Column blind area traffic accident early warning method and system

Abstract

The invention provides an upright post blind area traffic accident early warning method and system, and the method comprises the steps: collecting a video of an upright post blind area through a camera when a first road where the upright post blind area is located is red, inputting the video into a target detection model, and detecting whether a to-be-detected target exists in the upright post blind area; constructing a coordinate system for a column blind area in the video, positioning a to-be-detected target through the video and a sensor under the condition that the to-be-detected target is detected in the column blind area, and calculating the speed and acceleration of the to-be-detected target; according to the speed and the acceleration of the to-be-detected target and the distance between the to-be-detected target and the second road, the danger degree is obtained through comprehensive evaluation, and under different danger degrees, different early warnings are given to vehicles on the second road. By positioning the target and calculating the speed and the acceleration, the danger degree of the target is accurately pre-judged, traffic accidents caused by the fact that pedestrians are located in a blind area are effectively avoided, and the safety of traffic participants is guaranteed.

Description

Technical Field

[0001] The present invention relates to the field of intelligent transportation, and in particular to a method and system for early warning of accidents in blind spots of pillars. Background Art

[0002] Elevated roads are mainly built to increase driving speed or solve safety issues at the intersection of roads, railways or pedestrian routes. They are connected to ground roads through ramps and avoid intersections with ground roads by using three-dimensional intersections. In urban areas, in order to meet the need for rapid entry and exit of urban center areas, there are also dozens of kilometers of roads designed entirely on elevated roads.

[0003] Elevated roads not only bring great convenience to urban commuting, but also bring certain traffic safety risks. Figure 1 As shown, for vehicles passing through the intersection towards the main road, the area directly behind pillar one and the area to the right behind pillar two are blind spots, and this area happens to be where the non-motorized vehicle lane and zebra crossing are located. If a non-motorized vehicle or pedestrian rushes out of the blind spot when the vehicle passes through the intersection with a normal green light, it can easily cause a traffic accident.

[0004] After searching, it was found that the research of the prior art mainly focuses on the traffic accident warning of the right turn blind spot of the vehicle itself, such as patent document CN117912257A. The research on traffic accident warning of the blind spot behind the elevated column mainly uses motion sensors to detect whether there are moving objects in the blind spot to determine whether there are pedestrians or non-motor vehicles. Although this judgment method can detect pedestrians and non-motor vehicles, it can only indicate that there are people in the blind spot, and cannot predict whether pedestrians and non-motor vehicles will rush out of the blind spot, so the safety is limited. Summary of the invention

[0005] In view of the defects in the prior art, an object of the present invention is to provide a method and system for warning traffic accidents in the blind spot of a pillar.

[0006] A column blind spot traffic accident warning method provided by the present invention comprises: Target recognition step: when the traffic light of the first road where the pillar blind spot is located is red, the video of the pillar blind spot is collected by a camera, and the video is input into the target detection model to detect whether there is a target to be detected in the pillar blind spot; Motion state calculation steps: construct a coordinate system for the blind area of ​​the column in the video. When a target to be measured is detected in the blind area of ​​the column, the target to be measured is located through the video and the sensor, and the speed and acceleration of the target to be measured are calculated; Decision-making steps: Based on the speed, acceleration and distance of the target to be measured from the second road, a comprehensive assessment is made to obtain the degree of danger. Different warnings are issued to vehicles on the second road at different degrees of danger.

[0007] Furthermore, the method of locating the target to be measured includes: According to the position of the target to be measured in the video, the first position information (x1, y1, z1) of the target to be measured is determined, and the standard deviation of its position is (σ x1 , σ y1 , σ z1 ), the second position information (x2, y2, z2) of the target to be measured is determined by the millimeter wave radar, and the standard deviation of its position is (σ x2 , σ y2 , σ z2 ), the third position information (x3, y3, z3) of the target to be measured is determined by the laser sensor, and the standard deviation of the position is (σ x3 , σ y3 , σ z3 ), through the Bayesian fusion algorithm, the fused position information (x, y, z) and standard deviation (σ x , σ y , σ z ).

