal imaging and laser beam linkage of the present invention are: By setting up laser transmitters and laser receivers on both sides of the slope monitoring area, complete coverage of the slope area can be achieved, avoiding the problem of limited coverage. Then, the laser beam on-off status between the laser transmitter and the laser receiver can be determined through the laser beam monitoring module, so as to determine the slope disaster situation in real time and solve the hysteresis problem. For example, when the laser beam between the laser transmitter and the laser receiver is disconnected, the laser transmitter and the laser receiver can achieve millisecond-level response, and at the same time indicate that the laser beam between the laser transmitter and the laser receiver on the slope is blocked, and there may be objects or slope disasters, and then a preliminary disaster judgment is made on the slope based on the blocked laser beam. Then, the slope monitoring is obtained based on the thermal imager of the thermal imaging monitoring module. The thermal imaging image of the measuring area is obtained, and then the temperature distribution gradient, center of mass movement speed and contour morphology change rate of the target object in the slope monitoring area are extracted according to the thermal imaging image, and the temperature distribution gradient, center of mass movement speed and contour morphology change rate are input into the support vector machine classification model to accurately classify the objects blocking the laser beam on the slope. The type of object blocking the laser beam between the laser transmitter and the laser receiver on the slope can be obtained, so as to perform slope geological disaster analysis on the object type and slope disaster situation according to the warning module. When the slope disaster situation is a slope disaster and the object type is a disaster body, it means that a geological disaster has occurred. Only at this time does the warning module generate a disaster warning, thereby avoiding the problem of false alarms and providing accurate geological disaster predictions. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic diagram of the structure of an intelligent monitoring system for slope geological disasters based on the linkage of thermal imaging and laser beaming provided by an embodiment of the present invention; Figure 2 A schematic diagram of the process of generating a disaster warning according to an embodiment of the present invention.

[0017] Description of reference numerals: 1. Pole; 2. Laser transmitter; 3. Laser receiver; 4. Thermal imager; 5. Connecting arm; 6. Camera; 7. Equipment bracket; 8. Renewable energy power generation equipment; 9. Power distribution data transceiver box. DETAILED DESCRIPTION

[0018] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings. Although certain embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be construed as being limited to the embodiments described herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present invention. It should be understood that the drawings and embodiments of the present invention are for exemplary purposes only and are not intended to limit the scope of protection of the present invention. It should be understood that the various steps described in the method embodiments of the present invention can be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this respect.

[0019] The term "including" and its variations used in this document are open inclusions, that is, "including but not limited to"; the term "based on" means "based at least in part on"; the term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one other embodiment"; the term "some embodiments" means "at least some embodiments"; the term "optionally" means "optional embodiments". The relevant definitions of other terms will be given in the following description. It should be noted that the concepts of "first", "second", etc. mentioned in the present invention are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0020] It should be noted that the modifications of "one" and "multiple" mentioned in the present invention are illustrative rather than restrictive. Those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0021] The names of the messages or information exchanged between multiple devices in the embodiments of the present invention are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0022] In view of the problems existing in the above-mentioned related technologies, such as Figure 1 As shown, an embodiment of the present invention provides an intelligent monitoring system for slope geological disasters based on the linkage of thermal imaging and laser beaming, including a laser beaming monitoring module, a thermal imaging monitoring module and a warning module; The laser beam monitoring module is used to determine the slope disaster situation according to the on-off state of the laser beam between the laser transmitter 2 and the laser receiver 3 respectively arranged on both sides of the slope monitoring area.

