CN113808409B - Road safety monitoring method, system and computer equipment - Google Patents
Road safety monitoring method, system and computer equipment Download PDFInfo
- Publication number
- CN113808409B CN113808409B CN202010555778.4A CN202010555778A CN113808409B CN 113808409 B CN113808409 B CN 113808409B CN 202010555778 A CN202010555778 A CN 202010555778A CN 113808409 B CN113808409 B CN 113808409B
- Authority
- CN
- China
- Prior art keywords
- projectile
- information
- road
- track information
- attribute
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/04—Detecting movement of traffic to be counted or controlled using optical or ultrasonic detectors
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/048—Detecting movement of traffic to be counted or controlled with provision for compensation of environmental or other condition, e.g. snow, vehicle stopped at detector
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The application discloses a method, a system and computer equipment for monitoring road safety, which realize attribute identification or source positioning of a spilled object on a road, provide accurate road safety alarm and reduce traffic accidents caused by the spilled object on the road. The road safety monitoring method comprises the following steps: acquiring road monitoring information, and determining whether a projectile exists on a road; acquiring track information of at least one object on a road according to the road monitoring information; judging the attribute of the throwing object according to the track information of at least one object; an alert is issued based on the attributes of the projectile, wherein the at least one object comprises the projectile and/or a non-projectile. According to the method, the accuracy of detecting the attribute of the projectile can be improved, and the projectile can be timely processed by workers according to the alarm information, so that road traffic accidents are reduced.
Description
Technical Field
The invention relates to the field of computers, in particular to a method and a system for monitoring road safety and computer equipment.
Background
Keeping roads clean is important for vehicles to pass through quickly, but as roads increase, vehicles increase, and the objects thrown from the vehicles become one of the common causes of traffic accidents on the roads. When the motor vehicle running fast avoids or collides with a road and throws objects, great property loss, even great traffic accidents and casualties are easily caused. It is therefore an important issue to identify and deal with the road spill in a timely manner.
Identification and treatment of the sprinklers are difficult problems, firstly, because the types, materials and shapes of the sprinklers are various, the danger degree of the sprinklers can be divided into serious hidden traffic troubles and lower hidden traffic troubles, and the treatment methods are completely different. Secondly, the source of the sprinkled object needs to be judged and searched in time, and is blocked. In response to this problem, if the projectile is judged by only a visual method, erroneous judgment is liable to occur.
Disclosure of Invention
The application discloses a road safety monitoring method, computer equipment and system, which can realize attribute identification or source positioning of a sprinkled object on a road and reduce traffic accidents caused by the sprinkled object on the road.
In a first aspect, the present application provides a method for road safety monitoring, including:
acquiring road monitoring information and determining that a projectile exists on a road;
acquiring trajectory information of at least one object on the road according to the road monitoring information, wherein the at least one object comprises a projectile and/or at least one non-projectile; judging the attribute of the throwing object according to the track information of at least one object;
and sending an alarm according to the attribute of the throwing object.
By the method, the accuracy of determining the attribute of the sprinkled object can be improved, so that the danger degree of the sprinkled object is determined, accurate warning information is sent, and the possibility of traffic accidents caused by the sprinkled object can be effectively reduced.
In a possible implementation manner, the acquiring trajectory information of at least one object on the road, and the determining the attribute of the projectile according to the trajectory information of the at least one object includes:
acquiring track information of the sprinklers on the road, and judging the attributes of the sprinklers according to the track information of the sprinklers; or acquiring the track information of at least one non-projectile on the road, and judging the attribute of the projectile according to the track information of the at least one non-projectile; or the like, or, alternatively,
and acquiring the track information of at least one non-projectile and the track information of the projectile on the road, and judging the attribute of the projectile according to the track information of the at least one non-projectile and the track information of the projectile.
The weight of the projectile can be accurately judged through trajectory information of the projectile, such as speed, acceleration, trajectory midway stay time and the like, and the attribute of the projectile, such as whether the material is plastic, paper or metal, can be accurately judged; through the track information of the non-projectile, such as speed, acceleration and track lines, whether the non-projectile has an avoidance behavior aiming at the projectile can be judged, and therefore the danger degree of the projectile is accurately determined.
In a possible implementation manner, the acquiring the road monitoring information includes: the method comprises the steps of obtaining road monitoring image information through video monitoring equipment on a road, and obtaining road monitoring radar information through radar equipment. By integrating the image information and the radar information, the accuracy of judging the trajectory of the projectile can be improved.
In one possible implementation, the acquiring the track information of the at least one object on the road includes:
and acquiring first track information of at least one object according to the radar information, acquiring second track information of the at least one object according to the image information, and synthesizing the first track information and the second track information to obtain track information of the at least one object. At the near end, the accuracy of the track information in the image information is higher, and at the far end, the accuracy of the track information in the radar information is higher, and by combining the respective advantages of the radar information and the image information, more accurate track information can be obtained in the whole range of the near end and the far end.
In a possible implementation manner, the method further includes: and acquiring the image characteristics of the throwing object according to the image information.
In a possible implementation, the method further includes: and judging the attribute of the throwing object according to the image characteristics of the throwing object. By means of image characteristics such as size and shape, accuracy of judging attributes of the projectile can be improved in an auxiliary mode.
In one possible implementation, when the at least one object includes a projectile, the determining the attribute of the projectile includes:
and comparing the trajectory information of the projectile with the image characteristics of the projectile through the characteristic database to judge the attribute of the projectile.
The characteristic database stores information of the throwers with determined attributes, and the attributes of the throwers can be judged more quickly and accurately through characteristic comparison.
In one possible implementation, trajectory information or image features of the projectile are refreshed into the feature database in the event of unsuccessful comparison with the feature database. The characteristic database is refreshed, the characteristic data of the sprinkled objects in the characteristic database can be continuously enriched, and the characteristic database can be perfected through continuous accumulation, so that the aims of improving the speed and accuracy of judging the attributes of the sprinkled objects are fulfilled.
In one possible implementation, the attribute of the projectile includes a degree of danger of the projectile.
In one possible implementation, different levels of warning are issued depending on the different levels of risk of the projectile.
In one possible implementation, determining the presence of a projectile on a roadway includes:
an object in the image information is detected by an optical flow method, a type of the object is identified, and the object whose type is unknown is determined as a projectile.
In a possible implementation, the method further includes:
and determining the source of the projectile according to the condition that the trajectory information of the projectile is crossed with the trajectory information of at least one non-projectile.
In one possible implementation, the track information includes current track information and backward-extending track information of the current track information.
By the method, the source of the sprinkled object can be quickly positioned, and a worker can prevent a new sprinkled object from appearing on a road by processing the source of the sprinkled object, so that the number of the sprinkled objects is reduced, and the probability of safety accidents is reduced.
