A pedestrian crossing zebra crossing traffic safety signal and control system

Abstract

This invention relates to the field of safe traffic technology and proposes a pedestrian crossing safety signal and control system. The system comprises a data acquisition module for acquiring pedestrian status, identifying special groups of people, and obtaining vehicle type, speed, and weight data; a behavior analysis module, connected to the data acquisition module via data transmission technology, for predicting pedestrian behavior trends and vehicle passage; and a data analysis module, connected to the behavior analysis module via data transmission technology, for analyzing predicted data to determine whether pedestrians are allowed to cross the zebra crossing and estimating the duration of the crossing. By capturing changes in pedestrian walking status in real time and considering factors such as the possible speed recovery situation (PSRS) and the impossible speed recovery situation (ISRS) in the event of unexpected situations while crossing the zebra crossing, the system effectively prevents pedestrians from being stranded in the road due to improperly set signal light timing, significantly improving the safety and smoothness of pedestrian crossings.

Description

Technical Field

[0001] The present invention relates to the technical field of safe traffic, and in particular to a pedestrian crossing zebra crossing traffic safety signal and control system. Background Art

[0002] In urban traffic, pedestrian safety and traffic flow are critical issues. Traditional zebra crossing traffic light control methods typically use fixed time intervals. Regardless of changes in the number of pedestrians and vehicle traffic at the intersection, the traffic light switching time remains fixed. This method can cause vehicles to wait for long periods of time when pedestrian traffic is low and vehicle traffic is high. In sections with low pedestrian and vehicle traffic, pedestrian and vehicle alertness is relatively low, resulting in a higher likelihood of pedestrian accidents when crossing zebra crossings. For pedestrians with limited mobility, such as the blind, wheelchair users, and those using crutches, fixed signal light switching patterns are difficult to ensure their safe crossing. If the green light time is too short, these pedestrians may not be able to reach the other side of the road in time. If the green light time is too long, it will unnecessarily affect vehicle traffic efficiency. Therefore, a system that can detect the status of special pedestrians and intelligently control traffic lights accordingly is urgently needed to improve the safety of these pedestrians and the overall smoothness of traffic. Summary of the Invention

[0003] In view of the problems existing in the prior art, the purpose of the present invention is to provide a pedestrian crossing zebra crossing traffic safety signal and control system to solve the problems raised by the above background technology.

[0004] To achieve the above objectives, the present invention provides a pedestrian crossing zebra crossing traffic safety signal and control system, comprising:

[0005] Data acquisition module, used to obtain pedestrian status, identify special groups of people, and obtain vehicle type, speed and weight data;

[0006] The behavior analysis module is connected to the data acquisition module through data transmission technology and is used to predict pedestrian behavior trends and vehicle traffic conditions;

[0007] The data analysis module is connected to the behavior analysis module through data transmission technology and is used to analyze whether pedestrians are allowed to cross the zebra crossing and estimate the time it takes for pedestrians to cross the zebra crossing based on predictive data;

[0008] The warning trigger module is connected to the data analysis module through data transmission technology and is used to trigger a warning signal when it is determined that pedestrians are not allowed to pass;

[0009] The dynamic update module is connected to the data analysis module through data transmission technology and is used to update the pedestrian's predicted crossing time and crossing status in real time when the pedestrian crosses the zebra crossing;

[0010] The signal control module is connected to the data analysis module and the warning trigger module through data transmission technology. It is used to control the display of traffic lights, send out sound and light alarms to pedestrians after triggering warning information, and update the display of traffic lights in real time.

[0011] Preferably, the data acquisition module acquires the multimodal pedestrian status including the following steps:

[0012] S111. Generate a millimeter wave signal at a fixed frequency, calculate the reflected wave intensity based on the device's set transmit power, and use the formula: , where is the reflected wave intensity, The transmit power set for the device, and are the transmitting and receiving antenna gains, is the wavelength, and , , is the target distance;

[0013] S112. Using the Doppler effect, the pedestrian speed is calculated based on the frequency difference between the transmitted wave and the reflected wave. The formula for calculating the pedestrian speed is: , where is the wavelength, is a fixed frequency difference;

[0014] S113. Calculate the distance between the pedestrian and the radar by measuring the time delay between the transmitted signal and the received reflected signal. The formula is: , where is the target distance, that is, the distance between the pedestrian and the radar, is the speed of light, For time delay;

[0015] S114. Based on the target distance and pedestrian speed at different time points, where the target distance is the distance between the pedestrian and the radar, the Kalman filter algorithm is used to predict the pedestrian's position at the next moment. The position is updated in combination with the newly measured data to depict the pedestrian's movement trajectory. The formula is: , where is the pedestrian's position at the next moment, is the position of the pedestrian at the previous moment, is the state transition matrix, is the control matrix, is the control variable.