[0023] Specifically, the laser transmitter 2 and laser receiver 3 of the laser beam monitoring module are installed in stable areas on either side of the slope monitoring area, parallel to the horizontal plane of the slope. Multiple groups of laser transmitters 2 and laser receivers 3 can be installed in stages to fully cover the slope monitoring area. The laser transmitter 2 can be installed on one side of the slope monitoring area, and the laser receiver 3 on the other. Laser beams between the laser transmitter 2 and laser receiver 3 can be set at predetermined height intervals, for example, every 10 cm. During operation, the laser transmitter 2 transmits a laser beam in real time, which is received by the laser receiver 3. If an obstacle blocks the beam, the laser receiver 3 will not receive the corresponding laser beam, resulting in a slope hazard scenario indicating a disaster has occurred. The source of the disaster may include rockfall, debris flow, collapse, avalanche, or landslide. If there are no obstacles, the laser receiver 3 will receive the corresponding laser beam, resulting in a slope hazard scenario indicating no disaster has occurred. The laser beam monitoring module generates a slope hazard profile, enabling a preliminary assessment of the slope's potential hazards. The thermal imaging monitoring module then performs a secondary assessment, determining the cause of the slope hazard profile generated by the laser beam monitoring module, enabling a final early warning. For example, the laser transmitter 2 and laser receiver 3 can be located at a height of at least 4 meters. These devices, which are commercially available, form a three-dimensional geological hazard monitoring wall. These devices can also be equipped with protective covers to prevent damage from the source of the hazard or weather.

[0024] The thermal imaging monitoring module is used to obtain a thermal imaging image of the slope monitoring area using the thermal imager 4, and extract the temperature distribution gradient, center of mass movement speed, and contour morphology change rate of the target object in the slope monitoring area based on the thermal imaging image. The temperature distribution gradient, center of mass movement speed, and contour morphology change rate are input into a support vector machine classification model to generate the object type of the target object.

[0025] Specifically, the thermal imaging monitoring module is used to obtain thermal imaging images of the slope monitoring area based on the thermal imager 4, and extract the temperature distribution gradient, center of mass movement speed and contour morphology change rate of the target object in the slope monitoring area based on the thermal imaging image, and input the temperature distribution gradient, center of mass movement speed and contour morphology change rate as multidimensional features into the trained support vector machine classification model. The support vector machine classification model is used to convert the classification problem into solving the optimal hyperplane, so as to distinguish between disaster objects and non-disaster objects and generate the object type of the target object. For example, the trained support vector machine classification model can be trained through the existing support vector machine model, or the trained support vector machine classification model can be directly obtained through the Internet.

[0026] The warning module is used to generate a disaster warning when the slope disaster situation is a slope disaster and the object type is a disaster body.

[0027] Specifically, if Figure 2 As shown, the warning module generates a disaster warning only when the slope disaster situation is a slope disaster and the object type is a disaster body, and the laser beam monitoring module and the thermal imaging monitoring module double verify that a geological disaster has occurred, thereby ensuring the accuracy of the warning and avoiding false alarms.

[0028] In this embodiment, by arranging laser emitters 2 and laser receivers 3 in multiple groups on both sides of the slope monitoring area, complete coverage of the slope area can be achieved, avoiding the problem of limited coverage. Then, the on-off state of the laser beam between the laser emitter 2 and the laser receiver 3 can be determined through the laser beam monitoring module, so as to determine the slope disaster situation in real time and solve the hysteresis problem. For example, when the laser beam between the laser emitter 2 and the laser receiver 3 is disconnected, the laser emitter 2 and the laser receiver 3 can achieve millisecond-level response, and at the same time, it is explained that the laser beam between the laser emitter 2 and the laser receiver 3 on the slope is blocked, and there may be a non-disaster body passing through the beam or a disaster on the slope, and then a preliminary disaster judgment is made on the slope based on the blocked laser beam, and then, according to the thermal imaging monitoring The thermal imager 4 of the module obtains the thermal imaging image of the slope monitoring area, and then extracts the temperature distribution gradient, center of mass movement speed and contour morphology change rate of the target object in the slope monitoring area according to the thermal imaging image, and inputs the temperature distribution gradient, center of mass movement speed and contour morphology change rate into the support vector machine classification model, and accurately classifies the objects blocking the laser beam on the slope. The type of object blocking the laser beam between the laser transmitter 2 and the laser receiver 3 on the slope can be obtained, so as to perform slope geological disaster analysis on the object type and slope disaster situation according to the warning module. When the slope disaster situation is a slope disaster and the object type is a disaster body, it means that a geological disaster has occurred. Only at this time does the warning module generate a disaster warning, thereby avoiding the problem of false alarms and providing accurate geological disaster warnings.

