WO2022142922A1 - Road safety assessment method, video processing center, and storage medium - Google Patents

Abstract

A road safety assessment method, a video processing center, and a storage medium. The method relates to the technical field of data processing, and the method comprises: acquiring a video frame sequence collected by a video device installed on a road, and determining a motion region in the road (101); according to an image block corresponding to the motion region in each video frame in the video frame sequence, determining motion information in the motion region (102); and according to the motion information in the motion region, determining safety assessment information of the road (103).

Description

Road safety assessment method, video processing center and storage medium

CROSS-REFERENCE TO RELATED APPLICATIONS

This application is based on the Chinese patent application with the application number "202011595033.7" and the application date is December 29, 2020, and claims the priority of the Chinese patent application. The entire content of the Chinese patent application is hereby incorporated by reference. Application.

technical field

The embodiments of the present application relate to the technical field of data processing, and in particular, to a road safety assessment method, a video processing center, and a storage medium.

Background technique

With the development of big data technology and cloud computing technology, the concept of smart city has become more and more popular among the people. It connects and integrates urban systems and services to improve the efficiency of resource utilization, optimize urban management and services, and improve the quality of life of citizens. . In terms of people's travel, the electronic map in the terminal has become an indispensable auxiliary tool for people's travel. The current electronic map is no longer limited to the function of finding paths. Most electronic maps also include intelligent voice assistants, intelligent positioning, location Search services, traffic jam display and other functions. However, the commonly used electronic maps provide people with routes without considering the safety issues when people travel on the provided routes.

SUMMARY OF THE INVENTION

An embodiment of the present application provides a road safety assessment method, including: acquiring a video frame sequence collected by a video device installed on a road, and determining a motion area in the road; according to each of the video frames in the video frame sequence The image block corresponding to the motion area is determined, and the motion information in the motion area is determined; the safety assessment information of the road is determined according to the motion information in the motion area.

Embodiments of the present application further provide a video processing center, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores data that can be executed by the at least one processor The instructions are executed by the at least one processor to enable the at least one processor to perform the road safety assessment method as described above.

Embodiments of the present application further provide a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the above-mentioned road safety assessment method is implemented.

Description of drawings

1 is a flowchart of a road safety assessment method according to a first embodiment of the present application;

FIG. 2 is a flowchart of determining a motion area in a road according to step 101 in the first embodiment of the present application;

FIG. 3 is a flowchart according to a specific implementation manner of step 103 in the first embodiment of the present application;

4 is a flowchart of a road safety assessment method according to a second embodiment of the present application;

FIG. 5 is a flowchart according to a specific implementation manner of step 202 in the second embodiment of the present application;

6 is a flowchart of a road safety assessment method according to a third embodiment of the present application;

7 is a schematic diagram of an interface for presenting navigation information on an electronic map on a terminal according to a third embodiment of the present application;

FIG. 8 is a schematic structural diagram of a video processing center according to a fourth embodiment of the present application.

Detailed ways

The embodiments of the present application provide a road safety assessment method, a video processing center, and a storage medium, which can improve the safety of a user's travel.

The road safety assessment method, video processing center and storage medium proposed in this application acquire the video frame sequence collected by the video equipment installed on the road, and determine the motion area in the road; according to the corresponding motion area in each video frame in the video frame sequence According to the motion information in the motion area, the safety assessment information of the road is determined. Through this method, the safety assessment information of the road can be provided for the user, so that the user can know the safety of the road. Thereby, the safety of users' travel is improved.

In order to make the objectives, technical solutions and advantages of the embodiments of the present application more clear, each embodiment of the present application will be described in detail below with reference to the accompanying drawings. However, those of ordinary skill in the art can understand that, in each embodiment of the present application, many technical details are provided for the reader to better understand the present application. However, even without these technical details and various changes and modifications based on the following embodiments, the technical solutions claimed in the present application can be realized. The following divisions of the various embodiments are for the convenience of description, and should not constitute any limitation on the specific implementation of the present application, and the various embodiments may be combined with each other and referred to each other on the premise of not contradicting each other.

The first embodiment of the present application relates to a road safety assessment method, which is applied to a video processing center. The video processing center is a server or terminal with computing performance. The specific process is shown in Figure 1, including:

Step 101: Obtain a video frame sequence collected by a video device installed on the road, and determine a motion area on the road.

In this embodiment, the road may be multiple roads from the origin and destination obtained according to the navigation request of the terminal, or may be a road obtained according to the query request of the terminal, and the terminal is a mobile phone, a tablet computer, etc.; In the embodiment, the road includes a road as an example for description, but it is not limited to this. The video processing center can obtain the video frame sequence collected by the video equipment installed on the road in real time, or obtain the video frame sequence collected by the video equipment installed on the road according to the preset period. The preset period can be set according to actual needs. This implementation The example is not specifically limited, and the number of video devices on the road may be greater than one. At this time, the video processing module in the video processing center obtains the captured video frame sequence from each video device. On the road, there may be moving objects such as pedestrians, vehicles, animals, etc. that can move, and there may also be objects that do not move, such as background walls and trees. The moving area is the area where the moving objects move by summarizing the video frame sequence. .

