CN115662186A - Vehicle obstacle avoidance method and system based on artificial intelligence - Google Patents
Vehicle obstacle avoidance method and system based on artificial intelligence Download PDFInfo
- Publication number
- CN115662186A CN115662186A CN202211253757.2A CN202211253757A CN115662186A CN 115662186 A CN115662186 A CN 115662186A CN 202211253757 A CN202211253757 A CN 202211253757A CN 115662186 A CN115662186 A CN 115662186A
- Authority
- CN
- China
- Prior art keywords
- dangerous
- road section
- vehicle
- vehicles
- information
- 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.)
- Granted
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The invention is suitable for the field of computers, and provides a vehicle obstacle avoidance method and system based on artificial intelligence, wherein the method comprises the following steps: acquiring image data of a dangerous road section, and detecting dangerous information of the dangerous road section according to the image data, wherein the dangerous information comprises quantity information and movement information of dangerous targets; when the moving speed of the dangerous target is detected to be smaller than the preset speed and the moving distance of the dangerous target is smaller than the first threshold distance in the continuous detection period, estimating the time of the dangerous target approaching a dangerous road section lane, and sending a first early warning prompt instruction to the vehicle which is about to pass through the dangerous road section according to the time of the dangerous target approaching the dangerous road section lane; the invention has the beneficial effects that: by using technologies such as intelligent identification and detection in artificial intelligence, identification and detection of roads are combined with vehicle interaction, reliable reference can be provided for driving of vehicles on dangerous road sections, and application applicability is good.
Description
Technical Field
The invention belongs to the field of computers, and particularly relates to a vehicle obstacle avoidance method and system based on artificial intelligence.
Background
More and more products are developing towards networking, intellectualization and unmanned directions, especially in the vehicle industry, such as intelligent driving of automobiles, from assistant driving to advanced assistant driving and then to unmanned driving, and is also developing stepwise, vehicle-mounted people or vehicle-mounted objects bring great convenience to travel or transportation of people, safe driving of vehicles requires that roads have certain flatness and recognition capability of the vehicles, and drivers are also required to have abundant driving experiences, and the use obstacle avoidance capability of the vehicles is the comfort of passengers and drivers during driving and the complete and lossless guarantee of goods, and is also one of important embodiments of safe driving of the vehicles.
At present, high-level assistant driving is most promising and most possible to achieve currently, the most basic of the high-level assistant driving is vehicle obstacle avoidance, a decision layer of the high-level assistant driving generally utilizes an intelligent controller, a sensing layer of the high-level assistant driving generally utilizes an ultrasonic radar, a GPS (global positioning system), a laser radar, a camera and the like, an application layer of the high-level assistant driving generally utilizes application architectures such as EPS (expandable polystyrene), EBS (electromagnetic emission system) and the like to achieve, and the other application layers are embedded into an Adaptive Autosar architecture.
When an existing vehicle runs on a road, particularly when the existing vehicle runs on a road without a good protective measure, some obstacles may be encountered, whether living body obstacles or passively moving obstacles can cause serious influence on the running of the vehicle, even accidents occur, when high requirements are made on intelligent obstacle avoidance, the research on the prior art can find that the existing vehicle generally has high requirements on the vehicle, but the high-level intelligence inevitably causes that the obstacle avoidance does not have universality considering the application cost and the type of the vehicle.
Disclosure of Invention
The embodiment of the invention aims to provide a vehicle obstacle avoidance method and system based on artificial intelligence, and aims to solve the problems in the background technology.
The embodiment of the invention is realized in such a way that, on one hand, a vehicle obstacle avoidance method based on artificial intelligence comprises the following steps:
acquiring image data of a dangerous road section, and detecting dangerous information of the dangerous road section according to the image data, wherein the dangerous information comprises quantity information and movement information of dangerous targets;
when the moving speed of the dangerous target is detected to be smaller than the preset speed and the moving distance of the dangerous target is smaller than the first threshold distance in the continuous detection period, estimating the time of the dangerous target approaching the lane of the dangerous road section, and sending a first early warning prompt instruction to the vehicle about to pass through the dangerous road section according to the time of the dangerous target approaching the lane of the dangerous road section;
when the number of the dangerous targets is detected to be more than or equal to one, speed reduction reminding information is sent to vehicles which are about to arrive at the dangerous road section, and when the moving speed of at least one dangerous target is continuously detected to be not less than the preset speed, a second early warning prompting instruction is sent to accompanying vehicles which are about to arrive at the dangerous road section, wherein the vertical distance between at least two vehicles running in rows in the accompanying vehicles is within a second threshold distance.
As a further aspect of the present invention, before acquiring the dangerous road, the method further includes:
acquiring historical traffic data information;
counting accident types and accident frequencies in historical traffic data information, wherein the accident types are associated with danger information;
marking the road section danger level in the preset road section range according to the accident type and the accident frequency, and judging the sub road section in the preset road section range as the dangerous road section when the road section danger level is larger than the preset level.