[0029] Optionally, the thermal imaging image includes thermal images of continuous frames, and extracting the temperature distribution gradient, center of mass moving speed, and contour morphology change rate of the target object in the slope monitoring area based on the thermal imaging image includes: Determining the temperature gradient value of each pixel point of the thermal imaging image using a gradient operator according to the temperature data of the thermal imaging image, and generating the temperature distribution gradient according to the temperature gradient value of each pixel point; Determine the target center of mass coordinates of each frame in the thermal imaging image using a center of mass calculation method, and determine the center of mass moving speed based on the time corresponding to each target center of mass coordinate and the frame number; According to the thermal imaging image, an edge detection algorithm is used to extract the target contour of the target object for each of the frames, and the contour morphology change rate is determined according to the target contour and the time corresponding to the frames.

[0030] Specifically, the gradient operator is a core tool in image processing and computer vision for detecting local changes in images (such as edges and textures). In thermal imaging analysis for geological disaster monitoring, the gradient operator can extract the temperature distribution change characteristics of the target; the centroid calculation method is a basic operation in computer vision, image processing and other fields, used to determine the position characteristics of the target. In geological disaster monitoring, the centroid calculation can extract the position of the target (such as pedestrians, animals, and rolling stones) through thermal imaging or image data, and then analyze its motion trajectory; the edge detection algorithm is a technology used in image processing to identify point sets (i.e., edges) with obvious brightness changes in images. These edges usually correspond to the contours, surface changes or texture differences of objects. First, the thermal imaging image acquired by the thermal imager 4 is preprocessed to segment the thermal imaging image of the area corresponding to the disaster location on the slope. The temperature gradient value of each pixel of the thermal imaging image is calculated by a gradient operator, such as the Sobel operator, to obtain the temperature distribution gradient. Since the acquired thermal imaging image is continuous, the thermal imaging image is a continuous frame number. The centroid calculation method is used to determine the target centroid coordinates of the thermal imaging image corresponding to each frame number, and according to the target centroid coordinates of the thermal imaging image corresponding to the adjacent frame number, the target centroid coordinate change data under the frame number and the adjacent frame number is determined, and the corresponding transformation time is determined. The centroid movement speed is determined based on the target's centroid coordinate change data and transformation time. An edge detection algorithm is then used to extract the target object's contour for each frame, and the contour's perimeter, area, shape descriptor, and frame-time are calculated. The contour morphological change rate includes the perimeter change rate, area change rate, and shape descriptor change rate. The perimeter change rate is determined by the ratio of the perimeter difference between adjacent frames to time, the area change rate is determined by the ratio of the area difference between adjacent frames to time, and the shape descriptor change rate is determined by the ratio of the shape feature difference between adjacent frames to time. Shape features can be represented by the contour's Fourier descriptor or Hu moment. The contour morphological change rate can be used with a support vector machine classification model to determine whether the target object's changes are regular, thereby determining whether it is a hazard. For example, the contour changes of a pedestrian exhibit periodic patterns, while those of an animal exhibit irregular patterns. When a hazard object slides, the contour changes exhibit a continuous, abnormal trend. Combined with temperature and centroid velocity, the target object's type can be determined. For example, a hazard object exhibits low temperature and high speed, enabling target classification and early warning.