In one example, the flow chart for determining the motion area in the road is shown in Figure 2 and includes:

Step 1011 , performing differential processing on adjacent video frames in the video frame sequence to obtain each differential image.

Step 1012: Select target pixels whose pixel values are greater than a preset threshold from the pixels of each differential image, and determine a motion area according to the target pixels.

In this embodiment, the video processing center subtracts the pixels corresponding to adjacent video frames in the video frame sequence, then takes the absolute value of the difference, and determines each difference image according to the absolute value of the difference, for example: The pixels corresponding to the first video frame and the second video frame in the frame sequence are subtracted, and the absolute value of the difference is taken. The absolute value determines the first frame differential image. After each differential image is obtained, the pixels of each differential image are compared with a preset threshold, wherein the preset threshold can be set according to actual needs, which is not specifically limited in this embodiment. The target pixels whose pixel values are greater than the preset threshold are selected from the pixel points, so that certain interference information can be suppressed.

The adjacent video frames in the differential process are processed, and the video frame sequence of the differential image is obtained as

Then convert the video frame sequence of the differential image

The pixels in the video are compared with the preset threshold, and certain interference information is suppressed to obtain a video frame sequence.

Through such a method, the motion area can be determined by performing a simple calculation, the operation is simple, and the evaluation speed is improved.

In one example, after getting a sequence of video frames

After that, the resulting video frame sequence is also

Perform morphological processing to remove glitches, smooth boundaries, and obtain motion regions, for example: for the resulting video frame sequence

Carry out expansion corrosion operation. In one example, determining the motion area in the road includes: determining the motion area in the road through a three-frame difference method.

Step 102: Determine the motion information in the motion area according to the image blocks corresponding to the motion area in each video frame in the video frame sequence.

In this embodiment, the moving objects are detected from all the moving regions, and the motion information of the moving objects in the moving regions is determined according to the image blocks corresponding to the moving regions in each video frame. Wherein, the motion information includes at least one of the following information: the motion trajectory of the moving objects, the density of the moving objects, and the behavior of pedestrians. Since the motion trajectory of the moving objects, the density of the moving objects, and the behavior of pedestrians can all be more accurate The motion information of the moving object is reflected, so when the motion information includes at least one of them, the safety assessment information of the road can be more accurately determined.

Step 103: Determine the safety assessment information of the road according to the motion information in the motion area.

In one example, the motion information includes the behavior of pedestrians and the density of moving objects, and the safety assessment information includes a safety factor. :

Step 1031: Determine a first coefficient representing the congestion on the road according to the density of the moving objects.

Step 1032: Determine a second coefficient representing behavior safety on the road according to the behavior of the pedestrian.

In one example, the video processing center pre-establishes the correspondence between the density of moving objects on the entire road and the first coefficient representing the congestion situation on the road, and the correspondence between the behavior of pedestrians and the second coefficient representing the behavior safety on the road For example, when the density of moving objects on the entire road is high, the first coefficient representing the congestion on the road is 0.4, and when the pedestrian’s behavior includes fighting, the second coefficient representing the safety of behavior on the road is 0.4.

In one example, determining the first coefficient representing the congestion situation on the road according to the density of moving objects includes: according to the density of moving objects in each dangerous motion area, determining the corresponding congestion of each dangerous motion area and representing the congestion in the dangerous motion area The first sub-coefficient of the situation, according to each first sub-coefficient, determine the first coefficient that characterizes the congestion situation on the road; according to the behavior of pedestrians, determine the second coefficient that characterizes the behavior safety on the road, including: according to the pedestrians in each dangerous movement area determine the second sub-coefficient representing the behavioral safety of the dangerous motion area corresponding to each dangerous motion area; and determine the second coefficient representing the behavioral safety on the road according to each second sub-coefficient.