[0016] Preferably, the data acquisition module identifies special groups of people including the following steps:

[0017] S121, continuously collecting images at a fixed frame rate, compressing the image data in JPGE format, and transmitting the image data in real time to the special pedestrian recognition unit and the status analysis unit via Ethernet or Wi-Fi;

[0018] S122. Generate a depth image by combining the calculated target distance data with the time-of-flight method, and transmit the depth information in binary format to the special pedestrian recognition unit and the state analysis unit;

[0019] S123, using a Gaussian filter algorithm to reduce image noise, and updating each new pixel value in the image, the formula is: , where The image after Gaussian filtering and noise reduction is at coordinate The new pixel value at position, The coordinates in the original image are The pixel value at position, is the Gaussian kernel standard deviation, and histogram equalization is used to enhance image contrast. The formula is: , where is the grayscale histogram of the graphic, , is the cumulative distribution function, After histogram equalization, the image is at coordinate The new grayscale value of the pixel at position, The original image is at coordinates The grayscale value of the pixel at the position;

[0020] S124, through the convolution pooling operation, the convolution kernel is slid on the input feature map to perform point multiplication and accumulation calculation, and the coordinates in the output feature map are The formula for the element of position is: , where Output feature map The median coordinate is And the channel is is the coordinate index of the output feature map in the height and width directions, is the channel index of the input feature map, The coordinates in the convolution kernel are , the input channel is and the output channels are is the weight channel is the stride of the convolution operation;

[0021] S125. After multiple rounds of convolution and pooling, the feature map output by the last pooling layer is flattened to convert the multi-dimensional feature map into a one-dimensional vector. The formula is: , where is the one-dimensional image feature vector obtained after flattening operation, 、 The height, width and number of channels of the output feature map of the last convolutional pooling layer respectively;

[0022] S126. Input the extracted feature vector into a value classifier to calculate different types of pedestrians, including but not limited to ordinary pedestrians, blind people, people in wheelchairs, people with crutches, and people with abnormal walking conditions. The formula is: , where The output of the classifier The category index.

[0023] Preferably, the data acquisition module acquires the vehicle driving status data including the following steps:

[0024] S131. Multiple geomagnetic sensors are buried 5-10 cm below the lane within the preset sensing area of ​​the zebra crossing to detect the voltage signal generated when a vehicle passes by. The rising and falling edge times are recorded. The vehicle speed is calculated based on the time difference between vehicles passing adjacent geomagnetic sensors and the preset distance between adjacent geomagnetic sensors. The formula is: , where is the vehicle speed, The preset length between adjacent geomagnetic sensors, is the time difference between vehicles passing adjacent geomagnetic sensors;

[0025] S132. Estimate the vehicle length based on the sensing signal duration and speed using the following formula: , where To estimate the vehicle length, The time difference between the front and rear wheels of the vehicle passing the geomagnetic sensor;

[0026] S133. Collect vehicle image information and perform feature extraction and comparison on the detected vehicle image using the same feature extraction method as that used for pedestrian feature extraction to identify the specific vehicle model. The voltage signal of the vehicle passing by is obtained from the weighing sensor set between adjacent geomagnetic sensors, and the vehicle weight is calculated using a calibration method. The formula is: , where is the voltage signal, is the offset.

[0027] Preferably, the behavior analysis module combines the speed data measured by the millimeter wave radar and the speed estimation value obtained by the depth sensor with the visual analysis using a weighted fusion algorithm to obtain the fusion speed, and the formula is: , where is the fusion speed, and are the speed measured by the millimeter-wave radar and the speed estimate obtained by the depth sensor combined with visual analysis, and are the corresponding weights, and , and set the speed threshold , where For pedestrians at rest, In slow walking state, Normal walking state, In fast walking state, by integrating speed With set threshold speed The walking status of the pedestrian is judged by the ratio of .

[0028] Preferably, the behavior analysis module calculates the braking distance of the vehicle based on the vehicle weight, driving speed and vehicle type, using the formula: , where is the braking distance, is the braking coefficient, is the acceleration due to gravity.

[0029] Preferably, the data analysis module determines and calculates the duration of a pedestrian passing through a traffic light, including the following steps:

[0030] S31. Compare the actual distance between the vehicle and the zebra crossing with the calculated braking distance to determine whether it is safe for the pedestrian to cross the zebra crossing;

[0031] S32. When it is determined that the first vehicle in the traffic flow can still stop at the zebra crossing after adding the margin time and the yellow light time as reaction time, according to the kinematic formula , where is the final velocity of the first vehicle in the current traffic flow, that is , For the current speed, is the acceleration, For time, When the red light of the lane turns on, is the time required for the first vehicle in the traffic flow to brake, is a margin time, and The minimum value is , The yellow light duration of the lane, the value range is ;

[0032] S33. Based on the number of pedestrians in the group, with each pedestrian except the first one maintaining a safe distance from the previous pedestrian, calculate the time required for all types of pedestrians to cross the zebra crossing. The formula is: , where For the The time it takes for an individual to cross a zebra crossing, As the leader of the pedestrian team, is the length of the zebra crossing, is the average speed of the slowest person in the pedestrian group crossing the zebra crossing, Provide safe spacing between pedestrians;

[0033] S34, for the The time required for an individual to cross the zebra crossing is added with a margin time to calculate the green light time of the zebra crossing. The formula is: , where Green light time for zebra crossing, is the time required for the first vehicle in the traffic flow to brake, is another margin time, and The minimum value is , and add a zebra crossing yellow light time to calculate the lane red light time. The formula is , where The remaining time of the red light in the lane, The yellow light time of zebra crossing, the value range is .

