Channel occupancy monitoring method and system

Abstract

The present invention discloses a channel occupancy monitoring method and system, which relates to the field of safety monitoring technology. The method includes collecting initial multidimensional data of a fire channel and performing preprocessing, mapping the multidimensional data into a spatial coordinate system to generate an initial three-dimensional model; comparing real-time multidimensional data with data in the initial three-dimensional model to identify changing occupied objects and generate a preliminary bounding box, and optimizing the detected occupied object boundaries. The present invention collects multidimensional data within a fire channel and maps this data into a spatial coordinate system to generate an initial three-dimensional model. Based on changes in the three-dimensional model, an object bounding box is generated and optimized to capture the object's rotation information, identify boundary mutation points, and correct discontinuous areas, thereby generating a bounding box that better conforms to the object's true form. The optimized bounding box reflects the object's precise outline, improves the system's recognition accuracy and stability in complex scenarios, and effectively reduces false alarm rates and latency.

Description

Technical Field

[0001] The present invention relates to the technical field of safety monitoring, and in particular to a channel occupancy monitoring method and system. Background Art

[0002] In recent years, with the continuous advancement of intelligent technology, channel monitoring technology has been widely used in various security and management application scenarios. In areas such as traffic management, personnel evacuation, and fire emergency response, monitoring channel occupancy is crucial to ensuring smooth passage. Traditional channel occupancy monitoring methods mainly rely on camera monitoring, using simple two-dimensional images to identify occupied objects. However, two-dimensional monitoring technology has significant limitations. For example, due to viewing angles, lighting conditions, and occlusion in complex scenes, it is difficult to accurately capture the three-dimensional form of objects and the space they occupy. In addition, traditional monitoring technologies often rely on manual intervention and have a low degree of automation, making it difficult to meet the real-time and response efficiency requirements of complex applications. Summary of the Invention

[0003] In view of the problems existing in the above-mentioned existing channel occupancy monitoring methods and systems, the present invention is proposed.

[0004] Therefore, the problem to be solved by the present invention is that two-dimensional monitoring technology is difficult to accurately capture the three-dimensional shape of an object and its occupied space. Traditional monitoring technology often relies on manual intervention and has a low degree of automation, resulting in real-time and response efficiency that are difficult to meet complex application requirements.

[0005] To solve the above technical problems, the present invention provides the following technical solutions: a channel occupancy monitoring method, which includes collecting initial multidimensional data of fire channels and preprocessing it, mapping the multidimensional data into a spatial coordinate system to generate an initial three-dimensional model; comparing the real-time multidimensional data with the data in the initial three-dimensional model to identify the changed occupied objects and generate a preliminary bounding box, and optimizing the detected occupied object boundaries; calculating the volume of the occupied objects based on the boundary detection results, and taking different control measures based on the volume calculation results.

[0006] As a preferred solution of the channel occupancy monitoring method described in the present invention, the collection of initial multidimensional data of the fire channel and preprocessing thereof refers to deploying RGB cameras, lidars and depth sensors in the fire channel to collect the color information, two-dimensional contours, three-dimensional point cloud data and depth maps of the initial objects in the fire channel, and preprocessing and time synchronization calibration of the collected multidimensional data.

[0007] As a preferred embodiment of the channel occupancy monitoring method of the present invention, the multidimensional data is mapped into a spatial coordinate system to generate an initial three-dimensional model, the depth map and point cloud data are mapped into a unified three-dimensional coordinate system, and the mapped depth map and point cloud data are combined to form the three-dimensional geometric shape of the object;

[0008] The color and two-dimensional boundary of each object are extracted by collecting the two-dimensional contours of the objects in real time. The two-dimensional contours generated by the RGB image and the depth map are combined to generate an initial three-dimensional model of the fire passage. After standardization, the three-dimensional model is used as the standard state of the fire passage without occupied objects.

[0009] As a preferred embodiment of the channel occupancy monitoring method of the present invention, the method of comparing real-time multidimensional data with data in the initial three-dimensional model to identify changed occupied objects and generate a preliminary bounding box refers to collecting real-time multidimensional data in the fire channel and preprocessing it, then comparing the real-time collected data with the initial three-dimensional model frame by frame, calculating the difference between the position, color and depth of each point and the corresponding point in the initial three-dimensional model through the ICP algorithm, comparing all points one by one, and weighted fusion of the obtained difference values ​​to obtain a comprehensive change index, setting a change threshold K, and marking areas with a change index greater than or equal to K as changed areas;

[0010] The Kmeans++ clustering algorithm is used to cluster the change points in the marked change area. The clustering data k is set according to the change area detected in real time. All marked change points are assigned to different cluster categories through iterative optimization. For each clustering result, a preliminary bounding box of the occupied object is generated.