In a second aspect, the present application provides a method for monitoring road safety, comprising:
acquiring road monitoring information and determining that a throwing object exists on a road; acquiring trajectory information of a projectile and at least one non-projectile on the road according to the road monitoring information; and determining the source of the projectile according to the intersection condition of the trajectory information of the projectile and the trajectory information of at least one non-projectile, and sending an alarm according to the source of the projectile.
By the method, the source of the sprinkled object can be quickly positioned, and a worker can prevent a new sprinkled object from appearing on a road by processing the source of the sprinkled object, so that the number of the sprinkled objects is reduced, and the probability of safety accidents is reduced.
In a possible implementation manner, the acquiring the road monitoring information includes: the method comprises the steps of obtaining road monitoring image information through video monitoring equipment on a road and obtaining road monitoring radar information through radar equipment.
In one possible implementation, the acquired trajectory information of the projectile on the road includes: and acquiring first track information of the projectile from the radar information, acquiring second track information of the projectile from the image information, and synthesizing the first track information and the second track information to obtain track information of the projectile. By the method, the accuracy of the acquired track information can be improved.
In one possible implementation, determining the source of the projectile based on the intersection of the trajectory information includes:
if the trajectory information of the projectile and the trajectory information of the at least one non-projectile intersect at a first time, the projectile is from the at least one non-projectile; or
If the trajectory information of the projectile and the trajectory information of the at least two non-projectiles intersect at a first time, selecting the non-projectile closest to the projectile from the at least two projectiles as a source of the projectile.
At the same time, the trajectory information of the projectile and the non-projectile has a cross point, and the probability that the non-projectile closest to the cross point of the trajectory information is the source is the greatest through the condition of the cross of the trajectory information, so that the source of the projectile can be judged more accurately.
In one possible implementation, the track information includes current track information and backward-extending track information of the current track information. The track information is extended reversely, information which is not acquired by the monitoring equipment is supplemented, and the accuracy of finding the source of the projectile through the track information can be improved through more complete track information.
In a possible implementation manner, the method for monitoring road safety further includes:
judging the attribute of the projectile according to the track information of at least one non-projectile; or the like, or, alternatively,
judging the attribute of the projectile according to the trajectory information of the projectile; or the like, or, alternatively,
and judging the attribute of the projectile according to the trajectory information of the projectile and the trajectory information of at least one non-projectile.
In a possible implementation manner, the method for monitoring road safety further includes:
and acquiring the image characteristics of the throwing object according to the image information. The image characteristics can assist in judging the attributes of the projectile, and the accuracy of judging the attributes of the projectile is improved.
In a possible implementation, the method further includes: and judging the attribute of the throwing object according to the image characteristics of the throwing object.
In a third aspect, the present application provides a system for monitoring road safety, the system comprising: the monitoring device, the attribute detection device and the alarm device;
the monitoring device is used for acquiring road monitoring information and determining that the sprinklers exist on the road; acquiring trajectory information of at least one object on the road according to the road monitoring information, wherein the at least one object comprises a projectile and/or at least one non-projectile;
the attribute detection device is used for judging the attribute of the throwing object according to the track information of at least one object;
the warning device is used for giving a warning according to the attribute of the throwing object.
The system can quickly locate the attribute of the sprinkled object, timely send out safety alarm according to the attribute and the danger degree of the sprinkled object, and timely clear the sprinkled object from the road by the staff according to the level of the safety alarm, thereby reducing traffic accidents caused by the sprinkled object on the road.
In one possible implementation, the system further includes: an attribution judging means;
and the attribution judging device is used for determining the source of the projectile according to the condition that the trajectory information of the projectile is crossed with the trajectory information of at least one non-projectile.
The attribution judging device can enable workers to quickly locate the source of the sprinkled object, prevent the new sprinkled object from being added on the road, and reduce the probability of traffic safety accidents.
In a possible implementation manner, the attribute detecting device is configured to determine the attribute of the projectile according to the trajectory information of the at least one object, and includes:
acquiring track information of the sprinklers on the road, and judging the attributes of the sprinklers according to the track information of the sprinklers; or acquiring the track information of at least one non-projectile on the road, and judging the attribute of the projectile according to the track information of the at least one non-projectile; or the like, or a combination thereof,
acquiring track information of at least one non-projectile and trajectory information of the projectile on the road, and judging the attribute of the projectile according to the track information of the at least one non-projectile and the trajectory information of the projectile.
Through judging the attribute of the object to be thrown, the dangerous degree of the object to be thrown is determined, and the staff can be helped to timely handle the object to be thrown on the road with high dangerous degree.
In one possible implementation, the monitoring device includes: video monitoring equipment and radar equipment;
the video monitoring equipment acquires road monitoring image information, and the radar equipment acquires road monitoring radar information.
In a feasible implementation manner, the monitoring device acquires first track information of at least one object according to the radar information, acquires second track information of the at least one object according to the image information, and synthesizes the first track information and the second track information to obtain track information of the at least one object.
In a fourth aspect, the present application provides a system for road safety monitoring, the system comprising: the device comprises a monitoring device, an attribution judging device and an alarming device;
the monitoring device is used for acquiring road monitoring information and determining that the sprinklers exist on the road; acquiring track information of at least one object on the road according to the road monitoring information, wherein the at least one object comprises a projectile and/or at least one non-projectile;
the attribution judging device is used for determining the source of the projectile according to the condition that the trajectory information of the projectile is crossed with the trajectory information of at least one non-projectile;
the alarm device is used for giving an alarm according to the source of the sprinkled object.
Through above-mentioned system, the staff can fix a position the source of the thing of shedding on the road fast, prevents newly-increased thing of shedding, effectively reduces because of the probability that the thing of shedding leads to the traffic accident.
In one possible implementation, the system further includes: an attribute detection device;
the attribute detection device judges the attribute of the projectile according to the track information of at least one object.
In one possible implementation, the attribute detecting device is configured to determine the attribute of the projectile according to the trajectory information of the at least one object, and includes:
acquiring track information of the throwing objects on the road, and judging the attributes of the throwing objects according to the track information of the throwing objects; or acquiring the track information of at least one non-projectile on the road, and judging the attribute of the projectile according to the track information of the at least one non-projectile; or the like, or, alternatively,
acquiring track information of at least one non-projectile and trajectory information of the projectile on the road, and judging the attribute of the projectile according to the track information of the at least one non-projectile and the trajectory information of the projectile.
By the method, the attribute of the projectile can be judged quickly and accurately, the danger degree of the projectile is judged according to the attribute of the projectile, and workers can process the projectile on the road according to the danger degree.
