CN115223133A - Parking obstacle detection method, parking obstacle detection device, vehicle, and storage medium - Google Patents
Parking obstacle detection method, parking obstacle detection device, vehicle, and storage medium Download PDFInfo
- Publication number
- CN115223133A CN115223133A CN202210134702.3A CN202210134702A CN115223133A CN 115223133 A CN115223133 A CN 115223133A CN 202210134702 A CN202210134702 A CN 202210134702A CN 115223133 A CN115223133 A CN 115223133A
- Authority
- CN
- China
- Prior art keywords
- coordinate
- obstacle
- parking
- virtual
- determined
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Abstract
The application discloses a parking obstacle detection method, a parking obstacle detection device, a vehicle and a storage medium, wherein the parking obstacle detection method comprises the steps of obtaining a first coordinate of an ultrasonic sensor for detecting an obstacle; acquiring a visual recognition result corresponding to the obstacle image according to the obstacle image acquired by the visual sensor for the obstacle, wherein the visual recognition result at least comprises a second coordinate and a confidence coefficient; when the confidence degree is determined to be larger than or equal to the confidence degree threshold value, determining whether a first virtual obstacle indicated by the first coordinate is included in a second virtual obstacle indicated by the second coordinate; when it is determined that the first virtual obstacle is included in the second virtual obstacle, the first coordinates are determined as target coordinates of the obstacle, and the target coordinates are output. The method realizes that the coordinates of the obstacles are obtained by fusing the results of the ultrasonic sensor and the vision sensor for detecting the obstacles, can avoid that the ultrasonic sensor cannot detect the approaching short obstacles, and improves the detection accuracy of the obstacle detection.
Description
Technical Field
The present disclosure relates to the field of automatic parking technologies, and more particularly, to a parking obstacle detection method, a parking obstacle detection device, a vehicle, and a storage medium.
Background
The automatic parking process is a process that a control system of a vehicle automatically controls steering, braking, power, gears, parking and the like of the vehicle according to parking space position information sensed by a vehicle-mounted sensor so as to automatically park the vehicle in a parking space. During automatic parking, it is often necessary to detect obstacles in the parking path.
At present, obstacles are detected by using an ultrasonic sensor during automatic parking. However, when a short obstacle exists on the parking path and the vehicle approaches the short obstacle, the ultrasonic signal of the ultrasonic sensor is lost, and the ultrasonic sensor will misjudge that no obstacle exists on the parking path, so that the detection accuracy of detecting the obstacle in the automatic parking process is low.
Disclosure of Invention
In view of the above problems, the present application proposes a parking obstacle detection method, a detection device, a vehicle, and a storage medium to overcome or at least partially solve the above problems of the related art.
In a first aspect, an embodiment of the present application provides a parking obstacle detection method, including: acquiring a first coordinate of the obstacle detection of the ultrasonic sensor; acquiring a visual recognition result corresponding to the obstacle image according to the obstacle image acquired by the visual sensor for the obstacle, wherein the visual recognition result at least comprises a second coordinate and a confidence coefficient; when the confidence coefficient is determined to be larger than or equal to the confidence coefficient threshold value, determining whether a first virtual obstacle indicated by the first coordinate is contained in a second virtual obstacle indicated by the second coordinate; and when the first virtual obstacle is determined to be included in the second virtual obstacle, determining the first coordinate as a target coordinate of the obstacle, and outputting the target coordinate.
In a second aspect, an embodiment of the present application provides a parking obstacle detection device, including: the device comprises a first acquisition module, a second acquisition module, a first determination module and a second determination module. The first acquisition module is used for acquiring a first coordinate of the obstacle detection of the ultrasonic sensor; the second acquisition module is used for acquiring a visual recognition result corresponding to the obstacle image according to the obstacle image acquired by the visual sensor for the obstacle, and the visual recognition result at least comprises a second coordinate and a confidence coefficient; the first determining module is used for determining whether the first virtual obstacle indicated by the first coordinate is contained in the second virtual obstacle indicated by the second coordinate when the confidence coefficient is determined to be greater than or equal to the confidence coefficient threshold value; and the second determining module is used for determining the first coordinate as the target coordinate of the obstacle and outputting the target coordinate when the first virtual obstacle is determined to be included in the second virtual obstacle.
In a third aspect, an embodiment of the present application provides a vehicle, including: a memory; one or more processors coupled with the memory; one or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the one or more processors, the one or more application programs being configured to perform the parking obstacle detection method as provided in the first aspect described above.
In a fourth aspect, embodiments of the present application provide a computer-readable storage medium, in which program codes are stored, and the program codes can be called by a processor to execute the parking obstacle detection method provided in the first aspect.
According to the scheme provided by the application, the first coordinate of the obstacle detection by the ultrasonic sensor is obtained, the visual recognition result corresponding to the obstacle image is obtained according to the obstacle image acquired by the visual sensor for the obstacle, the visual recognition result at least comprises the second coordinate and the confidence coefficient, when the confidence coefficient is determined to be larger than or equal to the confidence coefficient threshold value, whether the first virtual obstacle indicated by the first coordinate is contained in the second virtual obstacle indicated by the second coordinate or not is determined, when the first virtual obstacle is determined to be contained in the second virtual obstacle, the first coordinate is determined as the target coordinate of the obstacle, the target coordinate is output, the obstacle detection result of the ultrasonic sensor and the visual sensor is fused, the obstacle coordinate is obtained, the situation that the ultrasonic sensor cannot detect a short and close obstacle can be avoided, and the obstacle detection accuracy is improved.
Furthermore, the visual recognition result with the confidence coefficient greater than or equal to the confidence coefficient threshold value is fused with the ultrasonic detection result to obtain the coordinates of the obstacle, so that the low detection accuracy of the obstacle detection caused by the fusion of the visual recognition result with the low confidence coefficient and the first coordinate can be avoided, and the detection accuracy of the obstacle detection is further improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the description below are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 shows a schematic view of a parking obstacle detection system according to an embodiment of the present application.
Fig. 2 is a schematic flow chart illustrating a parking obstacle detection method according to an embodiment of the present application.
Fig. 3 is another schematic flow chart of the parking obstacle detection method according to the embodiment of the present application.
Fig. 4 is a schematic flow chart illustrating a parking obstacle detection method according to an embodiment of the present application.
Fig. 5 is a block diagram showing a configuration of a parking obstacle detection device according to an embodiment of the present application.
FIG. 6 shows a functional block diagram of a vehicle provided by an embodiment of the present application.