[0031] Optionally, the object type includes the disaster object and the non-disaster object, and the inputting the temperature distribution gradient, the center of mass moving speed, and the contour morphology change rate into a support vector machine classification model to generate the object type of the target object includes: Respectively extracting the temperature feature vector of the temperature distribution gradient, the center of mass feature vector of the center of mass moving speed, and the contour feature vector of the contour morphology change rate, and inputting the temperature feature vector, the center of mass feature vector, and the contour feature vector into the support vector machine classification model; The support vector machine classification model solves the optimal hyperplane based on the constraint conditions and the objective function to generate the object category.

[0032] Specifically, the temperature feature vector, centroid feature vector and contour feature vector are input into the support vector machine classification model. The support vector machine classification model classifies the target object, which can be classified as a binary classification problem. That is, the goal of the support vector machine is to find an optimal hyperplane. The optimal hyperplane formula is w T x + b =0, where x is the target feature vector, namely the temperature feature vector, the centroid feature vector and the profile feature vector. The target feature vector is x =[ x 1, x 2, x 3], where x 1 represents the temperature eigenvector, x 2 represents the centroid eigenvector, x 3 represents the contour feature vector, w =[ w 1, w 2, w 3] is the weight vector of the hyperplane, w 1 is the weight of the temperature feature vector, w 2 is the weight of the centroid eigenvector, w 3 is the weight of the contour feature vector, T is the transposition operator, and b is the bias term. To find the optimal hyperplane, we can solve the objective function based on the constraints. The objective function aims to minimize the weighted sum of "structural risk" and "classification error". The constraints mean that while allowing for some sample classification errors, the basic correctness of the classification is guaranteed. By solving the objective function based on the constraints, we can obtain the optimal w and b in the optimal hyperplane formula, and for the new target feature vector x, we can output the formula f ( x )=sgn( w T x + b) to determine its category, where sgn is the sign function. Exemplarily, the objective function includes: ; in, Used to maximize the classification interval to improve the generalization ability of the model, Penalty term, C is the penalty function, is a slack variable used to control the tolerance of sample classification error, and N is the number of samples.

[0033] Constraints include: ; Among them, this constraint requires that each sample x i satisfy , ensuring that the function interval from the sample to the hyperplane is not less than , thereby ensuring the basic correctness of classification while allowing some sample classification errors. y i for x i The corresponding category label, disaster body y i 1, non-disaster body y i is -1, It is a slack variable used to allow some samples to be on the wrong side of the hyperplane to deal with nonlinear separable situations. “st” is the abbreviation of “subject to”, which means “subject to” and is used to limit the conditions that the variables in the optimization problem must satisfy.

[0034] Exemplarily, the specific steps of classifying the target object by the support vector machine classification model include: First, obtain the training data set through the Internet and set the category labels of the samples as: disaster body: y i 1. Non-disaster objects (pedestrians, animals): y i = -1, and the initial support vector machine classification model is trained by the training data set and category labels to obtain the weight w and bias term b in the optimal hyperplane formula, thereby obtaining a trained support vector machine classification model; Secondly, by performing vector extraction on the thermal imaging image obtained by the thermal imager 4, the target feature vector x is obtained, and the optimal hyperplane is calculated by the trained support vector machine classification model w T x + b The value of w T When x+b>0, that is yi is 1, the target object is judged to be a disaster object, when w T When x+b<0, that is y i If it is -1, the target object is judged to be a non-hazardous object.

[0035] Optionally, the non-disaster objects include pedestrians and animals, and the thermal imaging monitoring module is further used to extract a target centroid time series of the target object according to the centroid moving speed; Determine the Euclidean distance between each target element in the target centroid time series and each known element in the known centroid time series of each known type in the known sequence set, and construct a distance matrix; Determine the minimum cumulative distance between all elements in the distance matrix according to a dynamic programming algorithm to generate a DTW distance; According to the DTW distance and preset classification requirements, the target object is classified into the pedestrian, the animal, or the disaster object.