In this embodiment, the video processing center pre-establishes the correspondence between the density of moving objects in the dangerous movement area and the coefficients, uses the corresponding coefficient as the first sub-coefficient representing the congestion situation in the dangerous movement area, and pre-establishes the density of the moving objects in the dangerous movement area The corresponding relationship between pedestrian behavior and coefficient, the corresponding coefficient is used as the second sub-coefficient to characterize the behavior safety on the road; after each first sub-coefficient is obtained, the average value of each first sub-coefficient is taken as the indicator of road congestion. The first coefficient, for example, the density of moving objects in each dangerous sports area is: high, high, medium, and low, respectively, according to the corresponding relationship, the first sub-coefficients representing the congestion situation of the dangerous sports area corresponding to each dangerous sports area are obtained respectively. is: 0.4, 0.4, 0.3, 0.1, then the first coefficient representing the congestion on the road is the average value of each first sub-coefficient 0.3; after obtaining the second sub-coefficient, the average value of each second sub-coefficient is taken as the representation The second coefficient of behavioral safety on the road, for example, the behaviors of pedestrians in each dangerous sports area are: fighting, fighting and robbery, robbery, and normal behavior. The result of adding the coefficients corresponding to the behaviors of the two pedestrians can be used as the final coefficient. According to the corresponding relationship, the second sub-coefficients representing the behavioral safety of the dangerous motion areas corresponding to each dangerous motion area are respectively: 0.4, 1, 0.6 , 0, then the second coefficient representing behavior safety on the road is the average value of each second sub-coefficient 0.5. In an example, after each first sub-coefficient is obtained, a summation process may also be performed on each of the first sub-coefficients, and the result of the summation process is used as the first coefficient representing the congestion situation on the road, and after each second sub-coefficient is obtained After the coefficients, the second sub-coefficients can also be summed, and the result of the summation can be used as a second coefficient representing the congestion on the road.

Step 1033: Determine the safety factor of the road according to the first coefficient and the second coefficient.

In this embodiment, the video processing center may perform calculations such as addition or multiplication of the first coefficient and the second coefficient, and use the calculation result as the safety coefficient of the road. For example, if the first coefficient representing the congestion on the road is 0.4, and the second coefficient representing the behavior safety on the road is 0.4, the multiplication calculation is performed to obtain the safety coefficient of the road as 0.16.

Through this method, when determining the safety factor of the road, the first factor representing the congestion on the road and the second factor representing the behavioral safety on the road are considered at the same time. The factors considered are more comprehensive and the safety factor of the road is more accurate. And the pass coefficient can more intuitively identify the safety of the road.

In an example, according to the behavior of pedestrians in each dangerous movement area, determining the second sub-coefficient representing the behavioral safety of the dangerous movement area corresponding to each dangerous movement area, including: obtaining historical behaviors in each dangerous movement area from a preset database The preset database includes the historical behaviors and the probability of occurrence of historical behaviors in different sports areas in the historical time period; according to the behavior of pedestrians in each dangerous sports area and the historical behaviors The probability of occurrence is determined, and the second sub-coefficient representing the behavioral safety of the dangerous movement area corresponding to each dangerous movement area is determined.

In this embodiment, the preset database can be stored locally in the video processing center, and obtained directly from the local when the video processing center needs it; it can also be stored in an external server and obtained from the external server when the video processing center needs it. The preset database includes the historical behaviors and the probability of occurrence of historical behaviors in different motion areas in the historical time period, so the video processing center can obtain the probability of occurrence of historical behaviors in each dangerous motion area from the preset database, and the video processing The center pre-stores the corresponding relationship between the behaviors and coefficients of pedestrians in the dangerous motion areas, then the coefficients corresponding to the behaviors of pedestrians in each dangerous motion area and the probability of occurrence of historical behaviors in each dangerous motion area are weighted and summed to obtain The result is used as the second sub-coefficient representing the behavioral safety of the dangerous movement area corresponding to each dangerous movement area. For example, the behaviors of pedestrians in each dangerous sports area are: fighting, fighting and robbery, robbery, and normal behavior. According to the corresponding relationship, the corresponding coefficients are: 0.4, 1, 0.6, and 0, respectively. The occurrence probabilities are: fight 0.4 and robbery 0.3, fight 0.2 and robbery 0.4, fight 0.3 and robbery 0.2, fight 0.1 and robbery 0.1, then the coefficients corresponding to each dangerous sports area and the probability of occurrence of historical behavior in each dangerous sports area are calculated respectively. The weighted summation is carried out, and the obtained results are: 0.16, 0.32, 0.12, 0, respectively. Through this method, when determining the second sub-coefficient, the probability of historical behaviors in each dangerous sports area in the preset database is also considered, which is more comprehensive, so that the corresponding dangerous sports areas can be determined more accurately. Second sub-coefficient.