[0008] Furthermore, for the x coordinate: , ,

[0009] K= + +

[0010]

[0011]

[0012] The same goes for the y and z coordinates.

[0013] Furthermore, the speed calculation method of the target to be measured includes: Get the fusion position information of the target to be measured at time t1 (x t1 ,y t1 , z t1 ), and the fused position information at time t2 (x t2 ,y t2 , z t2 ), Δt= t2- t1; The speed of the target to be measured : .

[0014] Furthermore, the acceleration of the target to be measured is calculated by: Get the fusion position information of the target to be measured at time t3 (x t3 ,y t3 , z t3 ) The acceleration of the target to be measured in the x direction :

[0015] The acceleration of the target to be measured in the y and z directions , Same reason.

[0016] Furthermore, the comprehensive assessment of the degree of danger includes:

[0017] d is the vertical distance between the fused position information and the edge of the column blind spot close to the second road side.

[0018] Furthermore, when there is no target to be measured in the blind spot of the pillar, D=0, which is the first danger level, and the vehicles on the second road are warned by the green signal light. When D belongs to (0, D0), it is the second danger level, and the vehicles on the second road are warned by switching between red and yellow signal lights. When D is greater than or equal to D0, it is the third danger level, and the vehicles on the second road are warned by the red signal light and the projection light.

[0019] A column blind spot traffic accident warning system provided by the present invention comprises: Camera: When the traffic light on the first road where the pillar blind spot is located is red, collect the video of the pillar blind spot; Target detection model: obtain the video of the blind spot of the column collected by the camera, and detect whether there is a target to be detected in the blind spot of the column; Processing module: Construct a coordinate system for the blind spot of the pillar in the video. When a target to be measured is detected in the blind spot of the pillar, the target to be measured is located through video and sensors respectively, and the speed and acceleration of the target to be measured are calculated. According to the speed and acceleration of the target to be measured and the distance from the second road, a comprehensive assessment is made to obtain the degree of danger. Under different degrees of danger, different warnings are issued to vehicles on the second road.

[0020] Furthermore, the sensor includes: a millimeter wave radar and a laser sensor.

[0021] Furthermore, it also includes a signal light and a projection light, and early warning is performed through the signal light and the projection light.

[0022] Compared with the prior art, the present invention has the following beneficial effects: The present invention accurately predicts the danger level of the target by locating the target and calculating the speed and acceleration, effectively avoiding traffic accidents caused by pedestrians in blind spots, compensating for the inherent deficiencies of drivers and vehicles themselves in observing blind spots, and ensuring the safety of traffic participants.

[0023] The present invention fully utilizes the advantages of different sensors through multi-sensor fusion, improves the accuracy and reliability of detecting pedestrians in the blind spot behind the elevated column, and can effectively detect pedestrians regardless of daytime, nighttime or severe weather conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings: Figure 1 This is a schematic diagram of the road under the viaduct; Figure 2 It is a work flow chart of the present invention; Figure 3 It is a test effect diagram of the present invention. DETAILED DESCRIPTION

[0025] The present invention is described in detail below in conjunction with specific embodiments. The following embodiments will help those skilled in the art to further understand the present invention, but are not intended to limit the present invention in any form. It should be noted that, for those of ordinary skill in the art, several changes and improvements can also be made without departing from the concept of the present invention. These all belong to the protection scope of the present invention.

[0026] like Figure 2 As shown, a column blind spot traffic accident warning method provided by the present invention includes: Target identification steps: On the first road where the pillar blind spot is located ( Figure 1 When the traffic light on the non-motorized vehicle lane is red, the camera collects the video of the pillar blind spot, inputs the video into the target detection model, and detects whether there is a target in the pillar blind spot. Figure 1 There are two pillars in the vehicle, so there will be two blind spots on the second road (the main road part of the motor vehicle lane), where pillar one produces the first blind spot and pillar two produces the second blind spot, so they need to be detected separately.

