CN116022167A - Obstacle recognition method, obstacle recognition device, electronic equipment and storage medium - Google Patents
Obstacle recognition method, obstacle recognition device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN116022167A CN116022167A CN202211315207.9A CN202211315207A CN116022167A CN 116022167 A CN116022167 A CN 116022167A CN 202211315207 A CN202211315207 A CN 202211315207A CN 116022167 A CN116022167 A CN 116022167A
- Authority
- CN
- China
- Prior art keywords
- trailer
- target
- detected
- determining
- 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.)
- Pending
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 embodiment of the disclosure discloses an obstacle recognition method, an obstacle recognition device, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring trailer information of a detected trailer in a target vehicle sensing range, wherein the target vehicle comprises a target tractor and a target trailer towed by the target tractor; determining the trailer type of the detected trailer according to the trailer information and the association information of the target tractor, and/or determining the trailer type of the detected trailer according to the trailer information and the association information of the target trailer; and determining whether the detected trailer is an obstacle influencing the driving of the target vehicle according to the type of the detected trailer. The technical scheme of the disclosure improves the recognition accuracy of the obstacle.
Description
Technical Field
The disclosure relates to the technical field of automatic driving, and in particular relates to a method and a device for identifying obstacles, electronic equipment and a storage medium.
Background
In the automatic driving technology, collision detection is a basic functional safety requirement, and an automatic driving vehicle with a collision detection function can sense an obstacle with potential safety risk in advance and perform lane change avoidance or speed reduction parking and other operations, or take remedial measures after physical collision, such as no longer performing path planning and control, so as to reduce secondary injury.
Currently, the main stream in the industry is collision detection mainly based on a sensing scheme of laser radar, a camera or multi-sensor fusion. Compared with the traditional pressure sensor based on the collision strip, on one hand, the sensor can provide a larger range of sensing detection capability with a smaller hardware quantity, on the other hand, the flexibility and the robustness of sensing are greatly improved by virtue of the upgrade of calculation force and the improvement of an algorithm, but most importantly, the sensing increases the possibility for collision early warning, and the risk can be avoided before the personal life and property safety happens.
However, whichever approach is adopted, the perceived target is an obstacle, so accurately identifying an obstacle is a very critical step.
Disclosure of Invention
In order to solve the technical problems or at least partially solve the technical problems, embodiments of the present disclosure provide a method, an apparatus, an electronic device, and a storage medium for identifying an obstacle, which improve accuracy of identifying an obstacle.
In a first aspect, an embodiment of the present disclosure provides a method for identifying an obstacle, including:
acquiring trailer information of a detected trailer in a target vehicle sensing range, wherein the target vehicle comprises a target tractor and a target trailer towed by the target tractor;
determining the trailer type of the detected trailer according to the trailer information and the association information of the target tractor, and/or determining the trailer type of the detected trailer according to the trailer information and the association information of the target trailer;
and determining whether the detected trailer is an obstacle influencing the driving of the target vehicle according to the type of the detected trailer.
In a second aspect, an embodiment of the present disclosure further provides an obstacle identifying apparatus, including: the system comprises an acquisition module, a detection module and a control module, wherein the acquisition module is used for acquiring trailer information of a detected trailer in a target vehicle sensing range, and the target vehicle comprises a target tractor and a target trailer towed by the target tractor;
the first determining module is used for determining the trailer type of the detected trailer according to the trailer information and the association information of the target tractor, and/or determining the trailer type of the detected trailer according to the trailer information and the association information of the target trailer;
and the second determining module is used for determining whether the detected trailer is an obstacle influencing the driving of the target vehicle according to the type of the detected trailer.
In a third aspect, embodiments of the present disclosure further provide an electronic device, including: one or more processors; a storage means for storing one or more programs; the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the obstacle recognition method as described above.
In a fourth aspect, the presently disclosed embodiments also provide a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the obstacle recognition method as described above.
According to the obstacle recognition method provided by the embodiment of the disclosure, the type of the detected trailer is determined according to the trailer information of the detected trailer and the association information of the target tractor, and/or the type of the detected trailer is determined according to the trailer information and the association information of the target trailer; and determining whether the detected trailer is an obstacle influencing the driving of the target vehicle according to the type of the detected trailer, thereby improving the recognition accuracy.
Drawings
The above and other features, advantages, and aspects of embodiments of the present disclosure will become more apparent by reference to the following detailed description when taken in conjunction with the accompanying drawings. The same or similar reference numbers will be used throughout the drawings to refer to the same or like elements. It should be understood that the figures are schematic and that elements and components are not necessarily drawn to scale.
