Safety early warning method and system based on port monitoring data analysis

Abstract

This invention discloses a safety early warning method and system based on port monitoring data analysis, relating to the field of port safety monitoring technology. The method identifies human figures and mobile work equipment in the land-based work area from port monitoring videos and maps them onto a land-based work area plan. Simultaneously, it acquires data on ship entry and exit and cargo loading / unloading in the port's water-based work area, determining the tonnage and cargo volume of each berthed ship to form a ship / cargo parameter group. The land-based work area plans corresponding to ship / cargo parameter groups with a similarity greater than or equal to preset values ​​are integrated and categorized, and the performance characteristics of the human figure and mobile equipment mapping points are analyzed to derive characteristic parameters. These characteristic parameters are then mapped back to the land-based work area plan to form a plan template for analyzing real-time port monitoring data and issuing safety early warnings based on the analysis results. The above technical solution of this invention achieves port safety early warning and improves the safety of port operations.

Description

Technical Field

[0001] This invention relates to the field of port safety monitoring technology, and in particular to a safety early warning method and system based on port monitoring data analysis. Background Technology

[0002] With the rapid development of global trade, ports, as important hubs of international trade, are receiving increasing attention for their safe, efficient, and environmentally friendly operation. However, traditional port monitoring methods are no longer sufficient to meet the needs of modern port operations. Problems such as the fragmentation and silos of multi-source monitoring data, low data utilization, delayed safety early warnings, and limited monitoring methods are becoming increasingly prominent. Therefore, there is an urgent need for a safety early warning method and system based on port monitoring data. Summary of the Invention

[0003] The purpose of this invention is to provide a method and system for timely safety early warning based on port monitoring data analysis.

[0004] This invention discloses a safety early warning method based on port monitoring data analysis, including:

[0005] The port surveillance video was acquired, and human body recognition technology and landmark recognition technology were used to identify human bodies and mobile work equipment in the port land work area. A land work area plan was set up for the port land work area. The identified human bodies were mapped onto the land work area plan as human body mapping points, and the identified mobile work equipment was mapped onto the land work area plan as mobile equipment mapping points.

[0006] Synchronously acquire vessel entry and exit data and cargo loading and unloading data of each vessel in the port's water work area, determine the tonnage parameters of each berthed vessel in the vessel entry and exit data, determine the cargo loading and unloading volume parameters in the cargo loading and unloading data, and record the combination of tonnage parameters and cargo loading and unloading volume parameters of each berthed vessel as the vessel cargo parameter group.

[0007] The land work area plan corresponding to the ship cargo parameter groups with a similarity greater than or equal to the preset value is integrated and classified. The human body mapping point performance characteristics and mobile equipment mapping point performance characteristics are analyzed on the integrated and classified land work area plan to determine the human body mapping point performance characteristics parameters and mobile equipment mapping point performance characteristics parameters.

[0008] Map the human body mapping point performance characteristics parameters and mobile equipment mapping point performance characteristics parameters corresponding to each category of ship cargo parameter group onto the land work area plan to obtain the land work area plan template.

[0009] The port's real-time monitoring data is analyzed using the land-based work area template, and safety warnings are issued based on the analysis results.

[0010] In some embodiments disclosed in this invention, the method for identifying human bodies and mobile work equipment in port land work areas using human body recognition technology and marker recognition technology includes:

[0011] Human body detection is performed using human body recognition technology, including edge detection, shape analysis, and motion detection of surveillance video images. This process identifies image regions in the surveillance video images that match human body characteristics and marks these regions.

[0012] The detection of mobile work equipment is carried out using marker recognition technology, including edge detection, shape analysis and motion detection of surveillance video images, to identify image regions in the surveillance video images that match the characteristics of the work equipment, and to mark the image regions that match the characteristics of the work equipment.

[0013] In some embodiments disclosed in this invention, a land-based work area plan is set for the port's land-based work area, and the method for mapping identified human bodies and mobile work equipment onto the land-based work area plan as mapping points includes:

[0014] Based on the port's design drawings, a plan of the land-based work area is constructed, and several core work areas are divided into the land-based work area plan. A coordinate system for the land-based work area plan is then established.

[0015] Configure an image coordinate system for each surveillance video image, determine the correspondence between the area captured by the surveillance video image and the land work area plan, and match the image coordinate system and the plan coordinate system accordingly;

[0016] Identify the human image region and the working equipment image region in the surveillance video image, and determine the center point of the first region of the human image region and the center point of the second region of the working equipment image region.

[0017] The position coordinates of the center point of the first area relative to the monitoring video image are converted into position coordinates on the land work area plan, and then mapped on the land work area plan as human body mapping points. The position coordinates of the center point of the second area relative to the monitoring video image are converted into position coordinates on the land work area plan, and then mapped on the land work area plan as mobile device mapping points.

[0018] In some embodiments disclosed in this invention, the method for determining the proximity between ship cargo parameter groups includes:

[0019] The tonnage parameters of ships at each berth in the port are determined, and the tonnage parameters are sorted according to the order between berths. The cargo loading and unloading volume parameters of each ship are then configured after the corresponding tonnage parameters to obtain the ship cargo parameter group.