As a still further aspect of the present invention, the marking the road section risk level within the preset road section range according to the accident type and the accident frequency specifically includes:
calculating danger grade scores of sub-road sections in a preset road section range, wherein the scores of different accident types are different, and the danger grade score is the product of the score of the accident type and the corresponding accident frequency;
and dividing road section dangerous intervals according to the dangerous grade scores, wherein different dangerous road section intervals correspond to set dangerous grade score difference values.
As a still further aspect of the present invention, the acquiring image data of a dangerous road segment, and detecting dangerous information of the dangerous road segment according to the image data, where the dangerous information at least includes quantity information of dangerous objects and movement information specifically includes:
acquiring an acquisition cycle, and acquiring image data of a dangerous road section once every other acquisition cycle;
detecting whether the image data contains a preset dangerous target or not;
and if so, detecting the quantity information and the movement information of the dangerous targets, wherein the movement information at least comprises a movement distance and a movement speed.
As a further scheme of the present invention, the estimating a time when the dangerous target approaches the lane of the dangerous section, and sending the first warning prompt instruction to the vehicle about to pass through the dangerous section according to the time when the dangerous target approaches the lane of the dangerous section specifically includes:
acquiring the maximum moving distance of the dangerous target in each detection period, and calculating the maximum value of the moving speed of the dangerous target according to the maximum moving distance;
respectively calculating the time of the dangerous target moving from the current position to the lane edge position of the dangerous road section according to the maximum value of the moving speed of the dangerous target, generating first time corresponding to the maximum value of the moving speed of the dangerous target, and establishing a dangerous target moving time ranking according to the first time;
acquiring a second time of a vehicle about to enter the dangerous road section;
and when the difference value between the second time and the first time in the dangerous target moving time ranking is within a set time difference value, sending a first early warning prompt instruction to a vehicle about to enter a dangerous road section.
As a further aspect of the present invention, the method further comprises:
and estimating the volume of the dangerous target according to the area of the dangerous target in the image data, and sending road to-be-maintained prompt information to a road maintenance center when the volume of the dangerous target is larger than a set volume.
As a further scheme of the present invention, the sending a second warning prompt instruction to a company vehicle about to arrive at the dangerous segment specifically includes:
identifying all vehicles which are about to arrive at the dangerous road section and run in rows, and marking vehicles with the vertical distance between at least two vehicles in all vehicles within a second threshold distance as accompanying vehicles;
trying to establish information interaction channels among vehicle-mounted terminals of all accompanying vehicles, and synchronously sending a second early warning prompt instruction to the accompanying vehicles which are about to arrive at the dangerous road section, wherein the feedback instruction comprises a prompt for changing lanes carefully;
detecting a feedback instruction after the accompanying vehicle receives the second early warning prompt instruction, and identifying the accompanying vehicle which does not send the feedback instruction within a set time length, wherein the feedback instruction is used for representing the feedback of a driver of the accompanying vehicle to the second early warning prompt instruction;
if yes, marking the accompanying vehicle which does not send the feedback instruction as a first vehicle, marking other vehicles in the accompanying vehicle as second vehicles, positioning a third vehicle, wherein the third vehicle is a second vehicle which is not in the same lane as the first vehicle and is obliquely behind the first vehicle, and sending prompt information for paying attention to lane change of the vehicle to the third vehicle.
As a further aspect of the present invention, in another aspect, an artificial intelligence based vehicle obstacle avoidance system includes:
the system comprises an acquisition and detection module, a display module and a display module, wherein the acquisition and detection module is used for acquiring image data of a dangerous road section and detecting dangerous information of the dangerous road section according to the image data, and the dangerous information comprises quantity information and movement information of dangerous targets;
the first early warning module is used for estimating the time of the dangerous target approaching the dangerous road section lane when the moving speed of the dangerous target is detected to be smaller than the preset speed and the moving distance of the dangerous target is detected to be smaller than the first threshold distance in the continuous detection period, and sending a first early warning prompt instruction to the vehicle about to pass through the dangerous road section according to the time of the dangerous target approaching the dangerous road section lane;
and the second early warning module is used for sending a deceleration reminding message to vehicles which are about to arrive at the dangerous road section when the number of the dangerous targets is detected to be more than or equal to one, and sending a second early warning prompting instruction to accompanying vehicles which are about to arrive at the dangerous road section when the moving speed of at least one dangerous target is continuously detected to be not less than the preset speed, wherein the vertical distance between at least two vehicles running in rows in the accompanying vehicles is within a second threshold distance.
According to the vehicle obstacle avoidance method and system based on artificial intelligence, provided by the embodiment of the invention, the technologies such as intelligent identification and detection in artificial intelligence are utilized, the identification and detection of the road and the vehicle are combined interactively, a reliable reference can be provided for the driving of the vehicle in a dangerous road section, obstacle early warning is provided, the vehicle can conveniently avoid dangerous targets or obstacles caused by the dangerous targets, a good prompting effect is achieved, the occurrence of accidents such as scratch and rubbing can be reduced, the safety of the vehicle in the dangerous road section in driving can be guaranteed, and the universality of the vehicle obstacle avoidance application can be improved.
Drawings
Fig. 1 is a main flow chart of a vehicle obstacle avoidance method based on artificial intelligence.