In one possible implementation, the monitoring device includes: video monitoring equipment and radar equipment;
the video monitoring equipment acquires road monitoring image information, and the radar equipment acquires road monitoring radar information.
In a feasible implementation manner, the monitoring device is configured to obtain first trajectory information of the at least one object according to the radar information, obtain second trajectory information of the at least one object according to the image information, and synthesize the first trajectory information and the second trajectory information to obtain trajectory information of the at least one object.
In a fifth aspect, the present application provides a computer device for road safety monitoring, the computer device comprising a processor and a memory, wherein:
the memory has stored therein computer instructions;
the processor executes computer instructions to cause the computer apparatus to perform the method of the first aspect and its possible implementations.
In a sixth aspect, the present application provides a road safety monitoring computer device, the computer device comprising a processor and a memory, wherein:
the memory has stored therein computer instructions;
the processor executes computer instructions to cause the computer apparatus to perform the method of the second aspect and possible implementations thereof.
In a seventh aspect, the present application provides a computer-readable storage medium, which stores computer instructions, and when the computer instructions in the computer-readable storage medium are executed by a computer device, the computer device is caused to execute the method in any one of claims 1 to 13, or the computer device is caused to implement the functions of the apparatus in the system in the third aspect and the possible implementation manner.
In an eighth aspect, the present application provides a computer-readable storage medium storing computer instructions that, when executed by a computer device, cause the computer device to perform the method of any one of claims 14 to 21, or cause the computer device to implement the functions of the apparatus in the system of the fourth aspect and possible implementations thereof.
Drawings
While the drawings needed to describe the embodiments are briefly described below, it should be apparent that the drawings in the following description are merely examples of the invention and that other drawings may be derived from those drawings by those skilled in the art without inventive step.
FIG. 1 is a schematic view of a road projectile scene according to an embodiment of the present application;
FIG. 2 is a system diagram of an embodiment of the present application;
FIG. 3A is another system diagram of an embodiment of the present application;
FIG. 3B is a schematic view of another system in accordance with an embodiment of the present application;
FIG. 4 is a schematic diagram of the monitoring device function according to an embodiment of the present application;
FIG. 5 is a flowchart of a processing method of a monitoring device according to an embodiment of the present application;
FIG. 6 is a diagram illustrating the function of an attribute detection apparatus according to an embodiment of the present application;
FIG. 7 is a flowchart illustrating a processing method of an attribute detection apparatus according to an embodiment of the present application;
fig. 8 is a flowchart of a processing method of the attribution judging apparatus according to the embodiment of the present application;
fig. 9A is a schematic diagram of a projectile attribution determination scenario according to an embodiment of the present application;
fig. 9B is a schematic diagram of another projectile attribution determination scenario according to an embodiment of the present application;
FIG. 10 is a schematic diagram of the alert device function of an embodiment of the present application;
fig. 11 is a hardware schematic diagram of a computer device according to an embodiment of the present application.
Detailed Description
In the field of video surveillance, detection of projectiles on roads has always been an important issue, and projectiles are a major source of projectiles on roads. On the road with a lot of motor vehicles that travel fast, the suddenly appearing object throwing often lets the navigating mate prevent suddenly, under the condition that can't make correct evasion, causes the traffic accident very easily. Fig. 1 shows a scene diagram, which includes: two trucks 106 and 110, a car 102, a projectile 104, and a video surveillance device 112. Wherein the truck 106 is loaded with cargo and the cargo is thrown onto the road as a projectile 104. When the car 102 traveling fast on the road encounters a sudden sprinkled object 104, if the car is not evaded timely, traffic accidents are easily caused, and the sprinkled object 104 becomes a major potential safety hazard of the road.
To address this problem: on the one hand, the source of the projectile 104 is judged quickly, and the source of the projectile is cut off to prevent more projectiles from being thrown on the road; on the other hand, the type and the danger level of the projectile 104 are determined quickly, if the danger level of the projectile 104 is low, such as paper, plastic, etc., the priority can be lowered to allow the worker to clean the projectile regularly, but if the danger level of the projectile is high, such as tires, large stones, etc., the worker can deal with the projectile urgently.
In the prior art, a characteristic image is mainly obtained from a video monitoring device 112, and then the projectile 104 is identified from the characteristic image, one identification technical scheme is that the projectile 104 is identified by comparing the average pixel value of the projectile 104 in the characteristic image with the average pixel value of a road by using an average pixel value method, but the method can only identify whether the projectile exists on the road, cannot identify the type and the danger degree of the projectile 104, and cannot judge the source of the projectile 104. Another technical solution is to use the video monitoring device 112 to obtain image information on the road, and capture the projectile 104 by image recognition, but only identify the type of projectile marked in the database, and cannot identify all types of projectiles 104 and their corresponding risks, and cannot improve the recognition accuracy of the risks of the projectile. It is also not very accurate to determine the attribution of the projectile 104 by calculating the linear distance between the projectile 104 and its nearest vehicle when at rest, for example as shown in figure 1, the projectile 104 is at rest and the linear distance of the truck 110 from the projectile 104 is nearest, but the projectile 104 is from the truck 106 rather than the truck 104.
The present application provides a feasible technical solution based on the above problem, and in an embodiment, a system diagram of the solution will be described in detail with reference to fig. 2. The system 200 includes a monitoring device 202, an attribute detecting device 204, an attribution judging device 206, and an alerting device 208. The monitoring apparatus 202 obtains road information, which may include video equipment through which video information and image information on the road may be obtained and radar equipment through which radar information on the road may be obtained. Further, first trajectory information of at least one object on the road may be derived from the radar information, the at least one object including a projectile and other objects on the road, the other objects may be collectively referred to as non-projectiles, the non-projectiles including, for example, vehicles, non-vehicles, and pedestrians, etc. traveling on the road. In addition, the image information can also obtain second track information of at least one object, and track information of at least one object can be obtained by integrating the first track information and the second track information.
The attribute detection device 204 is used for detecting the attribute of at least one object, and includes: any one or combination of size, hazard level, type, etc. Specifically, the image information and the track information of the at least one object are analyzed and processed to obtain the image characteristics and the track information of the at least one object. Wherein the image features include: color histogram, color set, color moment, color aggregation vector, color correlation map, texture feature, SIFT (Scale-invariant feature transform) feature, and the like. The track information includes: velocity (including magnitude and direction), acceleration, trajectory stopover time, and the like.
The attribution judging device 206 acquires trajectory information of the projectile and the non-projectile, which includes the currently acquired trajectory information and a reverse extension thereof. Judging the attribution source of the projectile according to the intersection condition of the trajectory of the projectile and the trajectory of the non-projectile at the same time (first time), and developing according to the specific intersection condition later to discuss the details of the determination scheme of the attribution source of the projectile.