FIG. 1 is a flow chart of a method of obstacle identification in an embodiment of the disclosure;
FIG. 2 is a schematic view of a rectangle corresponding to the target tractor in one embodiment of the present disclosure;
FIG. 3 is a schematic diagram of a relationship for determining segmentation coefficients in an embodiment of the present disclosure;
FIG. 4 is a flow chart of a collision detection process in an embodiment of the present disclosure;
fig. 5 is a schematic structural diagram of an obstacle identifying apparatus in an embodiment of the disclosure;
fig. 6 is a schematic structural diagram of an electronic device in an embodiment of the disclosure.
Detailed Description
Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure have been shown in the accompanying drawings, it is to be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustration purposes only and are not intended to limit the scope of the present disclosure.
It should be noted that the terms "first," "second," and the like in this disclosure are merely used to distinguish between different devices, modules, or units and are not used to define an order or interdependence of functions performed by the devices, modules, or units.
The names of messages or information interacted between the various devices in the embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.
With the exploration and landing of more and more autopilot application scenes, the definition boundary of "autopilot" is continuously widened, for example, in a logistics scene, a trailer (hereinafter referred to as an autopilot trailer) towed by a logistics tractor with autopilot capability extends as "autopilot". The sensing system should filter the own truck trailer from the detected obstacle trailers, only the other truck trailer is reserved, or both are reserved, but the classification of the two is required to be clear to be different. However, in a logistics scene, the self-vehicle trailer and the other vehicle trailer are similar in appearance, the sizes, shapes and the like of the trailers towed by the same logistics tractor are different, the difficulty of distinguishing the two is high from the end-to-end object identification angle, the self-vehicle trailer is often predicted from the perspective of a kinematic model based on a certain priori knowledge (such as the number and the size of the trailers and the information of a certain area behind the logistics tractor), and the trailers meeting the conditions are classified into the self-vehicle trailer. However, in a practical application scenario, the movement path of the trailer is measured in a variable manner, which results in that the detection based on the foregoing method is likely to identify the own-vehicle trailer as another-vehicle trailer (hereinafter referred to as an own-vehicle trailer false detection).
Aiming at the problems, the embodiment of the disclosure provides an obstacle recognition method, which improves recognition accuracy, and particularly can accurately distinguish a self-vehicle trailer from other vehicle trailers. Fig. 1 is a flowchart of an obstacle recognition method in an embodiment of the disclosure. The method may be performed by an obstacle recognition device, which may be implemented in software and/or hardware, which may be configured in an electronic apparatus. As shown in fig. 1, the method specifically may include the following steps:
s110, acquiring trailer information of detected trailers in a target vehicle sensing range, wherein the target vehicle comprises a target tractor and target trailers towed by the target tractor.
The sensing range of the target vehicle is determined by the detection range of other sensing type sensors such as an on-board laser radar and/or an on-board camera of the target vehicle. The detected trailer comprises a self-vehicle trailer towed by the target tractor and other vehicle trailers towed by tractors of other vehicles.
The trailer information includes some information needed to determine whether the detected trailer is at risk of collision with the target tractor, including, for example, real-time location, direction of movement, speed of movement, etc. of the detected trailer.
S120, determining the trailer type of the detected trailer according to the trailer information and the association information of the target tractor, and/or determining the trailer type of the detected trailer according to the trailer information and the association information of the target trailer.
Wherein the association information of the target tractor includes, but is not limited to: size information (e.g., length, width of the target tractor) and location information (e.g., coordinates of four vertices of the target tractor) of the target tractor.
Illustratively, the determining the trailer type of the detected trailer according to the trailer information and the association information of the target tractor includes:
dividing the target tractor into a first part comprising a head and a second part comprising a tail according to the association information of the target tractor; determining a trailer type of the detected trailer based on the first portion and/or the second portion and the trailer information.
Further, the dividing the target tractor into a first part including a head and a second part including a tail according to the association information of the target tractor includes;
determining a corresponding rectangle according to the width and the length of the target tractor, and determining four vertex coordinates of the rectangle according to the position information in the associated information of the target tractor; determining the region range of the first part and the region range of the second part according to the segmentation coefficient and four vertex coordinates of the rectangle; wherein the segmentation factor is determined based on the width, length, center point, and angular range over which an obstacle may appear for the target tractor.