In one example, after determining the first sub-coefficient corresponding to each dangerous movement area and representing the congestion situation in the dangerous movement area and determining the second sub-coefficient corresponding to each dangerous movement area and representing the behavioral safety of the dangerous movement area, the method further includes: According to each of the first sub-coefficients and each of the second sub-coefficients, the respective safety factors corresponding to each dangerous movement area are determined, and the respective safety factors corresponding to each dangerous movement area are determined. In this embodiment, for a dangerous movement area, the first coefficient and the second coefficient corresponding to the movement area are multiplied or added, and the obtained result is used as the safety factor corresponding to the dangerous movement area, for example: each dangerous movement area The corresponding first sub-coefficients are: 0.4, 0.4, 0.3, and 0.1, respectively, and the second sub-coefficients corresponding to each dangerous sports area are: 0.4, 1, 0.6, and 0, respectively. The corresponding safety factors are: 0.16, 0.4, 0.18, and 0, respectively. In an example, after obtaining the safety factors corresponding to the dangerous movement areas, the method further includes: sending the safety factors corresponding to the dangerous movement areas to the terminal, and the terminal displays the safety factors in different colors on the electronic map. In this embodiment, the safety level can be determined according to the coefficient of each dangerous movement area, and each dangerous movement area is marked with different colors according to the preset colors representing the safety level, and different colors represent different safety levels.

In an example, determining the safety assessment information of the road according to the movement information in the movement area includes: respectively determining the safety assessment information of the different movement areas in the road according to the movement information of the different movement areas in the road. In this embodiment, the road is divided into different motion areas, which may be divided according to preset lengths, which is not specifically limited in this embodiment. According to the motion information in different motion areas, the safety assessment information of different motion areas in the road is determined, that is, the safety assessment information is included for different motion areas in the road, which can make the safety assessment information more comprehensive.

In this embodiment, the video frame sequence collected by the video equipment installed on the road is acquired to determine the motion area in the road; the motion information in the motion area is determined according to the image blocks corresponding to the motion area in each video frame in the video frame sequence ; According to the motion information in the motion area, determine the safety assessment information of the road, through this method, the user can be provided with the safety assessment information of the road, so that the user can know the safety of the road, thereby improving the safety of the user's travel.

The second embodiment of the present application relates to a road safety assessment method. The second embodiment is roughly the same as the first embodiment, with the main difference being that the motion information includes the motion trajectory of the moving object, the density of the moving object, the pedestrian's The specific implementation of determining the motion trajectory of moving objects, the density of moving objects, and the behavior of pedestrians is given. The specific flowchart is shown in Figure 4, including:

In step 201, a video frame sequence collected by a video device installed on the road is acquired, and a motion area in the road is determined.

Step 201 is similar to step 101 and will not be repeated here.

Step 202: Determine the motion intensity corresponding to the motion area according to the image blocks corresponding to the motion area in each video frame in the video frame sequence.

In an example, according to the image blocks corresponding to the motion area in each video frame in the video frame sequence, the specific flowchart of determining the motion intensity corresponding to the motion area is shown in FIG. 5 , including:

Step 2021 , using the optical flow method to calculate the optical flow values of the pixels in the image blocks corresponding to the motion area in each video frame in the video frame sequence respectively.

In this embodiment, the meaning of the optical flow value in the image refers to the motion vector, including the motion speed and direction of the pixel point. The video processing center can use the optical flow method to calculate the optical flow value of the pixel in the image block corresponding to the motion area in each video frame sequence. The optical flow value of the pixel includes the motion speed and direction of the pixel.

Step 2022: Determine the motion intensity corresponding to the motion area according to the optical flow value.

In one example, for each image block in the motion area, the motion speed of the pixels in the image block is compared with a preset speed, and the number of pixels greater than the preset speed is determined according to the comparison result, and then the number of pixels greater than the preset speed is determined according to the preset speed. The corresponding relationship between the number of predetermined pixels and the coefficient representing the intensity of motion is determined, and the coefficient representing the intensity of motion in the motion region where the image block is located is determined; wherein, the preset speed can be set according to actual needs, this embodiment No specific limitation is made; or, according to the preset corresponding relationship between the number of pixel points and the gears of the movement intensity, determine which gear the movement intensity of the image block is in is in. In an example, for each image block in the motion area, the average value of the motion speed of the pixel points in the image block can also be calculated, and then according to the corresponding relationship between the average value and the coefficient representing the intensity of motion, the image representing the image can be determined. The coefficient of the motion intensity of the motion area where it is located; or, according to the corresponding relationship between the average value and the gear of the motion intensity, determine which gear the motion intensity of the image block is in. Through such a method, the optical flow value of the pixels in the image block can be more accurately determined by the optical flow method, so as to more accurately determine the motion intensity corresponding to the motion area.

Step 203 , according to the motion intensity corresponding to the motion area, identify a dangerous motion area from the motion area.

In this embodiment, for each image block in the motion area, according to whether the motion intensity of the image block is higher than the preset motion intensity, the motion area where the image block greater than the preset motion intensity is located is taken as the motion area. Hazardous sports area. For example, the gears of the motion intensity are high, medium, and low. If the preset motion intensity is medium, the motion area where the image block with the high motion intensity is located is a dangerous motion area.

Step 204, detecting a moving object from the dangerous moving area.