[0034] Preferably, in step S31, when it is determined that it is unsafe for pedestrians to cross the zebra crossing, a signal is sent to the early warning trigger module, which first triggers an audible and visual alarm signal, and then calculates the countdown for the vehicle's green light and the pedestrian's red light. The countdown generation includes the following steps:

[0035] S41. Calculate the number of vehicles in the current traffic flow that can safely stop at the zebra crossing. Calculate the number of vehicles in the traffic flow that can safely stop at a speed of 0 using a kinematic formula. The formula is: , where is the acceleration of the vehicle at the moment of braking, The time it takes for the vehicle to stop safely from the start of braking, that is, the braking duration. The displacement of the vehicle from the start of braking to safe stopping, that is, the braking distance;

[0036] S42. Add a safety margin to the braking time to ensure that the vehicle has enough time to react and stop safely. The formula is: , where The remaining time of the green light for the lane, is another margin duration, and The minimum value is ;

[0037] S43. Calculate the duration of the red light at the zebra crossing based on the remaining green light duration in the lane. The formula is: , where The duration of the red light at the zebra crossing. The yellow light duration of the lane, the value range is , is another margin duration, and The minimum value is .

[0038] Preferably, the dynamic update module updates the pedestrian passing time on the zebra crossing, including the following steps:

[0039] S51. Use pressure sensors deployed on the zebra crossing to sense pressure changes in real time, record pedestrian footsteps and movement information, and calculate the speed changes of pedestrians on the zebra crossing in combination with image acquisition. The formula is: , where and are the walking speeds of pedestrians at adjacent moments, is the change in pedestrian walking speed, is the time interval;

[0040] S52, when pedestrian speed appears 、 When the pedestrian's posture is obviously unbalanced or paused, which does not conform to the normal model through image analysis, and the pressure sensor data shows that the footsteps move chaotically, it is determined that the walking state is abnormal. In the formula, and are the average speed and acceleration of pedestrians on the zebra crossing, 、 、 as well as are the minimum, maximum average speed and acceleration of pedestrians on the zebra crossing respectively;

[0041] S53. Calculate the remaining distance from the pedestrian to the destination using the following formula: , where is the remaining distance for the pedestrian to reach the destination, is the total length of the zebra crossing, is the distance the pedestrian has walked, and the time it takes for the pedestrian to cross the remaining zebra crossing distance is calculated using the formula: , where To predict the time it takes for pedestrians to cross the remaining zebra crossing distance, is the restitution coefficient, is the possible acceleration recovery situation of the pedestrian, Impossible acceleration recovery for pedestrians, is the possible acceleration recovery situation of the pedestrian, To accommodate the impossible acceleration recovery of pedestrians, update the green light duration of the zebra crossing and the red light duration of the lane. The calculation formula is: , where For the updated green light duration of zebra crossing, The green light duration of the zebra crossing. For the updated lane red light duration, The length of time the lane's red light has been on.

[0042] Preferably, the signal control module controls the signal light including the following steps:

[0043] S61. Receive instructions via wired or wireless communication and verify format and data integrity;

[0044] S62, converting the digital instruction into an analog control signal suitable for the drive circuit;

[0045] S63, driving the signal light driving circuit to control the on and off switching of the traffic light and the start and stop of the sound and light alarm;

[0046] S64: Feedback the working status of the traffic light to the data analysis module for data storage and update.

[0047] The present invention provides a pedestrian crossing zebra crossing traffic safety signal and control system, which has the following beneficial effects:

[0048] 1. Through multimodal sensor fusion technology, pedestrian walking status is monitored in all directions and in real time. By accurately controlling pedestrian crossing time and intelligently adjusting traffic lights, efficient coordination between pedestrian and vehicle traffic is achieved. While ensuring pedestrian crossing safety, it also reduces unnecessary waiting time for vehicles and optimizes traffic flow at intersections. Compared with traditional fixed-duration traffic light systems, it can greatly improve the alertness of pedestrians and drivers crossing intersections with few people and vehicles, which is conducive to improving road safety.

[0049] 2. By accurately identifying special pedestrians and their status, providing them with sufficient green light time and voice guidance, and by obtaining information on vehicle type, length, speed and weight, analyzing the distance the vehicle can brake, it can greatly optimize road traffic conditions and effectively avoid danger to special pedestrians when crossing the road due to unreasonable traffic light timing. While ensuring the safety of special pedestrians, it combines vehicle detection information to reasonably control traffic light timing and reduce unnecessary waiting time for vehicles.

[0050] 3. The dynamic update module has powerful adaptive capabilities. It can not only capture changes in pedestrian walking status in real time, but also use advanced algorithms to accurately predict the remaining pedestrian crossing time based on factors such as the possible speed recovery situation (PSRS) and impossible speed recovery situation (ISRS) when pedestrians encounter unexpected situations while crossing the zebra crossing. This dynamic and intelligent adjustment mechanism ensures that the traffic light duration is always matched with the actual crossing needs of pedestrians. When an abnormal pedestrian walking status is detected, it can quickly and accurately judge and accurately update the pedestrian crossing time based on a scientific calculation model, and promptly feedback to the traffic light control system and voice prompt system, effectively avoiding pedestrians being stranded in the road due to unreasonable traffic light timing settings, and significantly improving the safety and smoothness of pedestrian crossing. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. 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.