[0020] Based on the chronological order of occurrence, the ship cargo parameter groups are sorted by time to obtain the ship cargo parameter group sequence;

[0021] Corresponding to the changes in tonnage parameters for each ship position in the ship cargo parameter group sequence, a tonnage change curve is constructed. For the changes in cargo loading and unloading volume parameters corresponding to each ship position, a cargo loading and unloading volume change curve is constructed. The tonnage change curve is analyzed to determine the first abrupt change segment in the tonnage change curve where the rate of change of tonnage parameters is greater than or equal to a preset value, and the midpoint of the first abrupt change segment is marked as the first abrupt change reference node. The cargo loading and unloading volume change curve is analyzed to determine the second abrupt change segment in the volume change curve where the rate of change of loading and unloading volume parameters is greater than or equal to a preset value, and the midpoint of the second abrupt change segment is marked as the second abrupt change reference node.

[0022] For the distance between the first mutation reference nodes, a first node distance sequence is constructed. For the distance between the second mutation reference nodes, a second node distance sequence is constructed. By comparing the symmetry between the first node distance sequences and the second node distance sequences, the corresponding tonnage change curves and cargo loading and unloading volume change curves are aligned, and the curve matching parameters between each corresponding curve are determined. Based on the curve matching parameters of each corresponding curve, the closeness between the ship cargo parameter groups is determined.

[0023] In some embodiments disclosed in this invention, the method for determining the curve matching parameters between corresponding curves includes:

[0024] Identify the abrupt change and non-abrupt change segments on the curve, and set a first weight coefficient for the abrupt change segments and a second weight coefficient for the non-abrupt change segments respectively.

[0025] For the longitudinal difference value of different position nodes of the curve, if the longitudinal difference value is less than or equal to the preset value, the corresponding position node is identified as a matching position node. Based on the ratio of the number of matching position nodes to the number of nodes of all positions in each segment, the sub-curve matching parameters of the segment are determined.

[0026] Based on the attention weight coefficient of each segment on the curve and the sub-curve matching parameters, the curve matching parameters between the curves are determined.

[0027] The expression for calculating the curve matching parameters is as follows:

[0028] ;

[0029] Where W is the curve matching parameter, This is a function to determine the matching parameters of the sub-curves, used to judge whether the matching parameters of the sub-curves meet the preset criteria. If they meet the preset criteria, then... Output 1 otherwise output 0. Let be the number of matching nodes corresponding to the i-th segment in the curve. Let be the number of all position nodes corresponding to the i-th segment in the curve, and n be the total number of abrupt and non-abrupt segments in the curve. Let be the attention weight coefficient for the i-th segment, and C be the sub-curve matching parameter matching adjustment constant.

[0030] In some embodiments disclosed in this invention, the method for determining the degree of closeness between ship cargo parameter sets based on the curve matching parameters of each corresponding curve includes:

[0031] For each curve, several sub-curve matching parameter intervals are set, and each sub-curve matching parameter interval is set with a corresponding sub-proximity degree. By determining the sub-curve matching parameter interval to which the sub-curve matching parameter of each curve belongs, the sub-proximity degree corresponding to each curve is determined. The sum of the sub-proximity degrees of all curves is calculated to obtain the proximity degree between the ship cargo parameter groups.

[0032] In some embodiments disclosed in this invention, the methods for analyzing the performance characteristics of human body mapping points and mobile equipment mapping points on integrated and categorized land work area plans include:

[0033] Establish a time reference line and analyze the performance status of the land work area plan at different time nodes on the time reference line. The analysis method includes randomly selecting several coordinates relative to the land work area plan and determining the number of human body mapping points and the number of mobile equipment mapping points within a preset range near each random coordinate. Calculate the average number of human body mapping points and the average number of mobile equipment mapping points for all random coordinates.

[0034] The number of human body mapping points at each random coordinate is determined as a multiple of the average number of human body mapping points. If the multiple of human body mapping points is greater than or equal to a preset value, the random coordinate is identified as a dense coordinate of human body mapping points. The number of mobile device mapping points at each random coordinate is determined as a multiple of the average number of mobile device mapping points. If the multiple of mobile device mapping points is greater than or equal to a preset value, the random coordinate is identified as a dense coordinate of mobile device mapping points.

[0035] The dense coordinates of human body mapping points and the corresponding number of human body mapping points are identified as the sub-human body mapping point performance characteristic parameters. The sub-human body mapping point performance characteristic parameters are sorted according to the time reference line to obtain the human body mapping point performance characteristic parameters. The combination of the dense coordinates of mobile device mapping points and the corresponding number of mobile device mapping points is identified as the sub-mobile device mapping point performance characteristic parameters. The sub-mobile device mapping point performance characteristic parameters are sorted according to the time reference line to obtain the mobile device mapping point performance characteristic parameters.

[0036] In some embodiments disclosed in this invention, the method for mapping human body mapping point characteristic parameters and mobile device mapping point characteristic parameters onto a land-based work area map includes:

[0037] For each time node of the time reference line, a land work area plan is constructed. Based on the dense coordinates of human body mapping points corresponding to different time nodes and the corresponding number of human body mapping points, several marker human body mapping points are set on the land work area plan, and the number of human body mapping points is recorded at the corresponding marker human body mapping points.