Fig. 7 illustrates a computer-readable storage medium provided by an embodiment of the present application for storing or carrying program codes for implementing a parking obstacle detection method provided according to an embodiment of the present application.
Detailed Description
Reference will now be made in detail to embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative and are only for the purpose of explaining the present application and are not to be construed as limiting the present application.
The following disclosure provides many different embodiments or examples for implementing different features of the application. To simplify the disclosure of the present application, specific example components and arrangements are described below. Of course, they are merely examples and are not intended to limit the present application. Moreover, the present application may repeat reference numerals and/or letters in the various examples, such repetition is for the purpose of simplicity and clarity and does not in itself dictate a relationship between the various embodiments and/or configurations discussed.
The automatic parking process is a process that a control system of a vehicle automatically controls the steering, braking, power, gear, parking and the like of the vehicle according to the parking space position information sensed by a vehicle-mounted sensor so as to automatically park the vehicle in a parking space. During automatic parking, it is often necessary to detect obstacles on the parking path.
At present, obstacles are detected by using an ultrasonic sensor during automatic parking. However, when a short obstacle exists on the parking path and the vehicle approaches the short obstacle, the ultrasonic signal of the ultrasonic sensor is lost, and the ultrasonic sensor will misjudge that no obstacle exists on the parking path, resulting in low detection accuracy for detecting the obstacle in the automatic parking process.
In view of the above problems, the inventor has studied and proposed a parking obstacle detection method, a detection device, a vehicle, and a storage medium according to embodiments of the present application for a long time, so as to obtain coordinates of an obstacle by fusing results of obstacle detection by an ultrasonic sensor and a visual sensor, avoid that the ultrasonic sensor cannot detect a short and close obstacle, and improve detection accuracy of obstacle detection.
Furthermore, the visual recognition result with the confidence coefficient greater than or equal to the confidence coefficient threshold value is fused with the ultrasonic detection result to obtain the coordinates of the obstacle, so that the problem that the detection accuracy of the obstacle detection is low due to the fact that the visual recognition result with the low confidence coefficient is fused with the first coordinate can be avoided, and the detection accuracy of the obstacle detection is further improved.
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application.
Referring to fig. 1, a schematic view of an application scenario of a parking obstacle detection system according to an embodiment of the present application is shown, where the parking obstacle detection system includes a vehicle 100 and an obstacle 200, and the vehicle 100 may be configured to detect the obstacle 200 and automatically park in a parking space according to the detected obstacle 200.
In some embodiments, vehicle 100 may include a frame 110, a control module 120, an ultrasonic sensor 130, a vision sensor 140, and the like, wherein control module 120, ultrasonic sensor 130, and vision sensor 140 may be mounted to frame 110, and frame 110 may provide mounting support for control module 120, ultrasonic sensor 130, and vision sensor 140.
In some embodiments, the control module 120 may be electrically connected to the ultrasonic sensor 130 and the vision sensor 140, and the control module 120 may be configured to control the ultrasonic sensor 130 and the vision sensor 140 to detect the obstacle 200, respectively, and determine the position of the obstacle 200 according to the detection results of the ultrasonic sensor 130 and the vision sensor 140.
In some embodiments, the ultrasonic sensor 130 may be configured to detect the obstacle 200 according to a received reflected ultrasonic signal, wherein the reflected ultrasonic signal is formed based on the transmitted ultrasonic signal sent by the ultrasonic sensor 130 being reflected by the obstacle 200, and the ultrasonic sensor 130 may include a piezoelectric ultrasonic sensor, a magnetostrictive ultrasonic sensor, and the like.
In some embodiments, the vision sensor 140 may be configured to acquire an image of an obstacle of the obstacle 200, and the vision sensor 140 may be a head camera mounted on a head of the vehicle, a tail camera mounted on a tail of the vehicle, a panoramic camera composed of a plurality of cameras mounted on the head of the vehicle and the side of the vehicle, or the like, where the type of the vision sensor 140 is not limited, and may be specifically set according to actual needs.
In some embodiments, the obstacles 200 may include stops, stone mounds, ice cream cones, ground locks, pedestrians, bicycles, electric vehicles, and the like.
Referring to fig. 2, a flowchart of a parking obstacle detection method according to an embodiment of the present application is shown. In a specific embodiment, the parking obstacle detection method may be applied to the control module 120 in the parking obstacle detection system shown in fig. 1, and the flow shown in fig. 2 will be described in detail by taking the control module 120 as an example, and the parking obstacle detection method may include the following steps S110 to S140.
Step S110: a first coordinate of the obstacle detected by the ultrasonic sensor is acquired.
In this embodiment of the application, the control module may send a first detection instruction to the ultrasonic sensor, the ultrasonic sensor receives and responds to the first detection instruction, may send a transmission ultrasonic signal, and receives a reflection ultrasonic signal formed after the transmission ultrasonic signal is reflected by an obstacle, and may determine a distance between the obstacle and the ultrasonic sensor according to a time length of receiving the reflection ultrasonic signal and a propagation speed of the ultrasonic wave in the air, and may determine a first coordinate of the obstacle according to the distance, and send the first coordinate to the control module, and the control module receives the first coordinate returned by the ultrasonic sensor. Wherein the origin of the first coordinate is the center of the vehicle.
It can be understood that, in order to determine an obstacle, the ultrasonic sensor needs to acquire at least two coordinate points corresponding to the outline of the obstacle, and therefore, the first coordinate may include a first sub-coordinate P1 (x 1, y 1) and a second sub-coordinate P2 (x 2, y 2), where x1 ≦ x2 and y1 ≦ y2.
Step S120: and acquiring a visual identification result corresponding to the obstacle image according to the obstacle image acquired by the visual sensor for the obstacle.
In the embodiment of the application, in order to avoid that the ultrasonic sensor is close to a short obstacle, the ultrasonic sensor is lost due to the fact that the ultrasonic signal is reflected, and the short obstacle cannot be detected, the control module can send a second detection instruction to the vision sensor, the vision sensor receives and responds to the second detection instruction, an obstacle image of the obstacle can be collected, and the obstacle image is sent to the control module, the control module receives and responds to the obstacle image, and a visual identification result corresponding to the obstacle image is obtained. The visual recognition result at least includes the second coordinate, a confidence level, and the like, and the confidence level may be used to indicate a confidence level of the obstacle detected by the visual sensor.
Specifically, the control module can send a second detection instruction to the vision sensor, the vision sensor receives and responds to the second detection instruction, an obstacle image of an obstacle can be collected, the obstacle image is sent to the control module, the control module receives and responds to the obstacle image, the obstacle image is input to a deep learning network model trained in advance, the deep learning network model receives and responds to the obstacle image, a second coordinate and a confidence coefficient corresponding to the obstacle image are output to the control module, and the control module receives the second coordinate and the confidence coefficient output by the deep learning network model.