[0052] Figure 1 This is a system flow diagram of a pedestrian crossing zebra crossing traffic safety signal and control system provided in this application. DETAILED DESCRIPTION

[0053] The following embodiments of the present invention are described in further detail in conjunction with the accompanying drawings and examples. The following embodiments are only used to illustrate the present invention and are not intended to limit the scope of the present invention.

[0054] like Figure 1 As shown, this embodiment proposes a pedestrian crossing zebra crossing traffic safety signal and control system, including:

[0055] Data acquisition module, used to obtain pedestrian status, identify special groups of people, and obtain vehicle type, speed and weight data;

[0056] The behavior analysis module is connected to the data acquisition module through data transmission technology and is used to predict pedestrian behavior trends and vehicle traffic conditions;

[0057] The data analysis module is connected to the behavior analysis module through data transmission technology and is used to analyze whether pedestrians are allowed to cross the zebra crossing and estimate the time it takes for pedestrians to cross the zebra crossing based on predictive data;

[0058] The warning trigger module is connected to the data analysis module through data transmission technology and is used to trigger a warning signal when it is determined that pedestrians are not allowed to pass;

[0059] The dynamic update module is connected to the data analysis module through data transmission technology and is used to update the pedestrian's predicted crossing time and crossing status in real time when the pedestrian crosses the zebra crossing;

[0060] The signal control module is connected to the data analysis module and the warning trigger module through data transmission technology. It is used to control the display of traffic lights, send out sound and light alarms to pedestrians after triggering warning information, and update the display of traffic lights in real time.

[0061] Specifically, through multimodal sensor fusion technology, the walking status of pedestrians is monitored in all directions and in real time. By accurately controlling the time for pedestrians to cross the street and intelligently adjusting the traffic lights, efficient coordination between pedestrians and vehicles is achieved. While ensuring the safety of pedestrians crossing the street, it reduces unnecessary waiting time for vehicles and optimizes traffic flow at intersections. Compared with the traditional fixed-time traffic light system, it can greatly improve the alertness of pedestrians and drivers at intersections with few people and vehicles, which is conducive to improving road safety.

[0062] In this embodiment, the data acquisition module acquires the multimodal pedestrian status by the following steps:

[0063] S111. Generate a millimeter wave signal at a fixed frequency, calculate the reflected wave intensity based on the device's set transmit power, and use the formula: , where is the reflected wave intensity, The transmit power set for the device, and are the transmitting and receiving antenna gains, is the wavelength, and , , Target distance

[0064] S112. Using the Doppler effect, the pedestrian speed is calculated based on the frequency difference between the transmitted wave and the reflected wave. The formula for calculating the pedestrian speed is: , where is the wavelength, Fixed frequency difference

[0065] S113. Calculate the distance between the pedestrian and the radar by measuring the time delay between the transmitted signal and the received reflected signal. The formula is: , where is the target distance, that is, the distance between the pedestrian and the radar, is the speed of light, For time delay;

[0066] S114. Based on the target distance and pedestrian speed at different time points, where the target distance is the distance between the pedestrian and the radar, the Kalman filter algorithm is used to predict the pedestrian's position at the next moment. The position is updated in combination with the newly measured data to depict the pedestrian's movement trajectory. The formula is: , where is the pedestrian's position at the next moment, is the position of the pedestrian at the previous moment, is the state transition matrix, is the control matrix, is the control variable.

[0067] In this embodiment, the data acquisition module identifies special groups of people including the following steps:

[0068] S121, continuously collecting images at a fixed frame rate, compressing the image data in JPGE format, and transmitting the image data in real time to the special pedestrian recognition unit and the status analysis unit via Ethernet or Wi-Fi;

[0069] S122. Generate a depth image by combining the calculated target distance data with the time-of-flight method, and transmit the depth information in binary format to the special pedestrian recognition unit and the state analysis unit;

[0070] S123, using a Gaussian filter algorithm to reduce image noise, and updating each new pixel value in the image, the formula is: , where The image after Gaussian filtering and noise reduction is at coordinate The new pixel value at position, The coordinates in the original image are The pixel value at position, is the Gaussian kernel standard deviation And use histogram equalization to enhance the image contrast. The formula is: , where is the grayscale histogram of the graphic, , is the cumulative distribution function, After histogram equalization, the image is at coordinate The new grayscale value of the pixel at position, The original image is at coordinates Gray value of the pixel at position

[0071] S124, through the convolution pooling operation, the convolution kernel is slid on the input feature map to perform point multiplication and accumulation calculation, and the coordinates in the output feature map are The formula for the element of position is: , where Output feature map The median coordinate is And the channel is is the coordinate index of the output feature map in the height and width directions, is the channel index of the input feature map, The coordinates in the convolution kernel are , the input channel is and the output channels are is the weight channel is the stride of the convolution operation

[0072] S125. After multiple rounds of convolution and pooling, the feature map output by the last pooling layer is flattened to convert the multi-dimensional feature map into a one-dimensional vector. The formula is: , where is the one-dimensional image feature vector obtained after flattening operation, 、 The height, width and number of channels of the output feature map of the last convolutional pooling layer are respectively

[0073] S126. Input the extracted feature vector into a value classifier to calculate different types of pedestrians, including but not limited to ordinary pedestrians, blind people, people in wheelchairs, people with crutches, and people with abnormal walking conditions. The formula is: , where The output of the classifier The category index.