[0027] The camera is used to collect images or video information of the blind spots behind the elevated columns to provide basic data for subsequent image analysis. A camera with high resolution and high frame rate can be selected to ensure that clear images can be obtained under different lighting and weather conditions. The millimeter-wave radar can detect the distance, speed and location information of pedestrians by emitting and receiving millimeter-wave signals. It is particularly advantageous in severe weather or low-light conditions and can penetrate some obstacles for detection. The laser sensor can accurately measure the distance between pedestrians and columns, and accurately determine the location information of pedestrians by emitting laser beams and receiving reflected signals. In the present invention, it is preferred to turn on each sensor and start subsequent calculation steps after detecting the target to avoid wasting energy and computing resources. The installation position of each sensor can be in Figure 1 The back of the center column.

[0028] The target detection model uses deep learning algorithms to process the images or video data collected by the camera and identify pedestrians and non-motor vehicles. Deep learning architectures such as convolutional neural networks (CNNs) can be used here to automatically extract the features of pedestrians and non-motor vehicles in the image through pre-trained models.

[0029] Motion state calculation steps: Construct a coordinate system for the blind spot of the column in the video. When a target to be measured is detected in the blind spot of the column, locate the target to be measured through the video and the sensor, and calculate the speed and acceleration of the target to be measured.

[0030] In this step, the data collected by the sensor can first be converted into a format, de-noised, normalized, and other operations to make the data meet the requirements of subsequent processing. Then the data from different sensors are fused and processed, combining the image recognition information and the distance and speed information of the radar and laser sensors to comprehensively determine the accurate position and movement status of the pedestrian.

[0031] The methods for locating the target to be measured include: According to the position of the target to be measured in the video, the first position information (x1, y1, z1) of the target to be measured is determined, and the standard deviation of its position is (σ x1 , σ y1 , σ z1 ), the second position information (x2, y2, z2) of the target to be measured is determined by the millimeter wave radar, and the standard deviation of its position is (σ x2 , σ y2 , σ z2 ), the third position information (x3, y3, z3) of the target to be measured is determined by the laser sensor, and the standard deviation of the position is (σ x3 , σ y3 , σ z3 ), through the Bayesian fusion algorithm, the fused position information (x, y, z) and standard deviation (σx , σ y , σ z ).

[0032] For the x coordinate: , ,

[0033] K= + +

[0034]

[0035]

[0036] The same is true for the y-coordinate and z-coordinate. , , In the value of , the smaller the standard deviation of the sensor (the more reliable the measurement result), the larger its reciprocal is, and the greater the weight it occupies in the fusion calculation. In this way, the measurement accuracy of different sensors can be comprehensively considered, and more accurate measurement results can be given higher weights to obtain a more accurate and reliable pedestrian and non-motor vehicle position estimate.

[0037] Since different sensors have different performances under different environmental conditions (such as lighting, weather, occlusion, etc.), the accuracy of their pedestrian position measurements will also vary. The standard deviation can be used to quantify this difference and incorporate it into the information fusion calculation process, making the final fused pedestrian position information more accurate and reliable, thereby improving the accuracy and reliability of the entire system's detection of pedestrians in the blind spot behind the elevated column. By considering the standard deviation in the system, the characteristics and advantages of different sensors are fully utilized, the uncertainty of their measurements is taken into consideration, and the measurement errors caused by the limitations of a single sensor are avoided, providing a statistical and mathematical basis for improving the system's performance and more accurate pedestrian position judgment.

[0038] The speed calculation methods of the target to be measured include: Get the fusion position information of the target to be measured at time t1 (x t1 ,y t1 , z t1 ), and the fused position information at time t2 (x t2 ,y t2 , z t2 ),Δt= t2- t1.