[0011] As a preferred embodiment of the channel occupancy monitoring method of the present invention, the optimization of the detected occupied object boundary refers to detecting the object in the preliminary boundary box and calculating the rotation angle of each vertex of the object boundary. Identify the rotation information of an object:

[0012]

[0013] Where, is the distance between two boundary points in the y-axis direction, is the distance between two boundary points in the x-axis direction, and is the velocity of the object in the x and y directions, and is the acceleration of the object in the x and y directions, is the exponential decay coefficient, I(a) is the rotational inertia of the object, a is the angular velocity of the object, r is the rotation radius representing the distance of the object relative to the rotation axis, () is the inverse tangent function;

[0014] Mark the angular position of the rotating object according to the calculated angle information of the object boundary, and the angle change of each boundary vertex Perform calculations to identify angle mutation points:

[0015]

[0016] Where K(t-τ) is the Gaussian convolution kernel, is the angle of the i-th boundary point at time t, is the angle of the i+1th boundary point at time t, is the time derivative of the angle of the i-th boundary point, and is the boundary of the time interval, dτ is the small change in the integral variable τ;

[0017] Analyze the angle change of each mutation point. When the angle mutations of multiple adjacent vertices occur in the same area, there is discontinuity at the boundary of the area. Record each confirmed mutation point and discontinuous area.

[0018] The complex exponential coding formula is used to encode the rotation angle of each mutation point, and the angle information of the object boundary is converted into a smooth expression in the complex domain;

[0019] Adjust the angular frequency in real time according to the boundary characteristics of the object to control the smoothness of the encoding;

[0020] Recalculate and decode the rotation angle information using the inverse decoding formula of the complex exponential encoding;

[0021] Reconstruct the boundary segments based on the rotation angle of each vertex and the coordinates of the adjacent vertices;

[0022] After smoothness testing of the newly generated boundary segments, all boundary segments are reassembled to generate a complete object bounding box;

[0023] Perform pixel-level gradient analysis on the combined complete bounding box and use image gradient detection to identify discontinuous areas of the object boundary;

[0024] Set the gradient threshold W and mark the area with gradient value greater than or equal to W as the potential non-fitting phenomenon area. For the identified non-fitting phenomenon area, iteratively adjust the shape of the boundary through the active contour model;

[0025] Calculate the fit score S of the adjusted bounding box, evaluate the overlapping area between the bounding box and the true contour of the object, set the fit judgment threshold P, and if the fit score is greater than or equal to P, it means that the bounding box is optimized to high precision, then output the bounding box; if it is less than P, continue iterative optimization;

[0026] Use the dilation operation to expand the boundary, expand the original boundary points, and then use the erosion operation to gradually reduce the object boundary and remove the noise on the boundary to obtain the optimized bounding box.

[0027] As a preferred solution of the channel occupancy monitoring method described in the present invention, the method of calculating the volume of the occupied object based on the boundary detection results refers to dividing the three-dimensional contour of the occupied object into N triangular facets, calculating the area of ​​each triangle through the boundary points of the object, and calculating the total volume of the occupied object based on the area and height of each triangular facet, monitoring the changes of occupied objects in the fire channel in real time and adjusting the volume information of the occupied objects.

[0028] As a preferred embodiment of the channel occupancy monitoring method of the present invention, wherein: taking different control measures according to the volume calculation results refers to using an SVM model as a classification model to classify occupied objects into three violation levels as target labels of the model;

[0029] The target labels include minor violations, moderate violations, and severe violations;

[0030] The pre-processed historical object volume, position, and shape data are divided into training and test sets. The labeled training data set is used to train the SVM model. The SVM model parameters are optimized through cross-validation and grid search. After each training cycle, the model performance is evaluated using the test set. If there is no significant change in the verification difference after the training cycle, the model training is stopped. The trained SVM model is obtained and the real-time object volume, position, and shape data are input into the SVM model for classification to obtain the violation level of the occupied object.

[0031] If the occupied object is a minor violation, the first-level management measure will be triggered. A voice reminder will be issued through the speakers installed in the passage to notify on-site personnel to remove the occupied object in time. The relevant management personnel will be notified via SMS and app to handle the matter.

[0032] If the occupied object is a moderate violation, the secondary governance measures will be triggered, automatically marking and recording the image and video of the object, and sending the occupancy status to the management center, notifying security personnel and property personnel to go to the site and manually remove the occupied object;

[0033] If the occupied object is a serious violation, the third-level governance measures will be triggered, and a high-level alarm will be issued immediately to indicate serious occupation and notify the emergency management team to immediately deal with the object on site. If the fire escape is equipped with automatic cleaning equipment, a remote control command will be triggered to automatically clear the occupied object.

[0034] The high-level alarm includes sirens and red flashing lights;

[0035] After each level of governance measures is initiated, the status of the objects is continuously monitored and the removal status is regularly checked. The volume calculation results, governance measures and corresponding processing status of each time are stored in the database.