Exemplary, reference is made to a schematic diagram of a rectangle corresponding to the target tractor as shown in FIG. 2, with four vertex coordinates of the rectangle according to upper left vertex-upper right vertex-lower left vertex
The order of the point-lower right vertex is: (x) tl ,y tl )、(x tr ,y tr )、(x bl ,y bl )、(x br ,y br ). The target tractor is divided into a first portion including a head and a second portion including a tail according to the following expression.
Wherein, rect front The region range representing the first portion, the upper right vertex coordinate, lower left vertex coordinate, and upper left vertex coordinate of the first portion being (x_front) in this order tr ，y_front tr )、(x_front br ，y_front br )、(x_front bl ，y_front bl )、(x_front tl ，y_front tl )。
Rect rear The area range of the second part is represented, and the coordinates of the upper right vertex, the lower left vertex and the upper left vertex of the second part are (x_rear) in order tr ，y_rear tr )、(x_rear br ，y_rear br )、(x_rear bl ，y_rear bl )、(x_rear tl ，y_rear tl )。
r denotes the segmentation factor, which is determined according to the width, length, center point of the target tractor and the angular range θ in which an obstacle may appear. Referring to a schematic diagram of the relationship for determining the segmentation coefficients as shown in fig. 3, the following relationship can be obtained according to fig. 3:
where θ is the angular range in which the obstacle may appear, is an empirical value, r represents a segmentation factor, w represents the width of the target tractor, h represents the length of the target tractor, and o represents the center point of the target tractor. Based on this relation, a segmentation factor r can be calculated.
Further, the determining of the trailer type of the detected trailer based on the first portion and/or the second portion and the trailer information.
Determining, based on the trailer information, whether the detected trailer is at risk of collision with the first portion and whether there is risk of collision with the second portion; if the detected trailer has collision risk with the first part, determining the detected trailer as the other vehicle trailer; if collision risk exists between the detected trailer and the second part, determining the detected trailer as a self-vehicle trailer; correspondingly, the determining whether the detected trailer is an obstacle affecting the driving of the target vehicle according to the trailer type of the detected trailer comprises: and if the detected trailer is the other vehicle trailer, determining the detected trailer as an obstacle influencing the driving of the target vehicle. Namely, the trailer type comprises a trailer of other vehicles and a trailer of own vehicles.
In summary, the concept principle of determining the trailer type of the detected trailer according to the trailer information and the association information of the target tractor is as follows: 1. if a false detection occurs in the self-truck trailer, a safety risk is thus created when it is present in a certain range of the direction of travel of the target tractor, so that it should be logically classified as his truck trailer and treated as an obstacle. 2. His own truck trailer is less likely to appear within a certain range behind the target tractor, so an erroneously detected own truck trailer that appears within that range should be classified as an own truck trailer. Based on the above two points, this stage takes the approach of re-sectioning the target tractor, thereby creating two parts, front (front) which is the main body for detection, if there is a trailer that collides with this part, this is considered to be caused by his trailer, and rear (rear) which acts as a "buffer" and if there is a trailer that collides with this part, this is considered to be caused by the own-vehicle trailer.
Further, the determining the trailer type of the detected trailer according to the trailer information and the association information of the target trailer includes:
determining one or more of morphological characteristics, dimensional characteristics and motion characteristics of the detected trailer according to the trailer information; and determining the type of the detected trailer according to one or more of the morphological characteristics, the dimensional characteristics and the motion characteristics and the association information of the target trailer.
Illustratively, the morphological feature comprises an area of the detected trailer, the dimensional feature comprises a maximum side length of the detected trailer, and the movement feature comprises a speed magnitude and a speed direction of the detected trailer; the related information of the target trailer comprises the area of the target trailer, the maximum side length of the target trailer, the speed direction of the target trailer and the appearance area of the target trailer. Correspondingly, the determining the trailer type of the detected trailer according to one or more of the morphological feature, the dimensional feature and the motion feature and the associated information of the target trailer comprises the following steps:
constructing influencing factors according to one or more of the morphological characteristics, the dimensional characteristics and the motion characteristics and the associated information of the target trailer; determining the type of the detected trailer according to the influence factors; wherein the influencing factors comprise any one or more of the following: the method includes the steps of detecting a first ratio of an area of the trailer to an area of the target trailer, detecting a second ratio of a maximum side length of the trailer to a maximum side length of the target trailer, detecting a third ratio of a speed magnitude of the trailer to a speed magnitude of the target trailer, detecting a fourth ratio of a speed direction of the trailer to a speed direction of the target trailer, and detecting result information whether a geometric center of the trailer is a point in an appearance area of the target trailer (the result information includes two cases, one is that the geometric center of the trailer is a point in the appearance area of the target trailer and the other is that the geometric center of the trailer is not a point in the appearance area of the target trailer).