[0036] Specifically, Dynamic Time Warping (DTW) is an algorithm that calculates the optimal nonlinear alignment between two time series. Its core concept is to find the best matching path between the sequences by allowing the time axis to elastically expand and contract. Non-hazardous objects include pedestrians and animals. The thermal imaging monitoring module is also used to extract the target object's centroid time series based on its centroid speed. The dynamic programming algorithm is then used to determine the similarity between the two time series, for example, the similarity between the collected time series and a time series of a known type, thereby classifying the target object as a pedestrian, animal, or hazard. The distance formula can be used to determine the Euclidean distance, that is, the Euclidean distance between each target element in the target centroid time series and each known element in the known centroid time series of each known type in the known sequence set, and construct an m*n distance matrix, where m is the number of rows and n is the number of columns. Then, based on the dynamic programming algorithm, the minimum cumulative distance between all elements in the distance matrix is ​​determined to generate the DTW distance. Then, based on the minimum cumulative distance of all elements and the cumulative calculation formula group, the cumulative distance matrix is ​​determined to generate the DTW distance. Finally, based on the DTW distance and preset classification requirements, the target objects are classified as pedestrians, animals, or disaster objects, where the preset classification requirements include: When the DTW distance is less than 5, the target object is highly similar to the pedestrian feature sequence and is determined to be a pedestrian; When 5≤DTW distance≤10, the target object has a high similarity with the animal feature sequence and is determined to be an animal; When the DTW distance is greater than 10, the target object has the highest similarity with the characteristic sequence of the disaster body (such as the deformation body with low temperature and high speed movement) and is determined to be a disaster body.

[0037] Exemplarily, the distance formula includes: ; in, D(i,j) is the Euclidean distance, a i is the target centroid time series a Middle i target elements, b j For a time series with known centroid b Middle j known elements.

[0038] The cumulative calculation formula group includes: ; Among them, the formula group is used to calculate the cumulative distance matrix C(i,j) The unified recursive formula of , the cumulative distance matrix includes: , the cumulative distance matrix represents the distance from D (1,1) to D The minimum cumulative path of (m,n), that is, each C(i,j) It is necessary to comprehensively consider the minimum cumulative distance between the left, top and top left adjacent positions and the current D(i,j) The sum of the two is calculated from C(1,1)=D(1,1), and the matrix is ​​filled recursively in row and column order. C(m,n) That is, from D(1,1) to D(m,n) The minimum cumulative distance path value is obtained by gradually accumulating the minimum distance through dynamic programming, which is used to measure the similarity of two time series. That is, the final value obtained by the formula group is C (m,n) is the DTW distance. Exemplarily, the warning module is further configured to: when the object type obtained by the support vector machine classification model of the thermal imaging monitoring module is a disaster body, and the target object is classified as a disaster body according to the dynamic programming algorithm, that is, y i When it is 1 and the DTW distance is greater than 10, a disaster warning is generated.

[0039] The warning module is also used when the object type obtained by the support vector machine classification model is a disaster object, and the target object is classified as a pedestrian or an animal according to the dynamic programming algorithm. y i When the value is -1 and the DTW distance is less than 5 or 5≤DTW distance≤10, a command to stop generating slope disaster conditions is sent to the laser beam monitoring module.

[0040] In this embodiment, dual judgment is performed through the support vector machine classification model and the dynamic programming algorithm, which can greatly increase the accuracy of object classification, thereby improving the monitoring accuracy and early warning accuracy of geological disasters.

[0041] Optionally, the warning module is further configured to send an instruction to the laser beam monitoring module to stop generating the slope disaster situation when the target object is the pedestrian or the animal and the slope disaster situation is a disaster occurring on the slope.

[0042] Specifically, the warning module is also used when the target object is a pedestrian or an animal, that is, y i When it is -1 and the slope disaster situation is a slope disaster, an instruction to stop generating slope disaster situations is sent to the laser beam monitoring module. That is, the thermal imaging monitoring module determines that the laser beam of the laser beam monitoring module is blocked by pedestrians or animals, so that the laser beam monitoring module generates slope disaster information of the slope disaster situation. However, this information is inaccurate because the laser beam is blocked by pedestrians or animals, not by a geological disaster on the slope that causes the slope to move and block the laser beam. This is a false alarm phenomenon generated by the laser beam monitoring module, so it is necessary to send an instruction to stop generating slope disaster situations to the laser beam monitoring module to avoid false alarms.