[0038] Based on the dense coordinates of mobile equipment mapping points at different time points and the corresponding number of mobile equipment mapping points, several marker mobile equipment mapping points are set on the land work area plan, and the number of mobile equipment mapping points is recorded at the corresponding marker mobile equipment mapping points to obtain the land work area plan template.

[0039] In some embodiments disclosed in this invention, a safety early warning system based on port monitoring data analysis is also disclosed, including:

[0040] The first module is used to acquire port surveillance video and use human body recognition technology and landmark object recognition technology to identify human bodies and mobile work equipment in the port land work area. A land work area plan is set for the port land work area. The identified human bodies are mapped onto the land work area plan as human body mapping points, and the identified mobile work equipment is mapped onto the land work area plan as mobile equipment mapping points.

[0041] The second module is used to synchronously acquire the ship entry and exit data of the port water work area and the cargo loading and unloading data of each ship, determine the tonnage parameters of each berthed ship in the ship entry and exit data, determine the cargo loading and unloading volume parameters of the cargo loading and unloading data, and record the combination of the tonnage parameters and cargo loading and unloading volume parameters of each berthed ship as the ship cargo parameter group.

[0042] The third module is used to integrate and classify the land work area plan corresponding to the ship cargo parameter groups that are closer to each other than the preset value, and to perform human body mapping point performance feature analysis and mobile equipment mapping point performance feature analysis on the integrated and classified land work area plan, and determine the human body mapping point performance feature parameters and mobile equipment mapping point performance feature parameters.

[0043] The fourth module is used to map the human body mapping point performance characteristics parameters and mobile equipment mapping point performance characteristics parameters corresponding to each category of ship cargo parameter group onto the land work area plan, so as to obtain the land work area plan template.

[0044] The fifth module is used to analyze real-time monitoring data of the port using the land work area template, and to issue safety warnings based on the analysis results.

[0045] This invention discloses a safety early warning method and system based on port monitoring data analysis, relating to the field of port safety monitoring technology. The method identifies human figures and mobile work equipment in the land-based work area from port monitoring videos and maps them onto a land-based work area plan. Simultaneously, it acquires data on ship entry and exit and cargo loading / unloading in the port's water-based work area, determining the tonnage and cargo volume of each berthed ship to form a ship / cargo parameter group. The land-based work area plans corresponding to ship / cargo parameter groups with a similarity greater than or equal to preset values ​​are integrated and categorized, and the performance characteristics of the human figure and mobile equipment mapping points are analyzed to derive characteristic parameters. These characteristic parameters are then mapped back to the land-based work area plan to form a plan template for analyzing real-time port monitoring data and issuing safety early warnings based on the analysis results. The above technical solution of this invention achieves port safety early warning and improves the safety of port operations.

[0046] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0047] Figure 1 This is a flowchart illustrating the steps of a safety early warning method based on port monitoring data analysis disclosed in an embodiment of the present invention. Detailed Implementation

[0048] The technical solution of the present invention will be further described below with reference to the accompanying drawings and embodiments.

[0049] The technical solution of the present invention will be clearly and completely described below with reference to the accompanying drawings and specific embodiments. It should be understood that the preferred embodiments described herein are only for illustration and explanation of the present invention and should not be construed as limiting the scope of protection of the present invention. Those skilled in the art can make some non-essential improvements and adjustments based on the following content of the present invention. In the present invention, unless otherwise expressly specified and limited, the technical terms used in the present invention should have the ordinary meaning understood by those skilled in the art.

[0050] Example:

[0051] The purpose of this invention is to provide a method and system for timely safety early warning based on port monitoring data analysis.

[0052] This invention discloses a safety early warning method based on port monitoring data analysis, see reference. Figure 1 ,include:

[0053] Step S100: Acquire port monitoring video, and use human body recognition technology and landmark object recognition technology to identify human bodies and mobile work equipment in the port land work area. A land work area plan is set for the port land work area. The identified human bodies are mapped onto the land work area plan as human body mapping points, and the identified mobile work equipment is mapped onto the land work area plan as mobile equipment mapping points.

[0054] This step primarily involves the acquisition and processing of port surveillance video. First, surveillance cameras installed throughout the port capture real-time video footage. Next, advanced human body recognition technology is used to accurately identify people in the video. This technology, typically based on deep learning algorithms, analyzes pixel information in video frames to identify the shape, movement, and other features of the human body, thus accurately marking its position within the video. Simultaneously, landmark object recognition technology is used to identify mobile work equipment (such as cranes and forklifts) in the port's land-based work area. These devices often have unique shapes and markings, allowing the recognition algorithm to easily distinguish them from other objects. The identified human and equipment information is then mapped onto a pre-defined land-based work area map, displayed as human and mobile equipment mapping points, providing foundational data support for subsequent safety warnings.

[0055] In some embodiments disclosed in this invention, the method for identifying human bodies and mobile work equipment in port land work areas using human body recognition technology and marker recognition technology includes:

[0056] Step S101: Human body detection is performed using human body recognition technology, including edge detection, shape analysis and motion detection of the surveillance video image, to determine the image region in the surveillance video image that matches human body characteristics, and to mark the image region that matches human body characteristics.

[0057] Step S102: Detect the mobile work equipment using marker recognition technology, including edge detection, shape analysis, and motion detection of the monitoring video image, determine the image region in the monitoring video image that matches the characteristics of the work equipment, and mark the image region that matches the characteristics of the work equipment.