The Deep learning network model may be a Convolutional Neural Network (CNN) model, a Deep Belief Network (DBN) model, a Stacked Auto Encoder network (SAE) model, a Recurrent Neural Network (RNN) model, a Deep Neural Network (DNN) model, a Long Short Term Memory (Long Short Term Memory, LSTM) network model, or a threshold recycling unit (Gated recycling Units, GRU) model, and the like, where the type of the Deep learning network model is not limited, and may be specifically set according to actual requirements.
It can be understood that, in order to determine an obstacle, the vision sensor needs to acquire at least two coordinate points corresponding to the obstacle, and therefore, the second coordinate may include a third sub-coordinate P3 (x 3, y 3) and a fourth sub-coordinate P4 (x 4, y 4), where x3 ≦ x4 and y3 ≦ y4.
Step S130: when the confidence is determined to be greater than or equal to the confidence threshold, determining whether the first virtual obstacle indicated by the first coordinate is included in the second virtual obstacle indicated by the second coordinate.
In this embodiment of the application, in order to avoid that the detection accuracy of the obstacle detection is low due to the fact that the visual recognition result with the low confidence level is fused with the first coordinate, the control module may determine, according to the first coordinate and the second coordinate, whether the first virtual obstacle indicated by the first coordinate is included in the second virtual obstacle indicated by the second coordinate when determining that the confidence level is greater than or equal to the confidence level threshold, so that the detection accuracy of the obstacle may be improved.
In some embodiments, the control module may determine whether a first coordinate range corresponding to the first coordinate is in a second coordinate range corresponding to the second coordinate when the confidence is determined to be greater than or equal to the confidence threshold, and may determine whether the first virtual obstacle indicated by the first coordinate is included in the second virtual obstacle indicated by the second coordinate according to whether the first coordinate range is in the second coordinate range.
When the first coordinate range is determined to be in the second coordinate range, determining that the first virtual obstacle indicated by the first coordinate is included in the second virtual obstacle indicated by the second coordinate; when the first coordinate range is determined to be beyond the second coordinate range, it is determined that the first virtual obstacle indicated by the first coordinate is not included in the second virtual obstacle indicated by the second coordinate.
As an embodiment, the first coordinate may include a first sub-coordinate P1 (x 1, y 1) and a second sub-coordinate P2 (x 2, y 2), the second coordinate may include a third sub-coordinate P3 (x 3, y 3) and a fourth sub-coordinate P4 (x 4, y 4), and the control module may determine whether the first coordinate range is in the second coordinate range according to the first sub-coordinate P1 (x 1, y 1), the second sub-coordinate P2 (x 2, y 2), the third sub-coordinate P3 (x 3, y 3) and the fourth sub-coordinate P4 (x 4, y 4) when determining that the confidence is greater than or the confidence threshold.
If x1 is larger than or equal to x3, y1 is larger than or equal to y3, x2 is smaller than or equal to x4, and y2 is smaller than or equal to y4, determining that the first coordinate range is in the second coordinate range; if not, determining that the first coordinate range is not in the second coordinate range.
In some embodiments, when the control module determines that the confidence is greater than or equal to the confidence threshold value within the preset time period, it may be determined whether a first coordinate range corresponding to the first coordinate is in a second coordinate range corresponding to the second coordinate, and it may be determined whether the first virtual obstacle indicated by the first coordinate is included in a second virtual obstacle indicated by the second coordinate according to whether the first coordinate range is in the second coordinate range, so as to further improve the detection accuracy of the obstacle.
Step S140: when it is determined that the first virtual obstacle is included in the second virtual obstacle, the first coordinates are determined as target coordinates of the obstacle, and the target coordinates are output.
In the embodiment of the application, when the control module determines that the first virtual obstacle is included in the second virtual obstacle, the first coordinate of the obstacle detected by the ultrasonic sensor can be determined as the target coordinate, and the target coordinate is output, so that the result of the obstacle detection by combining the ultrasonic sensor and the visual sensor is realized, the coordinate of the obstacle is obtained, the condition that the ultrasonic sensor cannot detect the approaching short obstacle can be avoided, and the obstacle detection accuracy is improved.
In some embodiments, the number of the visual recognition results may be multiple, and each visual recognition result may include a corresponding one of the second coordinates and one of the confidence levels. The control module can obtain a first coordinate of the obstacle detection by the ultrasonic sensor, obtain a plurality of visual recognition results corresponding to the obstacle image according to the obstacle image acquired by the visual sensor for the obstacle, arrange a plurality of confidence degrees in a sequence from low to high, and use a second coordinate corresponding to the highest confidence degree as a current coordinate.
According to the scheme provided by the application, the first coordinate of the obstacle detection by the ultrasonic sensor is obtained, the visual recognition result corresponding to the obstacle image is obtained according to the obstacle image acquired by the visual sensor for the obstacle, the visual recognition result at least comprises the second coordinate and the confidence coefficient, when the confidence coefficient is determined to be larger than or equal to the confidence coefficient threshold value, whether the first virtual obstacle indicated by the first coordinate is contained in the second virtual obstacle indicated by the second coordinate or not is determined, when the first virtual obstacle is determined to be contained in the second virtual obstacle, the first coordinate is determined as the target coordinate of the obstacle, the target coordinate is output, the obstacle detection result of the ultrasonic sensor and the visual sensor is fused, the obstacle coordinate is obtained, the situation that the ultrasonic sensor cannot detect a short and close obstacle can be avoided, and the obstacle detection accuracy is improved.
Furthermore, the visual recognition result with the confidence coefficient greater than or equal to the confidence coefficient threshold value is fused with the ultrasonic detection result to obtain the coordinates of the obstacle, so that the low detection accuracy of the obstacle detection caused by the fusion of the visual recognition result with the low confidence coefficient and the first coordinate can be avoided, and the detection accuracy of the obstacle detection is further improved.
Referring to fig. 3, a flowchart of a parking obstacle detection method according to another embodiment of the present application is shown. In a specific embodiment, the parking obstacle detection method may be applied to the control module 120 in the parking obstacle detection system shown in fig. 1, and the flow shown in fig. 3 will be described in detail below by taking the control module 120 as an example, and the parking obstacle detection method may include the following steps S210 to S260.
Step S210: a first coordinate of the obstacle detected by the ultrasonic sensor is acquired.
