A method for predicting the position of a missing person under a mountain torrent debris flow disaster

Abstract

The application provides a method for predicting the position of missing personnel under debris flow disaster, and belongs to the field of disaster rescue. The method comprises the following steps: obtaining multi-source data fused with thermal infrared image, radar image and terrain; performing feature extraction on the obtained multi-source data to detect the position of missing personnel under debris flow disaster from the multi-source identification of personnel trajectory, human body heat radiation and human body skeleton; constructing a comprehensive analysis function based on the extracted features; obtaining the prediction value of different positions at time t based on the comprehensive analysis function, and completing the prediction of the position of missing personnel. The application aims to solve the problems of low accuracy and low efficiency of the existing method for predicting the position of missing personnel.

Description

Technical Field

[0001] This invention belongs to the field of disaster relief, and in particular relates to a method for predicting the location of missing persons in the event of flash floods and debris flows. Background Technology

[0002] Flash floods and mudslides are common natural disasters. Due to their suddenness and destructiveness, they often lead to people going missing, making rapid location of missing persons crucial for rescue efforts. Currently, rescue teams primarily use a combination of manual searches and drone patrols, while life detectors have also become an important disaster relief tool. However, traditional manual ground searches are greatly limited by terrain and are threatened by secondary disasters; traditional drone searches only retrieve surface information and are significantly affected by weather and visibility; and life detectors are only sensitive to people with vital signs, often reflecting weak signals to buried individuals who are stationary and have very weak vital signs. Due to the complex terrain and harsh environment at disaster sites, traditional search and rescue methods are often inefficient, inaccurate, and have limited coverage. Furthermore, missing persons may already be deceased, posing a significant challenge to search and rescue operations. Summary of the Invention

[0003] In view of the above-mentioned shortcomings in the existing technology, the present invention provides a method for predicting the location of missing persons under flash flood and debris flow disasters, which aims to solve the problems of low accuracy and low efficiency of existing methods for predicting the location of missing persons.

[0004] To achieve the above objectives, the technical solution adopted by this invention is: a method for predicting the location of missing persons under flash flood and debris flow disasters, comprising the following steps:

[0005] Acquire multi-source data that integrates thermal infrared imagery, radar imagery, and terrain data;

[0006] Feature extraction was performed on the acquired multi-source data to identify the location of missing persons in flash floods and debris flows based on multiple sources, including personnel trajectories, human thermal radiation, and human skeleton detection.

[0007] Based on the extracted features, a comprehensive analysis function is constructed.

[0008] Based on the comprehensive analysis function, the predicted values ​​of different locations at time t are obtained, thus completing the prediction of the location of the missing person.

[0009] The beneficial effects of this invention are: by fusing multi-source data to establish a personnel trajectory model, combining multi-source data fusion technology, and comprehensively considering factors such as thermal infrared data and radar image data, this invention can achieve accurate prediction of the location of missing persons. It can play an important role even when the missing persons have no vital signs, and provide effective technical support for disaster relief work.

[0010] Furthermore, the acquisition of multi-source data specifically involves:

[0011] Aerial surveys are conducted using drones equipped with positioning and attitude systems, optical cameras, thermal infrared sensors, and ground-penetrating radar. By acquiring positioning and attitude system (POS) data, ground object reflection intensity, target object radiation intensity, and underground echo reflection signals, terrain data, thermal infrared image data, and radar image data are obtained.

[0012] The beneficial effects of the above-mentioned further solutions are as follows: This invention innovatively integrates thermal infrared data, radar imagery data, and personnel trajectory data (personnel trajectory data is obtained from a personnel trajectory model, the data source is terrain data, and the terrain data is calculated from POS data combined with optical imagery in a stereoscopic relative manner). By acquiring information from different levels, it comprehensively analyzes the possible locations of missing persons, which is the core of achieving accurate prediction. That is, it integrates multi-source data from thermal infrared, radar, and personnel trajectory to accurately determine the location of missing persons from different dimensions. This invention effectively improves prediction accuracy by complementing each other's data, providing accurate direction for rescue efforts, avoiding blind searches, and improving rescue efficiency.

