Monitoring and early warning platform for unmanned operation area of port

Abstract

The invention relates to the technical field of port monitoring, and discloses a monitoring and early warning platform for an unmanned operation area of a port, which comprises an image acquisition module, an environmental data acquisition module, a model construction module, a monitoring and early warning module and an early warning display module. BIM is combined with a design drawing and geographic information to build a three-dimensional digital model, space coordinate points contain attribute information, a coordinate system is unified through a coordinate conversion algorithm, and an abnormal position can be accurately positioned; according to image early warning, the abnormal state of an object is judged through a gray difference value, the number of pixel points and distribution density, environment early warning is analyzed from two aspects of whether an environment parameter exceeds a preset range and whether a change rate exceeds a threshold value, and potential risks can be found in time; an early warning signal is transmitted to a monitoring center, and key information is recorded in combination with a three-dimensional model, so that quick response is facilitated.

Description

Technical Field

[0001] The present invention relates to the technical field of port monitoring, and in particular to a monitoring and early warning platform for an unmanned operation area of ​​a port. Background Art

[0002] In modern port operations, with the development of technology and the pursuit of efficiency and safety, the number of unmanned operation areas has gradually increased. These unmanned operation areas have significant advantages in improving port operation efficiency and reducing labor costs, but they also bring new challenges.

[0003] On the one hand, the equipment and cargo in the unmanned operation area of ​​the port are not under direct supervision, which poses a variety of potential risks. For example, equipment may fail due to high or low temperature, abnormal humidity may affect the quality of cargo storage, and excessive wind speed may damage port facilities. If the changes in these environmental factors cannot be monitored and warned in time, it may lead to serious economic losses and safety accidents. Traditional monitoring methods often rely on manual scheduled inspections or decentralized sensor data readings, which cannot achieve real-time and comprehensive environmental monitoring and make it difficult to detect these potential environmental risks in a timely manner.

[0004] On the other hand, in the unmanned operation area of ​​the port, abnormal conditions of objects may occur, such as the intrusion of unknown objects, abnormal displacement of cargo, or abnormal conditions of equipment. Due to the lack of effective real-time image monitoring and analysis methods, these abnormal conditions are difficult to be discovered and handled in a timely manner, which poses a threat to the safe operation of the port. Most of the current monitoring systems lack the ability to deeply analyze image data, and cannot accurately determine whether the state of an object is abnormal, nor can they quickly locate the location and type of abnormalities.

[0005] In addition, the existing port monitoring system is often isolated, and the data of each part cannot be effectively integrated. It is impossible to combine environmental data with image data for comprehensive analysis, and it is difficult to conduct comprehensive and accurate monitoring and early warning of the unmanned operation area of ​​the port as a whole. Therefore, there is an urgent need for a monitoring and early warning platform that can collect images and environmental data of the unmanned operation area of ​​the port in real time, and timely identify and warn potential risks through integrated analysis, so as to ensure the safe and stable operation of the unmanned operation area of ​​the port. Summary of the invention

[0006] The purpose of the present invention is to provide a monitoring and early warning platform for unmanned operation areas of ports, which solves the technical problems raised in the background technology.

[0007] The purpose of the present invention can be achieved through the following technical solutions: A monitoring and early warning platform for unmanned operation areas of ports, comprising: An image acquisition module is used to capture images at a fixed time interval T0 using a camera pre-installed in an unmanned operation area of ​​the port; Environmental data collection module, used to collect environmental data in real time using various sensors in the Internet of Things technology; Model building module, which is used to build a three-dimensional digital model of the port by using BIM technology and combining the port's design drawings and geographic information; The monitoring and early warning module is used to monitor unmanned operation areas in real time, automatically identify and warn of potential risks by analyzing images and the environment to determine whether there are abnormal conditions. The early warning display module is used to send the corresponding early warning signal to the port's monitoring center. The monitoring center records the time, location, and abnormality type of the early warning through a three-dimensional digital model.