Step S220: and acquiring a visual identification result corresponding to the obstacle image according to the obstacle image acquired by the visual sensor on the obstacle.
In this embodiment, step S210 and step S220 may refer to the content of the corresponding steps in the foregoing embodiments, and are not described herein again.
Step S230: when it is determined that the confidence is greater than or equal to the confidence threshold, it is determined whether the height of the second virtual obstacle is less than or equal to the height threshold.
In the embodiment of the application, when the ultrasonic sensor and the visual sensor are used for detecting the obstacle, the height of the obstacle needs to meet the height threshold value when the ultrasonic signal is lost, otherwise, the obstacle can be detected only by using the ultrasonic sensor. Accordingly, the control module may determine whether the height of the second virtual obstacle is less than or equal to the height threshold when it is determined that the confidence is greater than or equal to the confidence threshold.
Specifically, the control module calculates a height difference between the height of the second virtual obstacle and the height threshold, and may determine whether the height of the second virtual obstacle is less than or equal to the height threshold based on the height difference. When the height difference is less than or equal to zero, determining that the height of the second virtual obstacle is less than or equal to a height threshold; when the height difference is greater than zero, then it is determined that the height of the second virtual obstacle is greater than the height threshold.
Step S240: when the height of the second virtual obstacle is determined to be smaller than or equal to the height threshold, whether a first coordinate range corresponding to the first coordinate is in a second coordinate range corresponding to the second coordinate is determined.
Step S250: when the first coordinate range is determined to be in the second coordinate range, it is determined that the first virtual obstacle indicated by the first coordinate is included in the second virtual obstacle indicated by the second coordinate.
Step S260: when it is determined that the first virtual obstacle is included in the second virtual obstacle, the first coordinates are determined as target coordinates of the obstacle, and the target coordinates are output.
In the embodiment, the steps S240, S250 and S260 may refer to the content of the corresponding steps in the foregoing embodiment, and are not described herein again.
According to the scheme provided by the embodiment, the first coordinate of the obstacle detection by the ultrasonic sensor is obtained, the visual recognition result corresponding to the obstacle image is obtained according to the obstacle image acquired by the visual sensor for the obstacle, the visual recognition result at least comprises the second coordinate and the confidence coefficient, when the confidence coefficient is determined to be greater than or equal to the confidence coefficient threshold value, whether the height of the second virtual obstacle is smaller than or equal to the height threshold value is determined, when the height of the second virtual obstacle is determined to be smaller than or equal to the height threshold value, whether the first virtual obstacle indicated by the first coordinate is included in the second virtual obstacle indicated by the second coordinate is determined, when the first virtual obstacle is determined to be included in the second virtual obstacle, the first coordinate is determined to be the target coordinate of the obstacle, the target coordinate is output, the result of the obstacle detection by fusing the ultrasonic sensor and the visual sensor is obtained, the coordinate of the obstacle can be avoided that the ultrasonic sensor cannot detect a low obstacle, and the detection accuracy of the obstacle detection is improved.
Referring to fig. 4, a flowchart of a parking obstacle detection method according to still another embodiment of the present application is shown. In a specific embodiment, the parking obstacle detection method may be applied to the control module 120 in the parking obstacle detection system shown in fig. 1, and the flow shown in fig. 4 will be described in detail below by taking the control module 120 as an example, and the parking obstacle detection method may include the following steps S310 to S370.
Step S310: a first coordinate of the obstacle detected by the ultrasonic sensor is acquired.
Step S320: and acquiring a visual identification result corresponding to the obstacle image according to the obstacle image acquired by the visual sensor on the obstacle.
Step S330: when the confidence is determined to be greater than or equal to the confidence threshold, it is determined whether the first virtual obstacle indicated by the first coordinate is included in the second virtual obstacle indicated by the second coordinate.
Step S340: when it is determined that the first virtual obstacle is included in the second virtual obstacle, the first coordinates are determined as target coordinates of the obstacle, and the target coordinates are output.
In this embodiment, the steps S310, S320, S330 and S340 may refer to the content of the corresponding steps in the foregoing embodiments, and are not described herein again.
Step S350: and determining the relative position of the vehicle and the obstacle according to the target coordinates.
In this embodiment, the control module may determine the relative position of the vehicle and the obstacle based on the target coordinates after determining the first coordinates as the target coordinates of the obstacle and outputting the target coordinates. The relative position may include a relative distance, a relative angle, and the like.
In some embodiments, the control module may acquire driving state information of the vehicle after determining the first coordinate as a target coordinate of the obstacle and outputting the target coordinate, and may determine a relative distance and a relative angle of the vehicle from the obstacle based on the driving state information and the target coordinate. The driving state information may be at least one of shift position information (e.g., a forward (D) position, a reverse (R) position, and the like), speed information, steering angle information (steering wheel angle), and the like.
Step S360: and determining the target parking position of the vehicle according to the relative position.
In the embodiment, after the control module determines the relative position of the vehicle and the obstacle according to the target coordinate, the control module may determine the target parking position of the vehicle according to the relative position, so that the parking position of the vehicle is planned according to the detected coordinate of the obstacle, the collision between the vehicle and the obstacle in the automatic parking process can be avoided, and the safety of automatic parking is improved.
In some embodiments, the control module may determine a travel track of the vehicle based on the travel state information after determining the relative position of the vehicle and the obstacle based on the travel state information and the target coordinates, may determine whether the obstacle is within the travel track of the vehicle based on the target position and the travel track of the vehicle, and may determine the target parking position of the vehicle based on the travel track and the relative position when determining that the obstacle is within the travel track of the vehicle.
Step S370: and controlling the vehicle to park to the target parking position.
In the embodiment, after the control module determines the target parking position of the vehicle according to the relative position, the control module can control the vehicle to park to the target parking position, so that the vehicle can be prevented from colliding with an obstacle in the automatic parking process, and the safety of automatic parking is improved.
According to the scheme provided by the embodiment, the relative position of the vehicle and the obstacle is determined according to the target coordinate, the target parking position of the vehicle is determined according to the relative position, and the vehicle is controlled to park to the target parking position, so that the parking position of the vehicle is planned according to the detected coordinate of the obstacle, the vehicle and the obstacle can be prevented from colliding in the automatic parking process, and the safety of automatic parking is improved.
Referring to fig. 5, which illustrates a parking obstacle detection apparatus 500 according to an embodiment of the present application, the parking obstacle detection apparatus 500 may be applied to the control module 120 in the parking obstacle detection system shown in fig. 1, and the parking obstacle detection apparatus 500 shown in fig. 5 will be described in detail below by taking the control module 120 as an example, and the parking obstacle detection apparatus 500 may include a first obtaining module 510, a second obtaining module 520, a first determining module 530, and a second determining module 540.