Further, the determining the trailer type of the detected trailer according to the influencing factors includes:
determining first data for characterizing a trailer type of the detected trailer according to the first ratio; determining second data representing a trailer type of the detected trailer according to the second ratio; determining third data representing a trailer type of the detected trailer according to the third ratio; determining fourth data representing a trailer type of the detected trailer according to the fourth ratio; determining fifth data for representing the type of the detected trailer according to result information of whether the geometric center of the detected trailer is a point in the appearance area of the target trailer; weighting and summing the first data, the second data, the third data, the fourth data and the fifth data according to weights matched with the first ratio, the second ratio, the third ratio, the fourth ratio and the result information respectively to obtain a reference value; and determining the type of the detected trailer according to the parameter value and a preset threshold value.
Specifically, the idea principle of determining the trailer type of the detected trailer according to the trailer information and the association information of the target trailer is as follows: 1. false detection of a self-propelled vehicle trailer is usually a small part of the false detection trailer, and obstacles generated by the false detection trailer have larger differences in morphology compared with the actual other vehicle trailer; 2. the motion state of the self-vehicle trailer is highly correlated with the self-vehicle (i.e., the target tractor), and the motion state of the other vehicle trailer is less correlated, even has negative correlation.
To define morphological differences, embodiments of the present invention use two factors, area size, maximum side length. The area is a basic morphological feature, and the self-vehicle trailer is basically not completely exposed in the detection range when being misdetected, so that the size of a detection object generated by misdetection of the self-vehicle trailer is much smaller than that of the other vehicle trailer, and the self-vehicle trailer can be distinguished only by comparing the areas:
wherein detected area And a priority_knowledges area Respectively the area of the detected object (here, the area of the detected trailer is referred to as a trailer obstacle) and the priori knowledge of the actual size of the trailer (i.e. the area of the target trailer), f area Is the first ratio.
However, the actual sensing result is wavy and noisy, the pose of the other vehicle trailer is also uncertain, and the possibility that part of the body of the other vehicle trailer enters the sensing blind area is high, so that the situation that the self vehicle trailer is detected by mistake and the detected area of the other vehicle trailer is similar may occur, and the size of the single dependent area is unreliable. However, after an object is occluded, its one-dimensional information is typically retained, so the side length information is also taken into account:
wherein detected longest_side And priority_knowledgeable longest_side Respectively the maximum side length of the detected object (particularly referred to herein as the barrier of the trailer) and the priori knowledge of the actual maximum side length of the trailer (i.e., the second ratio of the maximum side length of the target trailer), f longest_side Is the second ratio.
On the other hand, the motion state uses speed, direction and trajectory information. The speed of the self-vehicle trailer is the same as that of the self-vehicle (namely the target tractor):
wherein detected velocity And vehicle velocity Respectively the speed of the detected object (here, the speed of the detected trailer) and the speed of the vehicle (i.e. the speed of the target trailer, the speed of the target tractor can be regarded as the speed of the target trailer), f velocity Is the third ratio.
However, the speed direction may differ greatly from the own vehicle due to the non-rigid connection, but for the case that an obstacle trawl differs more than 90 ° from the own vehicle in the speed direction, the probability is also high that it can be classified as the other vehicle trawl:
wherein detected direction And vehicle direction Respectively the speed direction of the detected object (here, the barrier of the trailer is pointed out) and the speed direction of the vehicle per se, f direction Is the fourth ratio.
The following track is a track, and since an obstacle is difficult to stably sense by a plurality of continuous frames, tracking loss is easy to occur and the number of detection frames is small, the track correlation between the obstacle and the vehicle is not stable and reliable. However, the area where the self-propelled vehicle trailer may appear at any moment can be determined by the kinematic model relationship between the target tractor and the self-propelled vehicle trailer, and then the self-propelled vehicle trailer and the other self-propelled vehicle trailer can be distinguished by judging whether the perceived obstacle trailer is in the area or not:
f trajectory ＝point_in_polygon((x,y),polygon)
where (x, y) represents the geometric center of the detected object (here, referred to as a trailer obstacle), polygon represents the area of the polygon where the predicted self-propelled trailer should appear, and point_in_polygon is a function of the decision point in the polygon, and can be formed by any algorithm for calculating geometry.