[0008] As a further solution of the present invention, the camera's shooting field of view is set to Ω, and each pixel point in the field of view is marked as (N, M). At the same time, the captured image is converted into a grayscale image, and the grayscale value of each pixel point on the grayscale image is marked as H. (N,M) , N = 1, 2, ... n, M = 1, 2, ... m, m × n is the number of all pixels in the field of view; At the same time, the image sets taken at different time points are marked as {J t}, where t=1, 2, ...e, t represents the time node, and e represents the number of time nodes.

[0009] As a further solution of the present invention: wherein the environmental data includes a temperature parameter collected by a temperature sensor, a humidity parameter collected by a humidity sensor, and a wind speed parameter collected by a wind speed sensor; Then, the temperature parameters, humidity parameters, and wind speed parameters collected at all time nodes are sequentially combined into a temperature data sequence {T t}、Humidity data series {H t}、Wind speed data series {V t}, and its acquisition time interval is consistent with the image acquisition time interval, that is, T0.

[0010] As a further solution of the present invention: wherein the three-dimensional digital model contains a plurality of pre-set spatial coordinate points P d (x,y,z), and each spatial coordinate point P d (x, y, z) all contain corresponding attribute information, which includes location attributes and facility type.

[0011] As a further solution of the present invention: during the model building process, data from different sources are unified into the same three-dimensional coordinate system through a coordinate conversion algorithm; In the port, extract the coordinates in the world coordinate system and mark them as (x w ,y w ,z w ), and the coordinates converted to the camera coordinate system are marked as (x c ,y c ,z c ), the coordinate transformation formula is as follows: , Where R is the rotation matrix and T is the translation vector, which is used to convert the coordinates in the world coordinate system to the coordinates in the camera coordinate system.

[0012] As a further solution of the present invention: the image early warning analysis method is as follows: StepA1.1. An image collected in the normal state of the unmanned operation area of ​​the port is used as the standard image and is recorded as J s , and the corresponding grayscale image pixel grayscale value is H s(N,M) ,The standard image represents the benchmark of the position and state of ,non-anomalous objects; StepA1.2, from the image set {J t} select an image at a specified time node as the analysis image J t , whose gray value is H t(N,M) ; StepA1.3, through: H0 (N,M) =H t(N,M) -H s(N,M) Calculate the grayscale difference H0 of each pixel between the standard image and the analysis image (N,M) ; StepA1.4, extract the preset grayscale difference threshold TH; StepA1.5, when H0 (N,M) >TH, it is determined that the pixel is abnormal; Similarly, all pixels in the entire field of view are traversed and judged to obtain a set of all abnormal pixels; StepA1.6: Determine whether the state of the object is abnormal by analyzing the set of abnormal pixels.

[0013] As a further solution of the present invention: the method for determining the abnormal state of the object in Step A1.6 is as follows: StepA1.6.1. Extract the number of abnormal pixels in the set of corresponding abnormal pixels and mark them as NA. StepA1.6.2, divide the analysis image into several sub-areas; Then, the number of abnormal pixels in each sub-region is counted, and then the number is divided by the area of ​​the sub-region to obtain the distribution density; The formula is as follows: , Where j = 1, 2, ..., m0, m0 represents the number of sub-regions after the image is divided, na j represents the number of abnormal pixels in the jth sub-region, S j represents the area of ​​the sub-region, then ρ j is the distribution density of abnormal pixels in the jth sub-region; StepA1.6.3, compare the number of abnormal pixels NA with the maximum number of abnormal pixels NA0 set in advance under normal conditions, and compare the distribution density of abnormal pixels in each sub-region with the distribution density range of each sub-region under normal conditions [ρ j,min ,ρ j,max ] for comparison: When NA>NA0, and the distribution density of abnormal pixels in at least one sub-region is not within the distribution density range of the corresponding sub-region under normal conditions [ρ j,min ,ρ j,max ], it is determined that the object state is abnormal and a warning signal corresponding to the abnormal object state is generated.