The first acquiring module 510 may be configured to acquire a first coordinate of the obstacle detection by the ultrasonic sensor; the second obtaining module 520 may be configured to obtain a visual recognition result corresponding to the obstacle image according to the obstacle image acquired by the visual sensor for the obstacle, where the visual recognition result at least includes a second coordinate and a confidence level; the first determining module 530 may be configured to determine whether the first virtual obstacle indicated by the first coordinate is included in the second virtual obstacle indicated by the second coordinate when the confidence is determined to be greater than or equal to the confidence threshold; the second determining module 540 may be configured to determine the first coordinates as target coordinates of the obstacle and output the target coordinates when it is determined that the first virtual obstacle is included in the second virtual obstacle.
In some embodiments, the second obtaining module 520 may include a obtaining unit and an input unit.
The acquisition unit can be used for acquiring an image of the obstacle acquired by the vision sensor; the input unit may be configured to input the obstacle image into a deep learning network model trained in advance, and obtain a second coordinate and a confidence degree corresponding to the obstacle image output by the deep learning network model.
In some embodiments, the first determining module 530 may include a first determining unit and a second determining unit.
The first determining unit may be configured to determine whether a first coordinate range corresponding to the first coordinate is in a second coordinate range corresponding to the second coordinate when it is determined that the confidence is greater than or equal to the confidence threshold; the second determination unit may be configured to determine that the first virtual obstacle indicated by the first coordinate is included in the second virtual obstacle indicated by the second coordinate when it is determined that the first coordinate range is in the second coordinate range.
In some embodiments, the first coordinate includes a first sub-coordinate P1 (x 1, y 1) and a second sub-coordinate P2 (x 2, y 2), x1 ≦ x2, y1 ≦ y2; the second coordinate comprises a third sub-coordinate P3 (x 3, y 3) and a fourth sub-coordinate P4 (x 4, y 4), x3 is less than or equal to x4, and y3 is less than or equal to y4. The first determination unit may include a first determination subunit and a second determination subunit.
The first determining subunit may be configured to, when it is determined that the confidence is greater than or equal to the confidence threshold, determine whether a first coordinate range corresponding to the first coordinate is in a second coordinate range corresponding to the second coordinate according to the first sub-coordinate P1 (x 1, y 1), the second sub-coordinate P2 (x 2, y 2), the third sub-coordinate P3 (x 3, y 3), and the fourth sub-coordinate P4 (x 4, y 4); the second determining subunit may be configured to determine that the first coordinate range is in the second coordinate range when x1 is greater than or equal to x3, y1 is greater than or equal to y3, x2 is less than or equal to x4, and y2 is less than or equal to y4.
In some embodiments, the parking obstacle detection apparatus 500 may further include a third determination module.
The third determination module may be configured to determine whether the height of the second virtual obstacle is less than or equal to the height threshold before the first determination unit determines whether the first coordinate range corresponding to the first coordinate is in the second coordinate range corresponding to the second coordinate.
In some embodiments, the first determination unit may further include a third determination subunit.
The third determining subunit may be configured to determine, when it is determined that the height of the second virtual obstacle is less than or equal to the height threshold, whether the first coordinate range corresponding to the first coordinate is in a second coordinate range corresponding to the second coordinate.
In some embodiments, the number of the visual recognition results is plural, and the parking obstacle detection apparatus 500 may further include a sorting module and a fourth determination module.
The sorting module may be configured to arrange the plurality of confidences in order from low to high before the first determining module 530 determines whether the first virtual obstacle indicated by the first coordinate is included in the second virtual obstacle indicated by the second coordinate; the fourth determining module may be configured to use the second coordinate corresponding to the highest confidence as the current coordinate.
In some embodiments, the first determining module 530 may further include a third determining unit.
The third determination unit may be configured to determine whether the first virtual obstacle indicated by the first coordinate is included in the current virtual obstacle indicated by the current coordinate.
In some embodiments, the second determining module 540 may include a fourth determining unit.
The fourth determination unit may be configured to determine the first coordinate as a target coordinate of the obstacle and output the target coordinate when it is determined that the first virtual obstacle is included in the current virtual obstacle.
In some embodiments, the parking obstacle detection apparatus 500 may further include a fifth determination module, a sixth determination module, and a control module.
The fifth determining module may be configured to determine, by the second determining module 540, after determining that the first virtual obstacle is included in the second virtual obstacle, the first coordinate as a target coordinate of the obstacle and outputting the target coordinate, determine a relative position of the vehicle and the obstacle according to the target coordinate, where the relative position includes a relative distance and a relative angle; the sixth determining module may be configured to determine a target parking position of the vehicle according to the relative position; the control module may be configured to control parking of the vehicle to the target parking location.
In some embodiments, the parking obstacle detection apparatus 500 may further include a third obtaining module.
The third obtaining module may be configured to obtain the driving state information of the vehicle before the fifth determining module determines the relative position of the vehicle and the obstacle according to the target coordinates, where the driving state information includes gear information, speed information, and steering angle information.
In some embodiments, the fifth determination module may include a fifth determination unit.
The fifth determination unit may be configured to determine a relative distance and a relative angle of the vehicle and the obstacle, based on the driving state information and the target coordinates.
In some embodiments, the parking obstacle detection apparatus 500 may further include a seventh determination module and an eighth determination module.
The seventh determining module may be configured to determine the driving trajectory of the vehicle according to the driving state information before the sixth determining module determines the target parking location of the vehicle according to the relative location; the eighth determination module may be configured to determine whether an obstacle is within a travel trajectory of the vehicle.
In some embodiments, the sixth determination module may include a sixth determination unit.
The sixth determination unit may be configured to determine the target parking position of the vehicle based on the travel trajectory and the relative position when it is determined that the obstacle is within the travel trajectory of the vehicle.
According to the scheme provided by the application, the first coordinate of the obstacle detection by the ultrasonic sensor is obtained, the visual recognition result corresponding to the obstacle image is obtained according to the obstacle image acquired by the visual sensor for the obstacle, the visual recognition result at least comprises the second coordinate and the confidence coefficient, when the confidence coefficient is determined to be larger than or equal to the confidence coefficient threshold value, whether the first virtual obstacle indicated by the first coordinate is contained in the second virtual obstacle indicated by the second coordinate or not is determined, when the first virtual obstacle is determined to be contained in the second virtual obstacle, the first coordinate is determined as the target coordinate of the obstacle, the target coordinate is output, the obstacle detection result of the ultrasonic sensor and the visual sensor is fused, the obstacle coordinate is obtained, the situation that the ultrasonic sensor cannot detect a short and close obstacle can be avoided, and the obstacle detection accuracy is improved.