[0043] Optionally, the intelligent monitoring system for slope geological disasters based on the linkage of thermal imaging and laser shooting also includes an audible and visual alarm, which is used to issue a corresponding alarm according to the disaster warning.

[0044] Specifically, the intelligent monitoring system for slope geological disasters based on the linkage of thermal imaging and laser shooting also includes an audible and visual alarm, which can be installed on roads and public places near the slope to issue corresponding alarms in time according to disaster warnings, so as to facilitate timely emergency measures to protect the safety of pedestrians and property.

[0045] Alternatively, as Figure 1 As shown, the intelligent monitoring system for slope geological disasters based on the linkage of thermal imaging and laser shooting also includes poles 1 respectively arranged on both sides of the slope monitoring area, and the laser transmitter 2, the laser receiver 3 and the thermal imager 4 are respectively arranged on the poles 1 on both sides of the slope monitoring area.

[0046] Specifically, the intelligent monitoring system for slope geological disasters based on the linkage of thermal imaging and laser shooting also includes poles 1 respectively arranged on both sides of the slope monitoring area. First, the base is cast with concrete, and rectangular or circular poles 1 are pre-embedded on the base. The number of bases and poles 1 and the number of laser emitters 2, laser receivers 3, and thermal imagers 4 are set correspondingly for installing laser emitters 2, laser receivers 3 and thermal imagers 4. The material of the pole 1, wind-resistant design, equipment lightning protection and grounding measures, etc. are comprehensively considered according to actual conditions. For example, the material can be selected as galvanized steel.

[0047] Alternatively, as Figure 1 As shown, the intelligent monitoring system for slope geological disasters based on the linkage of thermal imaging and laser shooting also includes a camera 6 arranged on the vertical pole 1 through a connecting arm 5.

[0048] Specifically, the intelligent monitoring system for slope geological disasters based on the linkage of thermal imaging and laser shooting also includes a camera 6 set on the vertical pole 1 through a connecting arm 5, and the camera 6 is communicatively connected to the power distribution data transceiver box 9 to transmit the monitoring information of the slope to the monitoring platform, so that the monitoring personnel can view the slope conditions and the disaster source conditions on the slope in real time through the monitoring platform when a disaster occurs.

[0049] Alternatively, as Figure 1 As shown, the intelligent monitoring system for slope geological disasters based on the linkage of thermal imaging and laser shooting also includes a power distribution data transceiver box 9 arranged on the vertical pole 1, and the power distribution data transceiver box 9 is respectively communicated with the laser transmitter 2, the laser receiver 3, the thermal imager 4, and the sound and light alarm.

[0050] Specifically, the intelligent monitoring system for slope geological disasters based on the linkage of thermal imaging and laser shooting also includes a power distribution data transceiver box 9 arranged on the pole 1. The power distribution data transceiver box 9 is respectively connected to the laser transmitter 2, the laser receiver 3, the thermal imager 4, and the sound and light alarm for transmitting various data between the laser transmitter 2, the laser receiver 3, the thermal imager 4, and the sound and light alarm.

[0051] Alternatively, as Figure 1 As shown, the intelligent monitoring system for slope geological disasters based on the linkage of thermal imaging and laser shooting also includes a renewable energy power generation device 8 arranged at the top of the vertical pole 1 through an equipment bracket 7, and the renewable energy power generation device 8 is electrically connected to the laser transmitter 2, the laser receiver 3, the thermal imager 4, the camera 6 and the power distribution data transceiver box 9 respectively.