[0058] In some embodiments disclosed in this invention, a land-based work area plan is set for the port's land-based work area, and the method for mapping identified human bodies and mobile work equipment onto the land-based work area plan as mapping points includes:

[0059] Step S103: Based on the port design drawings, construct a land work area plan, divide the land work area plan into several core work areas, and set a plan coordinate system for the land work area plan.

[0060] This step is fundamental to constructing the land-based work area plan. First, based on the port's design drawings, which typically contain detailed information such as the port's layout, facility locations, and dimensions, the plan serves as the accurate basis for construction. By carefully analyzing these drawings, the land-based work area plan can be constructed. On the plan, to further refine the work areas, several core work zones are defined, possibly based on function, equipment type, or workflow. Simultaneously, to ensure accurate positioning and analysis later, a coordinate system is established for the land-based work area plan.

[0061] Step S104: Configure an image coordinate system for each monitoring video image, determine the correspondence between the area captured by the monitoring video image and the land work area plan, and match the image coordinate system and the plan coordinate system accordingly.

[0062] This step is crucial for establishing the link between surveillance video images and the land-based work area plan. First, an image coordinate system is configured for each surveillance video image. This system is based on the pixel positions of the video images and describes the location of each pixel. Next, the correspondence between the area captured by the surveillance video images and the land-based work area plan needs to be determined. This is typically achieved through on-site surveys, measurements, or alignment using known landmarks. Finally, the image coordinate system and the plan coordinate system are matched. This process may involve coordinate transformations, scaling, and rotations to ensure that points in the image accurately correspond to points on the plan.

[0063] Step S105: Determine the human image region and the working equipment image region on the monitoring video image, and determine the first center point of the human image region and the second center point of the working equipment image region.

[0064] This step involves identifying and locating human figures and equipment in surveillance video images. First, image processing techniques (such as object detection and image segmentation) are used to determine the human figure image region and the equipment image region within the surveillance video image. These regions are sets of pixels in the image containing either a human figure or equipment. Then, to simplify subsequent processing, the center point of the first human figure image region and the center point of the second equipment image region are determined. These center points can be the centroid, geometric center, or representative points determined according to other rules; they represent the location of the entire region.

[0065] Step S106: Convert the position coordinates of the center point of the first area relative to the monitoring video image into position coordinates on the land work area plan, and map them on the land work area plan as human body mapping points. Convert the position coordinates of the center point of the second area relative to the monitoring video image into position coordinates on the land work area plan, and map them on the land work area plan as mobile device mapping points.

[0066] This step maps points in the surveillance video image to points on the land-based work area plan. First, the position coordinates of the center point of the first area (representing a human body) relative to the surveillance video image are converted into position coordinates on the land-based work area plan. This conversion process is based on the coordinate system correspondence established in step S104 and may involve coordinate transformation and calculation. Then, the human body is mapped onto the land-based work area plan as a human body mapping point, i.e., the location of the human body is marked on the plan. Similarly, the same coordinate transformation and mapping process is performed on the center point of the second area of ​​the work equipment image region, marking the location of the equipment on the land-based work area plan as a mobile device mapping point. In this way, the human body and mobile work equipment in the surveillance video image are mapped onto the land-based work area plan as mapping points.

[0067] Step S200: Simultaneously acquire the ship entry and exit data and cargo loading and unloading data of each ship in the port water work area, determine the tonnage parameters of each berthed ship in the ship entry and exit data, determine the cargo loading and unloading volume parameters of the cargo loading and unloading data, and record the combination of the tonnage parameters and cargo loading and unloading volume parameters of each berthed ship as the ship cargo parameter group.

[0068] This step focuses on acquiring and processing data on vessel entry and exit and cargo loading and unloading in the port's waterborne work area. Through the port's information management system, basic information such as vessel entry and exit times and tonnage can be obtained in real time. Simultaneously, the cargo loading and unloading record system records detailed cargo loading and unloading information for each vessel, including the type and quantity of cargo loaded and unloaded, and the loading and unloading time. This data is used to calculate the tonnage parameters and cargo volume parameters for each berthed vessel, forming a set of vessel and cargo parameters. These parameter sets not only reflect the vessel's transport capacity but also the port's workload and cargo handling capacity, providing crucial data for subsequent safety early warning systems.

[0069] In some embodiments disclosed in this invention, the method for determining the proximity between ship cargo parameter groups includes:

[0070] Step S201: Determine the tonnage parameters of the ships at each berth in the port, sort the tonnage parameters according to the order between berths, and configure the cargo loading and unloading volume parameters of each ship after the corresponding tonnage parameters to obtain the ship cargo parameter group.

[0071] This step aims to organize and process data on the tonnage and cargo handling volume of vessels at port berths. First, for each vessel at a port berth, its tonnage parameter is determined. This is typically one of the vessel's fundamental attributes, reflecting its carrying capacity. Then, these tonnage parameters are sorted according to the order of berths (e.g., from port entrance to exit, or according to a regulatory order). Next, the cargo handling volume parameter for each vessel is appended to its corresponding tonnage parameter, forming a vessel cargo parameter group that includes both tonnage and cargo handling volume. In this way, each vessel at a berth has a corresponding parameter group, facilitating subsequent analysis and processing.