[0074] In this embodiment, the data acquisition module acquires the vehicle driving status data including the following steps:

[0075] S131. Multiple geomagnetic sensors are buried 5-10 cm below the lane within the preset sensing area of ​​the zebra crossing to detect the voltage signal generated when a vehicle passes by. The rising and falling edge times are recorded. The vehicle speed is calculated based on the time difference between vehicles passing adjacent geomagnetic sensors and the preset distance between adjacent geomagnetic sensors. The formula is: , where is the vehicle speed, The preset length between adjacent geomagnetic sensors, is the time difference between vehicles passing adjacent geomagnetic sensors;

[0076] S132. Estimate the vehicle length based on the sensing signal duration and speed using the following formula: , where To estimate the vehicle length, The time difference between the front and rear wheels of the vehicle passing the geomagnetic sensor;

[0077] S133. Collect vehicle image information and perform feature extraction and comparison on the detected vehicle image using the same feature extraction method as that used for pedestrian feature extraction to identify the specific vehicle model. The voltage signal of the vehicle passing by is obtained from the weighing sensor set between adjacent geomagnetic sensors, and the vehicle weight is calculated using a calibration method. The formula is: , where is the voltage signal, is the offset

[0078] Preferably, the behavior analysis module combines the speed data measured by the millimeter wave radar and the speed estimation value obtained by the depth sensor with the visual analysis using a weighted fusion algorithm to obtain the fusion speed, and the formula is: , where is the fusion speed, and are the speed measured by the millimeter-wave radar and the speed estimate obtained by the depth sensor combined with visual analysis, and are the corresponding weights, and , and set the speed threshold , where For pedestrians at rest, In slow walking state, Normal walking state, In fast walking state, by integrating speed With set threshold speed The walking status of the pedestrian is judged by the ratio of .

[0079] In this embodiment, the data analysis module determines and calculates the duration of a pedestrian passing through a traffic light, including the following steps:

[0080] S31. Compare the actual distance between the vehicle and the zebra crossing with the calculated braking distance to determine whether it is safe for the pedestrian to cross the zebra crossing;

[0081] S32. When it is determined that the first vehicle in the traffic flow can still stop at the zebra crossing after adding the margin time and the yellow light time as reaction time, according to the kinematic formula , where is the final velocity of the first vehicle in the current traffic flow, that is , For the current speed, is the acceleration, For time, When the red light of the lane turns on, Time required to brake the first vehicle in the flow is a margin time, and The minimum value is , The yellow light duration of the lane, the value range is ;

[0082] S33. Based on the number of pedestrians in the group, with each pedestrian except the first one maintaining a safe distance from the previous pedestrian, calculate the time required for all types of pedestrians to cross the zebra crossing. The formula is: , where For the The time it takes for an individual to cross a zebra crossing, As the leader of the pedestrian team, is the length of the zebra crossing, is the average speed of the slowest person in the pedestrian group crossing the zebra crossing, Provide safe spacing between pedestrians;

[0083] S34, for the The time required for an individual to cross the zebra crossing is added with a margin time to calculate the green light time of the zebra crossing. The formula is: , where Green light time for zebra crossing, is the time required for the first vehicle in the traffic flow to brake, is another margin time, and The minimum value is , and add a zebra crossing yellow light time to calculate the lane red light time. The formula is , where The remaining time of the red light in the lane, The yellow light time of zebra crossing, the value range is .

[0084] In this embodiment, in step S31, when it is determined that it is unsafe for pedestrians to cross the zebra crossing, a signal is sent to the early warning trigger module, which first triggers an audible and visual alarm signal, and then calculates the countdown of the vehicle green light and the pedestrian red light. The countdown generation includes the following steps:

[0085] S41. Calculate the number of vehicles in the current traffic flow that can safely stop at the zebra crossing. Calculate the number of vehicles in the traffic flow that can safely stop at a speed of 0 using a kinematic formula. The formula is: , where is the acceleration of the vehicle at the moment of braking, The time it takes for the vehicle to stop safely from the start of braking, that is, the braking duration. The displacement of the vehicle from the start of braking to safe stopping, that is, the braking distance;

[0086] S42. Add a safety margin to the braking time to ensure that the vehicle has enough time to react and stop safely. The formula is: , where The remaining time of the green light for the lane, is another margin duration, and The minimum value is ;

[0087] S43. Calculate the duration of the red light at the zebra crossing based on the remaining green light duration in the lane. The formula is: , where The duration of the red light at the zebra crossing. The yellow light duration of the lane, the value range is , is another margin duration, and The minimum value is .

[0088] Specifically, by accurately identifying special pedestrians and their status, providing them with sufficient green light time and voice guidance, and by obtaining information on vehicle type, length, speed and weight, analyzing the distance that the vehicle can brake, it can greatly optimize road traffic effects, and effectively avoid special pedestrians from being in danger when crossing the road due to unreasonable traffic light timing. While ensuring the safety of special pedestrians, it combines vehicle detection information to reasonably control traffic light timing and reduce unnecessary waiting time for vehicles.