[0014] As a further solution of the present invention: the environmental early warning analysis method is as follows: StepV2.1. For each temperature parameter T in the temperature data sequence t : Extract the normal temperature range preset according to port equipment and operations [T min ,T max ]; When T t <T min or T t >T max When , the temperature at the corresponding time node is judged to be abnormal; Step V2.2, for each humidity parameter H in the humidity data sequence t : Extract the normal humidity range [H min ,H max ]; When H t <H min or H t >H max When , the humidity at the corresponding time node is judged to be abnormal; Step V2.3, for each wind speed parameter V in the wind speed data sequence t： Extract the normal wind speed range preset according to port equipment and operations [V min ,V max ]; When V t <V min or V t >V max When , the wind speed at the corresponding time node is judged to be abnormal; StepV2.4: At the corresponding time node, when any of the judgment results from StepV2.1 to StepV2.3 is abnormal, a corresponding environmental abnormality warning signal is generated.

[0015] As a further solution of the present invention: the environmental early warning analysis method is also as follows: StepA2.1, for the temperature data series: According to the time trend, calculate the difference between the temperature parameters at each adjacent time node and the ratio of the difference to the collection time interval T0, then calculate the average value of all the corresponding ratios and record the average value as the temperature change rate; The formula is as follows: , Where TBL is the temperature change rate; StepA2.2, for humidity data series: According to the time trend, calculate the difference between the humidity parameters at each adjacent time node, and the ratio of the difference to the collection time interval T0, then calculate the average value of all the corresponding ratios, and record the average value as the humidity change rate; The formula is as follows: , Where HBL is the humidity change rate; StepA2.3, for wind speed data sequence: According to the time trend, calculate the difference between the wind speed parameters at each adjacent time node, and the ratio of the difference to the collection time interval T0, then calculate the average value of all the corresponding ratios, and record the average value as the wind speed change rate; The formula is as follows: , Where VBL is the wind speed change rate; StepA2.4, compare the temperature change rate with the preset temperature change threshold, compare the humidity change rate with the preset humidity change threshold, and compare the wind speed change rate with the preset wind speed change threshold: When at least one of the temperature change rate is greater than the temperature change threshold, the humidity change rate is greater than the humidity change threshold, and the wind speed change rate is greater than the wind speed change threshold is true, it is judged that there is an abnormality in the port and a corresponding environmental abnormality warning signal is generated.

[0016] As a further solution of the present invention: wherein the abnormality type includes at least one of abnormal temperature, abnormal humidity, abnormal wind speed or abnormal object state.

[0017] Beneficial effects of the present invention: Comprehensive data collection ensures comprehensive monitoring: by pre-installing cameras in the unmanned operation area of ​​the port and taking images at a fixed time interval T0, a collection of images at different time nodes can be formed, providing rich materials for subsequent analysis and fully covering the visual information of the operation area. By using various sensors in the Internet of Things technology to collect environmental data in real time, and the collection time interval is consistent with image collection, it can fully reflect the changes in the port environment and realize real-time monitoring of environmental factors.

[0018] Advanced model building facilitates precise positioning: BIM technology is used to combine port design drawings and geographic information to build a three-dimensional digital model, in which each pre-set spatial coordinate point Pd (x, y, z) has attribute information such as location attributes and the type of facility it belongs to. During the model building process, data from different sources are unified into the same three-dimensional coordinate system through a coordinate conversion algorithm, which can accurately locate the location of abnormal situations in the port, facilitating rapid response by staff.

[0019] Image warning analysis: By converting the collected image into a grayscale image, taking the standard image under normal conditions as the benchmark, the grayscale difference of the pixels between the analysis image and the standard image is calculated and compared with the threshold to determine whether the pixel is abnormal. By further analyzing the number and distribution density of abnormal pixels and other information, it is possible to accurately determine whether the state of the object is abnormal, and effectively identify the potential risks brought about by changes in the state of objects in the unmanned operation area of ​​the port.