[0072] Step S202: Based on the chronological order of occurrence, sort the ship cargo parameter groups by time to obtain the ship cargo parameter group sequence.

[0073] Step S203: For the change of tonnage parameter corresponding to each ship position in the ship cargo parameter group sequence, construct a tonnage change curve. For the change of cargo loading and unloading volume parameter corresponding to each ship position, construct a cargo loading and unloading volume change curve. Analyze the tonnage change curve to determine the first abrupt change segment in the tonnage change curve where the rate of change of tonnage parameter is greater than or equal to a preset value, and mark the midpoint of the first abrupt change segment as the first abrupt change reference node. Analyze the cargo loading and unloading volume change curve to determine the second abrupt change segment in the volume change curve where the rate of change of loading and unloading volume parameter is greater than or equal to a preset value, and mark the midpoint of the second abrupt change segment as the second abrupt change reference node.

[0074] Step S204: For the distance between the first mutation reference nodes, construct a first node distance sequence; for the distance between the second mutation reference nodes, construct a second node distance sequence; and by comparing the symmetry between the first node distance sequences and the second node distance sequences, align the corresponding tonnage change curves and cargo loading / unloading volume change curves, determine the curve matching parameters between each corresponding curve, and determine the closeness between the ship cargo parameter groups based on the curve matching parameters of each corresponding curve.

[0075] In some embodiments disclosed in this invention, the method for determining the curve matching parameters between corresponding curves includes:

[0076] Step S2041: Determine the mutation and non-mutation segments on the curve, and set a first attention weight coefficient for the mutation segments and a second attention weight coefficient for the non-mutation segments.

[0077] Step S2042: For the longitudinal difference values ​​of different position nodes of the curve, if the longitudinal difference value is less than or equal to the preset value, the corresponding position node is identified as a matching position node. Based on the ratio of the number of matching position nodes in each segment to the number of nodes of all position nodes, the sub-curve matching parameters of the segment are determined.

[0078] Step S2043: Based on the attention weight coefficient of each segment on the curve and the sub-curve matching parameters, determine the curve matching parameters between the curves.

[0079] The expression for calculating the curve matching parameters is as follows:

[0080] .

[0081] Where W is the curve matching parameter, This is a function to determine the matching parameters of the sub-curves, used to judge whether the matching parameters of the sub-curves meet the preset criteria. If they meet the preset criteria, then... Output 1 otherwise output 0. Let be the number of matching nodes corresponding to the i-th segment in the curve. Let be the number of all position nodes corresponding to the i-th segment in the curve, and n be the total number of abrupt and non-abrupt segments in the curve. Let be the attention weight coefficient for the i-th segment, and C be the sub-curve matching parameter matching adjustment constant.

[0082] In some embodiments disclosed in this invention, the method for determining the degree of closeness between ship cargo parameter sets based on the curve matching parameters of each corresponding curve includes:

[0083] Step S2044: For each curve, several sub-curve matching parameter intervals are set, and each sub-curve matching parameter interval is set with a corresponding sub-proximity degree. By determining the sub-curve matching parameter interval to which the sub-curve matching parameter of each curve belongs, the sub-proximity degree corresponding to each curve is determined. The sum of the sub-proximity degrees of all curves is calculated to obtain the proximity degree between the ship cargo parameter groups.

[0084] Step S300: Integrate and classify the land work area plan corresponding to the ship cargo parameter groups that are closer to each other than or equal to the preset value, and perform human body mapping point performance feature analysis and mobile equipment mapping point performance feature analysis on the integrated and classified land work area plan to determine the human body mapping point performance feature parameters and mobile equipment mapping point performance feature parameters.

[0085] The core of this step lies in clustering the ship cargo parameter groups and extracting features from the clustered land-based work area plan. First, based on the similarity of the ship cargo parameter groups (such as tonnage, loading / unloading volume, etc.), the parameter groups are clustered, with groups of ship cargo parameters whose similarity is greater than or equal to a preset value grouped together. Then, the performance characteristics of human mapping points and mobile equipment mapping points are analyzed on the land-based work area plan corresponding to each group. This analysis may include the density, distribution pattern, and movement trajectory of the mapping points, aiming to extract characteristic parameters that reflect the port's operational status. These characteristic parameters will provide input for subsequent safety early warning models.

[0086] In some embodiments disclosed in this invention, the methods for analyzing the performance characteristics of human body mapping points and mobile equipment mapping points on integrated and categorized land work area plans include:

[0087] Step S301: Establish a time reference line and analyze the performance status of the land work area plan corresponding to different time nodes on the time reference line. The analysis method includes randomly selecting several random coordinates relative to the land work area plan and determining the number of human body mapping points and the number of mobile equipment mapping points within a preset range near each random coordinate. The average number of human body mapping points and the average number of mobile equipment mapping points for all random coordinates are then calculated.

[0088] Step S302: Determine the multiple of the number of human body mapping points at each random coordinate compared to the average number of human body mapping points. If the multiple of human body mapping points is greater than or equal to a preset value, then the random coordinate is identified as a dense coordinate of human body mapping points. Determine the multiple of the number of mobile device mapping points at each random coordinate compared to the average number of mobile device mapping points. If the multiple of mobile device mapping points is greater than or equal to a preset value, then the random coordinate is identified as a dense coordinate of mobile device mapping points.