[0036] Another object of the present invention is to provide a channel occupancy monitoring system, which comprises:

[0037] A data acquisition module is used to collect multimodal data of the initial fire escape passage and generate an initial three-dimensional model after pre-processing the collected multimodal data;

[0038] The object recognition module is used to compare the changes in real-time multi-dimensional data and the initial three-dimensional model data to identify the occupied objects in the fire passage and generate the corresponding preliminary bounding boxes;

[0039] Boundary optimization module, used to optimize the bounding box of the occupied object to generate an optimized bounding box and perform real-time volume calculation of the occupied object;

[0040] The classification management module is used to classify occupied objects using the SVM model and then take different management measures.

[0041] A computer device comprises: a memory and a processor; the memory stores a computer program, and the processor implements the steps of a channel occupancy monitoring method when executing the computer program.

[0042] A computer-readable storage medium stores a computer program, which implements the steps of a channel occupancy monitoring method when executed by a processor.

[0043] The beneficial effects of the present invention are as follows: the present invention collects multidimensional data in the fire passage and maps these data to a spatial coordinate system to generate an initial three-dimensional model. Based on the changes in the three-dimensional model, the object bounding box is generated and optimized to capture the rotation information of the object, identify the mutation points of the boundary and correct the discontinuous areas, thereby generating a bounding box that is more in line with the true form of the object. The optimized bounding box reflects the precise outline of the object, improves the recognition accuracy and stability of the system in complex scenarios, and effectively reduces the false alarm rate and delay. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0045] Figure 1 Schematic diagram of the flow of the channel occupancy monitoring method.

[0046] Figure 2 Schematic diagram of the operation flow of the channel occupancy monitoring method.

[0047] Figure 3 This is a structural diagram of the channel occupancy monitoring system. DETAILED DESCRIPTION

[0048] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0049] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0050] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it constitute a separate or selective embodiment that is mutually exclusive with other embodiments.

[0051] Example 1, with reference to Figure 1 and Figure 2 , which is the first embodiment of the present invention, provides a channel occupancy monitoring method, the channel occupancy monitoring method includes:

[0052] S1. Collect and pre-process the initial multi-dimensional data of the fire escape, and map the multi-dimensional data into a spatial coordinate system to generate an initial three-dimensional model;

[0053] Specifically, collecting the initial multi-dimensional data of the fire passage and performing preprocessing means deploying RGB cameras, lidars and depth sensors in the fire passage, collecting the color information, two-dimensional contours, three-dimensional point cloud data and depth maps of the initial objects in the fire passage, and preprocessing and time synchronization calibration of the collected multi-dimensional data.

[0054] The color information from the RGB camera can help identify objects of different materials, while the point cloud data from the LiDAR provides information on the object's three-dimensional shape, and the depth sensor further supplements the object's height and distance. By fusing multidimensional data, the system can generate high-precision three-dimensional models to better identify the size, position, and shape of occupied objects. The purpose of preprocessing is to clean up noisy data and standardize sensor outputs to ensure more accurate subsequent model generation and recognition. Specifically, data preprocessing includes removing invalid data points, filling in missing data, and aligning and standardizing data from different sensors. Through this preprocessing step, the system can reduce errors in sensor-collected data and improve data accuracy. Time synchronization calibration ensures the spatiotemporal consistency of multidimensional data, improving the real-time and accuracy of system recognition and avoiding data mismatches and misidentifications due to time differences.

[0055] Furthermore, the multidimensional data is mapped into a spatial coordinate system to generate an initial three-dimensional model. The depth map and point cloud data are mapped into a unified three-dimensional coordinate system, and the mapped depth map and point cloud data are combined to form the three-dimensional geometric shape of the object.

[0056] The color and two-dimensional boundary of each object are extracted by collecting the two-dimensional contours of the objects in real time. The two-dimensional contours generated by the RGB image and the depth map are combined to generate an initial three-dimensional model of the fire passage. After standardization, the three-dimensional model is used as the standard state of the fire passage without occupied objects.

[0057] By combining depth maps and point cloud data, the system captures the 3D geometry of objects and generates a complete initial 3D model. This addresses the inability of traditional 2D image recognition to accurately represent the spatial position and shape of objects, enabling the system to better handle complex fire escape scenarios, such as those with multiple objects overlapping or partially occluded. After generating the initial 3D model, the system extracts the color and boundary information of each object using real-time 2D contour data collected from the objects and combines this information with the depth map. This enables a more comprehensive description of objects, accurately identifying not only their boundaries and shapes but also surface features such as color. This enables precise identification of occupied objects, reducing false positives and missed detections. The generated 3D model is then normalized to a standard state where no objects are occupied within the fire escape. This allows for rapid comparison and identification during real-time data collection, enabling not only the detection of large objects but also smaller objects or subtle changes in occupancy. This increased accuracy ensures that even small or transient objects in fire escapes are not overlooked, significantly improving safety and reliability.