[0020] Environmental early warning analysis: On the one hand, for the temperature, humidity and wind speed data sequences, according to the preset normal range of port equipment and operations, determine whether the environmental parameters at each time node are abnormal; on the other hand, calculate the temperature, humidity and wind speed change rate and compare them with the corresponding thresholds, and conduct early warning analysis on environmental factors from both static and dynamic perspectives, so as to timely discover the risks that may be caused by environmental abnormalities, whether it is sudden environmental parameter abnormalities or gradually changing and accumulated environmental abnormalities.

[0021] Efficient early warning display enables rapid response: The early warning display module can send the corresponding early warning signal to the port monitoring center. The monitoring center can combine with the three-dimensional digital model to clearly record key information such as the time, location, and abnormality type of the early warning, so that the staff can quickly understand the overall picture of the abnormal situation and take timely response measures to ensure the safety and stability of the unmanned operation area of ​​the port. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The present invention will be further described below in conjunction with the accompanying drawings.

[0023] Figure 1 The system block diagram of the monitoring and early warning platform for unmanned operation areas of ports according to the present invention.

[0024] Figure 2 The present invention is a flow chart of a monitoring and early warning module in a monitoring and early warning platform for an unmanned operation area of ​​a port. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] Embodiment 1 See also Figure 1 and Figure 2 As shown, the present invention is a monitoring and early warning platform for unmanned operation areas of ports, comprising: An image acquisition module is used to capture images at a fixed time interval T0 using a camera pre-installed in an unmanned operation area of ​​the port; The camera’s field of view is set to Ω, and each pixel in the field of view is marked as (N, M). The captured image is converted into a grayscale image, and the grayscale value of each pixel on the grayscale image is marked as H. (N,M) , N = 1, 2, ... n, M = 1, 2, ... m, m × n is the number of all pixels in the field of view; At the same time, the image sets taken at different time points are marked as {J t}, where t=1, 2, ...e, t represents the time node, and e represents the number of time nodes; Environmental data collection module, used to collect environmental data in real time using various sensors in the Internet of Things technology; The environmental data includes temperature parameters collected by a temperature sensor, humidity parameters collected by a humidity sensor, and wind speed parameters collected by a wind speed sensor; Then, the temperature parameters, humidity parameters, and wind speed parameters collected at all time nodes are sequentially combined into a temperature data sequence {T t}、Humidity data series {H t}、Wind speed data series {V t}, and its acquisition time interval is consistent with the image acquisition time interval, that is, T0; Model building module, which is used to build a three-dimensional digital model of the port by using BIM technology and combining the port's design drawings and geographic information; The three-dimensional digital model contains several pre-set spatial coordinate points P d (x,y,z), and each spatial coordinate point P d (x, y, z) all contain corresponding attribute information, which includes location attributes and the type of facility to which it belongs; In the process of model building, the data from different sources are unified into the same three-dimensional coordinate system through the coordinate transformation algorithm; In the port, extract the coordinates in the world coordinate system and mark them as (x w ,y w ,z w ), and the coordinates converted to the camera coordinate system are marked as (x c ,y c ,z c ), the coordinate transformation formula is as follows: , In the formula, R is the rotation matrix and T is the translation vector, which is used to convert the coordinates in the world coordinate system into the coordinates in the camera coordinate system, so as to achieve accurate correspondence between the model and the collected data; The "1" in the coordinate transformation formula is part of the homogeneous coordinate representation. For a spatial coordinate point (x c ,y c ,z c ), which is expressed in homogeneous coordinates as (x c ,y c ,z c ,1), “1” is used to get the new coordinates (x c ,y c ,z c ) and then convert the homogeneous coordinates (x c ,y c ,z c ,1) Convert back to regular 3D coordinates; The monitoring and early warning module is used to monitor unmanned operation areas in real time, automatically identify and warn of potential risks by analyzing the early warning of images and environmental data to determine whether there are abnormal situations; The specific method is as follows: StepA1: Image warning analysis: StepA1.1. An image collected in the normal state of the unmanned operation area of ​​the port is used as the standard image and is recorded as J s , and the corresponding grayscale image pixel grayscale value is H s(N,M) ,The standard image represents the benchmark of the position