Furthermore, the visual recognition result with the confidence coefficient greater than or equal to the confidence coefficient threshold value is fused with the ultrasonic detection result to obtain the coordinates of the obstacle, so that the low detection accuracy of the obstacle detection caused by the fusion of the visual recognition result with the low confidence coefficient and the first coordinate can be avoided, and the detection accuracy of the obstacle detection is further improved.
It should be noted that, in the present specification, the embodiments are all described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments may be referred to each other. For the device-like embodiment, since it is basically similar to the method embodiment, the description is simple, and reference may be made to the partial description of the method embodiment for relevant points. For any processing manner described in the method embodiment, all the processing manners may be implemented by corresponding processing modules in the apparatus embodiment, and details in the apparatus embodiment are not described again.
In addition, functional modules in the embodiments of the present application may be integrated into one processing module, or each of the modules may exist alone physically, or two or more modules are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode.
Referring to fig. 6, which shows a functional block diagram of a vehicle 600 provided by another embodiment of the present application, the vehicle 600 may include one or more of the following components: memory 610, processor 620, and one or more applications, wherein the one or more applications may be stored in memory 610 and configured to be executed by the one or more processors 620, the one or more applications configured to perform a method as described in the aforementioned method embodiments.
The Memory 610 may include a Random Access Memory (RAM) or a Read-Only Memory (Read-Only Memory). The memory 610 may be used to store instructions, programs, code, sets of codes, or sets of instructions. The memory 610 may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing an operating system, instructions for implementing at least one function (e.g., obtaining first coordinates, obtaining visual recognition results, determining that a confidence is greater than or equal to a confidence threshold, determining that a first virtual obstacle is included in a second virtual obstacle, determining target coordinates, outputting target coordinates, obtaining an obstacle image, inputting an obstacle image to a deep learning network model, detecting coordinates of an obstacle image, detecting confidence in an obstacle image, obtaining second coordinates, obtaining a confidence, recording second coordinates, recording confidence, determining a coordinate range, determining whether a height is less than or equal to a height threshold, ranking confidence, determining current coordinates, determining relative positions, determining target parking positions, controlling vehicle parking, obtaining travel status information, determining relative distances, determining relative angles, determining travel trajectories, and determining whether an obstacle is within a travel trajectory, etc.), instructions for implementing various method embodiments described below, and the like. The storage data area may also store data created by the vehicle 600 in use (such as first coordinates, obstacle images, visual recognition results, second coordinates, confidence degrees, confidence degree thresholds, first virtual obstacles, second virtual obstacles, target coordinates, deep learning network models, a first coordinate range, a second coordinate range, first sub-coordinates, second sub-coordinates, third sub-coordinates, fourth sub-coordinates, heights of obstacles, height thresholds, current coordinates, relative positions, relative distances, relative angles, target parking positions, driving state information, gear position information, speed information, steering angle information, and driving trajectories), and the like.
Referring to fig. 7, a block diagram of a computer-readable storage medium according to an embodiment of the present application is shown. The computer readable storage medium 700 has stored therein a program code 710, the program code 710 being capable of being invoked by a processor to perform the methods described in the method embodiments above.
The computer-readable storage medium 700 may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read only memory), an EPROM, a hard disk, or a ROM. Optionally, the computer-readable storage medium 700 includes a non-volatile computer-readable storage medium. The computer readable storage medium 700 has storage space for program code 710 to perform any of the method steps of the method described above. The program code can be read from or written to one or more computer program products. The program code 710 may be compressed, for example, in a suitable form.
According to the scheme provided by the application, the first coordinate of the obstacle detection by the ultrasonic sensor is obtained, the visual recognition result corresponding to the obstacle image is obtained according to the obstacle image acquired by the visual sensor for the obstacle, the visual recognition result at least comprises the second coordinate and the confidence coefficient, when the confidence coefficient is determined to be larger than or equal to the confidence coefficient threshold value, whether the first virtual obstacle indicated by the first coordinate is contained in the second virtual obstacle indicated by the second coordinate or not is determined, when the first virtual obstacle is determined to be contained in the second virtual obstacle, the first coordinate is determined as the target coordinate of the obstacle, the target coordinate is output, the obstacle detection result of the ultrasonic sensor and the visual sensor is fused, the obstacle coordinate is obtained, the situation that the ultrasonic sensor cannot detect a short and close obstacle can be avoided, and the obstacle detection accuracy is improved.
Furthermore, the visual recognition result with the confidence coefficient greater than or equal to the confidence coefficient threshold value is fused with the ultrasonic detection result to obtain the coordinates of the obstacle, so that the low detection accuracy of the obstacle detection caused by the fusion of the visual recognition result with the low confidence coefficient and the first coordinate can be avoided, and the detection accuracy of the obstacle detection is further improved.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not necessarily depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.
Claims (12)
1. A parking obstacle detection method characterized by comprising:
acquiring a first coordinate of the obstacle detection of the ultrasonic sensor;
acquiring a visual recognition result corresponding to the obstacle image according to the obstacle image acquired by the visual sensor for the obstacle, wherein the visual recognition result at least comprises a second coordinate and a confidence coefficient;
when the confidence is determined to be larger than or equal to a confidence threshold value, determining whether a first virtual obstacle indicated by the first coordinate is included in a second virtual obstacle indicated by the second coordinate;
when it is determined that the first virtual obstacle is included in the second virtual obstacle, the first coordinate is determined as a target coordinate of the obstacle, and the target coordinate is output.
2. The method for detecting a parking obstacle according to claim 1, wherein the obtaining a visual recognition result corresponding to the obstacle image based on the obstacle image captured by the visual sensor for the obstacle, the visual recognition result including at least a second coordinate and a confidence level includes:
acquiring an obstacle image acquired by a vision sensor;
and inputting the obstacle image into a pre-trained deep learning network model, and obtaining a second coordinate and a confidence coefficient corresponding to the obstacle image output by the deep learning network model.
3. The parking obstacle detection method according to claim 1, wherein the determining whether a first virtual obstacle indicated by the first coordinate is included in a second virtual obstacle indicated by the second coordinate when it is determined that the confidence is greater than or equal to a confidence threshold value includes:
when the confidence coefficient is determined to be larger than or equal to a confidence coefficient threshold value, determining whether a first coordinate range corresponding to the first coordinate is in a second coordinate range corresponding to the second coordinate;
when it is determined that the first coordinate range is in the second coordinate range, it is determined that a first virtual obstacle indicated by the first coordinate is included in a second virtual obstacle indicated by the second coordinate.