[0052] Specifically, the intelligent monitoring system for slope geological disasters based on the linkage of thermal imaging and laser shooting also includes a renewable energy power generation device 8 arranged at the top of the vertical pole 1 through an equipment bracket 7, such as a solar panel or a wind power generation device. The renewable energy power generation device 8 converts renewable energy into electrical energy and supplies the laser transmitter 2, the laser receiver 3, the thermal imager 4, the camera 6 and the power distribution data transceiver box 9 for electrical connection, thereby achieving energy saving and environmental protection and reducing costs.

[0053] For example, during implementation, the laser beam monitoring module, thermal imaging monitoring module, and warning module, as the three core functional modules of the monitoring platform, operate in tandem. Information from the laser beam, thermal imaging, and video recording is communicated with the monitoring platform via the power distribution data transceiver box 9, ensuring real-time transmission of monitoring information. The monitoring platform can be located in a safe area and monitored by monitoring personnel on duty. When the thermal imaging monitoring module's support vector machine classification model identifies the target as a non-hazardous object, the warning module sends a termination warning instruction to the laser beam module. After the warning module sends the warning instruction to the laser beam module, the sound and light alarm immediately responds with a warning. The warning signal guides personnel and construction units at the bottom of the slope to evacuate urgently in real time.

[0054] Specifically, when the object type obtained by the support vector machine classification model of the thermal imaging monitoring module is a non-disaster object, that is, the laser beam of the laser beam monitoring module is blocked by a pedestrian or an animal, the warning module sends a termination warning instruction to the laser beam monitoring module; Specifically, when the target type obtained by the support vector machine classification model of the thermal imaging monitoring module is a disaster object, and the DTW distance of the dynamic programming algorithm is less than or equal to 10, it is determined to be a non-disaster object, and the warning module sends a termination warning instruction to the laser shooting module; Specifically, when the target type obtained by the support vector machine classification model of the thermal imaging monitoring module is a disaster body, and the DTW distance of the dynamic programming algorithm is greater than 10, it is judged to be a disaster body. The warning module determines that the target object is a disaster body through the dual verification mechanism of the support vector machine classification model of the thermal imaging monitoring module and the dynamic programming algorithm, and immediately sends an instruction to generate a slope disaster situation warning to the laser beam monitoring module, and the sound and light alarm responds to execute the warning response.

[0055] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware through a computer program. The program can be stored in a computer-readable storage medium. When executed, the program can include the processes in the above-described method embodiments. The storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM). In this application, the units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network elements. Some or all of these units can be selected based on actual needs to achieve the objectives of the embodiments of the present invention. Furthermore, the functional units in the various embodiments of the present invention can be integrated into a single processing unit, each unit can exist physically separately, or two or more units can be integrated into a single unit. These integrated units can be implemented in either hardware or software functional units.

[0056] Although the present invention is disclosed as above, the protection scope of the present invention is not limited thereto. Those skilled in the art may make various changes and modifications without departing from the spirit and scope of the present invention, and these changes and modifications will fall within the protection scope of the present invention.

Claims

1. An intelligent monitoring system for slope geological disasters based on thermal imaging and laser beaming, characterized in that: Including laser beam monitoring module, thermal imaging monitoring module and warning module; The laser beam monitoring module is used to determine the slope disaster situation based on the on-off state of the laser beam between the laser transmitter (2) and the laser receiver (3) respectively arranged on both sides of the slope monitoring area; The thermal imaging monitoring module is used to obtain a thermal imaging image of the slope monitoring area according to the thermal imager (4), and to extract the temperature distribution gradient, the center of mass moving speed and the contour morphology change rate of the target object in the slope monitoring area according to the thermal imaging image, and to input the temperature distribution gradient, the center of mass moving speed and the contour morphology change rate into a support vector machine classification model to generate the object type of the target object; The warning module is used to generate a disaster warning when the slope disaster situation is a slope disaster and the object type is a disaster body.

