CN-115657043-B - Parking space state identification method, device and equipment

CN115657043BCN 115657043 BCN115657043 BCN 115657043BCN-115657043-B

Abstract

The application provides a parking space state identification method, device and equipment, wherein the method comprises the steps of acquiring ultrasonic radar signals corresponding to a parking space to be identified through a radar; and identifying the ultrasonic radar signal feature vector by using a parking space state identification model to obtain the state of the parking space, wherein the state of the parking space comprises an idle state and a occupied state. By the method, the state of the parking space can be accurately identified under the condition that the traditional ultrasonic radar signal is weak to weak reflection object signals such as pedestrians and the like and the response to low obstacles is poor.

Inventors

MIAO QIHENG
XU WEI
SU WEI

Assignees

浙江华锐捷技术有限公司

Dates

Publication Date: 20260505
Application Date: 20221025

Claims (9)

1. A method for identifying a parking space state, the method comprising: collecting ultrasonic radar signals corresponding to a parking space to be identified through a radar; Performing feature construction of parking spaces to be identified based on the ultrasonic radar signals to obtain ultrasonic radar signal feature vectors corresponding to the parking spaces to be identified; Identifying the ultrasonic radar signal feature vector by using a parking space state identification model to obtain a parking space state, wherein the parking space state comprises an idle state and a occupied state; The parking space state recognition model is obtained by training based on a sample ultrasonic radar signal feature vector of a parking space and a first sample parking space state corresponding to the feature vector, and the first sample parking space state is determined based on a second sample parking space state corresponding to a sample vision signal associated with the sample ultrasonic radar signal; the first sample parking space state is determined by the following method: Aiming at a target parking space, acquiring a sample vision signal acquired by a camera at the same time and a sample ultrasonic radar signal acquired by a radar, wherein the sample vision signal comprises a plurality of frames of images, the images comprise at least one parking space, analyzing the sample vision signal, determining a second sample parking space state corresponding to the sample vision signal of the target parking space, and taking the second sample parking space state as a first sample parking space state corresponding to the sample ultrasonic radar signal associated with the sample vision signal.
2. The method of claim 1, wherein the analyzing the sample visual signal to determine a second sample parking space state corresponding to the sample visual signal of the target parking space comprises: analyzing the sample visual signal, and determining whether each frame of image of the sample visual signal contains the position information of the target parking space; And if the images of the continuous preset frame number in the sample visual signal all contain the position information of the target parking space, taking the sample visual signal as a visual signal corresponding to the target parking space, and taking the second sample parking space state corresponding to the visual signal as a sample parking space state corresponding to the target parking space.
3. The method of claim 2, wherein the sample ultrasonic radar signal associated with the sample vision signal is determined by: synchronizing the camera with a clock of the radar, and registering the camera with a coordinate system of the radar; And if the sample visual signal acquired by the camera is the same as the acquisition time of the sample ultrasonic radar signal acquired by the radar and the position information of the parking space contained in the sample visual signal is matched with the position information of the parking space contained in the sample ultrasonic radar signal, determining that the sample visual signal is related to the sample ultrasonic radar signal.
4. The method according to claim 1, wherein the performing feature construction of the parking space to be identified based on the ultrasonic radar signal to obtain an ultrasonic radar signal feature vector corresponding to the parking space to be identified, includes: performing feature construction based on ultrasonic radar signals of each unit area of the parking space to be identified to obtain ultrasonic radar signal feature vectors corresponding to each unit area; and combining the ultrasonic radar signal feature vectors corresponding to the unit areas to obtain the ultrasonic radar signal feature vector corresponding to the parking space to be identified.
5. The method according to claim 4, wherein the performing feature construction based on the ultrasonic radar signals of each unit area of the parking space to be identified to obtain the ultrasonic radar signal feature vector corresponding to each unit area comprises: And carrying out feature construction based on the position information of the vehicle to be parked at the current acquisition moment, the posture information of the vehicle to be parked and the ultrasonic radar signals corresponding to any one unit area of the parking space to be identified, and obtaining the ultrasonic radar signal feature vector corresponding to any one unit area of the parking space to be identified.
6. A parking space state identifying apparatus, characterized by comprising: the acquisition module is used for acquiring ultrasonic radar signals corresponding to the parking space to be identified through a radar; the construction module is used for carrying out feature construction of the parking space to be identified based on the ultrasonic radar signals to obtain ultrasonic radar signal feature vectors corresponding to the parking space to be identified; The identification module is used for identifying the ultrasonic radar signal feature vector by using a parking space state identification model to obtain a parking space state, wherein the parking space state comprises an idle state and a occupied state; The parking space state recognition model is obtained by training based on a sample ultrasonic radar signal feature vector of a parking space and a first sample parking space state corresponding to the feature vector, and the first sample parking space state is determined based on a second sample parking space state corresponding to a sample vision signal associated with the sample ultrasonic radar signal; the first sample parking space state is determined by the following method: Aiming at a target parking space, acquiring a sample vision signal acquired by a camera at the same time and a sample ultrasonic radar signal acquired by a radar, wherein the sample vision signal comprises a plurality of frames of images, the images comprise at least one parking space, analyzing the sample vision signal, determining a second sample parking space state corresponding to the sample vision signal of the target parking space, and taking the second sample parking space state as a first sample parking space state corresponding to the sample ultrasonic radar signal associated with the sample vision signal.
7. An automobile, the automobile comprising: The radar is used for collecting ultrasonic radar signals corresponding to the parking space to be identified and sending the ultrasonic radar signals to the electronic control unit; the camera is used for collecting sample visual signals of the parking space; the electronic control unit is used for receiving ultrasonic radar signals sent by the radar, and carrying out feature construction of parking spaces to be identified based on the ultrasonic radar signals to obtain ultrasonic radar signal feature vectors corresponding to the parking spaces to be identified; Identifying the ultrasonic radar signal feature vector by using a parking space state identification model to obtain a parking space state, wherein the parking space state comprises an idle state and a occupied state; The parking space state recognition model is obtained by training based on a sample ultrasonic radar signal feature vector of a parking space and a first sample parking space state corresponding to the feature vector, and the first sample parking space state is determined based on a second sample parking space state corresponding to a sample vision signal associated with the sample ultrasonic radar signal; the first sample parking space state is determined by the following method: Aiming at a target parking space, acquiring a sample vision signal acquired by a camera at the same time and a sample ultrasonic radar signal acquired by a radar, wherein the sample vision signal comprises a plurality of frames of images, the images comprise at least one parking space, analyzing the sample vision signal, determining a second sample parking space state corresponding to the sample vision signal of the target parking space, and taking the second sample parking space state as a first sample parking space state corresponding to the sample ultrasonic radar signal associated with the sample vision signal.
8. A parking space state identifying apparatus, characterized in that the apparatus comprises: And a memory communicatively coupled to the at least one processor, wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-5.
9. A computer storage medium, characterized in that the computer storage medium stores a computer program for causing a computer to perform the method according to any one of claims 1-5.