4. The parking obstacle detection method according to claim 3, wherein the first coordinates include a first sub-coordinate P1 (x 1, y 1) and a second sub-coordinate P2 (x 2, y 2), x1 ≦ x2, y1 ≦ y2; the second coordinates comprise a third sub-coordinate P3 (x 3, y 3) and a fourth sub-coordinate P4 (x 4, y 4), wherein x3 is less than or equal to x4, and y3 is less than or equal to y4;
when it is determined that the confidence is greater than or equal to a confidence threshold, determining whether a first coordinate range corresponding to the first coordinate is in a second coordinate range corresponding to the second coordinate, including:
when the confidence coefficient is determined to be greater than or equal to a confidence coefficient threshold value, determining whether a first coordinate range corresponding to the first coordinate is in a second coordinate range corresponding to the second coordinate according to the first sub-coordinate P1 (x 1, y 1), the second sub-coordinate P2 (x 2, y 2), the third sub-coordinate P3 (x 3, y 3) and the fourth sub-coordinate P4 (x 4, y 4);
and when x1 is larger than or equal to x3, y1 is larger than or equal to y3, x2 is smaller than or equal to x4, and y2 is smaller than or equal to y4, determining that the first coordinate range is in the second coordinate range.
5. The parking obstacle detection method according to claim 3, wherein before the determining whether a first coordinate range corresponding to the first coordinate is in a second coordinate range corresponding to the second coordinate, the parking obstacle detection method further comprises:
determining whether a height of the second virtual obstacle is less than or equal to a height threshold;
the determining whether the first coordinate range corresponding to the first coordinate is in the second coordinate range corresponding to the second coordinate includes:
when the height of the second virtual obstacle is determined to be smaller than or equal to a height threshold, determining whether a first coordinate range corresponding to the first coordinate is in a second coordinate range corresponding to the second coordinate.
6. The parking obstacle detection method according to claim 1, wherein the visual recognition result is plural, and before the determination as to whether the first virtual obstacle indicated by the first coordinate is included in the second virtual obstacle indicated by the second coordinate, the parking obstacle detection method further comprises:
arranging the confidence degrees in a sequence from low to high;
taking the second coordinate corresponding to the highest confidence coefficient as the current coordinate;
the determining whether a first virtual obstacle indicated by the first coordinate is included in a second virtual obstacle indicated by the second coordinate comprises:
determining whether a first virtual obstacle indicated by the first coordinate is included in a current virtual obstacle indicated by the current coordinate;
the determining the first coordinate as a target coordinate of the obstacle and outputting the target coordinate when it is determined that the first virtual obstacle is included in the second virtual obstacle, includes:
when it is determined that the first virtual obstacle is included in the current virtual obstacle, determining the first coordinate as a target coordinate of the obstacle, and outputting the target coordinate.
7. The parking obstacle detection method according to any one of claims 1 to 6, further comprising, after determining the first coordinate as a target coordinate of the obstacle and outputting the target coordinate when it is determined that the first virtual obstacle is included in the second virtual obstacle:
determining the relative position of the vehicle and the obstacle according to the target coordinates, wherein the relative position comprises a relative distance and a relative angle;
determining a target parking position of the vehicle according to the relative position;
and controlling the vehicle to park to the target parking position.
8. The parking obstacle detection method according to claim 7, further comprising, before the determining the relative position of the vehicle and the obstacle based on the target coordinates, the parking obstacle detection method:
acquiring running state information of the vehicle, wherein the running state information comprises gear information, speed information and steering angle information;
the determining the relative position of the vehicle and the obstacle according to the target coordinates comprises:
and determining the relative distance and the relative angle between the vehicle and the obstacle according to the running state information and the target coordinates.
9. The parking obstacle detection method according to claim 8, further comprising, before the determining a target parking position of the vehicle based on the relative position, the parking obstacle detection method:
determining a driving track of the vehicle according to the driving state information;
determining whether the obstacle is within a driving trajectory of the vehicle;
determining a target parking position of the vehicle according to the relative position comprises:
and when the obstacle is determined to be in the driving track of the vehicle, determining the target parking position of the vehicle according to the driving track and the relative position.
10. A parking obstacle detection device characterized by comprising:
the first acquisition module is used for acquiring a first coordinate of the obstacle detection of the ultrasonic sensor;
the second acquisition module is used for acquiring a visual recognition result corresponding to the obstacle image according to the obstacle image acquired by the visual sensor for the obstacle, and the visual recognition result at least comprises a second coordinate and a confidence coefficient;
a first determining module, configured to determine whether a first virtual obstacle indicated by the first coordinate is included in a second virtual obstacle indicated by the second coordinate when it is determined that the confidence is greater than or equal to a confidence threshold;
and the second determination module is used for determining the first coordinate as a target coordinate of the obstacle and outputting the target coordinate when the first virtual obstacle is determined to be included in the second virtual obstacle.
11. A vehicle, characterized by comprising:
a memory;
one or more processors coupled with the memory;
one or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by one or more processors, the one or more application programs being configured to perform the parking obstacle detection method according to any one of claims 1 to 9.