The foregoing illustrates the factors utilized by the present invention, but any single factor makes it difficult to determine whether the obstacle trawl is his car trawl or not, or the recognition accuracy is not high because each factor has noise interference. So after all factors are collected, a final trailer type judgment result can be generated through a certain decision, which is essentially a binary classification problem. The present invention uses a weight-based scoring mechanism. First, each factor is assigned a weight coefficient w x Where x is a factor subscript, representing the importance of the factor to the final result, if an obstacle trawl is judged to be his car trawl based on a certain factor, the factor's score is the value of its weight coefficient, otherwise no score is given. And if the trailer type of the detected trailer is determined to be the other vehicle trailer according to the first ratio, the first data used for representing the trailer type of the detected trailer can be 1, otherwise, the first data is 0. Determining second data representing a trailer type of the detected trailer according to the second ratio; root of Chinese characterDetermining third data characterizing a trailer type of the detected trailer according to the third ratio; determining fourth data representing a trailer type of the detected trailer according to the fourth ratio; and determining fifth data for representing the type of the trailer of the detected trailer according to result information of whether the geometric center of the detected trailer is a point in the appearance area of the target trailer, wherein the fifth data is similar to the determination mode of the first data.
Thus, all factors produce a score of T, only if T meets T>T obst And judging the obstacle trailer as the other vehicle trailer at the stage. Wherein w and T obst Can be determined by a machine learning method, such as SVM, deep learning, etc., after acquiring multiple sets of test data.
S130, determining whether the detected trailer is an obstacle influencing the driving of the target vehicle according to the type of the detected trailer.
The obstacle recognition method provided by the embodiment is a method for recognizing the trailer of the other vehicle based on a post-processing mode, and solves the problem of automatic driving irregularity caused by false detection of the trailer of the own vehicle due to similarity of the trailer in a logistics scene, thereby improving the accuracy of collision detection. Specifically, the invention judges the type of the trailer in two stages, on one hand, the damage degree of collision to the target tractor and the target trailer is considered to be different, and especially the target tractor needs to be more strict, so a redundancy mechanism is provided; on the other hand, the definition of the obstacle is different from that of the obstacle, and logically any object affecting the normal running of the target vehicle is an obstacle for the target vehicle even though it may be a part of the whole to which the target vehicle belongs.
It can be understood that the embodiment of the invention not only can solve the problems faced by automatic driving collision detection in a logistics scene, but also can be expanded to other scenes which are plagued by similar objects, in addition, the invention can also cope with the changes and differences which occur in the same scene or different scenes through the training and adjustment of parameters, and has higher flexibility.
The invention can reduce unexpected planning abnormality caused by false detection of the self-vehicle trailer in collision detection, such as lane change avoidance or parking, and the like, and reduce the irregularity of automatic driving; the invention has higher expansibility and flexibility, can longitudinally optimize parameters to ensure that the output result is more accurate, and can transversely incorporate more generalized or scene-specific factors, enrich judgment basis and improve robustness.
On the basis of the above technical solution, reference is made to a collision detection processing flowchart as shown in fig. 4, which includes the following steps: obstacle trailer classification, namely inputting the detected trailer of the other vehicle and the self-vehicle trailer generated by false detection into a recognition algorithm, respectively carrying out the recognition of the trailer of the other vehicle based on the target tractor and the recognition of the trailer of the other vehicle based on the target trailer, finally obtaining the recognition result of the trailer of the other vehicle, inputting the recognition result into a collision detection algorithm for processing, and further planning the vehicle behavior.
Fig. 5 is a schematic structural diagram of an obstacle identifying apparatus in an embodiment of the disclosure. As shown in fig. 5: the device comprises: an acquisition module 510, a first determination module 520, and a second determination module 530.
An obtaining module 510, configured to obtain trailer information of a detected trailer in a sensing range of a target vehicle, where the target vehicle includes a target tractor and a target trailer towed by the target tractor; a first determining module 520, configured to determine a trailer type of the detected trailer according to the trailer information and the association information of the target tractor, and/or determine a trailer type of the detected trailer according to the trailer information and the association information of the target trailer; a second determining module 530, configured to determine whether the detected trailer is an obstacle affecting driving of the target vehicle according to a trailer type of the detected trailer.