[0089] In this embodiment, the dynamic update module updates the pedestrian crossing time of the zebra crossing including the following steps:

[0090] S51. Use pressure sensors deployed on the zebra crossing to sense pressure changes in real time, record pedestrian footsteps and movement information, and calculate the speed changes of pedestrians on the zebra crossing in combination with image acquisition. The formula is: , where and are the walking speeds of pedestrians at adjacent moments, is the change in pedestrian walking speed, is the time interval;

[0091] S52, when pedestrian speed appears 、 When the pedestrian's posture is obviously unbalanced or paused, which does not conform to the normal model through image analysis, and the pressure sensor data shows that the footsteps move chaotically, it is determined that the walking state is abnormal. In the formula, and are the average speed and acceleration of pedestrians on the zebra crossing, 、 、 as well as are the minimum, maximum average speed and acceleration of pedestrians on the zebra crossing respectively;

[0092] S53. Calculate the remaining distance from the pedestrian to the destination using the following formula: , where is the remaining distance for the pedestrian to reach the destination, is the total length of the zebra crossing, is the distance the pedestrian has walked, and the time it takes for the pedestrian to cross the remaining zebra crossing distance is calculated using the formula: , where To predict the time it takes for pedestrians to cross the remaining zebra crossing distance, is the restitution coefficient, is the possible acceleration recovery situation of the pedestrian, Impossible acceleration recovery situations for pedestrians is the possible acceleration recovery situation of the pedestrian, To accommodate the impossible acceleration recovery of pedestrians, update the green light duration of the zebra crossing and the red light duration of the lane. The calculation formula is: , where For the updated green light duration of zebra crossing, The green light duration of the zebra crossing. For the updated lane red light duration, The length of time the lane's red light has been on.

[0093] In this embodiment, the signal control module controls the signal light including the following steps:

[0094] S61. Receive instructions via wired or wireless communication and verify format and data integrity;

[0095] S62, converting the digital instruction into an analog control signal suitable for the drive circuit;

[0096] S63, driving the signal light driving circuit to control the on and off switching of the traffic light and the start and stop of the sound and light alarm;

[0097] S64: Feedback the working status of the traffic light to the data analysis module for data storage and update.

[0098] Specifically, the dynamic update module has powerful adaptive capabilities. It can not only capture changes in pedestrians' walking status in real time, but also use advanced algorithms to accurately predict pedestrians' remaining passing time based on factors such as the possible speed recovery situation (PSRS) and impossible speed recovery situation (ISRS) when pedestrians encounter unexpected situations while crossing the zebra crossing. This dynamic and intelligent adjustment mechanism ensures that the traffic light duration always matches the actual crossing needs of pedestrians. When an abnormal pedestrian walking status is detected, it can quickly and accurately judge and accurately update the pedestrian passing time based on a scientific calculation model, and promptly feedback to the traffic light control system and voice prompt system, effectively avoiding pedestrians being stranded in the road due to unreasonable traffic light time settings, and significantly improving the safety and smoothness of pedestrian crossing.

[0099] The above embodiments are intended to illustrate the present invention only and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the embodiments, it should be understood by those skilled in the art that various combinations, modifications, or equivalent substitutions of the technical solutions of the present invention do not depart from the spirit and scope of the technical solutions of the present invention and should be encompassed by the scope of the claims of the present invention.