[0058] S2, comparing the real-time multi-dimensional data with the data in the initial three-dimensional model to identify the changed occupied objects and generate preliminary bounding boxes, and optimize the boundaries of the detected occupied objects;

[0059] Specifically, comparing real-time multidimensional data with data in the initial 3D model to identify changed occupied objects and generate a preliminary bounding box refers to collecting real-time multidimensional data in the fire passage and preprocessing it. The real-time collected data is then compared frame by frame with the initial 3D model. The ICP algorithm is used to calculate the difference between the position, color, and depth of each point and the corresponding point in the initial 3D model. All points are compared one by one, and the obtained difference values ​​are weighted and fused to obtain a comprehensive change index. The change threshold K is set using Otsu's method, and areas with a change index greater than or equal to K are marked as changed areas.

[0060] The Kmeans++ clustering algorithm is used to cluster the change points in the marked change area. The clustering data k is set according to the change area detected in real time. All marked change points are assigned to different cluster categories through iterative optimization. For each clustering result, a preliminary bounding box of the occupied object is generated.

[0061] By comparing real-time multi-dimensional data with the initial 3D model, it can efficiently and accurately identify newly added or moved occupied objects within fire escapes. The ICP algorithm offers exceptional accuracy in complex 3D environments, effectively aligning real-time data with every point in the model, reducing both false positives and missed negatives. This is crucial for detecting occupants within a fire escape, as multiple objects may occupy the same area and their positions may vary. Using Kmeans++ clustering, the system can classify detected change points and generate more accurate bounding boxes for the occupied objects based on these clustering results. Compared to simple thresholding methods, clustering algorithms effectively capture object shape and boundary features, ensuring that the generated bounding boxes more accurately reflect the actual object shape. The clustering algorithm's iterative optimization allows it to adapt to dynamic object changes. If an occupied object moves or changes shape, the clustering algorithm can dynamically adjust the bounding box, further enhancing detection accuracy. By setting an appropriate threshold, the system can focus on areas with significant occupancy changes, avoiding false positives due to subtle noise or non-critical changes, significantly improving overall detection accuracy.

[0062] Furthermore, optimizing the detected occupied object boundaries means detecting the objects in the preliminary bounding box and calculating the rotation angle of each vertex of the object boundary. Identify the rotation information of an object:

[0063] Existing techniques calculate angles by simple coordinate differences:

[0064]

[0065] This formula is suitable for stationary objects or linear scenes, but it cannot handle the influence of dynamic factors such as object speed, acceleration, and inertia. To consider the impact of object movement on the angle, we introduced velocity and acceleration correction terms into the original formula and used an exponential decay function to control these dynamic parameters:

[0066]

[0067] The exponential decay function can smoothly process angle changes under high speed and high acceleration conditions, ensuring that angle calculations are accurate even in dynamic scenes. To adapt to complex rotation scenarios, a correction term for rotational inertia is added, considering the impact of the object's inertia on the angle calculation to obtain the final rotation angle calculation formula:

[0068]

[0069] Where, is the distance between two boundary points in the y-axis direction, is the distance between two boundary points in the x-axis direction, and is the velocity of the object in the x and y directions, calculated from the rate of change of the object's coordinates over time, usually using the finite difference method, and is the acceleration of the object in the x and y directions, calculated from the rate of change of the object's velocity with time, using finite differences or second-order differentials. is the exponential decay coefficient, which controls the degree of attenuation of velocity and acceleration to angular changes. It can be determined through experiments or simulations. I(a) is the rotational inertia of the object, which describes the object's resistance to rotational changes. It is determined by the mass and shape of the object. a is the object's angular velocity. r is the rotation radius, which represents the distance of the object relative to the rotation axis and is calculated based on the object's geometric information. () is the inverse tangent function;

[0070] By correcting the rotational inertia, the system can accurately consider the influence of the object's mass distribution and the rotation radius on the angle, which is particularly important for calculating the rotation angle of objects with large mass or complex geometry.

[0071] Mark the angular position of the rotating object according to the calculated angle information of the object boundary, and the angle change of each boundary vertex Perform calculations to identify angle mutation points:

[0072] In the prior art, a sudden change in the boundary is detected by simply using the difference between adjacent angles:

[0073] ,

[0074] Although this formula can simply calculate angle mutations, it is easily affected by noise and is not sensitive enough to angle changes at complex boundaries. In order to improve the accuracy of detecting mutations at the boundaries of complex objects, a convolution operation is introduced to smooth the angle changes using a time window: Convolution can effectively reduce noise, especially when the angle changes dramatically. It can smooth the angle changes and make mutation detection more robust. In order to reflect the dynamic change of angle over time, the time derivative of the angle is added to the original formula to obtain the final angle mutation detection formula:

[0075]

[0076] Where K(t-τ) is the Gaussian convolution kernel, which is used to smooth the time variation of the angle. It is a dimensionless function and represents the smoothing window of the angle variation. The reasonable convolution kernel parameters can be measured experimentally. is the angle of the i-th boundary point at time t. By capturing the boundary position changes of the object at different time points, the boundary angle is calculated. is the angle of the i+1th boundary point at time t, calculated by the coordinate difference between two adjacent points, It is the time derivative of the angle of the i-th boundary point, which indicates the rate of change of the angle over time and reflects the dynamic characteristics of the angle change. It is usually obtained by numerically differentiating the time series. and It is the boundary of the time interval and is used to calculate the time window of the convolution integral. It reflects the angular change of the object within the time period and is set according to the actual application scenario. dτ is the small change in the integral variable τ, which is used to represent the change of the time variable in the convolution operation.