and state of ,non-anomalous objects; StepA1.2, from the image set {J t} select an image at a specified time node as the analysis image J t , whose gray value is H t(N,M) ; StepA1.3, through: H0 (N,M) =H t(N,M) -H s(N,M) Calculate the grayscale difference H0 of each pixel between the standard image and the analysis image (N,M) ; StepA1.4, extract the preset grayscale difference threshold TH; The threshold is obtained by analyzing and experimenting with a large amount of image data under normal and abnormal conditions, and is used to distinguish between grayscale changes caused by changes in the position or state of an object and grayscale changes caused by factors such as normal ambient lighting; StepA1.5, when H0 (N,M) >TH, it is determined that the pixel is abnormal; Similarly, all pixels in the entire field of view are traversed and judged to obtain a set of all abnormal pixels; StepA1.6, determine whether the state of the object is abnormal by analyzing the abnormal pixel set; The specific method is as follows: StepA1.6.1. Extract the number of abnormal pixels in the set of corresponding abnormal pixels and mark them as NA. StepA1.6.2, divide the analysis image into several sub-areas; Then, the number of abnormal pixels in each sub-region is counted, and then the number is divided by the area of ​​the sub-region to obtain the distribution density; The formula is as follows: , Where j = 1, 2, ..., m0, m0 represents the number of sub-regions after the image is divided, na j represents the number of abnormal pixels in the jth sub-region, S j represents the area of ​​the sub-region, then ρ j is the distribution density of abnormal pixels in the jth sub-region; In this embodiment, by analyzing the distribution density of each sub-area, the abnormal distribution of the surface of the object can be understood. If the distribution is relatively uniform under normal conditions, but the local density is too high or too low at present, it may indicate that the state of the object is abnormal. StepA1.6.3, compare the number of abnormal pixels NA with the maximum number of abnormal pixels NA0 set in advance under normal conditions, and compare the distribution density of abnormal pixels in each sub-region with the distribution density range of each sub-region under normal conditions [ρ j,min ,ρ j,max ] for comparison: When NA>NA0, and the distribution density of abnormal pixels in at least one sub-region is not within the distribution density range of the corresponding sub-region under normal conditions [ρ j,min ,ρ j,max ], it is determined that the state of the object is abnormal, and a warning signal corresponding to the abnormal state of the object is generated; Step A2: Environmental early warning analysis According to the temperature data series {T t}、Humidity data series {H t}、Wind speed data series {V t}, analyze whether the port environment is abnormal; Environmental early warning analysis methods are as follows: StepV2.1. For each temperature parameter T in the temperature data sequence t : Extract the normal temperature range preset according to port equipment and operations [T min ,T max ]; When T t <T min or T t >T max When , the temperature at the corresponding time node is judged to be abnormal; Step V2.2, for each humidity parameter H in the humidity data sequence t : Extract the normal humidity range [H min ,H max ]; When H t <H min or Ht >H max When , the humidity at the corresponding time node is judged to be abnormal; Step V2.3, for each wind speed parameter V in the wind speed data sequence t： Extract the normal wind speed range preset according to port equipment and operations [V min ,V max ]; When V t <V min or V t >V max When , the wind speed at the corresponding time node is judged to be abnormal; StepV2.4: At the corresponding time point, when any of the judgment results from StepV2.1 to StepV2.3 is abnormal, a corresponding environmental abnormality warning signal is generated; The early warning display module is used to send the corresponding early warning signal to the port's monitoring center. The monitoring center records the time, location, and abnormality type of the early warning through a three-dimensional digital model, and then activates the corresponding emergency plan according to the abnormality type. At the same time, staff are arranged to go to the abnormal area for on-site inspection and confirmation. The staff carry portable detection equipment to review the abnormal situation and promptly feedback the on-site situation to the monitoring center. The monitoring center adjusts the emergency plan or takes further measures based on the feedback information to ensure the safety and normal operation of the unmanned operation area of ​​the port; The abnormality type includes at least one of abnormal temperature, abnormal humidity, abnormal wind speed or abnormal object state, and the detection equipment includes a thermometer, a hygrometer, and an anemometer; The emergency plan includes: If the temperature is abnormal and exceeds the upper limit of the equipment's allowed high temperature, you may need to start cooling equipment, such as a water spray cooling system, ventilation equipment, etc., and check whether related equipment has overheating faults; If the wind speed is abnormal and may affect the safety of port equipment or the stability of cargo stacking, wind protection measures need to be taken, such as strengthening cargo lashings, suspending high-altitude operations, etc.