Claims

1. A pedestrian crossing zebra crossing traffic safety signal control system, characterized in that: include: Data acquisition module, used to obtain pedestrian status, identify special groups of people, and obtain vehicle type, speed and weight data; The data acquisition module acquires the multimodal pedestrian status including the following steps: S111, generate a millimeter wave signal at a fixed frequency, calculate the reflected wave intensity according to the transmission power set by the device; S112. Calculate the pedestrian's speed based on the frequency difference between the transmitted wave and the reflected wave using the Doppler effect; S113. Calculate the distance between the pedestrian and the radar by measuring the time delay between the transmitted signal and the received reflected signal; S114. Based on the target distance and pedestrian speed at different time points, where the target distance is the distance between the pedestrian and the radar, the pedestrian's next position is predicted using a Kalman filter algorithm. The position is updated in combination with the newly measured data to depict the pedestrian's movement trajectory. The following steps are also included: S121, continuously collecting images at a fixed frame rate, compressing the image data in JPGE format, and transmitting the image data in real time to the special pedestrian recognition unit and the status analysis unit via Ethernet or Wi-Fi; S122. Generate a depth image by combining the calculated target distance data with the time-of-flight method, and transmit the depth information in binary format to the special pedestrian recognition unit and the state analysis unit; S123, using a Gaussian filtering algorithm to reduce noise in the image, updating each new pixel value in the image, and using histogram equalization to enhance image contrast; S124, through the convolution pooling operation, the convolution kernel is slid on the input feature map to perform point multiplication and accumulation calculation, and the coordinates in the output feature map are Elements of position; S125. After multiple rounds of convolution and pooling, the feature map output by the last pooling layer is flattened to convert the multi-dimensional feature map into a one-dimensional vector. S126. Input the extracted feature vector into a value classifier to calculate different types of pedestrians, including but not limited to ordinary pedestrians, blind people, people in wheelchairs, people with crutches, and people with abnormal walking conditions; The following steps are also included: S131. Detect the voltage signal generated by a vehicle passing through multiple geomagnetic sensors buried 5-10 cm below the lane within a preset sensing area of ​​the zebra crossing, record the rising and falling edge times, and calculate the vehicle speed based on the time difference between the vehicles passing adjacent geomagnetic sensors and the preset distance between adjacent geomagnetic sensors. S132. Estimate the vehicle length based on the duration and speed of the sensing signal, collect vehicle image information, and use the same feature extraction method as the pedestrian feature extraction method to extract and compare features of the detected vehicle image to identify the specific vehicle model; S133, obtaining a voltage signal when a vehicle passes by using a weighing sensor provided between adjacent geomagnetic sensors, and calculating the vehicle weight using a calibration method; The behavior analysis module is connected to the data acquisition module through data transmission technology and is used to predict pedestrian behavior trends and vehicle traffic conditions; The data analysis module is connected to the behavior analysis module through data transmission technology and is used to analyze whether to allow pedestrians to cross the zebra crossing and estimate the time it takes for pedestrians to cross the zebra crossing based on predictive data. The module includes the following steps: S31. Compare the actual distance between the vehicle and the zebra crossing with the calculated braking distance to determine whether it is safe for the pedestrian to cross the zebra crossing; S32. When it is determined that the first vehicle in the traffic flow can still stop at the zebra crossing after adding the margin time and the yellow light time as reaction time, calculate the vehicle stopping position; S33. Based on the number of pedestrians in the group, with the exception of the first pedestrian, each subsequent pedestrian maintains a safe distance from the previous pedestrian, and calculate the time required for all types of pedestrians to cross the zebra crossing; S34, for the The time required for an individual to cross the zebra crossing is added with a margin time to calculate the green light time of the zebra crossing; The warning trigger module is connected to the data analysis module through data transmission technology. It is used to trigger the warning signal when it determines that pedestrians are not allowed to pass, and calculate the countdown of the vehicle green light and the pedestrian red light. It includes the following steps: S41. Calculate the number of vehicles in the current traffic flow that can safely stop at the zebra crossing, and calculate the number of vehicles in the traffic flow that can safely stop at a speed of zero using a kinematic formula; S42: Add a safety margin to the braking time to ensure that the vehicle has enough time to react and stop safely. S43. Calculate the duration of the red light at the zebra crossing based on the remaining duration of the green light in the lane; The dynamic update module is connected to the data analysis module through data transmission technology and is used to update the pedestrian's predicted crossing time and crossing status in real time when the pedestrian crosses the zebra crossing. The dynamic update module includes the following steps: S51. Using pressure sensors deployed on the zebra crossing to sense pressure changes in real time, record pedestrian footsteps and movement information, and calculate pedestrian speed changes on the zebra crossing based on image acquisition; S52: When the pedestrian's speed changes, or the image analysis shows that the pedestrian's posture is obviously unbalanced or the pauses do not conform to the normal model, and the pressure sensor data shows that the footsteps are chaotic, it is determined that the walking state is abnormal; S53, calculating the remaining distance of the pedestrian to the end point, and calculating the time it takes for the pedestrian to cross the remaining zebra crossing distance, and updating the green light duration of the zebra crossing and the red light duration of the lane; The signal control module is connected to the data analysis module and the warning trigger module through data transmission technology. It is used to control the display of traffic lights, send audible and visual alarms to pedestrians after triggering warning information, and update the display of traffic lights in real time; In step S32, the formula for calculating the vehicle stop position is: , where is the final velocity of the first vehicle in the current traffic flow, that is , For the current speed, is the acceleration, For time, When the red light of the lane turns on, is the time required for the first vehicle in the traffic flow to brake, is a margin time, and The minimum value is , The yellow light duration of the lane, the value range is In step S33, the formula for calculating the time required for all types of people to cross the zebra crossing is: , where For the The time it takes for an individual to cross a zebra crossing, As the leader of the pedestrian team, is the length of the zebra crossing, is the average speed of the slowest person in the pedestrian group crossing the zebra crossing, is the safe spacing distance between pedestrians. In step S34, the formula for calculating the green light time of the zebra crossing is: , where Green light time for zebra crossing, is the time required for the first vehicle in the traffic flow to brake, is another margin time, and The minimum value is , and add a zebra crossing yellow light time to calculate the lane red light time. The formula is , where The remaining time of the red light in the lane, The yellow light time of zebra crossing, the value range is ; In step S51, the formula for calculating the pedestrian's speed change is: , where and are the walking speeds of pedestrians at adjacent moments, is the change in pedestrian walking speed, is the time interval. In step S52, the formula for comparing pedestrian speed changes is: 、 Where, and are the average speed and acceleration of pedestrians on the zebra crossing, 、 、 as well as are the minimum and maximum average speeds and accelerations of the pedestrian on the zebra crossing, respectively. In step S53, the formula for calculating the remaining distance from the pedestrian to the end point is: , where is the remaining distance for the pedestrian to reach the destination, is the total length of the zebra crossing, is the distance the pedestrian has walked. The formula for calculating the remaining time for the pedestrian to cross the zebra crossing is: , where To predict the time it takes for pedestrians to cross the remaining zebra crossing distance, is the restitution coefficient, is the possible acceleration recovery situation of the pedestrian, To accommodate the impossible acceleration recovery of pedestrians, the formula for updating the green light duration at the zebra crossing and the red light duration at the lane is: , where For the updated green light duration of zebra crossing, The length of time the green light at the zebra crossing has been on. For the updated lane red light duration, The length of time the lane's red light has been on.