Fig. 2 is a flowchart of detecting danger information of a dangerous road segment according to the image data in an artificial intelligence-based vehicle obstacle avoidance method.
Fig. 3 is a flowchart of sending a first warning prompt instruction to a vehicle about to pass through a dangerous road section according to the time when the dangerous target approaches a lane of the dangerous road section in the artificial intelligence-based vehicle obstacle avoidance method.
Fig. 4 is a flowchart of the second warning instruction to the accompanying vehicle which is about to reach the dangerous segment.
Fig. 5 is a main structure diagram of a vehicle obstacle avoidance system based on artificial intelligence.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Specific implementations of the present invention are described in detail below with reference to specific embodiments.
According to the vehicle obstacle avoidance method and system based on artificial intelligence, provided by the invention, the technologies such as intelligent identification and detection in artificial intelligence are utilized, the identification and detection of the road and the vehicle are combined in an interactive mode, a reliable reference can be provided for the driving of the vehicle in a dangerous road section, obstacle early warning is provided, the vehicle can conveniently avoid dangerous targets or obstacles caused by the dangerous targets, a good prompting effect is achieved, the occurrence of events such as scratch and the like can be reduced, the driving safety of the vehicle in the dangerous road section is guaranteed, the universality of vehicle obstacle avoidance application can be improved, and the technical problems in the background technology are solved.
As shown in fig. 1, a main flow chart of an artificial intelligence based vehicle obstacle avoidance method according to an embodiment of the present invention is provided, where the artificial intelligence based vehicle obstacle avoidance method includes:
step S10: acquiring image data of a dangerous road section, and detecting dangerous information of the dangerous road section according to the image data, wherein the dangerous information comprises quantity information and movement information of dangerous targets;
step S11: when the moving speed of the dangerous target is detected to be smaller than the preset speed and the moving distance of the dangerous target is smaller than the first threshold distance in the continuous detection period, estimating the time of the dangerous target approaching the lane of the dangerous road section, and sending a first early warning prompt instruction to the vehicle about to pass through the dangerous road section according to the time of the dangerous target approaching the lane of the dangerous road section;
step S12: when the number of the dangerous targets is detected to be more than or equal to one, speed reduction reminding information is sent to vehicles which are about to arrive at the dangerous road section, and when the moving speed of at least one dangerous target is continuously detected to be not less than the preset speed, a second early warning prompting instruction is sent to accompanying vehicles which are about to arrive at the dangerous road section, wherein the vertical distance between at least two vehicles running in rows in the accompanying vehicles is within a second threshold distance.
When the method is applied, when the moving speed of the dangerous target is detected to be smaller than the preset speed and the moving distance of the dangerous target is detected to be smaller than the first threshold distance in the continuous detection period, the time that the dangerous target approaches the dangerous road section lane is estimated, and a first early warning prompt instruction is sent to a vehicle which is about to pass through the dangerous road section according to the time that the dangerous target approaches the dangerous road section lane, wherein the first early warning prompt instruction has better pertinence, can provide more reliable reference for the driving of the vehicle on the dangerous road section (for example, the driver in the vehicle), provides obstacle early warning, and facilitates the vehicle to avoid the dangerous target or obstacles caused by the obstacle early warning; when the number of the dangerous objects is detected to be more than or equal to one, speed reduction reminding information is sent to vehicles which are about to arrive at the dangerous road section, and when the moving speed of at least one dangerous object is continuously detected to be not less than the preset speed, a second early warning prompting instruction is sent to the accompanying vehicles which are about to arrive at the dangerous road section, wherein the vertical distance between at least two vehicles running in rows in the accompanying vehicles is within a second threshold distance, so that the accompanying vehicles pay attention to cautious lane change after paying attention to speed reduction running, a good prompting effect is achieved, the occurrence of accidents such as scratch can be reduced, the running safety of the vehicles on the dangerous road section is guaranteed, and the universality of vehicle obstacle avoidance application can be improved.
As a preferred embodiment of the present invention, before the dangerous road is acquired, the method further includes:
step S20: acquiring historical traffic data information;
step S21: counting accident types and accident frequencies in historical traffic data information, wherein the accident types are associated with danger information;
step S22: marking a road section danger level in a preset road section range according to the accident type and the accident frequency, and judging that the sub-road section in the preset road section range is a dangerous road section when the road section danger level is greater than the preset level.
In one aspect of this embodiment, the marking the road segment risk level within the preset road segment range according to the accident type and the accident frequency specifically includes:
step S221: calculating danger grade scores of sub-road sections within a preset road section range, wherein the scores of different accident types are different, and the danger grade score is the product of the score of the accident type and the corresponding accident frequency;
step S222: and dividing road section dangerous intervals according to the dangerous grade scores, wherein different dangerous road section intervals correspond to set dangerous grade score difference values. For example, the sub-links corresponding to the risk level score exceeding 60 are all dangerous links, and 60 is set according to the accident type and the accident frequency.
It can be understood that the accident type and the accident frequency are counted according to historical traffic data information, then the road section danger level in the preset road section range is marked according to the accident type and the accident frequency, and when the road section danger level is larger than the preset level, the sub-road section in the preset road section range is judged to be the dangerous road section, so that the judgment on the dangerous road section has a high reference value.
As shown in fig. 2, as a preferred embodiment of the present invention, the acquiring image data of a dangerous segment, and detecting dangerous information of the dangerous segment according to the image data, where the dangerous information at least includes quantity information of dangerous objects and movement information specifically includes:
step S101: acquiring an acquisition cycle, and acquiring image data of a dangerous road section once every other acquisition cycle;
step S102: detecting whether the image data contains a preset dangerous target or not;
step S103: and if so, detecting the quantity information and the movement information of the dangerous targets, wherein the movement information at least comprises a movement distance and a movement speed.
When the embodiment is applied, the acquisition period may be determined according to actual conditions and experience, for example, 0.5s, and whether the image data includes a preset dangerous target is detected, where the preset dangerous target may be an obviously moving obstacle such as an animal, or an obstacle that moves slowly and passively such as a stone, an object left beside a road or on a road, and an object that moves due to factors such as weather changes, and once the obstacle is on a road where a vehicle is moving, the obstacle may cause an obstacle to the vehicle, and even cause an accident.
As shown in fig. 3, as a preferred embodiment of the present invention, the estimating a time when a dangerous object approaches a lane of a dangerous segment, and sending a first warning prompt instruction to a vehicle about to pass through the dangerous segment according to the time when the dangerous object approaches the lane of the dangerous segment specifically includes:
step S111: acquiring the maximum moving distance of the dangerous target in each detection period, and calculating the maximum value of the moving speed of the dangerous target according to the maximum moving distance;
step S112: respectively calculating the time of the dangerous target moving from the current position to the lane edge position of the dangerous road section according to the maximum value of the moving speed of the dangerous target, generating first time corresponding to the maximum value of the moving speed of the dangerous target, and establishing a dangerous target moving time ranking according to the first time; here, the dangerous target moving time ranking may be a ranking of a first time corresponding to a maximum value of the plurality of dangerous target moving speeds;
step S113: acquiring a second time of a vehicle about to enter the dangerous road section; the second time can be estimated by the driving speed of the vehicle before the dangerous road section and the corresponding distance, for example, by the ratio of the distance to the maximum driving speed, or the ratio is multiplied by a corresponding correction coefficient (between 0 and 1), and of course, for the vehicle which is near to or driving at a constant speed, the second time is more convenient to calculate; since a plurality of dangerous objects may be spread over the dangerous segment, the calculation of the second time is started from the time of coming into the dangerous segment;
step S114: and when the difference value between the second time and the first time in the dangerous target moving time ranking is within a set time difference value, sending a first early warning prompt instruction to a vehicle about to enter a dangerous road section. The first warning prompt instruction may be a voice prompt, a vibration prompt, or the like, which is not limited herein.
It can be understood that the maximum moving distance is obtained according to several continuous detection cycles, and therefore has a certain reference value (corresponding correction coefficients can be given according to actual requirements), the first time is the time when the current position moves to the lane edge position of the dangerous road section, and it can be understood that a dangerous target may threaten the driving of a vehicle on the road and may threaten the driving of the vehicle, and the difference value between the first time and the second time indicates that the dangerous target may "meet" the driving vehicle on the road within a set time difference value, and threatens the corresponding vehicle, so that the first warning prompt instruction has a good pertinence, and provides a reliable reference for the driving of the vehicle on the dangerous road section, and provides a barrier warning, so that the dangerous target or a barrier caused thereby is conveniently avoided, and when the automatic driving level of the vehicle is not high, the barrier avoidance reference is provided for a driver.
As a preferred embodiment of the present invention, the method further comprises:
step S30: and estimating the volume of the dangerous target according to the area of the dangerous target in the image data, and sending road to-be-maintained prompt information to a road maintenance center when the volume of the dangerous target is larger than a set volume.
It can be understood that the larger the volume of the dangerous target is, the greater the hazard is on the premise of a certain speed, and a road driving obstacle which cannot be crossed by the vehicle may be directly caused, so that the road maintenance prompting information needs to be sent to the road maintenance center.
As shown in fig. 4, as a preferred embodiment of the present invention, the sending a second warning prompt instruction to a vehicle coming to a dangerous segment specifically includes:
step S121: identifying all vehicles which are about to arrive at the dangerous road section and run in rows, and marking the vehicles with the vertical distance between at least two vehicles in all the vehicles within a second threshold distance as accompanying vehicles;
step S122: trying to establish information interaction channels among vehicle-mounted terminals of all accompanying vehicles, and synchronously sending a second early warning prompt instruction to the accompanying vehicles which are about to arrive at the dangerous road section, wherein the feedback instruction comprises a prompt for changing lanes carefully; on-vehicle terminals include, but are not limited to, terminals for internet of vehicles;
step S123: detecting a feedback instruction after the accompanying vehicle receives the second early warning prompt instruction, and identifying the accompanying vehicle which does not send the feedback instruction within a set time length, wherein the feedback instruction is used for representing the feedback of a driver of the accompanying vehicle to the second early warning prompt instruction; when no feedback instruction is sent within a set time length, the vehicle-mounted terminal fails or a driver along with the vehicle does not feed back in time; the feedback accompanying the driver of the vehicle to the second warning prompt instruction may be a voice reception feedback, such as an "ok" reply, or a touch screen confirmation feedback, or a fingerprint confirmation feedback, indicating that the driver accompanying the vehicle maintains a basic awareness, such as has been read, of the second warning prompt instruction;
step S124: if yes, marking the accompanying vehicle which does not send the feedback instruction as a first vehicle, marking other vehicles in the accompanying vehicle as second vehicles, positioning a third vehicle, and sending prompt information for paying attention to the lane change of the vehicle to the third vehicle, wherein the third vehicle is a second vehicle which is not in the same lane as the first vehicle and is obliquely behind the first vehicle. Considering that lane changing may be left-handed or right-handed, the third vehicle may have two out of every three second vehicles in parallel;
generally, for a vehicle causing an accident by forcibly changing lanes, the process of the accident should be recorded by images and transmitted to a supervision center of a traffic control department.
It can be understood that the second early warning prompt instruction is sent to the accompanying vehicles which are about to arrive at the dangerous road section, so that the following vehicles can pay attention to cautious lane change after paying attention to deceleration driving, particularly for the accompanying vehicles which do not send feedback instructions within a set time length, a good prompt effect can be played for third vehicles which have a harmful relationship with the accompanying vehicles, and the occurrence of events such as scratch and the like can be reduced.
As shown in fig. 5, as another preferred embodiment of the present invention, in another aspect, an artificial intelligence based vehicle obstacle avoidance system includes:
the acquisition and detection module 100 is configured to acquire image data of a dangerous road segment, and detect dangerous information of the dangerous road segment according to the image data, where the dangerous information includes quantity information and movement information of dangerous targets;
the first early warning module 200 is configured to estimate time when the dangerous target approaches a dangerous section lane when the moving speed of the dangerous target is detected to be smaller than a preset speed and the moving distance of the dangerous target is detected to be smaller than a first threshold distance in a continuous detection period, and send a first early warning prompt instruction to a vehicle about to pass through the dangerous section according to the time when the dangerous target approaches the dangerous section lane;
and the second early warning module 300 is configured to send a deceleration reminding message to vehicles which are about to arrive at the dangerous section when the number of the dangerous targets is detected to be greater than or equal to one, and send a second early warning prompting instruction to accompanying vehicles which are about to arrive at the dangerous section when the moving speed of at least one dangerous target is continuously detected to be not less than the preset speed, wherein the vertical distance between at least two vehicles running in rows in the accompanying vehicles is within a second threshold distance.
The invention provides a vehicle obstacle avoidance method based on artificial intelligence, and provides a vehicle obstacle avoidance system based on artificial intelligence, when the moving speed of a dangerous target is detected to be smaller than a preset speed and the moving distance of the dangerous target is smaller than a first threshold distance in a continuous detection period, the time of the dangerous target approaching a dangerous road section lane is estimated, a first early warning prompt instruction is sent to a vehicle which is about to pass through the dangerous road section according to the time of the dangerous target approaching the dangerous road section lane, the first early warning prompt instruction has good pertinence, reliable reference can be provided for the driving of the vehicle on the dangerous road section, obstacle early warning is provided, and the vehicle can avoid the dangerous target or obstacles caused by the dangerous target conveniently; when the number of the dangerous objects is larger than or equal to one, speed reduction reminding information is sent to vehicles which are about to arrive at a dangerous road section, and when the moving speed of at least one dangerous object is continuously detected to be not smaller than a preset speed, a second early warning reminding instruction is sent to accompanying vehicles which are about to arrive at the dangerous road section, wherein the vertical distance between at least two lined running vehicles in the accompanying vehicles is within a second threshold distance, so that the accompanying vehicles pay attention to cautious lane change after paying attention to speed reduction running, a good reminding effect is achieved, the occurrence of accidents such as scratch and the like can be reduced, the running safety of the vehicles at the dangerous road section is guaranteed, and the universality of vehicle obstacle avoidance application can be improved.
In order to load the above method and system to operate smoothly, the system may include more or less components than those described above, or combine some components, or different components, besides the various modules described above, for example, input/output devices, network access devices, buses, processors, memories, and the like.
The processor may be a Central Processing Unit (CPU), other general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like that is the control center for the system and that connects the various components using various interfaces and lines.
The memory may be used to store computer and system programs and/or modules, and the processor may perform the various functions described above by operating or executing the computer programs and/or modules stored in the memory and invoking data stored in the memory. The memory may mainly include a program storage area and a data storage area, where the program storage area may store an operating system, an application program required by at least one function (such as an information collection template presentation function, a product information distribution function, and the like), and the like. The storage data area may store data created according to the use of the berth-state display system (e.g., product information acquisition templates corresponding to different product types, product information that needs to be issued by different product providers, etc.), and the like. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash memory card (FlashCard), at least one magnetic disk storage device, a flash memory device, or other volatile solid state storage device.
It should be understood that, although the steps in the flowcharts of the embodiments of the present invention are shown in sequence as indicated by the arrows, the steps are not necessarily executed in sequence as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a portion of the steps in various embodiments may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent should be subject to the appended claims.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (8)
1. A vehicle obstacle avoidance method based on artificial intelligence is characterized by comprising the following steps:
acquiring image data of a dangerous road section, and detecting dangerous information of the dangerous road section according to the image data, wherein the dangerous information comprises quantity information and movement information of dangerous targets;
when the moving speed of the dangerous target is detected to be smaller than the preset speed and the moving distance of the dangerous target is smaller than the first threshold distance in the continuous detection period, estimating the time of the dangerous target approaching the lane of the dangerous road section, and sending a first early warning prompt instruction to the vehicle about to pass through the dangerous road section according to the time of the dangerous target approaching the lane of the dangerous road section;
when the number of the dangerous targets is detected to be more than or equal to one, speed reduction reminding information is sent to vehicles which are about to arrive at the dangerous road section, and when the moving speed of at least one dangerous target is continuously detected to be not less than the preset speed, a second early warning prompting instruction is sent to accompanying vehicles which are about to arrive at the dangerous road section, wherein the vertical distance between at least two vehicles running in rows in the accompanying vehicles is within a second threshold distance.
2. The artificial intelligence based vehicle obstacle avoidance method of claim 1, wherein prior to acquiring a dangerous road, the method further comprises:
acquiring historical traffic data information;
counting accident types and accident frequencies in historical traffic data information, wherein the accident types are associated with danger information;
marking a road section danger level in a preset road section range according to the accident type and the accident frequency, and judging that the sub-road section in the preset road section range is a dangerous road section when the road section danger level is greater than the preset level.
3. The artificial intelligence based vehicle obstacle avoidance method according to claim 2, wherein the marking of the road section risk level within the preset road section range according to the accident type and the accident frequency specifically comprises:
calculating danger grade scores of sub-road sections in a preset road section range, wherein the scores of different accident types are different, and the danger grade score is the product of the score of the accident type and the corresponding accident frequency;
and dividing road section dangerous intervals according to the dangerous grade scores, wherein different dangerous road section intervals correspond to set dangerous grade score difference values.
4. The vehicle obstacle avoidance method based on artificial intelligence of claim 1, wherein the obtaining of image data of a dangerous road segment and the detecting of dangerous information of the dangerous road segment according to the image data include at least quantity information and movement information of dangerous objects, and the method specifically includes:
acquiring an acquisition cycle, and acquiring image data of a dangerous road section once every other acquisition cycle;
detecting whether the image data contains a preset dangerous target or not;
and if so, detecting the quantity information and the movement information of the dangerous targets, wherein the movement information at least comprises a movement distance and a movement speed.
5. The vehicle obstacle avoidance method based on artificial intelligence of claim 1, wherein the estimating a time when the dangerous object approaches the lane of the dangerous section, and the sending a first warning prompt instruction to a vehicle about to pass through the dangerous section according to the time when the dangerous object approaches the lane of the dangerous section specifically comprises:
acquiring the maximum moving distance of the dangerous target in each detection period, and calculating the maximum value of the moving speed of the dangerous target according to the maximum moving distance;
respectively calculating the time of the dangerous target moving from the current position to the lane edge position of the dangerous road section according to the maximum value of the moving speed of the dangerous target, generating first time corresponding to the maximum value of the moving speed of the dangerous target, and establishing a dangerous target moving time ranking according to the first time;
acquiring a second time of a vehicle about to enter the dangerous road section;
and when the difference value between the second time and the first time in the dangerous target moving time ranking is within a set time difference value, sending a first early warning prompt instruction to a vehicle about to enter a dangerous road section.
6. The artificial intelligence based vehicle obstacle avoidance method of claim 1, further comprising:
and estimating the volume of the dangerous target according to the area of the dangerous target in the image data, and sending road to-be-maintained prompt information to a road maintenance center when the volume of the dangerous target is larger than a set volume.
7. The artificial intelligence based vehicle obstacle avoidance method according to any one of claims 1 to 6, wherein the sending of the second warning prompt instruction to the accompanying vehicle which is about to arrive at the dangerous section specifically comprises:
identifying all vehicles which are about to arrive at the dangerous road section and run in rows, and marking vehicles with the vertical distance between at least two vehicles in all vehicles within a second threshold distance as accompanying vehicles;
trying to establish information interaction channels among vehicle-mounted terminals of all accompanying vehicles, and synchronously sending a second early warning prompt instruction to the accompanying vehicles which are about to arrive at the dangerous road section;
detecting a feedback instruction after the accompanying vehicle receives the second early warning prompt instruction, and identifying the accompanying vehicle which does not send the feedback instruction within a set time length, wherein the feedback instruction is used for representing the feedback of the second early warning prompt instruction of the accompanying vehicle;
if yes, marking the accompanying vehicle which does not send the feedback instruction as a first vehicle, marking other vehicles in the accompanying vehicle as second vehicles, positioning a third vehicle, wherein the third vehicle is a second vehicle which is not in the same lane as the first vehicle and is obliquely behind the first vehicle, and sending prompt information for paying attention to lane change of the vehicle to the third vehicle.
8. An artificial intelligence based vehicle obstacle avoidance system, the system comprising:
the system comprises an acquisition and detection module, a display module and a display module, wherein the acquisition and detection module is used for acquiring image data of a dangerous road section and detecting dangerous information of the dangerous road section according to the image data, and the dangerous information comprises quantity information and movement information of dangerous targets;
the first early warning module is used for estimating the time of the dangerous target approaching a dangerous road section lane when the moving speed of the dangerous target is detected to be smaller than the preset speed and the moving distance of the dangerous target is smaller than a first threshold distance in a continuous detection period, and sending a first early warning prompt instruction to a vehicle about to pass through the dangerous road section according to the time of the dangerous target approaching the dangerous road section lane;
and the second early warning module is used for sending a deceleration reminding message to vehicles which are about to arrive at the dangerous road section when the number of the dangerous targets is detected to be more than or equal to one, and sending a second early warning prompting instruction to accompanying vehicles which are about to arrive at the dangerous road section when the moving speed of at least one dangerous target is continuously detected to be not less than the preset speed, wherein the vertical distance between at least two vehicles running in rows in the accompanying vehicles is within a second threshold distance.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211253757.2A CN115662186B (en) | 2022-10-13 | 2022-10-13 | Vehicle obstacle avoidance method and system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211253757.2A CN115662186B (en) | 2022-10-13 | 2022-10-13 | Vehicle obstacle avoidance method and system based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115662186A true CN115662186A (en) | 2023-01-31 |
| CN115662186B CN115662186B (en) | 2023-09-15 |
Family
ID=84986649
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211253757.2A Active CN115662186B (en) | 2022-10-13 | 2022-10-13 | Vehicle obstacle avoidance method and system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115662186B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115900688A (en) * | 2023-02-01 | 2023-04-04 | 安徽信息工程学院 | High-precision map visual positioning method for automatic driving |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20160080231A (en) * | 2014-12-29 | 2016-07-07 | 재단법인대구경북과학기술원 | System and method for warning danger in driving section |
| CN107180543A (en) * | 2017-07-27 | 2017-09-19 | 安徽信息工程学院 | A kind of intelligent dynamic transport management system |
| KR101781754B1 (en) * | 2016-10-04 | 2017-10-10 | 황일 | Parking guidance system using lighting |
| WO2018019141A1 (en) * | 2016-07-28 | 2018-02-01 | 比亚迪股份有限公司 | Emergency driving method and system based on vehicle remote control, and vehicle |
| JP2018075890A (en) * | 2016-11-08 | 2018-05-17 | 日産自動車株式会社 | Parking assist method and parking assist device |
| KR20180061901A (en) * | 2016-11-30 | 2018-06-08 | 현대엠엔소프트 주식회사 | Method of providing driving guide information for vehicle |
| FR3076521A1 (en) * | 2018-01-05 | 2019-07-12 | Institut De Recherche Technologique Systemx | METHOD FOR ASSISTING DRIVING A VEHICLE AND ASSOCIATED DEVICES |
| EP3552902A1 (en) * | 2018-04-11 | 2019-10-16 | Hyundai Motor Company | Apparatus and method for providing a driving path to a vehicle |
| US10699347B1 (en) * | 2016-02-24 | 2020-06-30 | Allstate Insurance Company | Polynomial risk maps |
| CN111369831A (en) * | 2020-03-26 | 2020-07-03 | 径卫视觉科技（上海）有限公司 | Road driving danger early warning method, device and equipment |
| US20200292338A1 (en) * | 2019-03-12 | 2020-09-17 | Here Global B.V. | Dangerous lane strands |
| US10946793B1 (en) * | 2020-04-06 | 2021-03-16 | Ekin Teknoloji Sanayi Ve Ticaret Anonim Sirketi | Threat detection and mitigation apparatus and use thereof |
| CN113282090A (en) * | 2021-05-31 | 2021-08-20 | 三一专用汽车有限责任公司 | Unmanned control method and device for engineering vehicle, engineering vehicle and electronic equipment |
| CN114475102A (en) * | 2022-03-25 | 2022-05-13 | 南京交通职业技术学院 | Automobile driving control system based on intelligent tire perception |
| US20220307842A1 (en) * | 2021-03-29 | 2022-09-29 | Toyota Jidosha Kabushiki Kaisha | Vehicle controller, and method and computer program for controlling vehicle |
-
2022
- 2022-10-13 CN CN202211253757.2A patent/CN115662186B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20160080231A (en) * | 2014-12-29 | 2016-07-07 | 재단법인대구경북과학기술원 | System and method for warning danger in driving section |
| US10699347B1 (en) * | 2016-02-24 | 2020-06-30 | Allstate Insurance Company | Polynomial risk maps |
| WO2018019141A1 (en) * | 2016-07-28 | 2018-02-01 | 比亚迪股份有限公司 | Emergency driving method and system based on vehicle remote control, and vehicle |
| KR101781754B1 (en) * | 2016-10-04 | 2017-10-10 | 황일 | Parking guidance system using lighting |
| JP2018075890A (en) * | 2016-11-08 | 2018-05-17 | 日産自動車株式会社 | Parking assist method and parking assist device |
| KR20180061901A (en) * | 2016-11-30 | 2018-06-08 | 현대엠엔소프트 주식회사 | Method of providing driving guide information for vehicle |
| CN107180543A (en) * | 2017-07-27 | 2017-09-19 | 安徽信息工程学院 | A kind of intelligent dynamic transport management system |
| FR3076521A1 (en) * | 2018-01-05 | 2019-07-12 | Institut De Recherche Technologique Systemx | METHOD FOR ASSISTING DRIVING A VEHICLE AND ASSOCIATED DEVICES |
| EP3552902A1 (en) * | 2018-04-11 | 2019-10-16 | Hyundai Motor Company | Apparatus and method for providing a driving path to a vehicle |
| US20200292338A1 (en) * | 2019-03-12 | 2020-09-17 | Here Global B.V. | Dangerous lane strands |
| CN111369831A (en) * | 2020-03-26 | 2020-07-03 | 径卫视觉科技（上海）有限公司 | Road driving danger early warning method, device and equipment |
| US10946793B1 (en) * | 2020-04-06 | 2021-03-16 | Ekin Teknoloji Sanayi Ve Ticaret Anonim Sirketi | Threat detection and mitigation apparatus and use thereof |
| US20220307842A1 (en) * | 2021-03-29 | 2022-09-29 | Toyota Jidosha Kabushiki Kaisha | Vehicle controller, and method and computer program for controlling vehicle |
| CN113282090A (en) * | 2021-05-31 | 2021-08-20 | 三一专用汽车有限责任公司 | Unmanned control method and device for engineering vehicle, engineering vehicle and electronic equipment |
| CN114475102A (en) * | 2022-03-25 | 2022-05-13 | 南京交通职业技术学院 | Automobile driving control system based on intelligent tire perception |
Non-Patent Citations (2)
| Title |
|---|
| 刘志强;汪澎;秦洪懋;仲晶晶;宋世亮;: "基于多信息检测的车辆智能防撞预警技术研究", 中国安全科学学报, no. 01 * |
| 邹水龙;李永;: "基于复合传感实现路情实时识别和危险判断的方法及系统", 移动通信, no. 15 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115900688A (en) * | 2023-02-01 | 2023-04-04 | 安徽信息工程学院 | High-precision map visual positioning method for automatic driving |
| CN115900688B (en) * | 2023-02-01 | 2024-04-16 | 安徽信息工程学院 | High-precision map visual positioning method for automatic driving |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115662186B (en) | 2023-09-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11113961B2 (en) | Driver behavior monitoring | |
| RU2674744C1 (en) | Interaction between vehicles for streamlining traffic | |
| US11623644B2 (en) | Apparatus and method for controlling vehicle based on cut-in prediction in junction section | |
| US10710588B2 (en) | Merging and lane change acceleration prediction energy management | |
| CN108263383B (en) | Apparatus and method for controlling speed in a coordinated adaptive cruise control system | |
| EP2950114B1 (en) | Method for assisting a driver in driving a vehicle, a driver assistance system, a computer software program product and vehicle | |
| CN108263382B (en) | Cooperative adaptive cruise control system based on driving pattern of target vehicle | |
| US9889858B2 (en) | Confidence estimation for predictive driver assistance systems based on plausibility rules | |
| CN110562258B (en) | Method for vehicle automatic lane change decision, vehicle-mounted equipment and storage medium | |
| US9269264B2 (en) | Vehicle driving assistance device | |
| JP2016051467A (en) | Method and system using wide-area scene context for adaptation predict, corresponding program, and vehicle with the system | |
| EP3403219A1 (en) | Driver behavior monitoring | |
| JP7147442B2 (en) | map information system | |
| US11042160B2 (en) | Autonomous driving trajectory determination device | |
| CN112829753B (en) | Guard bar estimation method based on millimeter wave radar, vehicle-mounted equipment and storage medium | |
| US10916134B2 (en) | Systems and methods for responding to a vehicle parked on shoulder of the road | |
| CN110647801A (en) | Method and device for setting region of interest, storage medium and electronic equipment | |
| EP2913239A1 (en) | Method and unit for managing following space | |
| CN115662186A (en) | Vehicle obstacle avoidance method and system based on artificial intelligence | |
| CN114387821B (en) | Vehicle collision early warning method, device, electronic equipment and storage medium | |
| CN109887321B (en) | Unmanned vehicle lane change safety judgment method and device and storage medium | |
| CN113771841A (en) | Driving assistance system, method, computer device and storage medium for a fleet of vehicles | |
| US11640172B2 (en) | Vehicle controls based on reliability values calculated from infrastructure information | |
| US20230251366A1 (en) | Method and apparatus for determining location of pedestrian | |
| US20220319322A1 (en) | Drive assist apparatus and drive assist method |
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 |