In this embodiment, the video processing center inputs the image blocks corresponding to the dangerous motion area into the preset model for processing, and can detect multiple detection frames of the moving object, and obtains the moving object from the multiple detection frames; wherein, the preset model It can be obtained by pre-training according to actual needs, including but not limited to models such as convolutional neural network models.

After step 204, step 205 and step 208 are performed in parallel, step 206 and step 207 are performed after step 205, step 209 is performed after step 208, and step 2010 is entered after the execution of step 207 and step 209.

Step 205: Extract characteristic parameters representing the identity of the moving object from the image blocks corresponding to the moving area in each video frame.

Step 206 , according to the characteristic parameters that characterize the identity of the moving object extracted from each image block, determine the motion trajectory belonging to the same moving object.

In this embodiment, the video processing center may input the image blocks corresponding to the motion regions in each video frame into the preset model, and the preset model extracts and matches the characteristic parameters representing the identity of the moving objects, and outputs the output belonging to the same moving object Wherein, the preset model can be obtained by pre-training according to actual needs, and the preset model includes but is not limited to models such as convolutional neural network models. The video processing center can also directly extract the color, appearance, face shape, posture and other characteristic parameters of the moving object to obtain the characteristic parameters representing the identity of the moving object; Matching, for example, includes the features that the color of the clothes is red, the face shape is a melon face, and the body is slender as matching features, and then the image block is operated accordingly according to the matching features, that is, for a matching feature, if the i-th When there is no image block including the feature in the video frame, but there is an image block including the feature in the i+nth video frame, then a new motion track is added, and the image block including the feature in the i+n video frames is added. In the set of motion trajectories, if there is an image block including the feature in the i-th video frame and there is no image block including the feature in the i+n video frames, then the i+n video frames are not added to the existing ones. In the set of motion trajectories, if there is an image block including the feature in the i-th video frame and an image block including the feature in the i+n-th video frame, then add the i+n video frames to the existing image block. In the set of motion trajectories, the motion trajectories belonging to the same motion object can be determined according to the set of motion trajectories; wherein, n is a positive integer. Through such a method, a specific implementation method for determining the motion trajectories belonging to the same moving object is adopted.

In one example, when the features are matched, the feature parameters are calculated according to the feature parameters representing the identity of the moving object extracted from each image block, and according to the result of the generalized intersection calculation of the coordinates of the detection frame including the moving object. to match. In this embodiment, the generalized intersection ratio can be used to measure the correlation between two arbitrary shapes. For example, two arbitrary shapes are A and B, and the generalized intersection ratio=(A∩B)/(A∪B) ; That is, the video processing center performs matching not only according to the features that characterize the identity of the moving object, but also according to the calculation result of the generalized intersection ratio, which can make the matching result more accurate.

In one example, when the features are matched, the feature parameters are matched according to the feature parameters representing the identity of the moving object extracted from each image block and the speed of the moving object. In this embodiment, if the speed of the same moving object changes little, it can be determined as a matching feature according to the comparison result of the difference between the speed and the preset threshold; Matching is also performed according to the speed of the moving object, which can make the matching result more accurate.

Step 207 , analyze the motion trajectory of the moving object by using a statistical method, and determine the density of the moving object according to the analysis result.

In this embodiment, statistical methods include but are not limited to the following methods: methods such as histograms, line graphs, etc.; since the motion trajectory of the moving object may only exist in a partial area of the road, for example, for a dangerous motion area, There may be 5 motion trajectories of moving objects in the first half, and 8 motion trajectories of moving objects in the second half. In this embodiment, the motion area may be divided according to a preset area or according to each dangerous motion area, etc., the motion trajectories of the moving objects in each divided area are counted by a statistical method, and the motion of the moving objects in each divided area is obtained by analysis. The number of trajectories and the change of the number, and then according to the corresponding relationship between the change of the number and the number and the gear of the density of the moving objects, determine the density of the moving objects in each divided area; among them, the density of the gear can be It is high, medium and low gears, etc. It can also be the first gear, the second gear, the third gear and so on. After obtaining the density of moving objects in each divided area, you can also obtain the density of moving objects on the entire road according to the density of moving objects in each divided area. For example, if the density of moving objects in each dangerous motion area is dense When the number of high-grade levels is greater than the preset number, the density of moving objects on the entire road is high-grade. Through this method, the density of moving objects can be determined only by simple statistical method analysis, and the operation is relatively simple, and at this time, the motion information also includes the density of moving objects, and the factors considered are more comprehensive, so that the movement The information is more accurate, making the safety assessment information of the determined road more accurate. In an example, it can also be determined according to the analysis result whether the change trend of the moving object tends to be scattered or tend to converge.

Step 208: Extract characteristic parameters representing pedestrian behavior from the image blocks corresponding to the motion regions in each video frame.