2. A pedestrian crossing zebra crossing traffic safety signal control system according to claim 1, characterized in that: In step S111, the formula for calculating the reflected wave intensity is: , where is the reflected wave intensity, The transmit power set for the device, and are the transmitting and receiving antenna gains, is the wavelength, and , is the speed of light, is a fixed frequency, is the target radar cross section, is the target distance. In step S112, the formula for calculating the pedestrian speed is: , where is the pedestrian's current speed, is the wavelength, For a fixed frequency difference, in step S113, the formula for calculating the distance between the pedestrian and the radar is: , where is the target distance, that is, the distance between the pedestrian and the radar, is the speed of light, For time delay, in step S114, the formula for describing the pedestrian's motion trajectory is: , where is the pedestrian's position at the next moment, is the position of the pedestrian at the previous moment, is the state transition matrix, is the control matrix, is the control variable.

3. A pedestrian crossing zebra crossing traffic safety signal control system according to claim 2, characterized in that: In step S123, the image noise reduction formula is: , where The image after Gaussian filtering and noise reduction is at coordinate The new pixel value at position, The coordinates in the original image are The pixel value at position, is the Gaussian kernel standard deviation, and the formula for enhancing image contrast is: , where is the grayscale histogram of the graphic, and All are grayscale values, with a range of , is the cumulative distribution function, After histogram equalization, the image is at coordinate The new pixel grayscale value at position, The original image at coordinates The grayscale value of the pixel at the position, in step S124, the coordinates in the feature map are output The formula for the element of position is: , where Output feature map The median coordinate is And the channel is The element value of and are the coordinate indexes of the output feature map in the height and width directions, is the size of the convolution kernel in high dimensions, and are the indexes of the convolution kernel in high and wide dimensions respectively. is the channel index of the input feature map, The coordinates in the convolution kernel are , the input channel is and the output channels are The weight value of is the weight channel The bias value of is the step size of the convolution operation. In step S125, the formula for flattening the feature map is: , where is the one-dimensional image feature vector obtained after flattening operation, 、 and are the height, width and number of channels of the output feature map of the last convolutional pooling layer respectively. In step S126, the formula for calculating the different types of pedestrians is: , where The output of the classifier Class score, is the total number of categories, The category index.

4. A pedestrian crossing zebra crossing traffic safety signal control system according to claim 3, characterized in that: In step S131, the formula for calculating the vehicle speed is: , where is the vehicle speed, is the preset length between adjacent geomagnetic sensors, is the time difference between the vehicle passing adjacent geomagnetic sensors. In step S132, the formula for estimating the vehicle length is: , where To estimate the vehicle length, is the time difference between the front and rear wheels of the vehicle passing the geomagnetic sensor. In step S133, the formula for calculating the vehicle weight is: , where is the vehicle weight, is the calibration coefficient, is the voltage signal, is the offset.

5. A pedestrian crossing zebra crossing traffic safety signal control system according to claim 4, characterized in that: The behavior analysis module combines the speed data measured by the millimeter wave radar and the speed estimate obtained by the depth sensor with the visual analysis using a weighted fusion algorithm to obtain the fused speed. The formula is: , where is the fusion speed, and are the speed measured by the millimeter-wave radar and the speed estimate obtained by the depth sensor combined with visual analysis, and are the corresponding weights, and , and set the speed threshold , where For pedestrians at rest, In slow walking state, Normal walking state, In fast walking state, by integrating speed With set threshold speed The walking status of the pedestrian is judged by the ratio of .

6. A pedestrian crossing zebra crossing traffic safety signal control system according to claim 4, characterized in that: The data acquisition module calculates the braking distance of the vehicle based on the vehicle weight, driving speed and vehicle type. The formula is: , where is the braking distance, is the braking coefficient, is the acceleration due to gravity.

7. A pedestrian crossing zebra crossing traffic safety signal control system according to claim 6, characterized in that: In step S41, the dynamics formula is: , where is the acceleration of the vehicle at the moment of braking, The time it takes for the vehicle to stop safely from the start of braking, that is, the braking duration. The displacement of the vehicle from the start of braking to safe parking, i.e., the braking distance. In step S42, the braking time is calculated as follows: , where The remaining time of the green light for the lane, is another margin duration, and The minimum value is In step S43, the formula for calculating the duration of the zebra crossing red light is: , where The duration of the red light at the zebra crossing. The yellow light duration of the lane, the value range is , is another margin duration, and The minimum value is .

8. A pedestrian crossing zebra crossing traffic safety signal control system according to claim 1, characterized in that: The signal control module controls the signal light including the following steps: S61. Receive instructions via wired or wireless communication and verify format and data integrity; S62, converting the digital instruction into an analog control signal suitable for the drive circuit; S63, driving the signal light driving circuit to control the on and off switching of the traffic light and the start and stop of the sound and light alarm; S64: Feedback the working status of the traffic light to the data analysis module for data storage and update.

Images