[0089] Step S303: The dense coordinates of human body mapping points and the corresponding number of human body mapping points are identified as sub-human body mapping point performance characteristic parameters, and the sub-human body mapping point performance characteristic parameters are sorted according to the time reference line to obtain human body mapping point performance characteristic parameters. The combination of dense coordinates of mobile device mapping points and the corresponding number of mobile device mapping points is identified as sub-mobile device mapping point performance characteristic parameters, and the sub-mobile device mapping point performance characteristic parameters are sorted according to the time reference line to obtain mobile device mapping point performance characteristic parameters.

[0090] Step S400: Map the human body mapping point performance characteristic parameters and mobile equipment mapping point performance characteristic parameters corresponding to each category of ship cargo parameter group onto the land work area plan to obtain the land work area plan template.

[0091] This step maps the feature parameters extracted in the previous step back onto the land-based work area plan, creating a plan template. Specifically, for each category of ship cargo parameter group, the corresponding human body mapping point characteristic parameters and mobile equipment mapping point characteristic parameters are graphically displayed on the land-based work area plan. These feature parameters may be represented by markers of different colors, shapes, or sizes, forming an intuitive plan template. These templates not only reflect the characteristics of the port under different working conditions but also provide a visual reference for subsequent safety early warning.

[0092] In some embodiments disclosed in this invention, the method for mapping human body mapping point characteristic parameters and mobile device mapping point characteristic parameters onto a land-based work area map includes:

[0093] Step S401: For each time node of the time reference line, a land work area plan is constructed. Based on the dense coordinates of human body mapping points corresponding to different time nodes and the corresponding number of human body mapping points, several marker human body mapping points are set on the land work area plan, and the number of human body mapping points is recorded at the corresponding marker human body mapping points.

[0094] Step S402: Based on the dense coordinates of mobile equipment mapping points corresponding to different time nodes and the corresponding number of mobile equipment mapping points, set several marker mobile equipment mapping points on the land work area plan, and record the number of mobile equipment mapping points at the corresponding marker mobile equipment mapping points to obtain the land work area plan template.

[0095] Step S500: Analyze the real-time monitoring data of the port using the land work area template, and issue a safety warning based on the analysis results.

[0096] This step involves analyzing the port's real-time monitoring data using the land-based work area plan template generated in the previous step, and then issuing safety warnings. Specifically, by comparing the real-time monitoring data with the plan template, anomalies or potential risks in the port's operational status can be detected promptly. For example, if the distribution of human or mobile equipment mapping points shown in the real-time monitoring data differs significantly from the plan template, it may indicate a safety hazard or decreased operational efficiency at the port. In this case, the system will trigger a safety warning mechanism, reminding relevant personnel to take timely intervention or adjustment measures to ensure the normal operation and safety of the port.

[0097] In some embodiments disclosed in this invention, a safety early warning system based on port monitoring data analysis is also disclosed, including:

[0098] The first module is used to acquire port surveillance video and use human body recognition technology and landmark object recognition technology to identify human bodies and mobile work equipment in the port land work area. A land work area plan is set for the port land work area. The identified human bodies are mapped onto the land work area plan as human body mapping points, and the identified mobile work equipment is mapped onto the land work area plan as mobile equipment mapping points.

[0099] The second module is used to synchronously acquire the ship entry and exit data of the port water work area and the cargo loading and unloading data of each ship, determine the tonnage parameters of each berthed ship in the ship entry and exit data, determine the cargo loading and unloading volume parameters of the cargo loading and unloading data, and record the combination of the tonnage parameters and cargo loading and unloading volume parameters of each berthed ship as the ship cargo parameter group.

[0100] The third module is used to integrate and classify the land work area plan corresponding to the ship cargo parameter groups that are closer to each other than the preset value, and to perform human body mapping point performance feature analysis and mobile equipment mapping point performance feature analysis on the integrated and classified land work area plan, and determine the human body mapping point performance feature parameters and mobile equipment mapping point performance feature parameters.

[0101] The fourth module is used to map the human body mapping point performance characteristics parameters and mobile equipment mapping point performance characteristics parameters corresponding to each category of ship cargo parameter group onto the land work area plan, so as to obtain the land work area plan template.

[0102] The fifth module is used to analyze real-time monitoring data of the port using the land work area template, and to issue safety warnings based on the analysis results.

[0103] This invention discloses a safety early warning method and system based on port monitoring data analysis, relating to the field of port safety monitoring technology. The method identifies human figures and mobile work equipment in the land-based work area from port monitoring videos and maps them onto a land-based work area plan. Simultaneously, it acquires data on ship entry and exit and cargo loading / unloading in the port's water-based work area, determining the tonnage and cargo volume of each berthed ship to form a ship / cargo parameter group. The land-based work area plans corresponding to ship / cargo parameter groups with a similarity greater than or equal to preset values ​​are integrated and categorized, and the performance characteristics of the human figure and mobile equipment mapping points are analyzed to derive characteristic parameters. These characteristic parameters are then mapped back to the land-based work area plan to form a plan template for analyzing real-time port monitoring data and issuing safety early warnings based on the analysis results. The above technical solution of this invention achieves port safety early warning and improves the safety of port operations.