The first determination module 520 includes: the dividing unit is used for dividing the target tractor into a first part comprising a head and a second part comprising a tail according to the association information of the target tractor; and the first determining unit is used for determining the trailer type of the detected trailer based on the first part and/or the second part and the trailer information.
The trailer type comprises a trailer of other vehicles and a trailer of own vehicles; the first determining unit is specifically configured to: determining, based on the trailer information, whether the detected trailer is at risk of collision with the first portion and whether there is risk of collision with the second portion; if the detected trailer has collision risk with the first part, determining the detected trailer as the other vehicle trailer; if collision risk exists between the detected trailer and the second part, determining the detected trailer as a self-vehicle trailer; correspondingly, the second determining module 530 is configured to determine the detected trailer as an obstacle affecting driving of the target vehicle if the detected trailer is a trailer of another vehicle.
The dividing unit is specifically configured to: determining a corresponding rectangle according to the width and the length of the target tractor, and determining four vertex coordinates of the rectangle according to the position information in the associated information of the target tractor; determining the region range of the first part and the region range of the second part according to the segmentation coefficient and four vertex coordinates of the rectangle; wherein the segmentation factor is determined based on the width, length, center point, and angular range over which an obstacle may appear for the target tractor.
Optionally, the first determining module 520 includes: the second determining unit is used for determining one or more of morphological characteristics, dimensional characteristics and movement characteristics of the detected trailer according to the trailer information; and determining the type of the detected trailer according to one or more of the morphological characteristics, the dimensional characteristics and the motion characteristics and the association information of the target trailer.
Optionally, the morphological feature comprises an area of the detected trailer, the dimensional feature comprises a maximum side length of the detected trailer, and the motion feature comprises a speed and a speed direction of the detected trailer; the related information of the target trailer comprises the area of the target trailer, the maximum side length of the target trailer, the speed direction of the target trailer and the appearance area of the target trailer; the second determination unit includes: a construction subunit, configured to construct an influencing factor according to one or more of the morphological feature, the dimensional feature, and the motion feature, and the associated information of the target trailer; a determining subunit, configured to determine a trailer type of the detected trailer according to the influencing factor; wherein the influencing factors comprise any one or more of the following: the method comprises the steps of detecting a first ratio of the area of a trailer to the area of a target trailer, a second ratio of the maximum side length of the trailer to the maximum side length of the target trailer, a third ratio of the speed of the trailer to the speed of the target trailer, a fourth ratio of the speed direction of the trailer to the speed direction of the target trailer and result information of whether the geometric center of the trailer is a point in the appearance area of the target trailer.
Optionally, the determining subunit is specifically configured to: determining first data for characterizing a trailer type of the detected trailer according to the first ratio; determining second data representing a trailer type of the detected trailer according to the second ratio; determining third data representing a trailer type of the detected trailer according to the third ratio; determining fourth data representing a trailer type of the detected trailer according to the fourth ratio; determining fifth data for representing the type of the detected trailer according to result information of whether the geometric center of the detected trailer is a point in the appearance area of the target trailer; weighting and summing the first data, the second data, the third data, the fourth data and the fifth data according to weights matched with the first ratio, the second ratio, the third ratio, the fourth ratio and the result information respectively to obtain a reference value; and determining the type of the detected trailer according to the parameter value and a preset threshold value.
The obstacle recognition device provided by the embodiment of the disclosure can execute the steps in the obstacle recognition method provided by the embodiment of the disclosure, and has the corresponding functional modules and beneficial effects of the execution method.
Fig. 6 is a schematic structural diagram of an electronic device in an embodiment of the disclosure. Referring now in particular to fig. 6, a schematic diagram of an electronic device 500 suitable for use in implementing embodiments of the present disclosure is shown. The electronic device shown in fig. 6 is merely an example and should not be construed to limit the functionality and scope of use of the disclosed embodiments.
As shown in fig. 6, an electronic device 500 may include a processing means (e.g., a central processor, a graphics processor, etc.) 501 that may perform various suitable actions and processes to implement the methods of embodiments as described in the present disclosure according to a program stored in a Read Only Memory (ROM) 502 or a program loaded from a storage means 508 into a Random Access Memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the electronic apparatus 500 are also stored. The processing device 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.
In particular, according to embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a non-transitory computer readable medium, the computer program comprising program code for performing the method shown in the flowchart, thereby implementing the obstacle recognition method as described above. In such an embodiment, the computer program may be downloaded and installed from a network via the communication means 509, or from the storage means 508, or from the ROM 502. The above-described functions defined in the methods of the embodiments of the present disclosure are performed when the computer program is executed by the processing device 501.