[0013] Furthermore, the feature extraction includes:

[0014] Temperature anomaly extraction: Extract temperature anomaly regions from thermal infrared images and perform standardization processing.

[0015]

[0016] Where T(x,y,t) represents the radiation intensity detected by the thermal infrared sensor at position (x,y) and time t, I(x,y,t) represents the human body radiation intensity, and μ T (t) represents the average radiant intensity of the thermal infrared image at time t, σ T (t) represents the standard deviation of the radiation intensity of the thermal infrared image at time t, t0 represents the disaster start time, and τ represents the radiation decay time constant;

[0017] Ground-penetrating echo reflection signal analysis: This study analyzes the ground-penetrating echo reflection signals of human skeletons in radar image data and uses standardization processing to enhance the identification of these signals.

[0018]

[0019] Where R(x,y,t) represents the intensity of the ground-penetrating radar's underground echo reflection signal received at location (x,y) and time t, S(x,y,t) represents the underground echo reflection signal, μ R(t) represents the average echo intensity of the radar image data at time t, d(x,y) represents the burial depth, v represents the electromagnetic wave propagation speed, α(ξ) represents the soil medium attenuation coefficient, dξ represents the derivative of the integral variable, and Δt(x,y,t) represents the time difference between the ground penetrating radar transmitting electromagnetic waves at location (x,y) and time t and receiving the reflected echo.

[0020] Personnel trajectory analysis: Based on the POS data from the positioning attitude system and stereo relative modeling of optical images, terrain data is acquired. Through terrain analysis, considering the slope G(x,y), aspect D(x,y), and the difference Δt between the disaster occurrence time t and the disaster start time t0, the personnel trajectory model formula is constructed as follows:

[0021]

[0022] Where P(x,y,t) represents the probability distribution of the personnel trajectory model, σ represents the weighting parameter controlling the influence of terrain factors on the probability, θ0 represents the reference slope aspect value, and τ P This represents the time-dependent decay parameter.

[0023] The beneficial effects of the above-mentioned further solutions are: targeted processing and feature extraction of various types of data, such as temperature anomaly extraction from thermal infrared data, underground echo reflection signal analysis from radar image data, and model construction of personnel trajectories, laying the foundation for subsequent fusion analysis.

[0024] Furthermore, the expression for the comprehensive analysis function is as follows:

[0025] F(x,y,t)=ω1T(x,y,t)+ω2R(x,y,t)+ω3P(x,y,t)

[0026]

[0027] Where F(x,y,t) represents the predicted value at location (x,y) and time t, T(x,y,t) represents the radiation intensity detected by the thermal infrared sensor at location (x,y) and time t, R(x,y,t) represents the intensity of the radar echo reflection signal received by the ground penetrating radar at location (x,y) and time t, P(x,y,t) represents the probability distribution of the personnel trajectory model, ω1, ω2, and ω3 are all weighting coefficients, d(x,y) represents the burial depth, and d avg d represents the average burial depth of all detection points. max and d min These represent the maximum and minimum burial depths of all detection points, respectively.

[0028] The beneficial effects of the above-mentioned further solutions are: the present invention determines the weight of the comprehensive analysis function based on determinable factors such as burial depth, reasonably balances the role of different data sources in prediction, and improves prediction accuracy.

[0029] Furthermore, the prediction values ​​for different locations at time t are obtained based on the comprehensive analysis function, specifically as follows:

[0030] Set the judgment threshold F threshold When the comprehensive analysis function F(x,y,t) is greater than the judgment threshold F threshold If so, then there are missing persons at that location.

[0031] The beneficial effects of the above-mentioned further solutions are: by comparing the predicted values ​​of the comprehensive analysis function with the threshold, key areas can be quickly and accurately screened, enhancing the targeting of rescue efforts. Moreover, the threshold is set based on empirical science and can be flexibly adjusted to adapt to different disaster scenarios, thus buying time for rescue. Attached Figure Description

[0032] Figure 1 This is a flowchart of the method of the present invention.