[0077] The time derivative reflects the changing trend of the angle over time, making the system more sensitive to the dynamic changes of the angle when processing complex rotation scenes;

[0078] Analyze the angle change of each mutation point. When the angle mutations of multiple adjacent vertices occur in the same area, there is discontinuity at the boundary of the area. Record each confirmed mutation point and discontinuous area.

[0079] The complex exponential encoding formula is used to encode the rotation angle of each mutation point, and the angle information of the object boundary is converted into a smooth expression in the complex domain:

[0080]

[0081] Where z is the encoded complex value, θ is the angle of rotation of the object, w is the angular frequency, which is used to encode the frequency of the object's rotation angle and controls the smoothness of the angle. It is determined through experiments or debugging according to specific scenarios, and j is the imaginary unit.

[0082] Adjust the angular frequency in real time to control the smoothness of the encoding based on the boundary characteristics of the object (the shape complexity and rotation degree of the boundary. If the rotation angle changes greatly, set a high angular frequency to accelerate angle smoothing. For objects with complex shapes, set a low angular frequency to preserve boundary details and avoid over-speed smoothing).

[0083] Recalculate and decode the rotation angle information using the inverse decoding formula of the complex exponential encoding:

[0084]

[0085] Where ln() is the logarithm of the complex number, which is used to extract the phase information from the complex number, z is the complex number, j is the imaginary unit, and w is the angular frequency;

[0086] Reconstruct the boundary segments based on the rotation angle of each vertex and the coordinates of the adjacent vertices:

[0087]

[0088] Where, and are the coordinates of the adjacent vertices, and L is the length of the boundary segment;

[0089] After smoothness testing of the newly generated boundary segments, all boundary segments are reassembled to generate a complete object bounding box;

[0090] Perform pixel-level gradient analysis on the combined complete bounding box and use image gradient detection to identify discontinuous areas of the object boundary:

[0091]

[0092] Where, It's a pixel The gradient value at , I is the image brightness value, and Represent the image gradients in the horizontal and vertical directions respectively;

[0093] A gradient threshold W is set based on the gradient statistical distribution of the image, and regions with gradient values ​​greater than or equal to W are marked as potential non-fitting regions. For the identified non-fitting regions, the shape of the boundary is iteratively adjusted using the active contour model.

[0094] Calculate the fit score S of the adjusted bounding box, evaluating the overlap area between the bounding box and the true contour of the object:

[0095]

[0096] Where A is the true boundary of the object, B is the adjusted bounding box, represents the overlapping area between the two. represents the area of ​​the union of the two;

[0097] Set the fit judgment threshold P according to the needs of the specific application scenario. If the fit score is greater than or equal to P, it means that the bounding box is optimized to high precision and the bounding box is output. If it is less than P, continue iterative optimization.

[0098] In fire lane occupancy monitoring, for safety reasons, any possible occupancy behavior needs to be responded to quickly. Therefore, the P value can be set low to ensure that the system can quickly generate a bounding box and trigger an alert when any possible occupant appears. In some applications with higher fault tolerance, the P value can be set higher to reduce false alarms.

[0099] Use the dilation operation to expand the boundary, expand the original boundary points, and then use the erosion operation to gradually reduce the object boundary and remove the noise on the boundary to obtain the optimized bounding box.

[0100] Based on the initially generated bounding box, the system calculates the rotation angle of each vertex of the object's boundary to accurately identify the object's rotational state and capture rotational changes. This is particularly true when the object is dynamically moving or rotating, where traditional static bounding boxes cannot accurately depict the object's actual form. By calculating the rotation angle, the system generates a bounding box that more closely fits the object, avoiding boundary misalignment or distortion caused by object motion in static methods. This technology is particularly suitable for monitoring the occupancy of dynamic objects, ensuring accurate boundary identification. Using a Gaussian convolution kernel to smooth the angular changes of boundary points can detect sudden changes in the object's boundary. When the angles of multiple adjacent vertices suddenly change simultaneously, the system can identify discontinuities in the boundary. By marking sudden changes and discontinuities, the system can further optimize the complex object boundary, generating smoother and more accurate boundary segments. By converting the object's rotation angle information using complex exponential encoding, the system can smoothly represent the boundary information in the complex domain. This encoding eliminates small errors between boundary points, resulting in a smoother boundary line. The encoded data can be decoded in reverse to restore the rotation angle information while maintaining boundary continuity. Complex exponential encoding eliminates small perturbations during object boundary rotation, achieving smoother bounding box generation. This encoding technique is particularly suitable for objects with complex boundaries and irregular contours, significantly improving boundary recognition accuracy.