The warning device 208 obtains the attribute of the projectile and the source of the projectile, and sends out safety warnings of different degrees according to the risk level of the projectile, and in a feasible implementation manner, the following correspondence can be made: if the danger degree is high, the safety alarm is red; in the danger degree, the safety alarm is yellow; and if the danger degree is low, the safety alarm is green. According to different danger degree, the staff makes different reactions, for example when danger degree is high, then immediately carry out manual intervention immediately, carry out urgent processing to the road throwing thing, if danger degree is low, then can let the staff regularly normally handle can. On the other hand, the alert device 208 may report the source of the projectile to the crew, e.g., the projectile originates from a truck on the road, and the crew takes control of the truck, makes a blame, and conditions the truck.
In another embodiment, as shown in FIG. 3A, the system 300 includes a monitoring device 202, an attribute detection device 204, and an alerting device 208. The operation principle of the system 300 is similar to that of the system 200, and the detailed description thereof is omitted. The monitoring device 202 acquires monitoring information on a road, the attribute detection device 204 judges the attribute of the projectile according to the monitoring information, and the alarm device 208 sends out safety alarms with different degrees according to the attribute of the projectile and the danger degree of the projectile and does not report the source of the projectile to workers.
In another embodiment, as shown in FIG. 3B, the system 310 includes the monitoring device 202, the attribution determination device 206, and the alerting device 208. The working principle of the system 310 is similar to that of the system 200, and the detailed description is omitted here. The monitoring device 202 acquires monitoring information on a road, the attribution judging device 206 judges the source of the projectile through the monitoring information, the alarm device 208 sends a safety alarm according to the source of the projectile, and a worker timely processes the projectile on the road according to the safety alarm and cuts off the source of the projectile to prevent additional potential safety hazards caused by the newly added projectile.
Further, the system 200 is described in detail, and fig. 4 shows a detailed description of the monitoring device 202. In one embodiment, monitoring apparatus 202 includes a monitoring device 402 and an information processing module 408. Where monitoring device 402 includes a video monitoring device 404 and a radar device 406, video information on the road is obtained from video monitoring device 404 and radar information on the road is obtained from radar device 406. The information processing module 408 obtains trajectory information 410 and image information 412 of at least one formation based on the video information and the radar information, and completes projectile identification 414 from at least one object based on the information.
Fig. 5 describes the processing flow of the monitoring apparatus 202 in detail.
According to the process S502, the video information is parsed into video frames, and image information of consecutive frames is obtained.
According to the process S504, the difference between the image information of the consecutive frames before and after is compared by the optical flow method, and an object whose position changes is identified as a set a, and an object of a known type such as an automobile, a non-automobile, and a pedestrian is identified as a set B in the set a by an object detection algorithm based on deep learning.
According to the process S506, the objects in the set A are removed from the objects in the set B, and then the redundant objects are the sprinkles.
According to the process S508, the pixel point of at least one object in the image information is converted from the pixel coordinate to the world coordinate, and the trajectory information of the at least one object, which is called as second trajectory information, is generated.
According to the process S510, the radar device 406 directly detects and tracks the at least one object to obtain radar information of the at least one object.
According to the process S512, the detected pixel points of the at least one object in the radar information are converted from the polar coordinates to the world coordinates, so as to generate the trajectory information of the at least one object, i.e., the first trajectory information.
The execution sequence between the steps 502-506 and the steps 510-512 is not limited, and the steps 502-506 may be executed after the steps 510-512, or the steps 510-512 may be executed after the steps 502-506, or may be executed simultaneously.
According to the process S514, the first track information and the second track information are integrated, and finally the track information of at least one object is generated. The specific method comprises the following steps: firstly, establishing a one-to-one corresponding relation between at least one target in radar information and at least one target in image information; then, if the image information accuracy is high at the near end, adopting second track information as track information of at least one target, and if at least one target in the image information is lost, making up through first track information of at least one target in the corresponding radar information to be used as track information of at least one target; and if the radar information accuracy is higher at the far end, using the first track information of the at least one target in the radar information as the track information of the at least one target.
The obtained image information and trajectory information of the at least one object are transmitted to the attribute detection device, and fig. 6 describes the attribute detection device 204 in detail. The attribute detection device 204 includes a projectile attribute determination module 602 and a feature database 610. Wherein the projectile attribute determination 602 includes an image characteristic determination 604 of the projectile, a trajectory information determination 608 of the projectile, and an attribute determination 606 based on the behavior of the surrounding vehicle. Feature database 610 contains an image feature table 614 and a trajectory information table 612. The projectile property determination module 602 may determine the property of the projectile based on the image feature, trajectory information, and projectile-surrounding vehicle behavior of the projectile, or may determine the property, risk level, and the like of the projectile based on any combination of these factors.
Fig. 7 explains the flow of the attribute detection device in detail.
According to the process S702, the attribute detecting device 204 first obtains image features from the image information of at least one object, and obtains track information from the track information. Wherein the at least one object comprises: projectiles, and vehicle, pedestrian, etc. around projectiles.
According to the process S704, the attribute detection device 204 queries and compares the obtained image features and trajectory information of the projectile with the data in the feature database 610, and the image feature table 614 and trajectory information table 612 in the feature database 610 store the attributes of the marked object and the corresponding trajectory information and image features.
According to the process S706, when the image feature and/or the trajectory information of the projectile corresponds to the image feature and/or the trajectory information of the object in the feature database 610, for example, the similarity can be higher than a threshold, the attribute of the object is returned to the projectile attribute determination 602.
According to the process S708, trajectory information of vehicles around the projectile in a certain time period before and after the stationary time of the projectile is obtained, and compared, the difference between the trajectory information of the vehicle with the projectile and the trajectory information of the vehicle without the projectile is compared. The definition of perimeter as referred to herein, in one possible implementation, may include the lane in which the projectile is located, as well as the lanes on the left and right sides.
According to the process S710, a threshold is set according to the distance between the surrounding vehicle and the projectile, and some invalid trajectory information of the surrounding vehicle is filtered out, for example, in a possible implementation, the lane where the projectile is located and the lanes on the left and right sides of the lane where the projectile is located may be taken. The trajectory information of the vehicle exceeding this distance range is negligible.
According to the process S712, the similarity of the trajectory information of the vehicle around the projectile in the vicinity of the projectile within a certain time period is first calculated, and then the judgment is performed, if the similarity is smaller than a threshold, it is proved that the change of the trajectory occurs due to the presence of the projectile in the vehicle around the projectile, and an avoidance behavior is performed, which indicates that the projectile has a certain risk. If the similarity is larger than the threshold value, the surrounding vehicles are proved not to have avoidance behaviors, and the throwing object is not dangerous.