[0027] In this embodiment, the image acquisition module regularly captures the image of the unmanned operation area of ​​the port and converts it into a grayscale image for detailed marking, and the environmental data acquisition module synchronously collects temperature, humidity, and wind speed data. The two have the same collection time interval, which provides rich and synchronous information for subsequent monitoring and early warning, and can more accurately grasp the regional conditions. The BIM technology is used to combine the port design and geographic information to build a three-dimensional digital model, and the data coordinate system is unified through the coordinate conversion algorithm. This makes the model correspond accurately to the collected data, facilitates accurate positioning and correlation of data in the analysis, and enhances the spatial analysis ability, such as accurately determining the position of the object in the port space. First, the standard image is determined as the benchmark, the grayscale difference between the pixel points of the image and the standard image is calculated and analyzed, and the pixel points are judged to be abnormal in combination with the threshold, and then the abnormal pixel point set is determined. The state of the object is also comprehensively judged by analyzing the number of abnormal pixels, dividing the image sub-area to calculate the distribution density, etc. This multi-level method can accurately identify the abnormal position and state of the object and improve the monitoring accuracy. For the temperature, humidity, and wind speed data sequences, the parameters of each time node are judged to be abnormal according to the preset normal range, and an early warning signal is generated if any parameter is abnormal. Comprehensively ensure that the environmental conditions are normal to avoid adverse effects on port equipment and operations. The early warning display module sends a signal to the monitoring center, which records key information based on the 3D model, activates the emergency plan, and arranges personnel to review abnormal situations with equipment and provide feedback. Timely response, accurate judgment, and effective handling of abnormalities ensure the safety and normal operation of the unmanned operation area of ​​the port.

[0028] Embodiment 2 As the second embodiment of the present invention, when the present application is implemented, compared with the first embodiment, the difference between the technical solution of the present embodiment and the first embodiment is that in the present embodiment, the environmental early warning analysis method is also as follows: StepA2.1, for the temperature data series: According to the time trend, calculate the difference between the temperature parameters at each adjacent time node and the ratio of the difference to the collection time interval T0, then calculate the average value of all the corresponding ratios and record the average value as the temperature change rate; The formula is as follows: , Where TBL is the temperature change rate; StepA2.2, for humidity data series: According to the time trend, calculate the difference between the humidity parameters at each adjacent time node, and the ratio of the difference to the collection time interval T0, then calculate the average value of all the corresponding ratios, and record the average value as the humidity change rate; The formula is as follows: , Where HBL is the humidity change rate; StepA2.3, for wind speed data sequence: According to the time trend, calculate the difference between the wind speed parameters at each adjacent time node, and the ratio of the difference to the collection time interval T0, then calculate the average value of all the corresponding ratios, and record the average value as the wind speed change rate; The formula is as follows: , Where VBL is the wind speed change rate; StepA2.4, compare the temperature change rate with the preset temperature change threshold, compare the humidity change rate with the preset humidity change threshold, and compare the wind speed change rate with the preset wind speed change threshold: When at least one of the temperature change rate is greater than the temperature change threshold, the humidity change rate is greater than the humidity change threshold, and the wind speed change rate is greater than the wind speed change threshold, it is judged that there is an abnormality in the port, which may affect the port facilities and operation safety, and a corresponding environmental abnormality warning signal is generated.