2. The intelligent monitoring system for slope geological disasters based on thermal imaging and laser beaming according to claim 1 is characterized in that: The thermal imaging image includes a thermal image of continuous frames, and the step of extracting the temperature distribution gradient, the center of mass moving speed, and the contour morphology change rate of the target object in the slope monitoring area based on the thermal imaging image includes: Determining the temperature gradient value of each pixel point of the thermal imaging image using a gradient operator according to the temperature data of the thermal imaging image, and generating the temperature distribution gradient according to the temperature gradient value of each pixel point; Determine the target center of mass coordinates of each frame in the thermal imaging image using a center of mass calculation method, and determine the center of mass moving speed based on the time corresponding to each target center of mass coordinate and the frame number; According to the thermal imaging image, an edge detection algorithm is used to extract the target contour of the target object for each of the frames, and the contour morphology change rate is determined according to the target contour and the time corresponding to the frames.

3. The intelligent monitoring system for slope geological disasters based on thermal imaging and laser beaming according to claim 1 is characterized in that: The object types include the disaster object and the non-disaster object, and the inputting of the temperature distribution gradient, the center of mass moving speed, and the contour morphology change rate into a support vector machine classification model to generate the object type of the target object includes: Respectively extracting the temperature feature vector of the temperature distribution gradient, the center of mass feature vector of the center of mass moving speed, and the contour feature vector of the contour morphology change rate, and inputting the temperature feature vector, the center of mass feature vector, and the contour feature vector into the support vector machine classification model; The support vector machine classification model solves the optimal hyperplane based on the constraint conditions and the objective function to generate the object category.

4. The intelligent monitoring system for slope geological disasters based on thermal imaging and laser beaming according to claim 3 is characterized in that: The non-disaster objects include pedestrians and animals, and the thermal imaging monitoring module is further used to extract the target center of mass time series of the target object according to the center of mass moving speed; Determine the Euclidean distance between each target element in the target centroid time series and each known element in the known centroid time series of each known type in the known sequence set, and construct a distance matrix; Determine the minimum cumulative distance between all elements in the distance matrix according to a dynamic programming algorithm to generate a DTW distance; According to the DTW distance and preset classification requirements, the target object is classified into the pedestrian, the animal, or the disaster object.

5. The intelligent monitoring system for slope geological disasters based on thermal imaging and laser beaming according to claim 4 is characterized in that: The warning module is further configured to send an instruction to the laser beam monitoring module to stop generating the slope disaster situation when the target object is the pedestrian or the animal and the slope disaster situation is a disaster occurring on the slope.

6. The intelligent monitoring system for slope geological disasters based on thermal imaging and laser beaming according to claim 1 is characterized in that: It also includes an audible and visual alarm, which is used to issue a corresponding alarm according to the disaster warning.

7. The intelligent monitoring system for slope geological disasters based on the linkage of thermal imaging and laser beaming according to any one of claims 1 to 6, characterized in that: It also includes poles (1) respectively arranged on both sides of the slope monitoring area, and the laser transmitter (2), the laser receiver (3) and the thermal imager (4) are respectively arranged on the poles (1) on both sides of the slope monitoring area.

8. The intelligent monitoring system for slope geological disasters based on thermal imaging and laser beaming according to claim 7 is characterized in that: It also includes a camera (6) arranged on the upright pole (1) via a connecting arm (5).

9. The intelligent monitoring system for slope geological disasters based on thermal imaging and laser beaming according to claim 8 is characterized in that: It also includes a power distribution data transceiver box (9) arranged on the pole (1), and the power distribution data transceiver box (9) is communicatively connected to the laser transmitter (2), the laser receiver (3), the thermal imager (4), and the sound and light alarm.

10. The intelligent monitoring system for slope geological disasters based on thermal imaging and laser beaming according to claim 9 is characterized in that: It also includes a renewable energy power generation device (8) arranged on the top of the pole (1) through an equipment bracket (7), and the renewable energy power generation device (8) is electrically connected to the laser transmitter (2), the laser receiver (3), the thermal imager (4), the camera (6) and the power distribution data transceiver box (9) respectively.

Images