According to the process S716, when the feature data of the projectile does not exist in the feature database, the image feature and the trajectory information of the projectile are bound with the attribute and the risk degree of the projectile, and then updated to the feature database, so that when the projectile with the same image feature and/or trajectory information appears on the road in the future, the system can directly judge the attribute of the projectile, and the risk degree is high.
According to the process S718, obtaining the determined attribute of the projectile according to the image feature, the trajectory information and the behavior feature of the surrounding vehicle, where the attribute may include: the size, hazard level, type, etc. of the projectile. In a feasible mode, the attribute of the projectile can be judged only by the behavior characteristics of the surrounding vehicles; in another feasible mode, the attribute of the projectile can be judged according to any two items of the image characteristics, the track information and the behavior characteristics of the surrounding vehicle.
The graphic information and the track information of the at least one object acquired by the monitoring apparatus 202 are simultaneously transmitted to the attribution judging apparatus 206, and fig. 8 describes in detail a processing flow of the attribution judging apparatus 206. Wherein the at least one object comprises a projectile and a non-projectile, the non-projectile comprising an automobile, a non-automobile, a pedestrian, and the like.
According to the process S802, a reverse prediction is first performed based on the trajectory information of the projectile to obtain a reverse extended trajectory of the projectile, as shown in fig. 9A, the current trajectory 908 of the projectile 912 is a portion shown by a solid line, 904 is a reverse extended line of the current trajectory 908 and is shown by a dotted line, and the complete trajectory of the projectile is shown by a solid line portion 908 and a dotted line portion 904. The trajectory information of the projectile consists of current trajectory information and reverse extension trajectory information thereof.
According to the process S804, the intersection point between the projectile and the vehicle/non-vehicle/pedestrian is calculated, as shown in fig. 9A, there is a vehicle 910 in the figure, and the trajectory information thereof is used to obtain a motion trajectory 902, and there is an intersection point 906 between the trajectory of the projectile 912 and the motion trajectory at the same time.
According to the process S806, it is determined how many intersections are located at the same time, and if none of the intersections is located, the process directly skips to the process S814, and the attribution relationship of the projectile is output, and the attribution relationship is displayed as unknown. If there is a cross point, the flow jumps to a flow S808.
According to the process S808, if there is only one intersection point between the trajectory of the projectile and the trajectory of the vehicle/non-vehicle/pedestrian at the same time, as shown in fig. 9A, there is only one intersection point 908, it is determined that the projectile is from the truck 910. The process goes to S814, where the attribution relationship of the projectile 912 is output as the truck 910.
According to the process S808, if the trajectory of the projectile and the trajectory of the vehicle/non-vehicle/pedestrian are more than one intersection at the same time, as shown in fig. 9B, there are three intersections: 930. 932 and 938. The flow jumps to the flow S810.
According to the process S810, the attribution relation which is not possible is filtered out through the attribute of the throwing object. As shown in fig. 9B, there are 3 non-projectiles: van 922, van 920 and bicycle 940, one projectile 936, one bicycle track 940, two van tracks 940 and 924, projectile tracks 934 and 928. Three intersections 932, 930 and 938 are created at the same time, so the projectile 936, which may belong to a bicycle 940, a truck 920 or a truck 922. However, by the nature of projectile 936, such as size, it may be determined that projectile 936 is unlikely to be from bicycle 940. After excluding the impossible throw affiliation, the process proceeds to the next flow S812.
According to the process S812, the motor vehicle/non-motor vehicle/person closest to the starting point of the projectile and the intersection is selected as the belonging target. As shown in fig. 9B, the origin at which the projectile 936 is detected is the origin of the current trajectory 934 of the projectile 936, which is closer to the intersection 930 than to the intersection 938, and thus the projectile 936 is assigned to the truck 922, rather than the truck 920.
According to the process S814, the process S814 outputs the attribution relationship of the projectile to the alarm device 208 according to the determination result of the previous process.
Referring to FIG. 10 for further details of the alerting device 208, the alerting device 208 includes three sub-modules: hazard display 1002, home vehicle display 1004, manual intervention alert 1006. Firstly, judging the danger of the projectile according to the attributes of the projectile, such as: the object is very big, and the object is very heavy, and the object peripheral vehicle has the behavior of dodging, and the dangerous degree of this object is high, then dangerous demonstration 1002 presents the danger height. After the danger is displayed, the horse needs to find the source of the projectile to prevent more projectiles from appearing on the road, so after the projectile attribution judging device 206 determines the attribution relationship of the projectile, the belonging vehicle display module 1004 is used to display the relevant information of the vehicle to which the projectile belongs, such as the license plate of the vehicle, the type of the vehicle, and the like. In this scenario, the manual intervention alert 1006 needs to accomplish two things, first, the handling of the projectile, and when the risk is high, an alert is needed to prompt the user to intervene and remove the projectile from the road. Then, processing a throwing object source, and after the throwing object source is positioned, alarming is needed to prompt that manual intervention is needed, for example, workers can find a motor vehicle/non-motor vehicle/pedestrian generating the throwing object in time to process; or the telephone of the driver of the vehicle license plate is inquired through the traffic system, and the driver is informed of emergency stop and is treated through the telephone, so that the generation of new sprinkled objects is prevented. On the other hand, if the resulting projectile causes a traffic accident, the system will help to find responsible parties, helping to assist in liability determination.
In another embodiment, as described in the scenario of the system 300, in the case that the attribution judging device 206 is not included, the sub-module of the belonging vehicle display 1004 is not included in the warning device 208, the warning device 208 performs the above functions through the risk display 1002, and the manual intervention warning 1006 prompts the staff to handle the sprinkled object on the road in time according to the risk of the sprinkled object, and when the risk is high, the staff is required to handle the object immediately, and if the risk is low, the staff can handle the object periodically.
In another embodiment, as the scenario described in the system 310, in the case that the attribute detection device 204 is not included, there is no sub-module of the hazard display 1002 in the alert device 208, the alert device 208 performs the above function through the home vehicle display, and the manual intervention alert 1006 cuts off the source of the projectile according to the vehicle home relationship of the projectile, so as to prevent additional road safety hazards caused by the newly added projectile, and the manual intervention includes: for example, the staff can find the motor vehicle/non-motor vehicle/pedestrian producing the throwing object in time to process; or the telephone of the driver of the vehicle license plate is inquired through the traffic system, and the driver is informed of emergency stop and is treated through the telephone, so that the generation of new sprinkled objects is prevented. On the other hand, if the resulting projectile causes a traffic accident, the system will help to find responsible parties, helping to assist in liability determination.