Step 209: Determine the behavior of the pedestrian according to the characteristic parameters of the same pedestrian extracted from each image block that characterize the behavior of the pedestrian.

In this embodiment, the video processing center may input the image blocks corresponding to the motion area in each video frame into the preset model, and the preset model outputs the behavior of the pedestrian through the extracted characteristic parameters of the same pedestrian that characterize the behavior of the pedestrian; Among them, the preset model can be obtained by pre-training according to actual needs, and the preset model includes but is not limited to models such as convolutional neural network models; and then the feature parameters of the same pedestrian extracted from each image block that characterize pedestrian behavior are successively input into 2D Convolutional neural network model and 1D time-series convolutional neural network model, so that the behavior of pedestrians can be determined; wherein, the characteristic parameters that characterize pedestrian behavior include but are not limited to pedestrian speed, spatial position of feature points and other characteristic parameters, behaviors include but not limited to Normal behavior, fighting, robbery, theft, etc. Through this method, a specific implementation method for determining the behavior of pedestrians is provided, and at this time, the behavior of pedestrians is also included in the motion information, and the factors considered are more comprehensive, so that the motion information is more accurate, and the safety assessment information of the determined road is determined. more precise.

Step 2010: Determine the safety assessment information of the road according to the motion information in the motion area.

Step 2010 is similar to step 103 and will not be repeated here.

In one example, steps 205-207 can also be performed before steps 208-209, and in one example, steps 208-209 can also be performed before steps 205-207. In one example, step 207 may be performed at any step after step 206.

In one example, the motion information includes at least one of the following pieces of information: motion trajectories of moving objects, density of moving objects, and behavior of pedestrians. Since the motion trajectories of the moving objects, the density of the moving objects, and the behavior of pedestrians can more accurately reflect the motion information of the moving objects, the safety assessment information of the road can be more accurately determined when the motion information includes at least one of them.

In this embodiment, the motion information of the moving object includes the motion trajectory of the moving object, the density of the moving object, and the behavior of pedestrians. The factors considered are more comprehensive, so that the motion information is more accurate, and the safety assessment information of the determined road is more accurate.

The third embodiment of the present application relates to a road safety assessment method. The third embodiment is substantially the same as the first embodiment, with the main difference being that the road includes a route from the origin to the destination obtained according to the navigation request of the terminal. For multiple roads, after determining the safety assessment information of the road, it also includes: generating navigation information and sending the navigation information to the terminal. The specific flowchart is shown in Figure 6, including:

In step 301, a video frame sequence collected by a video device installed on the road is acquired, and a motion area in the road is determined.

Step 302: Determine the motion information in the motion area according to the image blocks corresponding to the motion area in each video frame in the video frame sequence.

Step 303: Determine the safety assessment information of the road according to the motion information in the motion area.

Steps 301-303 are similar to steps 101-103, and are not repeated here.

Step 304 , select a target road from a plurality of roads according to the safety assessment information of the road, and generate navigation information; wherein, the navigation information includes the target road and the safety assessment information of the target road.

In this embodiment, safety evaluation information is included for each road; according to the safety evaluation information of the road, a road that satisfies the preset conditions is selected from multiple roads, and navigation information is generated, and the navigation information includes the target road and the target road. Security assessment information; the preset condition may be set according to actual needs, which is not specifically limited in this embodiment. For example: when the safety assessment information includes a safety factor, if it is determined that the safety factors of each road are: 0.8, 0.6, 0.5, 0.3, and the preset condition is that the safety factor is not less than 0.5, select 0.8, Roads corresponding to 0.6 and 0.5.

In one example, if there are multiple target roads, the navigation information further includes a result of sorting the target roads according to the safety assessment information of the target roads. In this embodiment, the target roads are sorted according to the safety assessment information of the target roads, and the navigation information includes the sorting results. Through this method, the user can be made aware of the existence of multiple target roads and the safety conditions of the multiple target roads, which is helpful for the user. Based on actual needs, choose the road by yourself to improve the reference basis. In an example, the target roads may also be sorted according to the safety assessment information of the target road, the distance and speed recommendations of the target road, etc., to obtain a sorting result.

Step 305: Send the navigation information to the terminal for the terminal to display on the electronic map.

In this embodiment, the video processing center sends the navigation information to the terminal. After the terminal receives the navigation information, the terminal presents the navigation information on the electronic map. The navigation information can be displayed in a floating manner, and can be divided into two parts and presented on the electronic map. On the electronic map, as shown in Figure 7, a schematic diagram of the interface for presenting navigation information for the electronic map on the terminal, one part is the suggested interface, including the proposed target road and other information, and the other part is the display interface, including the safety assessment information of the target road and other information. In an example, the terminal can also display different roads in different colors according to the road safety assessment information, and different colors represent different safety conditions.