[0033] Figure 2 This is a schematic diagram of the method framework of the present invention. Detailed Implementation

[0034] The specific embodiments of the present invention are described below to enable those skilled in the art to understand the present invention. However, it should be understood that the present invention is not limited to the scope of the specific embodiments. For those skilled in the art, various changes are obvious as long as they are within the spirit and scope of the present invention as defined and determined by the appended claims. All inventions utilizing the concept of the present invention are protected.

[0035] Example

[0036] like Figure 1 and Figure 2 As shown, this invention provides a method for predicting the location of missing persons during flash floods and debris flows, the implementation of which is as follows:

[0037] Acquiring multi-source data by fusing thermal infrared imagery, radar imagery, and terrain data, specifically:

[0038] Aerial surveys are conducted using drones equipped with positioning and attitude systems, optical cameras, thermal infrared sensors, and ground-penetrating radar. By acquiring positioning and attitude system (POS) data, ground object reflection intensity, target object radiation intensity, and underground echo reflection signals, terrain data, thermal infrared image data, and radar image data are obtained.

[0039] In this embodiment, an aerial survey is conducted using a UAV equipped with a Positioning Attitude System (POS), an optical camera, a thermal infrared sensor, and a ground-penetrating radar to acquire POS data, ground object reflection intensity, target object radiation intensity, and underground echo reflection signals, thereby obtaining terrain data, thermal infrared images, and radar image data.

[0040] UAV aerial surveying: Acquires optical image data and UAV positioning attitude system (POS) data, including position and attitude information, to provide a spatial positioning basis for subsequent data processing.

[0041] Thermal infrared detection: This method uses an infrared detection lens (or thermal infrared sensor) to capture the infrared radiation emitted by the human body and obtain the radiation intensity value of the target object. Even if a human body has no vital signs, it will still emit infrared radiation before it completely loses its temperature, which is helpful for detecting missing persons.

[0042] Ground-penetrating radar (GPR) detection. Based on the differences in electromagnetic wave characteristics of different materials, high-frequency electromagnetic waves are emitted underground. When these waves encounter human bones, they reflect strong underground echo signals. The target location is determined by the time difference of the reflected underground echo signals and the propagation speed of the electromagnetic waves.

[0043] Feature extraction was performed on the acquired multi-source data to identify the location of missing persons in flash floods and debris flows based on multiple sources, including personnel trajectories, human thermal radiation, and human skeleton detection.

[0044] In this embodiment, temperature anomaly extraction involves extracting temperature anomaly regions from thermal infrared images and performing standardization processing to highlight these regions.

[0045]

[0046] Where T(x,y,t) represents the radiation intensity detected by the thermal infrared sensor at position (x,y) and time t, I(x,y,t) represents the human body radiation intensity, and μ T (t) represents the average radiant intensity of the thermal infrared image at time t, σ T (t) represents the standard deviation of the radiation intensity of the thermal infrared image at time t, t0 represents the start time of the disaster, and τ represents the radiation decay time constant (empirical value is 2 to 6 hours).

[0047] Ground-penetrating echo reflection signal analysis: This study analyzes the ground-penetrating echo reflection signals of human skeletons in radar image data and enhances the ability to identify these signals through standardization processing.

[0048]

[0049] Where R(x,y,t) represents the intensity of the ground-penetrating radar's underground echo reflection signal received at location (x,y) and time t, S(x,y,t) represents the underground echo reflection signal, μ R (t) represents the average echo intensity of the radar image data at time t, d(x,y) represents the burial depth, v represents the electromagnetic wave propagation speed, α(ξ) represents the soil medium attenuation coefficient, dξ represents the derivative of the integral variable, represents the small displacement increment on the path, and Δt(x,y,t) represents the time difference between the ground penetrating radar transmitting electromagnetic waves at position (x,y) and time t and receiving the reflected echo.