The present application also provides a computer device 1100 as shown in fig. 11, comprising: a processor 1102, a memory 1104, a communication interface 1106, and a communication bus 1108. A processor 1102 in the computer device 1100 reads a set of computer instructions stored by a memory 1104 to perform the method of road safety monitoring described above to implement the functionality of any of the devices of any of the systems 200, 300 and 310.
It should be noted that, in the embodiments of the present application, the video monitoring device included in the monitoring apparatus may be an intelligent camera with certain computing capability.
It should be understood that the present application does not impose a limiting limitation on the division of functionality of various portions of the apparatus described above, nor on the environment in which the apparatus is specifically deployed. In actual application, appropriate function division adjustment and adaptive deployment can be performed according to the computing capability of each computer device or specific application requirements. For example: the functions performed by the information processing module 408 can be performed by the monitoring device 202 or the attribute detecting device 204. The functions implemented by the alerting means 208, the functions implemented by the attribute detecting means 204, and the functions implemented by the attribution judging means 206 may be performed by one computer device 1100.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical division, and other divisions may be implemented, for example, multiple modules or components may be combined or integrated with another system, or some features may be omitted, or not implemented. In addition, the shown or discussed mutual coupling or direct coupling or communication link may be an indirect coupling or communication link of some interfaces, devices or modules, and may be in an electrical, mechanical or other form.
The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical modules, may be located in one place, or may be distributed on a plurality of network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, functional modules in the embodiments of the present invention may be integrated into one processing module, or each module may exist alone physically, or two or more modules are integrated into one module. The integrated module can be realized in a hardware form, and can also be realized in a form of hardware and a software functional module.
It should be understood that the term "and/or" herein is merely one type of association relationship that describes an associated object, meaning that three relationships may exist, e.g., a and/or B may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship.
It is to be understood that the term "at least one" herein means one or more, and a plurality means two or more. At least one equivalent term is synonymous.
The integrated module implemented in the form of a software functional module may be stored in a computer-readable storage medium. The software functional module is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute some steps of the methods described in the embodiments of the present invention. The storage medium may be a readable non-volatile storage medium, and includes: a mobile hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other media capable of storing program codes.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and these modifications or substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (36)
1. A method of road safety monitoring, comprising:
acquiring road monitoring information and determining that a projectile exists on a road;
acquiring trajectory information of at least one object on the road according to the road monitoring information, wherein the at least one object comprises the projectile and at least one non-projectile; judging the attribute of the throwing object according to the track information of the at least one object;
sending an alarm according to the attribute of the throwing object;
wherein the method further comprises:
determining the source of the projectile based on the intersection of the trajectory information of the projectile and the trajectory information of the at least one non-projectile.
2. The method of claim 1, wherein obtaining trajectory information of at least one object on the roadway, and determining the attribute of the projectile from the trajectory information of the at least one object comprises:
acquiring track information of the throwing objects on the road, and judging the attributes of the throwing objects according to the track information of the throwing objects; or acquiring the track information of at least one non-projectile on the road, and judging the attribute of the projectile according to the track information of the at least one non-projectile; or the like, or, alternatively,
and acquiring track information of at least one non-projectile on the road and track information of the projectile, and judging the attribute of the projectile according to the track information of the at least one non-projectile and the track information of the projectile.
3. The method of claim 1, wherein the obtaining the road monitoring information comprises: road monitoring image information is obtained through video monitoring equipment on a road, and road monitoring radar information is obtained through radar equipment.
4. The method of claim 3, wherein the obtaining trajectory information of at least one object on the road comprises:
and acquiring first track information of the at least one object according to the radar information, acquiring second track information of the at least one object according to the image information, and integrating the first track information and the second track information to obtain track information of the at least one object.
5. The method of claim 3, further comprising: and acquiring the image characteristics of the projectile according to the image information.
6. The method of claim 5, further comprising: and judging the attribute of the projectile according to the image characteristics of the projectile.
7. The method of claim 6, wherein, when the at least one object includes the projectile, the determining the attribute of the at least one object projectile specifically comprises:
and comparing the trajectory information of the projectile with the image characteristics of the projectile through a characteristic database, and judging the attribute of the projectile.
8. The method of claim 7, wherein in the event of an unsuccessful comparison with the feature database, the trajectory information or image features of the projectile are refreshed into the feature database.
9. The method of any one of claims 1-7, wherein the property of the projectile comprises a degree of danger of the projectile.
10. The method of claim 9, wherein different levels of warning are issued based on different levels of risk of the projectile.
11. The method of any of claims 3-8, wherein determining the presence of a projectile on the roadway comprises:
detecting an object in the image information by an optical flow method, identifying a type of the object, and determining an object whose type is unknown as the projectile.
12. The method of any of claims 1, 2, 3, 4, 5, 6, 7, 8, 10, wherein the track information comprises current track information and oppositely extending track information of the current track information.
13. The method of claim 9, wherein the track information comprises current track information and backward-extended track information of the current track information.
14. The method of claim 11, wherein the track information comprises current track information and backward-extended track information of the current track information.
15. A method of road safety monitoring, comprising:
acquiring road monitoring information and determining that a projectile exists on a road; acquiring trajectory information of a projectile and at least one non-projectile on the road according to the road monitoring information; determining the source of the projectile according to the intersection condition of the trajectory information of the projectile and the trajectory information of the at least one non-projectile;
and sending an alarm according to the source of the throwing object.
16. The method of claim 15, wherein the obtaining the road monitoring information comprises: and acquiring road monitoring image information through the video monitoring equipment on the road and acquiring road monitoring radar information through the radar equipment.
17. The method of claim 16, wherein the obtaining trajectory information of a projectile on the roadway comprises: and acquiring first track information of the projectile from the radar information, acquiring second track information of the projectile from the image information, and synthesizing the first track information and the second track information to obtain track information of the projectile.
18. The method of claim 15, wherein determining the source of the projectile based on the crossing of the trajectory information comprises:
if the trajectory information of the projectile and the trajectory information of the at least one non-projectile intersect at a first time, the projectile is from the at least one non-projectile; or
Selecting from said at least two of said projectiles the non-projectile closest to said projectile as the source of said projectile if said projectile trajectory information and at least two non-projectile trajectory information intersect at a first time.
19. The method of any one of claims 15-18, wherein the track information includes current track information and backward-extended track information of the current track information.
20. The method of any one of claims 15-18, wherein the method of road safety monitoring further comprises:
judging the attribute of the projectile according to the track information of the at least one non-projectile; or the like, or, alternatively,
judging the attribute of the projectile according to the track information of the projectile; or the like, or, alternatively,
and judging the attribute of the projectile according to the trajectory information of the projectile and the trajectory information of the at least one non-projectile.