[0029] Based on the environmental warning analysis in Example 1, this embodiment further calculates the ratio of the difference between the parameters at adjacent time nodes in the temperature, humidity, and wind speed data sequence to the collection time interval according to the time trend, and takes the average value to obtain the temperature change rate, humidity change rate, and wind speed change rate. By comparing these change rates with the corresponding preset thresholds, it is determined whether there is an abnormality in the port. This analysis method not only focuses on whether the absolute value of the environmental parameters at each time node is abnormal, but also considers the changes of the environmental parameters over time. It can more keenly capture the dynamic change trend of the environment, discover potential abnormal situations that may affect port facilities and operational safety in advance, and further improve the comprehensiveness and accuracy of the environmental warning analysis.

[0030] Embodiment 3 As the third embodiment of the present invention, when the present application is specifically implemented, compared with the first and second embodiments, the technical solution of this embodiment is to combine the solutions of the first and second embodiments mentioned above for implementation.

[0031] This embodiment combines the solutions of embodiment one and embodiment two, and can enjoy the advantages of embodiment one, such as comprehensive data collection, accurate model construction, detailed image warning analysis, comprehensive environmental warning analysis, and effective warning display and emergency treatment, and can also combine the advantages of embodiment two in analyzing the rate of change of environmental parameters, to achieve more comprehensive, in-depth and accurate monitoring and warning of the unmanned operation area of ​​the port. By combining the characteristics of the two solutions, it can play a stronger role in ensuring the safety and normal operation of the unmanned operation area of ​​the port, and minimize the risks caused by various abnormal situations.

[0032] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0033] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A monitoring and early warning platform for unmanned operation areas in ports, characterized in that: include: An image acquisition module is used to capture images at fixed time intervals using a camera pre-installed in an unmanned operation area of ​​the port; Environmental data collection module, used to collect environmental data in real time using various sensors in the Internet of Things technology; Model building module, which is used to build a three-dimensional digital model of the port by using BIM technology and combining the port's design drawings and geographic information; The monitoring and early warning module is used to monitor unmanned operation areas in real time, automatically identify and warn of potential risks by analyzing images and the environment to determine whether there are abnormal conditions. The early warning display module is used to send the corresponding early warning signal to the port's monitoring center. The monitoring center records the time, location, and abnormality type of the early warning through a three-dimensional digital model.

2. A monitoring and early warning platform for unmanned operation areas in ports according to claim 1, characterized in that: The image warning analysis method is as follows: StepA1.

1. An image collected in the normal state of the unmanned operation area of ​​the port is used as the standard image and is recorded as J s , and the corresponding grayscale image pixel grayscale value is H s(N,M) ,The standard image represents the benchmark of the position and state of ,non-anomalous objects; StepA1.2, from the image set {J t } select an image at a specified time node as the analysis image J t , whose gray value is H t(N,M) ; StepA1.3, through: H0 (N,M) =H t(N,M) -H s(N,M) Calculate the grayscale difference H0 of each pixel between the standard image and the analysis image (N,M) ; StepA1.4, extract the preset grayscale difference threshold TH; StepA1.5, when H0 (N,M) >TH, it is determined that the pixel is abnormal; Similarly, all pixels in the entire field of view are traversed and judged to obtain a set of all abnormal pixels; StepA1.6: Determine whether the state of the object is abnormal by analyzing the set of abnormal pixels.

3. The monitoring and early warning platform for unmanned operation areas of ports according to claim 2 is characterized in that: The method for judging abnormal state of objects in StepA1.6 is as follows: StepA1.6.

1. Extract the number of abnormal pixels in the set of corresponding abnormal pixels and mark them as NA. StepA1.6.2, divide the analysis image into several sub-areas; Then, the number of abnormal pixels in each sub-region is counted and then divided by the area of ​​the sub-region to obtain the distribution density; StepA1.6.3, compare the number of abnormal pixels NA with the maximum number of abnormal pixels NA0 that is preset under normal conditions, and compare the distribution density of abnormal pixels in each sub-region with the distribution density range of each sub-region under normal conditions: When NA>NA0, and the distribution density of abnormal pixels in at least one sub-region is not within the distribution density range of the corresponding sub-region under normal conditions, it is determined that the object state is abnormal, and a warning signal corresponding to the abnormal object state is generated.