[0050] Personnel trajectory analysis: Based on the POS data from the positioning attitude system, and by analyzing the terrain (such as slope, aspect, etc.), considering the slope G(x,y), aspect D(x,y), and the difference between the disaster occurrence time t and the disaster start time t0, Δt = t - t0, a personnel trajectory model formula is constructed:

[0051]

[0052] Where P(x,y,t) represents the probability distribution of the personnel trajectory model, θ0 represents a reference slope aspect value related to common escape directions (which can be set empirically; for example, in mountainous areas, downhill along the valley is generally considered a common escape direction, so the slope aspect of this direction can be set as θ0), σ represents the weighting parameter controlling the influence of terrain factors on probability, and τ P This represents a time-related error reduction parameter (which can be set according to the type of disaster and past experience; for example, in flash floods and debris flows, it can be set to 1-3 hours, indicating that the probability of people remaining in place or moving along their original trajectory gradually decreases over time). This formula comprehensively considers the influence of terrain and time factors on the probability of people's possible locations through an exponential function, without relying on historical data statistical analysis.

[0053] Based on the extracted features, a comprehensive analysis function is constructed.

[0054] In this embodiment, a comprehensive analysis function is constructed, which comprehensively considers personnel trajectory models, thermal infrared data, and ground-penetrating radar image data factors, and performs weighted superposition to establish a personnel location model. This comprehensive analysis function is defined as follows:

[0055] F(x,y,t)=ω1T(x,y,t)+ω2R(x,y,t)+ω3P(x,y,t)

[0056] Considering the impact of burial depth d(x,y) on the reliability of different detection data, the weights are determined as follows:

[0057]

[0058] Where F(x,y,t) represents the predicted value at location (x,y) and time t, T(x,y,t) represents the radiation intensity detected by the thermal infrared sensor at location (x,y) and time t, R(x,y,t) represents the intensity of the radar echo reflection signal received by the ground penetrating radar at location (x,y) and time t, P(x,y,t) represents the probability distribution of the personnel trajectory model, ω1, ω2, and ω3 are all weighting coefficients, d(x,y) represents the burial depth, and d avg d represents the average burial depth of all detection points. max and d min These represent the maximum and minimum burial depths of all detection points, respectively.

[0059] This weighting method is based on the determinable factor of burial depth. As the burial depth increases, thermal infrared data is more affected and its weight decreases; radar image data is relatively more reliable and its weight increases; the weight of personnel trajectory model takes into account the relationship between burial depth and average burial depth in order to balance the role of each data at different depths.

[0060] Based on the comprehensive analysis function, the predicted values ​​for different locations at time t are obtained, thus completing the prediction of the location of the missing person. Specifically:

[0061] Set the judgment threshold F threshold When the comprehensive analysis function F(x,y,t) is greater than the judgment threshold F threshold If so, then there are missing persons at that location.

[0062] In this embodiment, the present invention combines optical imagery acquired by UAV aerial surveying to mark locations that meet the criteria on the optical imagery, generating a final thematic map of the prediction results. Rescue personnel can quickly locate areas where missing persons may exist based on the marked locations on the thematic map, improving rescue efficiency.

[0063] In summary, based on the above design, the beneficial effects of the present invention include:

[0064] Enhanced Precision Positioning: By integrating multi-source data from thermal infrared sensors, ground-penetrating radar, and personnel trajectory data, the location of missing persons can be accurately determined from different dimensions. The various data sources complement each other, effectively improving prediction accuracy, providing precise direction for rescue efforts, avoiding blind searches, and increasing rescue efficiency.

[0065] Adaptability to complex environments: Thermal infrared is not affected by light, radar is not affected by obstruction, and personnel trajectory takes into account terrain and time, enabling the method to adapt to the complex environment after flash floods and mudslides, overcome the limitations of traditional methods, broaden the scope of application, and enhance the reliability of rescue.

[0066] Highly efficient response: Employing advanced data processing technology and specific weighting methods, prediction results are generated rapidly. This helps rescuers seize the golden rescue time, increases the chances of rescuing missing persons, and creates more opportunities for life-saving rescues.