21. The method of claim 19, wherein the method of road safety monitoring further comprises:
judging the attribute of the projectile according to the track information of the at least one non-projectile; or the like, or, alternatively,
judging the attribute of the projectile according to the track information of the projectile; or the like, or, alternatively,
and judging the attribute of the projectile according to the trajectory information of the projectile and the trajectory information of the at least one non-projectile.
22. The method of claim 16 or 17, wherein the method of road safety monitoring further comprises:
and acquiring the image characteristics of the throwing object according to the image information.
23. The method of claim 22, further comprising: and judging the attribute of the projectile according to the image characteristics of the projectile.
24. A system for road safety monitoring, the system comprising: the monitoring device, the attribute detection device and the alarm device;
the monitoring device is used for acquiring road monitoring information and determining that a projectile exists on a road; acquiring trajectory information of at least one object on the road according to the road monitoring information, wherein the at least one object comprises the projectile and at least one non-projectile;
the attribute detection device is used for judging the attribute of the throwing object according to the track information of the at least one object;
the alarm device is used for giving an alarm according to the attribute of the throwing object;
wherein the system further comprises: an affiliation determination device;
and the attribution judging device is used for determining the source of the projectile according to the condition that the track information of the projectile is crossed with the track information of the at least one non-projectile.
25. The system of claim 24, wherein the attribute detection device is configured to determine the attribute of the projectile based on the trajectory information of the at least one object, comprising:
acquiring track information of the throwing objects on the road, and judging the attributes of the throwing objects according to the track information of the throwing objects; or acquiring track information of at least one non-projectile on the road, and judging the attribute of the projectile according to the track information of the at least one non-projectile; or the like, or, alternatively,
and acquiring the track information of at least one non-projectile on the road and the track information of the projectile, and judging the attribute of the projectile according to the track information of the at least one non-projectile and the track information of the projectile.
26. The system of claim 24, wherein the monitoring device comprises: video monitoring equipment and radar equipment;
the video monitoring equipment acquires road monitoring image information, and the radar equipment acquires road monitoring radar information.
27. The system of claim 26, wherein the monitoring device obtains first trajectory information of the at least one object according to the radar information, obtains second trajectory information of the at least one object according to the image information, and combines the first trajectory information and the second trajectory information to obtain trajectory information of the at least one object.
28. A system for road safety monitoring, the system comprising: the device comprises a monitoring device, an attribution judging device and an alarming device;
the monitoring device is used for acquiring road monitoring information and determining that a projectile exists on a road; acquiring trajectory information of at least one object on the road according to the road monitoring information, wherein the at least one object comprises the projectile and at least one non-projectile;
the attribution judging device is used for determining the source of the projectile according to the condition that the track information of the projectile is crossed with the track information of the at least one non-projectile;
the alarm device is used for giving an alarm according to the source of the throwing object.
29. The system of claim 28, further comprising: an attribute detection device;
and the attribute detection device judges the attribute of the throwing object according to the track information of the at least one object.
30. The system of claim 29, wherein the attribute detection device is configured to determine the attribute of the projectile based on the trajectory information of the at least one object, comprising:
acquiring track information of the throwing objects on the road, and judging the attributes of the throwing objects according to the track information of the throwing objects; or acquiring track information of at least one non-projectile on the road, and judging the attribute of the projectile according to the track information of the at least one non-projectile; or the like, or, alternatively,
and acquiring track information of at least one non-projectile on the road and track information of the projectile, and judging the attribute of the projectile according to the track information of the at least one non-projectile and the track information of the projectile.
31. The system of claim 28, wherein the monitoring device comprises: video monitoring equipment and radar equipment;
the video monitoring equipment acquires road monitoring image information, and the radar equipment acquires road monitoring radar information.
32. The system according to claim 31, wherein the monitoring device is configured to obtain first trajectory information of the at least one object according to the radar information, obtain second trajectory information of the at least one object according to the image information, and synthesize the first trajectory information and the second trajectory information to obtain trajectory information of the at least one object.
33. A computer device for road safety monitoring, the computer device comprising a processor and a memory, wherein:
the memory having stored therein computer instructions;
the processor executes the computer instructions to cause the computer device to perform the method of any of claims 1-14.
34. A computer device for road safety monitoring, the computer device comprising a processor and a memory, wherein:
the memory having stored therein computer instructions;
the processor executing the computer instructions to cause the computer device to perform the method of any of the claims 15-23.
35. A computer-readable storage medium, having stored thereon computer instructions, which, when executed by a computer device, cause the computer device to perform the method of any one of claims 1 to 14 or cause the computer device to implement the functions of the system of any one of claims 24 to 27.