[0101] By analyzing pixel-level gradients, the system accurately identifies areas of non-fitting object boundaries—that is, areas with discontinuous boundaries. Using the active contour model (also known as the Snakes model), the boundaries of these areas are iteratively adjusted to more closely align with the object's true contours. The active contour model exhibits strong adaptability when processing complex objects, automatically adjusting the boundary position to achieve a more accurate bounding box. Compared to traditional boundary fitting methods, the active contour model dynamically adjusts the boundary based on the object's true shape, significantly improving the fit between the bounding box and the object's true contour. In the final stage of boundary optimization, the system combines dilation and erosion operations to further refine the object's boundary. Dilation expands the boundary to cover subtle structures or complex morphologies on the object's surface, while erosion removes noise points along the boundary to ensure the accuracy of boundary segments. This process not only preserves the object's true morphological features but also eliminates boundary anomalies caused by sensor noise or errors. The combination of dilation and erosion provides a refined approach to the final bounding box generation, ensuring that the bounding box accurately reflects the object's contour while eliminating noise and unnecessary errors.

[0102] S3. Calculate the volume of the occupied object based on the boundary detection results, and take different control measures based on the volume calculation results;

[0103] Specifically, calculating the volume of an occupied object based on the boundary detection results means dividing the 3D contour of the occupied object into N triangular patches using the Delaunay triangulation algorithm, and calculating the area of ​​each triangle using the boundary points of the object:

[0104]

[0105] Where F is the area of ​​each triangle, v is the side length of the triangle, and b is the height of each triangle. The side length and height of the triangle are calculated by the distance between the triangle vertices.

[0106] Calculate the total volume of the object based on the area and height of each triangle:

[0107]

[0108] Where V is the volume of the object, F is the area of ​​each triangle, b is the height of each triangle, n is the total number of triangles, and i is the index variable;

[0109] Monitor changes in occupied objects in fire passages in real time and adjust the volume information of occupied objects.

[0110] The Delaunay triangulation algorithm offers significant advantages in geometric optimization, maximizing the minimum angle of triangles and ensuring uniformity and stability in the generated triangular mesh. This algorithm avoids the generation of long, thin triangles, ensuring smooth and accurate object boundaries, making it particularly suitable for 3D modeling of complex and irregular objects. In fire escape occupancy monitoring scenarios, objects may have irregular shapes. This algorithm efficiently segments the object's 3D contour into multiple triangular facets with stable structures, ensuring the accuracy of subsequent volume calculations. By extracting the object's boundary points, the vertices of the triangular facets can be precisely defined. The area of ​​the triangle is calculated from the coordinates of these vertices, reflecting the object's local surface area. Combining the area of ​​each triangular facet with its height effectively calculates the facet's volume in 3D space, enabling accurate volume calculation of irregularly shaped objects while avoiding errors associated with simple geometric estimation methods. Through real-time data acquisition and dynamic volume updates, the system continuously monitors changes in the occupancy of objects within fire escapes. Whether an object moves, changes in volume, or even the addition of a new object, the system can respond promptly by rapidly calculating and updating volume information.

[0111] Furthermore, taking different governance measures based on the volume calculation results refers to using the SVM model as a classification model to classify occupied objects into three violation levels as the target labels of the model;

[0112] The target labels include minor violations, moderate violations, and severe violations;

[0113] The pre-processed historical object volume, position, and shape data are divided into training and test sets. The labeled training data set is used to train the SVM model. The SVM model parameters are optimized through cross-validation and grid search. After each training cycle, the model performance is evaluated using the test set. If there is no significant change in the verification difference after the training cycle, the model training is stopped. The trained SVM model is obtained and the real-time object volume, position, and shape data are input into the SVM model for classification to obtain the violation level of the occupied object.

[0114] If the occupied object is a minor violation, the first-level management measure will be triggered. A voice reminder will be issued through the speakers installed in the passage to notify on-site personnel to remove the occupied object in time. The relevant management personnel will be notified via SMS and app to handle the matter.

[0115] If the occupied object is a moderate violation, the secondary governance measures will be triggered, automatically marking and recording the image and video of the object, and sending the occupancy status to the management center, notifying security personnel and property personnel to go to the site and manually remove the occupied object;

[0116] If the use of objects is a serious violation, the third-level governance measures will be triggered, and a high-level alarm will be issued immediately to indicate serious occupation, and the emergency management team will be notified to immediately deal with the objects on site. If the fire escape is equipped with automatic cleaning equipment, remote control commands will be triggered to automatically clear the occupied objects.

[0117] The high-level alarm includes sirens and red flashing lights;

[0118] After each level of governance measures is initiated, the status of the objects is continuously monitored and the removal status is regularly checked. The volume calculation results, governance measures and corresponding processing status of each time are stored in the database.