It should be noted that the computer readable medium described in the present disclosure may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this disclosure, a computer-readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present disclosure, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, fiber optic cables, RF (radio frequency), and the like, or any suitable combination of the foregoing.
The computer readable medium may be contained in the electronic device; or may exist alone without being incorporated into the electronic device. The computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to perform the obstacle recognition method.
Alternatively, the electronic device may perform other steps described in the above embodiments when the above one or more programs are executed by the electronic device.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The foregoing description is only of the preferred embodiments of the present disclosure and description of the principles of the technology being employed. It will be appreciated by persons skilled in the art that the scope of the disclosure referred to in this disclosure is not limited to the specific combinations of features described above, but also covers other embodiments which may be formed by any combination of features described above or equivalents thereof without departing from the spirit of the disclosure. Such as those described above, are mutually substituted with the technical features having similar functions disclosed in the present disclosure (but not limited thereto).
Claims (10)
1. A method of identifying an obstacle, the method comprising:
acquiring trailer information of a detected trailer in a target vehicle sensing range, wherein the target vehicle comprises a target tractor and a target trailer towed by the target tractor;
determining the trailer type of the detected trailer according to the trailer information and the association information of the target tractor, and/or determining the trailer type of the detected trailer according to the trailer information and the association information of the target trailer;
and determining whether the detected trailer is an obstacle influencing the driving of the target vehicle according to the type of the detected trailer.
2. The method of claim 1, wherein the determining the trailer type of the detected trailer based on the trailer information and the association information of the target tractor comprises:
dividing the target tractor into a first part comprising a head and a second part comprising a tail according to the association information of the target tractor;
determining a trailer type of the detected trailer based on the first portion and/or the second portion and the trailer information.
3. The method of claim 2, wherein the trailer types include his car and self car trailers;
the determining a trailer type of the detected trailer based on the first portion and/or the second portion and the trailer information, comprising:
determining, based on the trailer information, whether the detected trailer is at risk of collision with the first portion and whether there is risk of collision with the second portion;
if the detected trailer has collision risk with the first part, determining the detected trailer as the other vehicle trailer;
if collision risk exists between the detected trailer and the second part, determining the detected trailer as a self-vehicle trailer;
correspondingly, the determining whether the detected trailer is an obstacle affecting the driving of the target vehicle according to the trailer type of the detected trailer comprises:
and if the detected trailer is the other vehicle trailer, determining the detected trailer as an obstacle influencing the driving of the target vehicle.
4. The method of claim 2, wherein the dividing the target tractor into a first portion including a head and a second portion including a tail according to the association information of the target tractor comprises;
determining a corresponding rectangle according to the width and the length of the target tractor, and determining four vertex coordinates of the rectangle according to the position information in the associated information of the target tractor;
determining the region range of the first part and the region range of the second part according to the segmentation coefficient and four vertex coordinates of the rectangle;
wherein the segmentation factor is determined based on the width, length, center point, and angular range over which an obstacle may appear for the target tractor.
5. The method of claim 1, wherein the determining the trailer type of the detected trailer based on the trailer information and the association information of the target trailer comprises:
determining one or more of morphological characteristics, dimensional characteristics and motion characteristics of the detected trailer according to the trailer information;
and determining the type of the detected trailer according to one or more of the morphological characteristics, the dimensional characteristics and the motion characteristics and the association information of the target trailer.
6. The method of claim 5, wherein the morphological feature comprises an area of the inspected bucket, the dimensional feature comprises a maximum side length of the inspected bucket, and the movement feature comprises a speed magnitude and a speed direction of the inspected bucket;
the related information of the target trailer comprises the area of the target trailer, the maximum side length of the target trailer, the speed direction of the target trailer and the appearance area of the target trailer;
correspondingly, the determining the trailer type of the detected trailer according to one or more of the morphological feature, the dimensional feature and the motion feature and the associated information of the target trailer comprises the following steps:
constructing influencing factors according to one or more of the morphological characteristics, the dimensional characteristics and the motion characteristics and the associated information of the target trailer;
determining the type of the detected trailer according to the influence factors;
wherein the influencing factors comprise any one or more of the following: the method comprises the steps of detecting a first ratio of the area of a trailer to the area of a target trailer, a second ratio of the maximum side length of the trailer to the maximum side length of the target trailer, a third ratio of the speed of the trailer to the speed of the target trailer, a fourth ratio of the speed direction of the trailer to the speed direction of the target trailer and result information of whether the geometric center of the trailer is a point in the appearance area of the target trailer.