12. A computer-readable storage medium, characterized in that a program code is stored therein, the program code being invokable by a processor to execute the parking obstacle detection method according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210134702.3A CN115223133A (en) | 2022-02-14 | 2022-02-14 | Parking obstacle detection method, parking obstacle detection device, vehicle, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210134702.3A CN115223133A (en) | 2022-02-14 | 2022-02-14 | Parking obstacle detection method, parking obstacle detection device, vehicle, and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115223133A true CN115223133A (en) | 2022-10-21 |
Family
ID=83606784
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210134702.3A Pending CN115223133A (en) | 2022-02-14 | 2022-02-14 | Parking obstacle detection method, parking obstacle detection device, vehicle, and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115223133A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117048596A (en) * | 2023-08-04 | 2023-11-14 | 广州汽车集团股份有限公司 | Method, device, vehicle and storage medium for avoiding obstacle |
| CN117048596B (en) * | 2023-08-04 | 2024-05-10 | 广州汽车集团股份有限公司 | Method, device, vehicle and storage medium for avoiding obstacle |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20150051426A (en) * | 2013-11-04 | 2015-05-13 | 현대모비스 주식회사 | Obstacle Site Indication Controlling System and the Method of |
| CN109572693A (en) * | 2019-01-24 | 2019-04-05 | 湖北亿咖通科技有限公司 | Vehicle obstacle-avoidance householder method, system and vehicle |
| CN111137283A (en) * | 2019-12-27 | 2020-05-12 | 奇瑞汽车股份有限公司 | Sensor data fusion method and device, advanced driving assistance system and vehicle |
| CN111731272A (en) * | 2020-06-17 | 2020-10-02 | 重庆长安汽车股份有限公司 | Obstacle collision avoidance method based on automatic parking system |
| CN112002125A (en) * | 2020-08-10 | 2020-11-27 | 广州汽车集团股份有限公司 | Vertical parking space fusion identification method and system |
| CN112084810A (en) * | 2019-06-12 | 2020-12-15 | 杭州海康威视数字技术股份有限公司 | Obstacle detection method and device, electronic equipment and storage medium |
| CN112651359A (en) * | 2020-12-30 | 2021-04-13 | 深兰科技（上海）有限公司 | Obstacle detection method, obstacle detection device, electronic apparatus, and storage medium |
| CN112776797A (en) * | 2021-02-27 | 2021-05-11 | 重庆长安汽车股份有限公司 | Original parking space parking establishment method and system, vehicle and storage medium |
| CN112799098A (en) * | 2020-12-08 | 2021-05-14 | 深兰科技（上海）有限公司 | Radar blind area monitoring method and device, electronic equipment and storage medium |
| CN113156421A (en) * | 2021-04-07 | 2021-07-23 | 南京邮电大学 | Obstacle detection method based on information fusion of millimeter wave radar and camera |
| CN113428137A (en) * | 2021-08-06 | 2021-09-24 | 浙江吉利控股集团有限公司 | Parking control method and device and storage medium |
-
2022
- 2022-02-14 CN CN202210134702.3A patent/CN115223133A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20150051426A (en) * | 2013-11-04 | 2015-05-13 | 현대모비스 주식회사 | Obstacle Site Indication Controlling System and the Method of |
| CN109572693A (en) * | 2019-01-24 | 2019-04-05 | 湖北亿咖通科技有限公司 | Vehicle obstacle-avoidance householder method, system and vehicle |
| CN112084810A (en) * | 2019-06-12 | 2020-12-15 | 杭州海康威视数字技术股份有限公司 | Obstacle detection method and device, electronic equipment and storage medium |
| CN111137283A (en) * | 2019-12-27 | 2020-05-12 | 奇瑞汽车股份有限公司 | Sensor data fusion method and device, advanced driving assistance system and vehicle |
| CN111731272A (en) * | 2020-06-17 | 2020-10-02 | 重庆长安汽车股份有限公司 | Obstacle collision avoidance method based on automatic parking system |
| CN112002125A (en) * | 2020-08-10 | 2020-11-27 | 广州汽车集团股份有限公司 | Vertical parking space fusion identification method and system |
| CN112799098A (en) * | 2020-12-08 | 2021-05-14 | 深兰科技（上海）有限公司 | Radar blind area monitoring method and device, electronic equipment and storage medium |
| CN112651359A (en) * | 2020-12-30 | 2021-04-13 | 深兰科技（上海）有限公司 | Obstacle detection method, obstacle detection device, electronic apparatus, and storage medium |
| CN112776797A (en) * | 2021-02-27 | 2021-05-11 | 重庆长安汽车股份有限公司 | Original parking space parking establishment method and system, vehicle and storage medium |
| CN113156421A (en) * | 2021-04-07 | 2021-07-23 | 南京邮电大学 | Obstacle detection method based on information fusion of millimeter wave radar and camera |
| CN113428137A (en) * | 2021-08-06 | 2021-09-24 | 浙江吉利控股集团有限公司 | Parking control method and device and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| SHIDIAN MA 等: "Parking Space and Obstacle Detection Based on a Vision Sensor and Checkerboard Grid Laser", 《APPLIED SCIENCES》, pages 1 - 17 * |
| 王中立;牛颖;: "基于多传感器信息融合的机器人障碍物检测", 《中国测试》, vol. 43, no. 08, pages 80 - 85 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117048596A (en) * | 2023-08-04 | 2023-11-14 | 广州汽车集团股份有限公司 | Method, device, vehicle and storage medium for avoiding obstacle |
| CN117048596B (en) * | 2023-08-04 | 2024-05-10 | 广州汽车集团股份有限公司 | Method, device, vehicle and storage medium for avoiding obstacle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112329552B (en) | Obstacle detection method and device based on automobile | |
| CN110325818B (en) | Joint 3D object detection and orientation estimation via multimodal fusion | |
| US11155259B2 (en) | System and method for egocentric-vision based future vehicle localization | |
| CN110488319B (en) | Ultrasonic wave and camera fusion-based collision distance calculation method and system | |
| CN109712427B (en) | Parking space detection method and device | |
| CN113267199B (en) | Method and device for planning driving track | |
| CN111507157A (en) | Method and device for optimizing resource allocation during automatic driving based on reinforcement learning | |
| JP6544594B2 (en) | INFORMATION PROCESSING SYSTEM, INFORMATION PROCESSING METHOD, PROGRAM, AND VEHICLE | |
| CN114323054B (en) | Method and device for determining running track of automatic driving vehicle and electronic equipment | |
| CN115087573B (en) | Key target selection method, device and system | |
| CN106183979A (en) | A kind of method and apparatus vehicle reminded according to spacing | |
| CN114074681A (en) | Lane change decision and movement planning system and method based on probability | |
| JP6500984B2 (en) | Vehicle control apparatus and vehicle control method | |
| US11017245B2 (en) | Parking assist apparatus | |
| CN113561963A (en) | Parking method and device and vehicle | |
| CN110647801A (en) | Method and device for setting region of interest, storage medium and electronic equipment | |
| CN112009468A (en) | Multi-hypothesis object tracking for autonomous driving systems | |
| KR20210008260A (en) | Apparatus for controlling behavior of autonomous vehicle and method thereof | |
| US20210088650A1 (en) | Predicting the course of a road on the basis of radar data | |
| CN115223133A (en) | Parking obstacle detection method, parking obstacle detection device, vehicle, and storage medium | |
| KR101734726B1 (en) | Method of tracking parking space and apparatus performing the same | |
| CN115214626B (en) | Parking control method, parking control device, vehicle and storage medium | |
| KR20210005393A (en) | Apparatus for controlling u-turn of autonomous vehicle and method thereof | |
| CN113611008B (en) | Vehicle driving scene acquisition method, device, equipment and medium | |
| JP6996368B2 (en) | Server, obstacle recognition device |
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 |