Description

Parking space state identification method, device and equipment Technical Field The present application relates to the field of automatic driving technologies, and in particular, to a method, an apparatus, and a device for identifying a parking space state. Background Intellectualization is one of the important trends in the development of the automotive industry today, and intelligent driving technologies and systems will rapidly develop worldwide. Ultrasonic radar and vision systems are currently the most widely used parking scene sensing sensors for intelligent driving. According to the physical characteristics of the two, the vision system is more suitable for scene semantic analysis, and the ultrasonic radar has more advantages for detecting short-distance general obstacles. The current mass production ultrasonic radar is mainly used for providing obstacle position information in the detection range of a corresponding sensor and is applied to a parking auxiliary system to generate corresponding obstacle avoidance and parking space information. The traditional ultrasonic radar signal is weak to weak reflection object signals such as pedestrians and the like, and has poor response to low obstacles, so that the state of a parking space cannot be accurately identified. Disclosure of Invention The embodiment of the application provides a parking space state identification method, device and equipment, which can accurately identify the state of a parking space under the condition that the traditional ultrasonic radar signal is weak to weak reflection object signals such as pedestrians and the like and has poor response to low obstacles. In a first aspect, an embodiment of the present application provides a method for identifying a parking space state, where the method includes: collecting ultrasonic radar signals corresponding to a parking space to be identified through a radar; Performing feature construction of parking spaces to be identified based on the ultrasonic radar signals to obtain ultrasonic radar signal feature vectors corresponding to the parking spaces to be identified; Identifying the ultrasonic radar signal feature vector by using a parking space state identification model to obtain a parking space state, wherein the parking space state comprises an idle state and a occupied state; The parking space state recognition model is obtained by training based on a sample ultrasonic radar signal feature vector of a parking space and a first sample parking space state corresponding to the feature vector, and the first sample parking space state is determined based on a second sample parking space state corresponding to a sample visual signal associated with the sample ultrasonic radar signal. In the embodiment, the parking space state recognition model is utilized to recognize the ultrasonic radar signal feature vector, the robustness of the ultrasonic parking space detection mode is better than that of the traditional threshold filtering, and the second sample parking space state corresponding to the sample vision signal associated with the sample ultrasonic radar signal is used as the first sample parking space state corresponding to the ultrasonic radar signal feature vector to supervise the training process of the parking space state recognition model, so that the ultrasonic radar training supervision signal is easier to generate. In one possible embodiment, the first sample parking space state is determined in the following manner: aiming at a target parking space, acquiring a sample visual signal acquired by a camera at the same time and a sample ultrasonic radar signal acquired by a radar, wherein the sample visual signal comprises a plurality of frame images, and the images comprise at least one parking space; Analyzing the sample visual signal, and determining a second sample parking space state corresponding to the sample visual signal of the target parking space; And taking the second sample parking space state as a first sample parking space state corresponding to the sample ultrasonic radar signal associated with the sample visual signal. In the above embodiment, the training tag corresponding to the ultrasonic radar signal is generated based on the visual semiautomatic labeling mode, so that the ultrasonic radar training supervision signal is easier to generate. In one possible implementation manner, the analyzing the sample visual signal of the target parking space, and determining the second sample parking space state corresponding to the sample visual signal, includes: Analyzing the sample visual signal, and determining whether each frame of image of the sample visual signal contains the position information of the target parking space; And if the images of the continuous preset frame number in the sample visual signal all contain the position information of the target parking space, taking the sample visual signal as a visual signal corresponding to the target parking space, and taki