[0039] The speed of the target to be measured :

[0040] The acceleration is calculated by: Get the fusion position information of the target to be measured at time t3 (x t3 ,y t3 , z t3 ).

[0041] The acceleration of the target to be measured in the x direction :

[0042] The acceleration of the target to be measured in the y and z directions , Same reason.

[0043] Furthermore, the comprehensive assessment of the degree of danger includes:

[0044] d is the distance of the fused position information from the blind spot of the column close to the second road ( Figure 1 The vertical distance from the edge of one side of the motor vehicle lane.

[0045] By comprehensively considering the position coordinates and distance d, speed, and acceleration factors of the pedestrian, the degree of danger is calculated and quantified, which enables the system to more accurately assess the dangerous situation of the pedestrian and avoid the ambiguity and uncertainty of subjective judgment. The system can reasonably allocate resources according to different danger levels. For example, for situations with a higher degree of danger, the system can increase the scanning frequency of the sensor, or increase the volume and intensity of the alarm to ensure that the driver can respond in time.

[0046] Decision-making steps: Based on the speed, acceleration and distance of the target to be measured from the second road, a comprehensive assessment is made to obtain the degree of danger. Different warnings are issued to vehicles on the second road at different degrees of danger.

[0047] like Figure 3 As shown, when there is no target to be measured in the blind spot of the column, D=0, which is the first danger level. The green signal light "Pay attention to the blind spot, slow down" is used to warn the vehicles on the second road. When D belongs to (0, D0), it is the second danger level. The red signal light "Pay attention to non-motor vehicle intrusion" and the yellow signal light (pay attention to the sign) are switched to warn the vehicles on the second road. When D is greater than or equal to D0, it is the third danger level. The red signal light "Pay attention to non-motor vehicle intrusion" and the projection light project "Pay attention to non-motor vehicle intrusion" onto the road surface of the second road to warn the vehicles on the second road. After several months of testing, according to the data provided by the traffic control department, the present invention can make the accident pressure reduction rate reach more than 50% year-on-year.

[0048] The present invention also provides a pillar blind spot traffic accident warning system, which can be implemented by executing the process steps of the pillar blind spot traffic accident warning method, that is, those skilled in the art can understand the pillar blind spot traffic accident warning method as a preferred implementation of the pillar blind spot traffic accident warning system. The system includes: Camera: When the traffic light on the first road where the pillar blind spot is located is red, collect the video of the pillar blind spot; Target detection model: obtain the video of the blind spot of the column collected by the camera, and detect whether there is a target to be detected in the blind spot of the column; Processing module: Construct a coordinate system for the blind spot of the pillar in the video. When a target to be measured is detected in the blind spot of the pillar, the target to be measured is located through video and sensors respectively, and the speed and acceleration of the target to be measured are calculated. According to the speed and acceleration of the target to be measured and the distance from the second road, a comprehensive assessment is made to obtain the degree of danger. Under different degrees of danger, different warnings are issued to vehicles on the second road.

[0049] Those skilled in the art know that, in addition to realizing the system and its various devices, modules, and units provided by the present invention in a purely computer-readable program code, it is entirely possible to realize the same functions in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers by logically programming the method steps. Therefore, the system and its various devices, modules, and units provided by the present invention can be considered as a hardware component, and the devices, modules, and units included therein for realizing various functions can also be regarded as structures within the hardware component; the devices, modules, and units for realizing various functions can also be regarded as both software modules for realizing the method and structures within the hardware component.

[0050] In the description of the present application, it should be understood that the terms "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0051] The above describes the specific embodiments of the present invention. It should be understood that the present invention is not limited to the above specific embodiments, and those skilled in the art can make various changes or modifications within the scope of the claims, which does not affect the essence of the present invention. In the absence of conflict, the embodiments of the present application and the features in the embodiments can be combined with each other arbitrarily.