In one example, determining the safety assessment information of the road according to the movement information in the movement area includes: respectively determining the safety assessment information of the different movement areas in the road according to the movement information of the different movement areas in the road. In this embodiment, the safety assessment information of different movement areas on the road is determined according to the movement information in different movement areas, that is, the safety assessment information is included for different movement areas in the road, and the safety assessment information of different movement areas can be Different sports areas on the road are displayed in different colors, and different colors represent different safety conditions. For example, red is a sports area with poor safety conditions, and red is used to warn users.

In one example, the navigation information further includes the location of the video device in the road and a sequence of video frames captured by the video device. In one example, the navigation information also includes pedestrians of pedestrians in the road. At this time, the display interface for presenting the navigation information on the electronic map on the terminal also includes the location of the video device and the sequence of video frames shot by the video device.

In this embodiment, since the target road selected according to the safety assessment information is a relatively safe road, the travel safety of the user is further improved, and the generated navigation information is displayed on the electronic map of the terminal, which makes up for the commonly used electronic Pedestrian safety issues are not considered when providing and displaying alternative roads in the map.

The steps of the above various methods are divided only for the purpose of describing clearly. During implementation, they can be combined into one step or some steps can be split and decomposed into multiple steps. As long as the same logical relationship is included, they are all within the protection scope of this patent. ;Adding insignificant modifications to the algorithm or process or introducing insignificant designs, but not changing the core design of the algorithm and process are all within the scope of protection of this patent.

The fourth embodiment of the present application relates to a video processing center. The video processing center is a server or terminal with computing performance. As shown in FIG. 8 , the video processing center includes at least one processor 402; and a memory 401 communicatively connected to the at least one processor. wherein, the memory 401 stores instructions executable by the at least one processor 402, and the instructions are executed by the at least one processor 402, so that the at least one processor 402 can execute the above embodiments of the road safety assessment method.

The memory 401 and the processor 402 are connected by a bus, and the bus may include any number of interconnected buses and bridges, and the bus connects one or more processors 402 and various circuits of the memory 401 together. The bus may also connect together various other circuits, such as peripherals, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. The bus interface provides the interface between the bus and the transceiver. A transceiver may be a single element or multiple elements, such as multiple receivers and transmitters, providing a means for communicating with various other devices over a transmission medium. The data processed by the processor 402 is transmitted on the wireless medium through the antenna, and further, the antenna also receives the data and transmits the data to the processor 402 .

The processor 402 is responsible for managing the bus and general processing, and may also provide various functions including timing, peripheral interface, voltage regulation, power management, and other control functions. And the memory 401 may be used to store data used by the processor 402 in performing operations.

The fifth embodiment of the present application relates to a computer-readable storage medium storing a computer program. The above method embodiments are implemented when the computer program is executed by the processor.

That is, those skilled in the art can understand that all or part of the steps in the method for implementing the above embodiments can be completed by instructing the relevant hardware through a program, and the program is stored in a storage medium and includes several instructions to make a device ( It may be a single chip microcomputer, a chip, etc.) or a processor (processor) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, Read-Only Memory (ROM, Read-Only Memory), Random Access Memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program codes .

Those of ordinary skill in the art can understand that the above-mentioned embodiments are specific embodiments for realizing the present application, and in practical applications, various changes in form and details can be made without departing from the spirit and the spirit of the present application. scope.

Claims (16)

1. A road safety assessment method comprising:

   Obtain the video frame sequence collected by the video equipment installed on the road, and determine the motion area in the road;

   Determine the motion information in the motion area according to the image blocks corresponding to the motion area in each of the video frames in the video frame sequence;

   According to the motion information in the motion area, the safety assessment information of the road is determined.
2. The road safety assessment method according to claim 1, wherein the road comprises a plurality of roads from the origin to the destination obtained according to the navigation request of the terminal;

   After the determination of the safety assessment information of the road according to the motion information in the motion area, the method further includes:

   According to the safety assessment information of the road, a target road is selected from the plurality of roads, and navigation information is generated; wherein the navigation information includes the target road and the safety assessment information of the target road;

   The navigation information is sent to the terminal for the terminal to display on the electronic map.
3. The road safety assessment method according to claim 2, wherein if there are multiple target roads, the navigation information further includes a result of sorting the target roads according to the safety assessment information of the target roads.
4. The road safety assessment method according to any one of claims 1 to 3, wherein the determining the safety assessment information of the road according to the movement information in the movement area comprises:

   According to the motion information of the different motion areas in the road, the safety assessment information of the different motion areas in the road is respectively determined.
5. The road safety assessment method according to any one of claims 1 to 4, wherein the moving area is determined according to the image blocks corresponding to the moving area in each of the video frames in the video frame sequence sports information in , including:

   According to the image blocks corresponding to the motion area in each of the video frames in the video frame sequence, determine the motion intensity corresponding to the motion area;