[0067] Resource allocation optimization: Accurate forecasting enables more rational allocation of rescue resources, avoiding the resource waste caused by the blindness of traditional search and rescue. It can improve resource utilization, reduce costs, and ensure the safety of rescue personnel.

[0068] Excellent scalability and compatibility: This invention has good scalability and compatibility, is easy to integrate with new data sources and processing methods, is universally applicable, is easy to combine with existing rescue systems, and is conducive to large-scale promotion and application.

Claims

1. A method for predicting the location of missing persons under flash flood and debris flow disasters, characterized in that, Includes the following steps: Acquire multi-source data that integrates thermal infrared imagery, radar imagery, and terrain data; Feature extraction was performed on the acquired multi-source data to identify the location of missing persons in flash floods and debris flows based on multiple sources, including personnel trajectories, human thermal radiation, and human skeleton detection. The feature extraction includes: Temperature anomaly extraction: Extract temperature anomaly regions from thermal infrared images and perform standardization processing. in, Indicates the position of the thermal infrared sensor and time t The radiation intensity detected at that location, Indicates the intensity of radiation on the human body. Indicates time t The average radiant intensity of the thermal infrared image. Indicates time t Standard deviation of radiation intensity in thermal infrared images Indicates the start time of the disaster. Represents the radiation decay time constant; Ground-penetrating echo reflection signal analysis: This study analyzes the ground-penetrating echo reflection signals of human skeletons in radar image data and uses standardization processing to enhance the identification of these signals. in, Indicates the location of the ground-penetrating radar. and time The intensity of the radar skeleton underground echo reflection signal received at the location, Indicates underground echo reflection signal, Indicates time The average echo intensity of the radar image data at that time Indicates the burial depth. Indicates the speed of electromagnetic wave propagation. Indicates the soil medium attenuation coefficient. Represents the derivative of the integral variable. Indicates the location of the ground-penetrating radar. Location and Time The time difference between the emission of an electromagnetic wave and the receipt of the reflected echo; Personnel trajectory analysis: Based on POS data from the positioning attitude system and stereo relative modeling of optical images, terrain data is acquired, and slope is considered through terrain analysis. Slope aspect and time With the start time of the disaster The difference Formula for constructing a personnel trajectory model: in, This represents the probability distribution of the personnel trajectory model. The weighting parameter represents the control over the influence of terrain factors on probability. Indicates the reference slope aspect value. This represents the time-dependent decay parameter; Based on the extracted features, a comprehensive analysis function is constructed. Based on the comprehensive analysis function, the time at different locations is obtained. t The predicted values ​​are used to predict the location of the missing persons.

2. The method for predicting the location of missing persons under flash flood and debris flow disasters according to claim 1, characterized in that, The acquisition of multi-source data specifically refers to: Aerial surveys are conducted using drones equipped with positioning and attitude systems, optical cameras, thermal infrared sensors, and ground-penetrating radar. By acquiring positioning and attitude system (POS) data, ground object reflection intensity, target object radiation intensity, and underground echo reflection signals, terrain data, thermal infrared image data, and radar image data are obtained.

3. The method for predicting the location of missing persons under flash flood and debris flow disasters according to claim 1, characterized in that, The expression for the comprehensive analysis function is as follows: in, Indicates position and time The predicted value at that location, Indicates the position of the thermal infrared sensor and time t The radiation intensity detected at that location, Indicates the location of the ground-penetrating radar. and time The intensity of the radar skeleton underground echo reflection signal received at the location, This represents the probability distribution of the personnel trajectory model. , and All represent weighting coefficients. Indicates the burial depth. This represents the average burial depth of all detection points. and These represent the maximum and minimum burial depths of all detection points, respectively.

4. The method for predicting the location of missing persons under flash flood and debris flow disasters according to claim 1, characterized in that, The method, based on a comprehensive analysis function, obtains the time at different locations. t The predicted value is as follows: Set the judgment threshold When the comprehensive analysis function Greater than the judgment threshold If so, then there are missing persons at that location.

Images