4. The monitoring and early warning platform for unmanned port operation areas according to claim 1 is characterized in that: Environmental early warning analysis methods are as follows: StepV2.

1. For each temperature parameter T in the temperature data sequence t : Extract the normal temperature range preset according to port equipment and operations [T min ,T max ]; When T t <T min or T t >T max When , the temperature at the corresponding time node is judged to be abnormal; Step V2.2, for each humidity parameter H in the humidity data sequence t : Extract the normal humidity range [H min ,H max ]; When H t <H min or H t >H max When , the humidity at the corresponding time node is judged to be abnormal; Step V2.3, for each wind speed parameter V in the wind speed data sequence t : Extract the normal wind speed range preset according to port equipment and operations [V min ,V max ]; When V t <V min or V t >V max When , the wind speed at the corresponding time node is judged to be abnormal; StepV2.4: At the corresponding time node, when any of the judgment results from StepV2.1 to StepV2.3 is abnormal, a corresponding environmental abnormality warning signal is generated.

5. The monitoring and early warning platform for unmanned operation areas of ports according to claim 1 is characterized in that: Environmental early warning analysis methods are as follows: StepA2.1, for the temperature data series: According to the time trend, calculate the difference between the temperature parameters at each adjacent time node and the ratio of the difference to the collection time interval, then calculate the average value of all the corresponding ratios and record the average value as the temperature change rate; StepA2.2, for humidity data series: According to the time trend, calculate the difference between the humidity parameters at each adjacent time node, and the ratio of the difference to the collection time interval, then calculate the average value of all the corresponding ratios, and record the average value as the humidity change rate; StepA2.3, for wind speed data sequence: According to the time trend, calculate the difference between the wind speed parameters at each adjacent time node, and the ratio of the difference to the collection time interval, then calculate the average value of all the corresponding ratios, and record the average value as the wind speed change rate; StepA2.4, compare the temperature change rate with the preset temperature change threshold, compare the humidity change rate with the preset humidity change threshold, and compare the wind speed change rate with the preset wind speed change threshold: When at least one of the temperature change rate is greater than the temperature change threshold, the humidity change rate is greater than the humidity change threshold, and the wind speed change rate is greater than the wind speed change threshold is true, it is judged that there is an abnormality in the port and a corresponding environmental abnormality warning signal is generated.

6. The monitoring and early warning platform for unmanned port operation areas according to claim 1 is characterized in that: in, The camera's field of view is set to Ω, and each pixel in the field of view is marked as (N, M). At the same time, the captured image is converted into a grayscale image, and the grayscale value of each pixel on the grayscale image is marked as H. (N,M) , N = 1, 2, ... n, M = 1, 2, ... m, m × n is the number of all pixels in the field of view; At the same time, the image sets taken at different time points are marked as {J t }, where t=1, 2, ...e, t represents the time node, and e represents the number of time nodes.

7. The monitoring and early warning platform for unmanned port operation areas according to claim 1 is characterized in that: in, The environmental data includes temperature parameters collected by a temperature sensor, humidity parameters collected by a humidity sensor, and wind speed parameters collected by a wind speed sensor; Then, the temperature parameters, humidity parameters, and wind speed parameters collected at all time nodes are sequentially combined into a temperature data sequence {T t }、Humidity data series {H t }、Wind speed data series {V t }, and its acquisition time interval is consistent with the image acquisition time interval, that is, T0.

8. The monitoring and early warning platform for unmanned port operation areas according to claim 1 is characterized in that: in, The three-dimensional digital model contains a number of pre-set spatial coordinate points, and each spatial coordinate point contains corresponding attribute information, and the attribute information includes location attributes and the type of facility to which it belongs.

9. The monitoring and early warning platform for unmanned port operation areas according to claim 2 is characterized in that: During the model construction process, data from different sources are unified into the same three-dimensional coordinate system through coordinate transformation algorithms.

10. The monitoring and early warning platform for unmanned port operation areas according to claim 1 is characterized in that: in, The abnormality type includes at least one of abnormal temperature, abnormal humidity, abnormal wind speed, or abnormal object state.

Images