Claims

1. A method for warning traffic accidents in pillar blind spots, characterized in that: include: Target recognition step: when the traffic light of the first road where the pillar blind spot is located is red, the video of the pillar blind spot is collected by the camera, and the video is input into the target detection model to detect whether there is a target to be detected in the pillar blind spot; Motion state calculation steps: construct a coordinate system for the blind area of ​​the column in the video. When a target to be measured is detected in the blind area of ​​the column, the target to be measured is located through the video and the sensor, and the speed and acceleration of the target to be measured are calculated; Decision-making steps: Based on the speed, acceleration and distance of the target to be measured from the second road, a comprehensive assessment is made to obtain the degree of danger. Different warnings are issued to vehicles on the second road at different degrees of danger.

2. The pillar blind spot traffic accident warning method according to claim 1, characterized in that: The methods for locating the target to be measured include: According to the position of the target to be measured in the video, the first position information (x1, y1, z1) of the target to be measured is determined, and the standard deviation of its position is (σ x1 , σ y1 , σ z1 ), the second position information (x2, y2, z2) of the target to be measured is determined by the millimeter wave radar, and the standard deviation of its position is (σ x2 , σ y2 , σ z2 ), the third position information (x3, y3, z3) of the target to be measured is determined by the laser sensor, and the standard deviation of the position is (σ x3 , σ y3 , σ z3 ), through the Bayesian fusion algorithm, the fused position information (x, y, z) and standard deviation (σ x , σ y , σ z ).

3. The pillar blind spot traffic accident warning method according to claim 2 is characterized in that: For the x coordinate: ， ， K= + + The same goes for the y and z coordinates.

4. The pillar blind spot traffic accident warning method according to claim 3 is characterized in that: The speed calculation methods of the target to be measured include: Get the fusion position information of the target to be measured at time t1 (x t1 ,y t1 , z t1 ), and the fused position information at time t2 (x t2 ,y t2 , z t2 ), Δt= t2- t1; The speed of the target to be measured : 。 5. The pillar blind spot traffic accident warning method according to claim 4, characterized in that: The calculation method of the acceleration of the target to be measured includes: Get the fusion position information of the target to be measured at time t3 (x t3 ,y t3 , z t3 ) The acceleration of the target to be measured in the x direction : The acceleration of the target to be measured in the y and z directions , Same reason.

6. The pillar blind spot traffic accident warning method according to claim 5, characterized in that: Comprehensive assessment of the degree of risk includes: d is the vertical distance between the fused position information and the edge of the column blind spot close to the second road side.

7. The pillar blind spot traffic accident warning method according to claim 6, characterized in that: When there is no target to be measured in the blind spot of the column, D=0, which is the first danger level, and the vehicles on the second road are warned by the green signal light. When D belongs to (0, D0), it is the second danger level, and the vehicles on the second road are warned by switching between red and yellow signal lights. When D is greater than or equal to D0, it is the third danger level, and the vehicles on the second road are warned by the red signal light and the projection light.

8. A pillar blind spot traffic accident warning system, characterized in that: include: Camera: When the traffic light on the first road where the pillar blind spot is located is red, collect the video of the pillar blind spot; Target detection model: obtain the video of the blind spot of the column collected by the camera, and detect whether there is a target to be detected in the blind spot of the column; Processing module: Construct a coordinate system for the blind spot of the pillar in the video. When a target to be measured is detected in the blind spot of the pillar, the target to be measured is located through video and sensors respectively, and the speed and acceleration of the target to be measured are calculated. According to the speed and acceleration of the target to be measured and the distance from the second road, a comprehensive assessment is made to obtain the degree of danger. Under different degrees of danger, different warnings are issued to vehicles on the second road.

9. The pillar blind spot traffic accident warning system according to claim 8, characterized in that: The sensors include: millimeter wave radar and laser sensor.

10. The pillar blind spot traffic accident warning system according to claim 8, characterized in that: It also includes a signal light and a projection light, through which an early warning is given.

Images