36. A computer-readable storage medium storing computer instructions which, when executed by a computer device, cause the computer device to perform the method of any one of claims 15 to 23 or cause the computer device to implement the functions of the system of any one of claims 28 to 32.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010555778.4A CN113808409B (en) | 2020-06-17 | 2020-06-17 | Road safety monitoring method, system and computer equipment |
| PCT/CN2021/098258 WO2021254175A1 (en) | 2020-06-17 | 2021-06-04 | Road safety monitoring method and system, and computer device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010555778.4A CN113808409B (en) | 2020-06-17 | 2020-06-17 | Road safety monitoring method, system and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113808409A CN113808409A (en) | 2021-12-17 |
| CN113808409B true CN113808409B (en) | 2023-02-10 |
Family
ID=78892727
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010555778.4A Active CN113808409B (en) | 2020-06-17 | 2020-06-17 | Road safety monitoring method, system and computer equipment |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN113808409B (en) |
| WO (1) | WO2021254175A1 (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115311850A (en) * | 2022-07-15 | 2022-11-08 | 重庆长安汽车股份有限公司 | Sprinkler identification and early warning method and system based on crowdsourcing mode |
| CN116994216A (en) * | 2023-09-27 | 2023-11-03 | 深圳市九洲卓能电气有限公司 | Highway casting object detection method and system based on deep learning |
| CN117494029B (en) * | 2023-12-29 | 2024-04-19 | 苏州映赛智能科技有限公司 | Road casting event identification method and device |
| CN117593890B (en) * | 2024-01-18 | 2024-03-29 | 交通运输部公路科学研究所 | Detection method and device for road spilled objects, electronic equipment and storage medium |
Family Cites Families (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3607841B2 (en) * | 1999-09-10 | 2005-01-05 | 富士通株式会社 | Obstacle detection device |
| JP3977802B2 (en) * | 2003-12-16 | 2007-09-19 | 株式会社東芝 | Obstacle detection device, obstacle detection method, and obstacle detection program |
| JP2009086788A (en) * | 2007-09-28 | 2009-04-23 | Hitachi Ltd | Vehicle surrounding monitoring device |
| WO2012117044A2 (en) * | 2011-03-01 | 2012-09-07 | Continental Teves Ag & Co. Ohg | Method and device for the prediction and adaptation of movement trajectories of motor vehicles |
| WO2015037117A1 (en) * | 2013-09-13 | 2015-03-19 | 日立マクセル株式会社 | Information display system, and information display device |
| DE102014208524A1 (en) * | 2014-05-07 | 2015-11-12 | Robert Bosch Gmbh | LOCAL TRANSPORTATION ANALYSIS WITH DETECTION OF A TRAFFIC PATH |
| CN105589875B (en) * | 2014-10-22 | 2019-10-25 | 方正国际软件(北京)有限公司 | A kind of method and device that multi-trace is drawn |
| CN106297278B (en) * | 2015-05-18 | 2019-12-20 | 杭州海康威视数字技术股份有限公司 | Method and system for querying a projectile vehicle |
| US9606539B1 (en) * | 2015-11-04 | 2017-03-28 | Zoox, Inc. | Autonomous vehicle fleet service and system |
| US10233679B1 (en) * | 2016-04-11 | 2019-03-19 | State Farm Mutual Automobile Insurance Company | Systems and methods for control systems to facilitate situational awareness of a vehicle |
| CN205621297U (en) * | 2016-05-03 | 2016-10-05 | 上海市城市建设设计研究总院 | Tram safety device |
| CN106781570B (en) * | 2016-12-30 | 2019-08-02 | 大唐高鸿信息通信研究院（义乌）有限公司 | A kind of identification of highway danger road conditions and alarm method suitable for vehicle-mounted short distance communication network |
| WO2018173581A1 (en) * | 2017-03-21 | 2018-09-27 | 株式会社デンソー | Driving assistance device |
| CN107392937B (en) * | 2017-07-14 | 2023-03-14 | 腾讯科技（深圳）有限公司 | Target tracking method and device and electronic equipment |
| CN109327676B (en) * | 2017-07-31 | 2021-02-12 | 杭州海康威视数字技术股份有限公司 | High-altitude falling object monitoring system, method and device |
| JP6859907B2 (en) * | 2017-09-08 | 2021-04-14 | トヨタ自動車株式会社 | Vehicle control unit |
| CN110275220A (en) * | 2018-03-15 | 2019-09-24 | 阿里巴巴集团控股有限公司 | Detection method, the method for detecting position of target object, alarm method |
| CN110196440B (en) * | 2018-05-22 | 2022-01-11 | 腾讯大地通途（北京）科技有限公司 | Method and device for identifying coincident track, electronic equipment and storage medium |
| CN109309811B (en) * | 2018-08-31 | 2021-02-19 | 中建三局智能技术有限公司 | High-altitude parabolic detection system and method based on computer vision |
| CN109544934A (en) * | 2018-12-19 | 2019-03-29 | 同济大学 | Efficiency safety monitoring system based on urban intersection mixed traffic flow three-dimensional track |
| CN109801508B (en) * | 2019-02-26 | 2021-06-04 | 百度在线网络技术（北京）有限公司 | Method and device for predicting movement track of obstacle at intersection |
| CN110659560B (en) * | 2019-08-05 | 2022-06-28 | 深圳市优必选科技股份有限公司 | Method and system for identifying associated object |
| CN110473402B (en) * | 2019-08-20 | 2021-04-27 | 河北德冠隆电子科技有限公司 | Abnormal event detection and early warning system based on target abnormal behavior trajectory analysis |
| CN110427927A (en) * | 2019-09-29 | 2019-11-08 | 恒大智慧科技有限公司 | Hold-up interception method, interceptor control system and the storage medium of falling object from high altitude |
| CN111127507A (en) * | 2019-12-18 | 2020-05-08 | 成都通甲优博科技有限责任公司 | Method and system for determining throwing object |
| CN111274982B (en) * | 2020-02-04 | 2023-04-07 | 浙江大华技术股份有限公司 | Method and device for identifying projectile and storage medium |
| CN111126362B (en) * | 2020-03-26 | 2020-08-07 | 北京三快在线科技有限公司 | Method and device for predicting obstacle track |
-
2020
- 2020-06-17 CN CN202010555778.4A patent/CN113808409B/en active Active
-
2021
- 2021-06-04 WO PCT/CN2021/098258 patent/WO2021254175A1/en active Application Filing
Also Published As
| Publication number | Publication date |
|---|---|
| CN113808409A (en) | 2021-12-17 |
| WO2021254175A1 (en) | 2021-12-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113808409B (en) | Road safety monitoring method, system and computer equipment | |
| JP7140922B2 (en) | Multi-sensor data fusion method and apparatus | |
| KR102628790B1 (en) | Risk processing for vehicles having autonomous driving capabilities | |
| US10220841B2 (en) | Method and system for assisting a driver of a vehicle in driving the vehicle, vehicle and computer program | |
| US9524643B2 (en) | Orientation sensitive traffic collision warning system | |
| US10336252B2 (en) | Long term driving danger prediction system | |
| JP2018152056A (en) | Risk-based driver assistance for approaching intersections with limited visibility | |
| US9626867B2 (en) | False warning suppression in a collision avoidance system | |
| WO2019075341A1 (en) | Detection of driving actions that mitigate risk | |
| CN108073893B (en) | Detection of plants using distance data | |
| JP5898001B2 (en) | Vehicle periphery monitoring device | |
| US10916134B2 (en) | Systems and methods for responding to a vehicle parked on shoulder of the road | |
| CN113674523A (en) | Traffic accident analysis method, device and equipment | |
| US20240149915A1 (en) | Classification and prioritization of objects for autonomous driving | |
| CN114537374A (en) | Vehicle front anti-collision system based on travelable area | |
| CN114379574B (en) | Object reminding device, system and method for vehicle | |
| US20230356751A1 (en) | Malicious event detection for autonomous vehicles | |
| KR20220089138A (en) | Road Dangerous Object Recognition Apparatus and Method | |
| CN112866636B (en) | Group fog identification early warning method and system based on farthest visible distance and electronic equipment | |
| WO2019127076A1 (en) | Automated driving vehicle control by collision risk map | |
| JP2015026004A (en) | Visual recognition action evaluation device | |
| KR102499056B1 (en) | Method, apparatus and server to monitor driving status based vehicle route | |
| US20220067403A1 (en) | Visual guidance system and method | |
| EP4372715A1 (en) | Vehicle collision threat assessment | |
| EP3757966A1 (en) | Method and system for identifying hazard objects around a vehicle |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |