CN114325756A - Short-distance obstacle avoidance method and device based on laser radar, vehicle and storage medium - Google Patents
Short-distance obstacle avoidance method and device based on laser radar, vehicle and storage medium Download PDFInfo
- Publication number
- CN114325756A CN114325756A CN202111533955.XA CN202111533955A CN114325756A CN 114325756 A CN114325756 A CN 114325756A CN 202111533955 A CN202111533955 A CN 202111533955A CN 114325756 A CN114325756 A CN 114325756A
- Authority
- CN
- China
- Prior art keywords
- obstacle avoidance
- avoidance area
- vehicle
- obstacle
- obstacles
- 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.)
- Pending
Links
Images
Abstract
The invention discloses a short-distance obstacle avoidance method and device based on a laser radar, a vehicle and a storage medium, wherein the method comprises the following steps: acquiring an image frame generated by scanning vehicle peripheral information in real time by a laser radar; when an obstacle is detected to exist in a first obstacle avoidance area of the vehicle in a current frame, sending a parking instruction to the vehicle, and recording the number of the obstacles in a second obstacle avoidance area of the vehicle in the current frame, wherein the number represents the dynamic state of the obstacles entering or leaving the second obstacle avoidance area; the second obstacle avoidance area is larger than the first obstacle avoidance area; and sending a starting instruction to the vehicle when N continuous frames detect that no barrier exists in the first obstacle avoidance area and the number of the barriers in the second obstacle avoidance area is zero. The invention only depends on the laser radar to sense the observation information, and under the condition that the obstacle is not sensed, the short-distance obstacle avoidance can be realized by judging the number of the obstacles in the short-distance area of the vehicle.
Description
Technical Field
The invention relates to the technical field of automatic driving, in particular to a short-distance obstacle avoidance method and device based on a laser radar, a vehicle and a storage medium.
Background
With the development of AI technology, vehicle obstacle avoidance active safety technology is more and more concerned by technical engineers. The active vehicle obstacle avoidance safety technology is a core part of an automatic driving vehicle, and how the automatic driving vehicle can accurately identify and detect an obstacle target and safely, accurately and faultlessly avoid the obstacle is one of necessary skills of the automatic driving vehicle.
At present, in the field of automatic driving, obstacle avoidance of vehicles relates to safety, stability and instantaneity of automatic driving. If a multi-sensor fusion mode cannot be used due to the field environment or other objective factors, obstacle avoidance is performed only by relying on field-end laser radar sensing information, which is relatively difficult. In addition, under the short-distance obstacle avoidance scene, due to the perception principle of the laser radar, the perception of people or bicycles can be integrated with the vehicles, so that the people cannot perceive through the laser radar, and in addition, under the condition that a detection blind area exists without the assistance of vehicle-end ultrasonic waves or in an auxiliary mode, the existence of the people cannot be detected. Based on the two points, the existing obstacle avoidance method cannot ensure the integrity and the real-time performance of observation information due to radar sensing information loss or the limitation of other sensors, so that short-distance personnel cannot be identified, further the obstacle avoidance is invalid, and even safety accidents are caused.
Disclosure of Invention
The technical problem to be solved by the embodiments of the present invention is to provide a method, an apparatus, a vehicle and a storage medium for short-distance obstacle avoidance based on a laser radar, which only rely on the laser radar to sense observation information, and realize short-distance obstacle avoidance by determining the number of obstacles in a short-distance area of the vehicle under the condition that the obstacles are not sensed.
In order to achieve the above object, an embodiment of the present invention provides a short-distance obstacle avoidance method based on a laser radar, including:
acquiring an image frame generated by scanning vehicle peripheral information in real time by a laser radar;
when an obstacle is detected to exist in a first obstacle avoidance area of the vehicle in a current frame, sending a parking instruction to the vehicle, and recording the number of the obstacles in a second obstacle avoidance area of the vehicle in the current frame, wherein the number represents the dynamic state of the obstacles entering or leaving the second obstacle avoidance area; the second obstacle avoidance area is larger than the first obstacle avoidance area;
and sending a starting instruction to the vehicle when N continuous frames detect that no barrier exists in the first obstacle avoidance area and the number of the barriers in the second obstacle avoidance area is zero.
As an improvement of the above scheme, the first obstacle avoidance area is obtained by the following steps:
receiving position information sent by the vehicle in real time; wherein the position information comprises an abscissa, an ordinate and an orientation;
and calculating the area in the preset range of the vehicle in real time by taking the center of the vehicle as a geometric center according to the position information to obtain a first obstacle avoidance area.
As an improvement of the above scheme, the detecting, by the consecutive N frames, that no obstacle exists in the first obstacle avoidance area, and then further includes:
and updating the number of obstacles in the second obstacle avoidance area according to the observation information in the image frame.
As an improvement of the above scheme, the updating the number of obstacles in the second obstacle avoidance area according to the observation information in the image frame specifically includes:
tracking observation information of obstacles in the preset range of the vehicle in continuous M frames according to a nearest distance principle; wherein the observation information includes at least coordinates, speed, and direction;
calculating whether the barrier in each frame is in the second obstacle avoidance area or not according to the observation information;
and increasing or decreasing the number of obstacles in the second obstacle avoidance area according to the calculation result.
As an improvement of the above scheme, the increasing or decreasing the number of obstacles in the second obstacle avoidance area according to the calculation result specifically includes:
recording the state of each obstacle in the continuous M frames by adopting a queue based on the calculation result; wherein 1 represents that the obstacle in the current frame is in the second obstacle avoidance area, and 0 represents that the obstacle in the current frame is not in the second obstacle avoidance area;
traversing the queue, and judging whether the barrier in the M frame is in the second obstacle avoidance area;
if the obstacle is in the second obstacle avoidance area, the number of the obstacles in the second obstacle avoidance area is correspondingly increased;
and if the obstacles are not in the second obstacle avoidance area, correspondingly reducing the number of the obstacles in the second obstacle avoidance area.
As an improvement of the above solution, the updating the number of obstacles in the second obstacle avoidance area according to the observation information in the image frame further includes:
and when the fact that no barrier exists in the first obstacle avoidance area and the number of barriers in the second obstacle avoidance area is not zero is detected, the vehicle keeps a stop state.
As an improvement of the scheme, when the obstacles in the image frame are detected, a Hungarian tracking algorithm based on the horse-type distance is adopted.
The embodiment of the invention also provides a short-distance obstacle avoidance device based on the laser radar, which comprises:
the acquisition module is used for acquiring image frames generated by scanning the peripheral information of the vehicle in real time by the laser radar;
the parking module is used for sending a parking instruction to the vehicle when detecting that an obstacle exists in a first obstacle avoidance area of the vehicle in the current frame, and recording the number of the obstacles in a second obstacle avoidance area of the vehicle in the current frame, wherein the number represents the dynamic state of the obstacles entering or leaving the second obstacle avoidance area; the second obstacle avoidance area is larger than the first obstacle avoidance area;
and the starting module is used for sending a starting instruction to the vehicle when N continuous frames detect that no barrier exists in the first obstacle avoidance area and the number of the barriers in the second obstacle avoidance area is zero.
The embodiment of the invention also provides a vehicle, which comprises a processor, a memory and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the lidar-based short-distance obstacle avoidance method described in any one of the above items when executing the computer program.
The embodiment of the invention also provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program runs, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned laser radar-based short-distance obstacle avoidance methods.
Compared with the prior art, the short-distance obstacle avoidance method, the short-distance obstacle avoidance device, the vehicle and the storage medium based on the laser radar have the advantages that: acquiring an image frame generated by scanning vehicle peripheral information in real time by a laser radar; when an obstacle is detected to exist in a first obstacle avoidance area of the vehicle in a current frame, sending a parking instruction to the vehicle, and recording the number of the obstacles in a second obstacle avoidance area of the vehicle in the current frame, wherein the number represents the dynamic state of the obstacles entering or leaving the second obstacle avoidance area; the second obstacle avoidance area is larger than the first obstacle avoidance area; and sending a starting instruction to the vehicle when N continuous frames detect that no barrier exists in the first obstacle avoidance area and the number of the barriers in the second obstacle avoidance area is zero. According to the embodiment of the invention, observation information is sensed only by the laser radar, the position of the obstacle is judged through the matching between frames, and the obstacle avoidance in a short distance is realized through judging the number of the obstacles in a short-distance area, so that the obstacle can enter a certain distance of a vehicle, the effect of obstacle avoidance and parking can be achieved even though the sensing cannot be obtained, and the reliability and the stability of the obstacle avoidance are ensured.
Drawings
Fig. 1 is a schematic flow chart of a short-distance obstacle avoidance method based on a laser radar according to a preferred embodiment of the present invention;
fig. 2 is a schematic diagram of the position of an obstacle detected in a preferred embodiment of a short-distance obstacle avoidance method based on a laser radar provided by the invention;
fig. 3 is a schematic diagram of the position of an obstacle detected in a preferred embodiment of a short-distance obstacle avoidance method based on a laser radar provided by the invention;
fig. 4 is a schematic diagram of the position of an obstacle detected in a preferred embodiment of a short-distance obstacle avoidance method based on a laser radar provided by the invention;
fig. 5 is a schematic diagram of the position of an obstacle detected in a preferred embodiment of a short-distance obstacle avoidance method based on a laser radar provided by the invention;
fig. 6 is a schematic diagram of the position of an obstacle detected in a preferred embodiment of a short-distance obstacle avoidance method based on a laser radar provided by the present invention;
fig. 7 is a schematic diagram of obstacle detection in a preferred embodiment of a short-distance obstacle avoidance method based on a laser radar according to the present invention;
fig. 8 is a schematic structural diagram of a preferred embodiment of a short-distance obstacle avoidance device based on a laser radar provided by the invention;
fig. 9 is a schematic structural diagram of a preferred embodiment of a vehicle according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, fig. 1 is a schematic flowchart illustrating a short-distance obstacle avoidance method based on a lidar according to a preferred embodiment of the present invention. The short-distance obstacle avoidance method based on the laser radar comprises the following steps:
s1, acquiring image frames generated by the laser radar scanning the information around the vehicle in real time;
s2, when detecting that an obstacle exists in a first obstacle avoidance area of the vehicle in the current frame, sending a parking instruction to the vehicle, and recording the number of obstacles in a second obstacle avoidance area of the vehicle in the current frame, wherein the number represents the dynamic state of the obstacle entering or leaving the second obstacle avoidance area; the second obstacle avoidance area is larger than the first obstacle avoidance area;
and S3, sending a starting instruction to the vehicle when N continuous frames detect that no obstacle exists in the first obstacle avoidance area and the number of obstacles in the second obstacle avoidance area is zero.
Specifically, the field-end laser radar is used for scanning the periphery of the vehicle, and image frames generated by the laser radar scanning the information of the periphery of the vehicle in real time are obtained. When the situation that an obstacle appears in a first obstacle avoidance area of the vehicle in the current frame and two continuous frames of obstacles are in the first obstacle avoidance area is detected, sending a parking instruction to the vehicle, and recording the number of the obstacles in a second obstacle avoidance area of the vehicle in the current frame, wherein the number represents the dynamic state of the obstacles entering or leaving the second obstacle avoidance area; and the second obstacle avoidance area is larger than the first obstacle avoidance area. When N continuous frames detect that no obstacle exists in the first obstacle avoidance area, at this time, no obstacle exists in the first obstacle avoidance area, and the obstacle can also approach the vehicle, so that the laser radar cannot sense the obstacle, and at this time, the number of obstacles in the second obstacle avoidance area needs to be judged. When the fact that no barrier exists in the first obstacle avoidance area, the number of barriers in the second obstacle avoidance area is zero, and no barrier exists in the second obstacle avoidance area for 5 continuous frames is detected, it is indicated that no barrier exists around the vehicle, and a starting instruction is sent to the vehicle.
It should be noted that N is a positive integer greater than 1, and N is preferably 5 in this embodiment, that is, when it is detected that no obstacle exists in the first obstacle avoidance area through 5 consecutive frames and the number of obstacles in the second obstacle avoidance area is zero, a start instruction is sent to the vehicle. In practical application, N can be selected according to practical situations.
This embodiment only relies on laser radar perception observation information, judges the position of barrier through the matching between frame and the frame, through judging the quantity of barrier in the short distance region to realize keeping away the barrier closely, thereby guarantee that the barrier gets into in the vehicle certain distance, can still play the effect of keeping away the barrier parking though can't acquire the perception, guarantee to keep away the reliability and the stability of barrier.
In another preferred embodiment, the first obstacle avoidance area is obtained by:
receiving position information sent by the vehicle in real time; wherein the position information comprises an abscissa, an ordinate and an orientation;
and calculating the area in the preset range of the vehicle in real time by taking the center of the vehicle as a geometric center according to the position information to obtain a first obstacle avoidance area.
Specifically, position information (x, y, heading) sent by the vehicle is received in real time, wherein x is an abscissa of the position of the vehicle, y is an ordinate of the position of the vehicle, and heading is the direction of the vehicle. And calculating an area in a preset range of the vehicle in real time by taking the center of the vehicle as a geometric center according to the position information (x, y, heading) to obtain a first obstacle avoidance area, wherein the calculated frequency is the frequency of the vehicle for sending the position information.
It should be noted that the first obstacle avoidance area and the second obstacle avoidance area are not limited to rectangles, and can be selected according to actual situations.
In another preferred embodiment, the detecting, by the N consecutive frames, that no obstacle exists in the first obstacle avoidance area, and then further includes:
and updating the number of obstacles in the second obstacle avoidance area according to the observation information in the image frame.
Specifically, when N consecutive frames detect that no obstacle exists in the first obstacle avoidance area, at this time, there may be no obstacle in the first obstacle avoidance area, and the obstacle may also approach the vehicle, so that the laser radar cannot sense the obstacle, and at this time, the number of obstacles in the second obstacle avoidance area needs to be updated according to the observation information in the image frames. And judging the number of the obstacles in the second obstacle avoidance area so as to realize short-distance obstacle avoidance.
For example, please refer to fig. 2 to fig. 6, and fig. 2, fig. 3, fig. 4, fig. 5 and fig. 6 are schematic diagrams illustrating the position of an obstacle detected in a preferred embodiment of a method for short-distance obstacle avoidance based on a lidar according to the present invention. The stop frame is a first obstacle avoidance area, the diff frame is a second obstacle avoidance area, the diff frame is one meter longer and wider than the stop frame, and pedestrians are obstacles. When an obstacle is detected in the first obstacle avoidance area in the current frame, the number of recorded obstacles in the second obstacle avoidance area, namely the initial value of the difference value of the entering and exiting people, is made to be the initial value of in _ out _ dif. In the figure 2, a pedestrian I enters a stop frame, stops driving, and enters a stop frame monitoring mode, namely whether a person exists in the stop frame is detected in real time, and the person stops immediately. And the number of pedestrians in the diff frame at this time is recorded as an initial value in _ out _ dif (4 in this case), and there are pedestrians No. one and No. two in the start _ stop area. Pedestrian number one in fig. 3 walks out of the stop box, where the stop box is only one person number two, and still in stop box monitoring mode, where the in _ out _ dif value is still 4. In fig. 4, the pedestrian No. one or four walks out of the diff box, and in _ out _ diff-2 is 2, so that the stop box is only one person No. two, and the vehicle continues to stop in the stop box monitoring mode. The third pedestrian in fig. 5 goes out of the diff box, and in _ out _ diff-1 is 1. And when the second pedestrian approaches the vehicle, the radar perceives that the pedestrian and the vehicle are integrated, the pedestrian cannot be perceived, no person exists in the stop frame at the moment, the stop frame enters an in _ out _ dif detection mode, namely, only the in _ out _ dif value is detected, and if the in _ out _ dif value is not 0, the vehicle continues to stop. In fig. 6, the pedestrian No. two walks out of the dif box, the in _ out _ diff value is 0, no person is in the stop box, and the vehicle walks.
It should be noted that, when the lidar senses two similar objects, the positions of the two objects cannot be distinguished, and the two objects are considered as one object. In view of the defects, when a person or a bicycle enters an area within about 30cm of the edge of the bicycle, the radar cannot successfully sense the person, the person and the bicycle are considered to be integrated, so that the person cannot be detected in a normal dangerous area, the bicycle can continue to run because no person is around, but the person is still in the dangerous area at the moment, and thus a safety accident is caused. Based on the above, an in _ out _ dif monitoring mode is introduced, the number of obstacles in the second obstacle avoidance area is updated according to the observation information in the image frame, and the short-distance obstacle avoidance is realized by judging the number of obstacles in the short-distance area of the vehicle. The obstacles in this embodiment include, but are not limited to, pedestrians and bicycles, and the value of N can be selected according to actual needs.
In another preferred embodiment, the updating the number of obstacles in the second obstacle avoidance area according to the observation information in the image frame specifically includes:
tracking observation information of obstacles in the preset range of the vehicle in continuous M frames according to a nearest distance principle; wherein the observation information includes at least coordinates, speed, and direction;
calculating whether the barrier in each frame is in the second obstacle avoidance area or not according to the observation information;
and increasing or decreasing the number of obstacles in the second obstacle avoidance area according to the calculation result.
Illustratively, when the number of obstacles in the second obstacle avoidance area is updated according to the observation information in the image frames, the observation information of the obstacles in the range of 12m of the vehicle in 4 continuous frames is tracked according to the principle of the shortest distance, and the observation information at least comprises coordinates, speed and direction. And calculating whether the obstacle in each frame is in the second obstacle avoidance area or not according to the observation information. And increasing or decreasing the number of the obstacles in the second obstacle avoidance area according to the calculation result.
It should be noted that M is a positive integer greater than 1, M in this embodiment is preferably 4, and the preset vehicle range is preferably a vehicle 12M range. In practical application, both M and the preset range can be selected according to practical situations.
In another preferred embodiment, the increasing or decreasing the number of obstacles in the second obstacle avoidance area according to the calculation result specifically includes:
recording the state of each obstacle in the continuous M frames by adopting a queue based on the calculation result; wherein 1 represents that the obstacle in the current frame is in the second obstacle avoidance area, and 0 represents that the obstacle in the current frame is not in the second obstacle avoidance area;
traversing the queue, and judging whether the barrier in the M frame is in the second obstacle avoidance area;
if the obstacle is in the second obstacle avoidance area, the number of the obstacles in the second obstacle avoidance area is correspondingly increased;
and if the obstacles are not in the second obstacle avoidance area, correspondingly reducing the number of the obstacles in the second obstacle avoidance area.
Specifically, the state of each obstacle in 4 continuous frames is recorded by using a queue based on the calculation result, wherein 1 represents that the obstacle in the current frame is in the second obstacle avoidance area, and 0 represents that the obstacle in the current frame is not in the second obstacle avoidance area. Traversing the queue, and judging whether the barrier in the 4 th frame is in the second obstacle avoidance area; if the obstacles are in the second obstacle avoidance area, the number of the obstacles in the second obstacle avoidance area is correspondingly increased; and if the obstacles are not in the second obstacle avoidance area, the number of the obstacles in the second obstacle avoidance area is correspondingly reduced. For example, when the queue is 0011, in _ out _ dif + 1; when the queue is 1100, in _ out _ dif-1.
In a further preferred embodiment, the updating the number of obstacles in the second obstacle avoidance area according to the observation information in the image frame further includes:
and when the fact that no barrier exists in the first obstacle avoidance area and the number of barriers in the second obstacle avoidance area is not zero is detected, the vehicle keeps a stop state.
Specifically, after the number of obstacles in the second obstacle avoidance area is updated according to the observation information in the image frame, if it is detected that no obstacle exists in the first obstacle avoidance area and the number of obstacles in the second obstacle avoidance area is not zero, it is determined that the obstacle is within a short-distance range of the vehicle body, and therefore, the vehicle still remains in a stopped state at this time. And sending a starting instruction to the vehicle until the number of the obstacles in the second obstacle avoidance area is 0 and no obstacle exists in the second obstacle avoidance area for 5 continuous frames.
As an optimal scheme, when the obstacles in the image frame are detected, a Hungarian tracking algorithm based on the Marangoni distance is adopted.
Specifically, please refer to fig. 7, fig. 7 is a schematic diagram illustrating the detection of an obstacle in a preferred embodiment of a method for close-range obstacle avoidance based on a lidar according to the present invention. Due to the nature of lidar sensing, two pedestrians are sensed as a bicycle or motorcycle when they are close enough. Then when in _ out _ dif detection is performed, if matching of the frame with the frame before is performed based on the euclidean distance, the following situation may result: the first pedestrian of the Nth frame is in the diff frame, the third pedestrian is not far away from the diff frame, and the first pedestrian walks towards the third pedestrian at the moment. In the (N + 1) th frame, only one piece of bicycle information outside the diff frame can be obtained, so that the pedestrian can always lose the position information, the queue detection of the pedestrian only has 1 without 0, the in _ out _ dif cannot be set to 0, and the vehicle can be locked. Therefore, in order to solve the above problem, a horse-like distance is introduced, and the speed of the observing pedestrian is added to the matching amount. The speed of the pedestrian in the first frame is not 0, but the speed of the pedestrian in the third frame is 0, and when the speed of the pedestrian in the first frame is N +1, the speed and the direction of the bicycle can be matched with the pedestrian in the first frame through Hungary based on the horse-type distance, so that the covariance of the position and the speed of the same pedestrian between the two frames needs to be determined according to the definition of the horse-type distance. Because the model of the motion in the actual environment is not completely uniform, and the process noise is assumed to be originated from the acceleration, an acceleration noise transfer matrix is added to the model based on the uniform velocity assumption:
v1＝v0+aΔt
namely, it is
Wherein v is0,d0Δ t is the velocity, displacement and time interval, v, respectively, of the previous moment1,d1Δ t is the velocity, displacement and time interval at this moment; x is the number of1＝[d1x,d1y,v1x,v1y]TFor this state of time, d1x,d1y,v1x,v1yDisplacement and velocity in x and y directions, respectively; x is the number of0＝[d0x,d0y,v0x,v0y]TAt the last moment, d0x,d0y,v0x,v0yDisplacement and velocity in x and y directions, respectively; a, ax,ayAcceleration is the acceleration in the x-direction and the acceleration in the y-direction.
Order to
Due to the covariance matrix Qv＝E(qqT)＝GQGT. Wherein the acceleration in the x-direction is uncorrelated with the acceleration in the y-direction,
then
Correspondingly, the invention also provides a short-distance obstacle avoidance device based on the laser radar, which can realize all the processes of the short-distance obstacle avoidance method based on the laser radar in the embodiment.
Referring to fig. 8, fig. 8 is a schematic structural diagram of a short-distance obstacle avoidance device based on a laser radar according to a preferred embodiment of the present invention. The short-distance obstacle avoidance device based on the laser radar comprises:
an obtaining module 801, configured to obtain an image frame generated by scanning, in real time, vehicle peripheral information by a laser radar;
the parking module 802 is configured to send a parking instruction to the vehicle when detecting that an obstacle exists in a first obstacle avoidance area of the vehicle in a current frame, and record the number of obstacles in a second obstacle avoidance area of the vehicle in the current frame, where the number represents a dynamic state of the obstacle entering or leaving the second obstacle avoidance area; the second obstacle avoidance area is larger than the first obstacle avoidance area;
the starting module 803 is configured to send a starting instruction to the vehicle when N consecutive frames detect that no obstacle exists in the first obstacle avoidance area and the number of obstacles in the second obstacle avoidance area is zero.
Preferably, the first obstacle avoidance area is obtained by:
receiving position information sent by the vehicle in real time; wherein the position information comprises an abscissa, an ordinate and an orientation;
and calculating the area in the preset range of the vehicle in real time by taking the center of the vehicle as a geometric center according to the position information to obtain a first obstacle avoidance area.
Preferably, the starting module 803 detects that no obstacle exists in the first obstacle avoidance area by the consecutive N frames, and then further includes:
and updating the number of obstacles in the second obstacle avoidance area according to the observation information in the image frame.
Preferably, the updating the number of obstacles in the second obstacle avoidance area according to the observation information in the image frame specifically includes:
tracking observation information of obstacles in the preset range of the vehicle in continuous M frames according to a nearest distance principle; wherein the observation information includes at least coordinates, speed, and direction;
calculating whether the barrier in each frame is in the second obstacle avoidance area or not according to the observation information;
and increasing or decreasing the number of obstacles in the second obstacle avoidance area according to the calculation result.
Preferably, the increasing or decreasing the number of obstacles in the second obstacle avoidance area according to the calculation result specifically includes:
recording the state of each obstacle in the continuous M frames by adopting a queue based on the calculation result; wherein 1 represents that the obstacle in the current frame is in the second obstacle avoidance area, and 0 represents that the obstacle in the current frame is not in the second obstacle avoidance area;
traversing the queue, and judging whether the barrier in the M frame is in the second obstacle avoidance area;
if the obstacle is in the second obstacle avoidance area, the number of the obstacles in the second obstacle avoidance area is correspondingly increased;
and if the obstacles are not in the second obstacle avoidance area, correspondingly reducing the number of the obstacles in the second obstacle avoidance area.
Preferably, the updating the number of obstacles in the second obstacle avoidance area according to the observation information in the image frame further includes:
and when the fact that no barrier exists in the first obstacle avoidance area and the number of barriers in the second obstacle avoidance area is not zero is detected, the vehicle keeps a stop state.
Preferably, a marquee distance-based hungarian tracking algorithm is adopted when detecting the obstacles in the image frame.
In a specific implementation, the working principle, the control flow and the implementation technical effect of the laser radar-based short-distance obstacle avoidance apparatus provided in the embodiment of the present invention are the same as those of the laser radar-based short-distance obstacle avoidance method in the above embodiment, and are not described herein again.
Referring to fig. 9, fig. 9 is a schematic structural diagram of a preferred embodiment of a vehicle according to the present invention. The vehicle comprises a processor 901, a memory 902 and a computer program stored in the memory 902 and configured to be executed by the processor 901, wherein the processor 901 implements the lidar-based short-distance obstacle avoidance method according to any of the above embodiments when executing the computer program.
Preferably, the computer program may be divided into one or more modules/units (e.g. computer program 1, computer program 2, … …) which are stored in the memory 902 and executed by the processor 901 to implement the invention. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution of the computer program in the vehicle.
The Processor 901 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, a discrete hardware component, etc., the general purpose Processor may be a microprocessor, or the Processor 901 may be any conventional Processor, the Processor 901 is a control center of the vehicle, and various interfaces and lines are used to connect various parts of the vehicle.
The memory 902 mainly includes a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function, and the like, and the data storage area may store related data and the like. In addition, the memory 902 may be a high speed random access memory, a non-volatile memory such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card), and the like, or the memory 902 may be other volatile solid state memory devices.
It should be noted that the vehicle may include, but is not limited to, a processor and a memory, and those skilled in the art will understand that the structural diagram of fig. 9 is only an example of the vehicle and does not constitute a limitation of the vehicle, and may include more or less components than those shown, or combine some components, or different components.
The embodiment of the invention also provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program runs, a device where the computer-readable storage medium is located is controlled to execute the laser radar-based short-distance obstacle avoidance method according to any one of the above embodiments.
The embodiment of the invention provides a short-distance obstacle avoidance method and device based on a laser radar, a vehicle and a storage medium, wherein an image frame generated by scanning peripheral information of the vehicle in real time by the laser radar is acquired; when an obstacle is detected to exist in a first obstacle avoidance area of the vehicle in a current frame, sending a parking instruction to the vehicle, and recording the number of the obstacles in a second obstacle avoidance area of the vehicle in the current frame, wherein the number represents the dynamic state of the obstacles entering or leaving the second obstacle avoidance area; the second obstacle avoidance area is larger than the first obstacle avoidance area; and sending a starting instruction to the vehicle when N continuous frames detect that no barrier exists in the first obstacle avoidance area and the number of the barriers in the second obstacle avoidance area is zero. According to the embodiment of the invention, observation information is sensed only by the laser radar, the position of the obstacle is judged through the matching between frames, and the obstacle avoidance in a short distance is realized through judging the number of the obstacles in a short-distance area, so that the obstacle can enter a certain distance of a vehicle, the effect of obstacle avoidance and parking can be achieved even though the sensing cannot be obtained, and the reliability and the stability of the obstacle avoidance are ensured.
It should be noted that the above-described system embodiments are merely illustrative, where the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. In addition, in the drawings of the embodiment of the system provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, and may be specifically implemented as one or more communication buses or signal lines. One of ordinary skill in the art can understand and implement it without inventive effort.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention.
Claims (10)
1. A short-distance obstacle avoidance method based on a laser radar is characterized by comprising the following steps:
acquiring an image frame generated by scanning vehicle peripheral information in real time by a laser radar;
when an obstacle is detected to exist in a first obstacle avoidance area of the vehicle in a current frame, sending a parking instruction to the vehicle, and recording the number of the obstacles in a second obstacle avoidance area of the vehicle in the current frame, wherein the number represents the dynamic state of the obstacles entering or leaving the second obstacle avoidance area; the second obstacle avoidance area is larger than the first obstacle avoidance area;
and sending a starting instruction to the vehicle when N continuous frames detect that no barrier exists in the first obstacle avoidance area and the number of the barriers in the second obstacle avoidance area is zero.
2. The lidar-based short-distance obstacle avoidance method according to claim 1, wherein the first obstacle avoidance region is obtained by the following steps:
receiving position information sent by the vehicle in real time; wherein the position information comprises an abscissa, an ordinate and an orientation;
and calculating the area in the preset range of the vehicle in real time by taking the center of the vehicle as a geometric center according to the position information to obtain a first obstacle avoidance area.
3. The lidar-based short-distance obstacle avoidance method according to claim 1, wherein the detecting of the absence of the obstacle in the first obstacle avoidance area by the consecutive N frames further comprises:
and updating the number of obstacles in the second obstacle avoidance area according to the observation information in the image frame.
4. The lidar-based short-distance obstacle avoidance method according to claim 3, wherein the updating of the number of obstacles in the second obstacle avoidance area according to the observation information in the image frame specifically comprises:
tracking observation information of obstacles in the preset range of the vehicle in continuous M frames according to a nearest distance principle; wherein the observation information includes at least coordinates, speed, and direction;
calculating whether the barrier in each frame is in the second obstacle avoidance area or not according to the observation information;
and increasing or decreasing the number of obstacles in the second obstacle avoidance area according to the calculation result.
5. The lidar-based short-distance obstacle avoidance method according to claim 4, wherein the increasing or decreasing of the number of obstacles in the second obstacle avoidance area according to the calculation result specifically comprises:
recording the state of each obstacle in the continuous M frames by adopting a queue based on the calculation result; wherein 1 represents that the obstacle in the current frame is in the second obstacle avoidance area, and 0 represents that the obstacle in the current frame is not in the second obstacle avoidance area;
traversing the queue, and judging whether the barrier in the M frame is in the second obstacle avoidance area;
if the obstacle is in the second obstacle avoidance area, the number of the obstacles in the second obstacle avoidance area is correspondingly increased;
and if the obstacles are not in the second obstacle avoidance area, correspondingly reducing the number of the obstacles in the second obstacle avoidance area.
6. The lidar-based short-distance obstacle avoidance method according to claim 3, wherein the updating of the number of obstacles in the second obstacle avoidance area according to the observation information in the image frame further comprises:
and when the fact that no barrier exists in the first obstacle avoidance area and the number of barriers in the second obstacle avoidance area is not zero is detected, the vehicle keeps a stop state.
7. The short-distance obstacle avoidance method based on the lidar as recited in claim 1, wherein a Hungarian tracking algorithm based on the Marangoni distance is adopted when detecting the obstacles in the image frame.
8. The utility model provides a keep away barrier device closely based on laser radar which characterized in that includes:
the acquisition module is used for acquiring image frames generated by scanning the peripheral information of the vehicle in real time by the laser radar;
the parking module is used for sending a parking instruction to the vehicle when detecting that an obstacle exists in a first obstacle avoidance area of the vehicle in the current frame, and recording the number of the obstacles in a second obstacle avoidance area of the vehicle in the current frame, wherein the number represents the dynamic state of the obstacles entering or leaving the second obstacle avoidance area; the second obstacle avoidance area is larger than the first obstacle avoidance area;
and the starting module is used for sending a starting instruction to the vehicle when N continuous frames detect that no barrier exists in the first obstacle avoidance area and the number of the barriers in the second obstacle avoidance area is zero.
9. A vehicle comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, the processor implementing the lidar-based close-range obstacle avoidance method of any of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, comprising a stored computer program, wherein when the computer program runs, the computer-readable storage medium is controlled to execute the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111533955.XA CN114325756A (en) | 2021-12-15 | 2021-12-15 | Short-distance obstacle avoidance method and device based on laser radar, vehicle and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111533955.XA CN114325756A (en) | 2021-12-15 | 2021-12-15 | Short-distance obstacle avoidance method and device based on laser radar, vehicle and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114325756A true CN114325756A (en) | 2022-04-12 |
Family
ID=81051872
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111533955.XA Pending CN114325756A (en) | 2021-12-15 | 2021-12-15 | Short-distance obstacle avoidance method and device based on laser radar, vehicle and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114325756A (en) |
-
2021
- 2021-12-15 CN CN202111533955.XA patent/CN114325756A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106255899B (en) | Device for signaling an object to a navigation module of a vehicle equipped with such a device | |
| US11615629B2 (en) | Estimation of time to collision in a computer vision system | |
| CN113561963B (en) | Parking method and device and vehicle | |
| US9123251B2 (en) | Image system for automotive safety applications | |
| US9798937B2 (en) | Vehicle control method for safety driving and device thereof | |
| EP4089659A1 (en) | Map updating method, apparatus and device | |
| US11738747B2 (en) | Server device and vehicle | |
| US11436815B2 (en) | Method for limiting object detection area in a mobile system equipped with a rotation sensor or a position sensor with an image sensor, and apparatus for performing the same | |
| CN112158197A (en) | Vehicle blind area obstacle avoiding method, device and system | |
| CN106560861A (en) | Intelligent supervision method based on computer vision | |
| CN111497741B (en) | Collision early warning method and device | |
| JP3301995B2 (en) | Stereo exterior monitoring device | |
| US20200074848A1 (en) | Travel control system for vehicle | |
| CN107826092A (en) | Advanced drive assist system and method, equipment, program and medium | |
| Choi et al. | Cut-in vehicle warning system exploiting multiple rotational images of SVM cameras | |
| US20170263127A1 (en) | Vehicle collision system and method of using the same | |
| CN113650607A (en) | Automatic driving method and system for low-speed scene and automobile | |
| JP3235831B2 (en) | Stereo exterior monitoring device | |
| EP4365046A1 (en) | Pedestrian minor-collision identification method and system in low-speed scenario | |
| CN114325756A (en) | Short-distance obstacle avoidance method and device based on laser radar, vehicle and storage medium | |
| JP7334632B2 (en) | Object tracking device and object tracking method | |
| US20200072968A1 (en) | Method for indicating obstacle by smart roadside unit | |
| CN114715031A (en) | Vehicle reversing control method, device, system and medium | |
| JP7113935B1 (en) | Road surface detection device and road surface detection method | |
| CN113814979B (en) | Big data-based intelligent robot environment recognition system |
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 |