[0104] Through the above description of the embodiments, those skilled in the art can clearly understand that the present invention can be implemented in hardware or by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solution of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) and includes several instructions to cause a computer device (such as a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0105] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the technical solutions of the present invention, and these modifications or equivalent substitutions cannot cause the modified technical solutions to deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. A safety early warning method based on port monitoring data analysis, characterized in that, include: The port surveillance video was acquired, and human body recognition technology and landmark recognition technology were used to identify human bodies and mobile work equipment in the port land work area. A land work area plan was set up for the port land work area. The identified human bodies were mapped onto the land work area plan as human body mapping points, and the identified mobile work equipment was mapped onto the land work area plan as mobile equipment mapping points. Synchronously acquire vessel entry and exit data and cargo loading and unloading data of each vessel in the port's water work area, determine the tonnage parameters of each berthed vessel in the vessel entry and exit data, determine the cargo loading and unloading volume parameters in the cargo loading and unloading data, and record the combination of tonnage parameters and cargo loading and unloading volume parameters of each berthed vessel as the vessel cargo parameter group. The land work area plan corresponding to the ship cargo parameter groups with a similarity greater than or equal to the preset value is integrated and classified. The human body mapping point performance characteristics and mobile equipment mapping point performance characteristics are analyzed on the integrated and classified land work area plan to determine the human body mapping point performance characteristics parameters and mobile equipment mapping point performance characteristics parameters. Map the human body mapping point performance characteristics parameters and mobile equipment mapping point performance characteristics parameters corresponding to each category of ship cargo parameter group onto the land work area plan to obtain the land work area plan template. The port's real-time monitoring data is analyzed using the land-based work area template, and safety warnings are issued based on the analysis results.

2. The safety early warning method based on port monitoring data analysis according to claim 1, characterized in that, Methods for identifying human bodies and mobile work equipment in port land-based work areas using human body recognition technology and marker recognition technology include: Human body detection is performed using human body recognition technology, including edge detection, shape analysis, and motion detection of surveillance video images. This process identifies image regions in the surveillance video images that match human body characteristics and marks these regions. The detection of mobile work equipment is carried out using marker recognition technology, including edge detection, shape analysis and motion detection of surveillance video images, to identify image regions in the surveillance video images that match the characteristics of the work equipment, and to mark the image regions that match the characteristics of the work equipment.

3. The safety early warning method based on port monitoring data analysis according to claim 2, characterized in that, For port land work areas, a land work area plan is established. Methods for mapping identified human figures and mobile work equipment onto the land work area plan as mapping points include: Based on the port's design drawings, a plan of the land-based work area is constructed, and several core work areas are divided into the land-based work area plan. A coordinate system for the land-based work area plan is then established. Configure an image coordinate system for each surveillance video image, determine the correspondence between the area captured by the surveillance video image and the land work area plan, and match the image coordinate system and the plan coordinate system accordingly; Identify the human image region and the working equipment image region in the surveillance video image, and determine the center point of the first region of the human image region and the center point of the second region of the working equipment image region. The position coordinates of the center point of the first area relative to the monitoring video image are converted into position coordinates on the land work area plan, and then mapped on the land work area plan as human body mapping points. The position coordinates of the center point of the second area relative to the monitoring video image are converted into position coordinates on the land work area plan, and then mapped on the land work area plan as mobile device mapping points.

4. The safety early warning method based on port monitoring data analysis according to claim 1, characterized in that, Methods for determining the proximity between ship cargo parameter groups include: The tonnage parameters of ships at each berth in the port are determined, and the tonnage parameters are sorted according to the order between berths. The cargo loading and unloading volume parameters of each ship are then configured after the corresponding tonnage parameters to obtain the ship cargo parameter group. Based on the chronological order of occurrence, the ship cargo parameter groups are sorted by time to obtain the ship cargo parameter group sequence; Corresponding to the changes in tonnage parameters for each ship position in the ship cargo parameter group sequence, a tonnage change curve is constructed. For the changes in cargo loading and unloading volume parameters corresponding to each ship position, a cargo loading and unloading volume change curve is constructed. The tonnage change curve is analyzed to determine the first abrupt change segment in the tonnage change curve where the rate of change of tonnage parameters is greater than or equal to a preset value, and the midpoint of the first abrupt change segment is marked as the first abrupt change reference node. The cargo loading and unloading volume change curve is analyzed to determine the second abrupt change segment in the volume change curve where the rate of change of loading and unloading volume parameters is greater than or equal to a preset value, and the midpoint of the second abrupt change segment is marked as the second abrupt change reference node. For the distance between the first mutation reference nodes, a first node distance sequence is constructed. For the distance between the second mutation reference nodes, a second node distance sequence is constructed. By comparing the symmetry between the first node distance sequences and the second node distance sequences, the corresponding tonnage change curves and cargo loading and unloading volume change curves are aligned, and the curve matching parameters between each corresponding curve are determined. Based on the curve matching parameters of each corresponding curve, the closeness between the ship cargo parameter groups is determined.