7. The method of claim 6, wherein the determining the type of the detected trailer based on the influencing factor comprises:
determining first data for characterizing a trailer type of the detected trailer according to the first ratio;
determining second data representing a trailer type of the detected trailer according to the second ratio;
determining third data representing a trailer type of the detected trailer according to the third ratio;
determining fourth data representing a trailer type of the detected trailer according to the fourth ratio;
determining fifth data for representing the type of the detected trailer according to result information of whether the geometric center of the detected trailer is a point in the appearance area of the target trailer;
weighting and summing the first data, the second data, the third data, the fourth data and the fifth data according to weights matched with the first ratio, the second ratio, the third ratio, the fourth ratio and the result information respectively to obtain a reference value;
and determining the type of the detected trailer according to the parameter value and a preset threshold value.
8. An obstacle recognition device, characterized by comprising:
the system comprises an acquisition module, a detection module and a control module, wherein the acquisition module is used for acquiring trailer information of a detected trailer in a target vehicle sensing range, and the target vehicle comprises a target tractor and a target trailer towed by the target tractor;
the first determining module is used for determining the trailer type of the detected trailer according to the trailer information and the association information of the target tractor, and/or determining the trailer type of the detected trailer according to the trailer information and the association information of the target trailer;
and the second determining module is used for determining whether the detected trailer is an obstacle influencing the driving of the target vehicle according to the type of the detected trailer.
9. An electronic device, the electronic device comprising:
one or more processors;
a storage means for storing one or more programs;
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of any of claims 1-7.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the method according to any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211315207.9A CN116022167A (en) | 2022-10-26 | 2022-10-26 | Obstacle recognition method, obstacle recognition device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211315207.9A CN116022167A (en) | 2022-10-26 | 2022-10-26 | Obstacle recognition method, obstacle recognition device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116022167A true CN116022167A (en) | 2023-04-28 |
Family
ID=86080235
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211315207.9A Pending CN116022167A (en) | 2022-10-26 | 2022-10-26 | Obstacle recognition method, obstacle recognition device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116022167A (en) |
-
2022
- 2022-10-26 CN CN202211315207.9A patent/CN116022167A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11433812B2 (en) | Hitching maneuver | |
| CN111712829B (en) | Detecting a blocking stationary vehicle | |
| KR102098140B1 (en) | Method for monotoring blind spot of vehicle and blind spot monitor using the same | |
| KR102098131B1 (en) | Method for monotoring blind spot of vehicle and blind spot minotor using the same | |
| CN107609522B (en) | Information fusion vehicle detection system based on laser radar and machine vision | |
| Ferryman et al. | Visual surveillance for moving vehicles | |
| CN102997900B (en) | Vehicle systems, devices, and methods for recognizing external worlds | |
| US10748295B2 (en) | Object tracking in blind-spot | |
| CN113370977B (en) | Intelligent vehicle forward collision early warning method and system based on vision | |
| CN110794406A (en) | Multi-source sensor data fusion system and method | |
| CN108657173B (en) | ECU, autonomous vehicle including the same, and method of identifying nearby vehicles | |
| Liu et al. | Vehicle detection and ranging using two different focal length cameras | |
| CN114454875A (en) | Urban road automatic parking method and system based on reinforcement learning | |
| CN115993597A (en) | Visual radar perception fusion method and terminal equipment | |
| WO2019065970A1 (en) | Vehicle exterior recognition device | |
| CN115923839A (en) | Vehicle path planning method | |
| Qing et al. | A novel particle filter implementation for a multiple-vehicle detection and tracking system using tail light segmentation | |
| US20220171975A1 (en) | Method for Determining a Semantic Free Space | |
| CN110119751B (en) | Laser radar point cloud target segmentation method, target matching method, device and vehicle | |
| CN114296095A (en) | Method, device, vehicle and medium for extracting effective target of automatic driving vehicle | |
| US11631255B2 (en) | Apparatus and method for controlling door opening | |
| JPH11142168A (en) | Environment-recognizing apparatus | |
| JP6657934B2 (en) | Object detection device | |
| Corcoran et al. | Background foreground segmentation for SLAM | |
| CN116022167A (en) | Obstacle recognition method, obstacle recognition device, electronic equipment and storage medium |
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 |