[0119] By combining multi-dimensional data such as the volume, location, and shape of occupied objects, SVMs can automatically classify objects into minor, moderate, and severe violations. This is more intelligent and efficient than traditional manual classification or simple rule-based classification. The introduction of the SVM model not only handles complex multi-dimensional features but also effectively avoids misclassification. The SVM model's classification accuracy is particularly outstanding when dealing with irregular objects. By categorizing occupied objects into different levels and implementing flexible remediation measures, the system's response capabilities are significantly improved. Level one remediation measures effectively avoid over-response, saving management costs and time. Level two remediation measures ensure complete information recording, facilitating post-event review and management follow-up. Level three remediation measures significantly enhance the intelligence of channel occupancy management, reduce the burden of manual intervention, and provide managers with efficient and accurate response methods. After each level of remediation is activated, the system continuously monitors the status of the object to ensure its removal. This continuous monitoring function prevents recurrence of violations. By recording the remediation process and results of each remediation, the system can automatically learn and optimize, gradually improving its efficiency in responding to different types of violations. This not only ensures the safety and smooth flow of fire escape routes, but also provides management departments with comprehensive historical data support, facilitating the formulation of future safety management and emergency response strategies.

[0120] Example 2, reference Figure 3 , which is a second embodiment of the present invention, is different from the previous embodiment and provides a channel occupancy monitoring system, which includes:

[0121] A data acquisition module is used to collect multimodal data of the initial fire escape passage and generate an initial three-dimensional model after pre-processing the collected multimodal data;

[0122] The object recognition module is used to compare the changes in real-time multi-dimensional data and the initial three-dimensional model data to identify the occupied objects in the fire passage and generate the corresponding preliminary bounding boxes;

[0123] Boundary optimization module, used to optimize the bounding box of the occupied object to generate an optimized bounding box and perform real-time volume calculation of the occupied object;

[0124] The classification management module is used to classify occupied objects using the SVM model and then take different management measures.

[0125] If the functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage media include various media capable of storing program code, such as USB flash drives, mobile hard drives, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0126] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0127] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, and then editing, interpreting, or processing in another suitable manner as necessary, and then storing it in a computer memory.

[0128] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having logic gate circuits for implementing logic functions on data signals, an application-specific integrated circuit having suitable combinational logic gate circuits, a programmable gate array (PGA), a field-programmable gate array (FPGA), etc.

Claims

1. A channel occupancy monitoring method, characterized by: include, Collect and pre-process the initial multi-dimensional data of the fire escape, and map the multi-dimensional data into a spatial coordinate system to generate an initial three-dimensional model; Compare real-time multi-dimensional data with data in the initial 3D model to identify changing occupied objects and generate preliminary bounding boxes, optimizing the boundaries of detected occupied objects; Calculate the volume of occupied objects based on boundary detection results, and take different governance measures based on the volume calculation results; Optimizing the detected occupied object boundary refers to detecting the object in the preliminary bounding box and calculating the rotation angle of each vertex of the object boundary. Identify the rotation information of an object: ； Where, is the distance between two boundary points in the y-axis direction, is the distance between two boundary points in the x-axis direction, and is the velocity of the object in the x and y directions, and is the acceleration of the object in the x and y directions, is the exponential decay coefficient, I(a) is the rotational inertia of the object, a is the angular velocity of the object, r is the rotation radius representing the distance of the object relative to the rotation axis, () is the inverse tangent function; Mark the angular position of the rotating object according to the calculated angle information of the object boundary, and the angle change of each boundary vertex Perform calculations to identify angle mutation points: ； Where K(t-τ) is the Gaussian convolution kernel, is the angle of the i-th boundary point at time t, is the angle of the i+1th boundary point at time t, is the time derivative of the angle of the i-th boundary point, and is the boundary of the time interval, dτ is the small change in the integral variable τ; Analyze the angle change of each mutation point. When the angle mutations of multiple adjacent vertices occur in the same area, there is discontinuity at the boundary of the area. Record each confirmed mutation point and discontinuous area. The complex exponential coding formula is used to encode the rotation angle of each mutation point, and the angle information of the object boundary is converted into a smooth expression in the complex domain; Adjust the angular frequency in real time according to the boundary characteristics of the object to control the smoothness of the encoding; Recalculate and decode the rotation angle information using the inverse decoding formula of the complex exponential encoding; Reconstruct the boundary segments based on the rotation angle of each vertex and the coordinates of the adjacent vertices; After smoothness testing of the newly generated boundary segments, all boundary segments are reassembled to generate a complete object bounding box; Perform pixel-level gradient analysis on the combined complete bounding box and use image gradient detection to identify discontinuous areas of the object boundary; Set the gradient threshold W and mark the area with gradient value greater than or equal to W as the potential non-fitting phenomenon area. For the identified non-fitting phenomenon area, iteratively adjust the shape of the boundary through the active contour model; Calculate the fit score S of the adjusted bounding box, evaluate the overlapping area between the bounding box and the true contour of the object, set the fit judgment threshold P, and if the fit score is greater than or equal to P, it means that the bounding box is optimized to high precision, then output the bounding box; if it is less than P, continue iterative optimization; Use the dilation operation to expand the boundary, expand the original boundary points, and then use the erosion operation to gradually reduce the object boundary and remove the noise on the boundary to obtain the optimized bounding box.