5. The safety early warning method based on port monitoring data analysis according to claim 4, characterized in that, Methods for determining the curve matching parameters between corresponding curves include: Identify the abrupt change and non-abrupt change segments on the curve, and set a first weight coefficient for the abrupt change segments and a second weight coefficient for the non-abrupt change segments respectively. For the longitudinal difference value of different position nodes of the curve, if the longitudinal difference value is less than or equal to the preset value, the corresponding position node is identified as a matching position node. Based on the ratio of the number of matching position nodes to the number of nodes of all positions in each segment, the sub-curve matching parameters of the segment are determined. Based on the attention weight coefficient of each segment on the curve and the sub-curve matching parameters, the curve matching parameters between the curves are determined. The expression for calculating the curve matching parameters is as follows: ； Where W is the curve matching parameter, This is a function to determine the matching parameters of the sub-curves, used to judge whether the matching parameters of the sub-curves meet the preset criteria. If they meet the preset criteria, then... Output 1 otherwise output 0. Let be the number of matching nodes corresponding to the i-th segment in the curve. Let be the number of all position nodes corresponding to the i-th segment in the curve, and n be the total number of abrupt and non-abrupt segments in the curve. Let be the attention weight coefficient for the i-th segment, and C be the sub-curve matching parameter matching adjustment constant.

6. The safety early warning method based on port monitoring data analysis according to claim 5, characterized in that, Methods for determining the degree of similarity between ship cargo parameter sets based on the curve matching parameters of each corresponding curve include: For each curve, several sub-curve matching parameter intervals are set, and each sub-curve matching parameter interval is set with a corresponding sub-proximity degree. By determining the sub-curve matching parameter interval to which the sub-curve matching parameter of each curve belongs, the sub-proximity degree corresponding to each curve is determined. The sum of the sub-proximity degrees of all curves is calculated to obtain the proximity degree between the ship cargo parameter groups.

7. The safety early warning method based on port monitoring data analysis according to claim 1, characterized in that, Methods for analyzing the characteristics of human body mapping points and mobile equipment mapping points on integrated and categorized land work area maps include: Establish a time reference line and analyze the performance status of the land work area plan at different time nodes on the time reference line. The analysis method includes randomly selecting several coordinates relative to the land work area plan and determining the number of human body mapping points and the number of mobile equipment mapping points within a preset range near each random coordinate. Calculate the average number of human body mapping points and the average number of mobile equipment mapping points for all random coordinates. The number of human body mapping points at each random coordinate is determined as a multiple of the average number of human body mapping points. If the multiple of human body mapping points is greater than or equal to a preset value, the random coordinate is identified as a dense coordinate of human body mapping points. The number of mobile device mapping points at each random coordinate is determined as a multiple of the average number of mobile device mapping points. If the multiple of mobile device mapping points is greater than or equal to a preset value, the random coordinate is identified as a dense coordinate of mobile device mapping points. The dense coordinates of human body mapping points and the corresponding number of human body mapping points are identified as the sub-human body mapping point performance characteristic parameters. The sub-human body mapping point performance characteristic parameters are sorted according to the time reference line to obtain the human body mapping point performance characteristic parameters. The combination of the dense coordinates of mobile device mapping points and the corresponding number of mobile device mapping points is identified as the sub-mobile device mapping point performance characteristic parameters. The sub-mobile device mapping point performance characteristic parameters are sorted according to the time reference line to obtain the mobile device mapping point performance characteristic parameters.

8. The safety early warning method based on port monitoring data analysis according to claim 7, characterized in that, Methods for mapping the characteristic parameters of human body mapping points and mobile device mapping points onto land-based work area maps include: For each time node of the time reference line, a land work area plan is constructed. Based on the dense coordinates of human body mapping points corresponding to different time nodes and the corresponding number of human body mapping points, several marker human body mapping points are set on the land work area plan, and the number of human body mapping points is recorded at the corresponding marker human body mapping points. Based on the dense coordinates of mobile equipment mapping points at different time points and the corresponding number of mobile equipment mapping points, several marker mobile equipment mapping points are set on the land work area plan, and the number of mobile equipment mapping points is recorded at the corresponding marker mobile equipment mapping points to obtain the land work area plan template.

9. A safety early warning system based on port monitoring data analysis, characterized in that, include: The first module is used to acquire port surveillance video and use human body recognition technology and landmark object recognition technology to identify human bodies and mobile work equipment in the port land work area. A land work area plan is set for the port land work area. The identified human bodies are mapped onto the land work area plan as human body mapping points, and the identified mobile work equipment is mapped onto the land work area plan as mobile equipment mapping points. The second module is used to synchronously acquire the ship entry and exit data and the cargo loading and unloading data of each ship in the port water work area, determine the tonnage parameters of each berthed ship in the ship entry and exit data, determine the cargo loading and unloading volume parameters of the cargo loading and unloading data, and record the combination of the tonnage parameters and cargo loading and unloading volume parameters of each berthed ship as the ship cargo parameter group. The third module is used to integrate and classify the land work area plan corresponding to the ship cargo parameter groups that are closer to each other than the preset value, and to perform human body mapping point performance feature analysis and mobile equipment mapping point performance feature analysis on the integrated and classified land work area plan, and determine the human body mapping point performance feature parameters and mobile equipment mapping point performance feature parameters. The fourth module is used to map the human body mapping point performance characteristics parameters and mobile equipment mapping point performance characteristics parameters corresponding to each category of ship cargo parameter group onto the land work area plan, so as to obtain the land work area plan template. The fifth module is used to analyze real-time monitoring data of the port using the land work area template, and to issue safety warnings based on the analysis results.

Images