   Identifying a dangerous motion area from the motion area according to the motion intensity corresponding to the motion area;

   detecting a moving object from the dangerous movement area;

   Determine the motion information of the moving object in the motion area according to the image blocks corresponding to the motion area in each of the video frames.
6. The road safety assessment method according to claim 5, wherein the motion information includes a motion trajectory of a moving object, and the motion is determined according to the image blocks corresponding to the motion area in each of the video frames The motion information of the object in the motion area, including:

   extracting characteristic parameters representing the identity of the moving object from the image blocks corresponding to the moving region in each of the video frames;

   According to the feature parameters that characterize the identity of the moving object extracted from each of the image blocks, the motion trajectory belonging to the same moving object is determined.
7. The road safety assessment method according to claim 6, wherein the moving objects include pedestrians, and the motion information further includes behaviors of pedestrians, and the image corresponding to the moving area in each of the video frames block, determining the motion information of the moving object in the motion area, further comprising:

   extracting characteristic parameters characterizing pedestrian behavior from the image blocks corresponding to the motion area in each of the video frames;

   The behavior of the pedestrian is determined according to the characteristic parameters of the same pedestrian extracted from each of the image blocks that characterize the behavior of the pedestrian.
8. The road safety assessment method according to claim 7, wherein the motion information further includes the density of moving objects, and in the process of determining that the moving objects belong to the same motion according to the characteristics of the moving objects extracted from each of the image blocks After the motion trajectory of the object, it also includes:

   A statistical method is used to analyze the motion trajectory of the moving object, and the density of the moving object is determined according to the analysis result.
9. The road safety evaluation method according to claim 8, wherein the safety evaluation information includes a safety factor, and the determining the safety evaluation information of the road according to the motion information in the movement area includes:

   determining a first coefficient representing congestion on the road according to the density of the moving objects;

   determining a second coefficient representing behavioral safety on the road according to the behavior of the pedestrian;

   According to the first coefficient and the second coefficient, the safety coefficient of the road is determined.
10. The road safety assessment method according to claim 9, wherein the determining the first coefficient representing the congestion situation on the road according to the density of the moving objects comprises:

    According to the density of the moving objects in each of the dangerous movement areas, determine the first sub-coefficient corresponding to each of the dangerous movement areas and represent the congestion situation of the dangerous movement area;

    determining, according to each of the first sub-coefficients, a first coefficient representing the congestion situation on the road;

    The determining, according to the behavior of the pedestrian, the second coefficient representing the behavior safety on the road, including:

    According to the behavior of pedestrians in each of the dangerous motion areas, determine the second sub-coefficients representing the behavioral safety of the dangerous motion areas corresponding to each of the dangerous motion areas;

    From each of the second sub-coefficients, a second coefficient characterizing the behavioral safety on the road is determined.
11. The road safety assessment method according to claim 10, wherein, according to the behavior of pedestrians in each of the dangerous movement areas, the second sub-sections representing the behavioral safety of the dangerous movement areas corresponding to each of the dangerous movement areas are determined. coefficients, including:

    Obtain the probability of occurrence of historical behavior in each dangerous sports area from a preset database; wherein, the preset database includes the historical behavior of pedestrians in different sports areas within a historical time period and the probability of occurrence of the historical behavior;

    According to the behavior of pedestrians in each dangerous movement area and the occurrence probability of the historical behavior in each dangerous movement area, a second sub-coefficient corresponding to each dangerous movement area representing the behavior safety of the dangerous movement area is determined.
12. The road safety assessment method according to any one of claims 5 to 11, wherein the moving area is determined according to the image blocks corresponding to the moving area in each of the video frames in the video frame sequence Corresponding exercise intensity, including:

    Calculate the optical flow values of the pixels in the image blocks corresponding to the motion area in each of the video frames in the video frame sequence by using the optical flow method;

    The motion intensity corresponding to the motion region is determined according to the optical flow value.
13. The road safety assessment method according to any one of claims 1 to 12, wherein the determining a motion area in the road comprises:

    Perform differential processing on adjacent video frames in the video frame sequence to obtain each differential image;

    A target pixel point whose pixel value is greater than a preset threshold is selected from the pixel points of each of the differential images, and a motion region in each of the video frames is determined according to the target pixel point.
14. The road safety assessment method according to any one of claims 1 to 13, wherein the motion information includes at least one of the following information: the motion track of the moving object, the density of the moving object, and the behavior of pedestrians.
15. A video processing center, including:

    at least one processor; and,

    a memory communicatively coupled to the at least one processor; wherein,

    the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the execution of any one of claims 1 to 14 road safety assessment methods.
16. A computer-readable storage medium storing a computer program, when the computer program is executed by a processor, the road safety assessment method according to any one of claims 1 to 14 is implemented.

Images