2. The channel occupancy monitoring method according to claim 1, wherein: The collecting of initial multi-dimensional data of the fire passage and pre-processing thereof refers to deploying RGB cameras, lidars and depth sensors in the fire passage, collecting the color information, two-dimensional contours, three-dimensional point cloud data and depth maps of the objects in the initial fire passage, and pre-processing and time synchronization calibration of the collected multi-dimensional data.

3. The channel occupancy monitoring method according to claim 2, wherein: The multi-dimensional data is mapped into a spatial coordinate system to generate an initial three-dimensional model, the depth map and the point cloud data are mapped into a unified three-dimensional coordinate system, and the mapped depth map and the point cloud data are combined to form the three-dimensional geometric shape of the object; The color and two-dimensional boundary of each object are extracted by collecting the two-dimensional contours of the objects in real time. The two-dimensional contours generated by the RGB image and the depth map are combined to generate an initial three-dimensional model of the fire passage. After standardization, the three-dimensional model is used as the standard state of the fire passage without occupied objects.

4. The channel occupancy monitoring method according to claim 3, wherein: The comparing of the real-time multi-dimensional data with the data in the initial three-dimensional model to identify the changed occupied objects and generate a preliminary bounding box refers to collecting the real-time multi-dimensional data in the fire passage and performing pre-processing before comparing the real-time collected data with the initial three-dimensional model frame by frame, calculating the difference between the position, color and depth of each point and the corresponding point in the initial three-dimensional model by the ICP algorithm, comparing all points one by one, performing weighted fusion on the obtained difference values ​​to obtain a comprehensive change index, setting a change judgment threshold K, and marking the area with a change index greater than or equal to K as a changed area; The Kmeans++ clustering algorithm is used to cluster the change points in the marked change area. The clustering data k is set according to the change area detected in real time. All marked change points are assigned to different cluster categories through iterative optimization. For each clustering result, a preliminary bounding box of the occupied object is generated.

5. The channel occupancy monitoring method according to claim 4, wherein: Calculating the volume of the occupied object based on the boundary detection results refers to dividing the three-dimensional outline of the occupied object into N triangular facets, calculating the area of ​​each triangle through the boundary points of the object, and calculating the total volume of the occupied object based on the area and height of each triangular facet, monitoring the changes of occupied objects in the fire passage in real time and adjusting the volume information of the occupied objects.

6. The channel occupancy monitoring method according to claim 5, characterized in that: Taking different governance measures based on volume calculation results refers to using the SVM model as a classification model to classify occupied objects into three violation levels as target labels of the model; The target labels include minor violations, moderate violations, and severe violations; The pre-processed historical object volume, position, and shape data are divided into training and test sets. The labeled training data set is used to train the SVM model. The SVM model parameters are optimized through cross-validation and grid search. After each training cycle, the model performance is evaluated using the test set. If there is no significant change in the verification difference after the training cycle, the model training is stopped. The trained SVM model is obtained and the real-time object volume, position, and shape data are input into the SVM model for classification to obtain the violation level of the occupied object. If the occupied object is a minor violation, the first-level management measure will be triggered. A voice reminder will be issued through the speakers installed in the passage to notify on-site personnel to remove the occupied object in time. The relevant management personnel will be notified via SMS and app to handle the matter. If the occupied object is a moderate violation, the secondary governance measures will be triggered, automatically marking and recording the image and video of the object, and sending the occupancy status to the management center, notifying security personnel and property personnel to go to the site and manually remove the occupied object; If the occupied object is a serious violation, the third-level governance measures will be triggered, and a high-level alarm will be issued immediately to indicate serious occupation and notify the emergency management team to immediately deal with the object on site. If the fire escape is equipped with automatic cleaning equipment, a remote control command will be triggered to automatically clear the occupied object. The high-level alarm includes sirens and red flashing lights; After each level of governance measures is initiated, the status of the objects is continuously monitored and the removal status is regularly checked. The volume calculation results, governance measures and corresponding processing status of each time are stored in the database.

7. A channel occupancy monitoring system based on the channel occupancy monitoring method according to any one of claims 1 to 6, characterized in that: include, A data acquisition module is used to collect multimodal data of the initial fire escape passage and generate an initial three-dimensional model after pre-processing the collected multimodal data; The object recognition module is used to compare the changes in real-time multi-dimensional data and the initial three-dimensional model data to identify the occupied objects in the fire passage and generate the corresponding preliminary bounding boxes; Boundary optimization module, used to optimize the bounding box of the occupied object to generate an optimized bounding box and perform real-time volume calculation of the occupied object; The classification management module is used to classify occupied objects using the SVM model and then take different management measures.

8. A computer device comprising: memory and processor; The memory stores a computer program, and is characterized in that when the processor executes the computer program, the steps of the channel occupancy monitoring method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the channel occupancy monitoring method according to any one of claims 1 to 6 are implemented.

Images