CN-116012216-B - Driving assistance image processing method, device, equipment and medium

CN116012216BCN 116012216 BCN116012216 BCN 116012216BCN-116012216-B

Abstract

The application discloses a driving auxiliary image processing method, a device, equipment and a medium, which relate to the technical field of computers and comprise the steps of collecting original images around a target vehicle; and carrying out corresponding processing on the original image by utilizing the image processing node in the target image processing thread so as to acquire a target driving auxiliary image corresponding to the auxiliary image acquisition instruction. The target image processing thread and the image processing node in the target image processing thread are determined according to the received target instruction, namely, unnecessary target image processing threads and unnecessary image processing nodes are not needed to be adopted, and the target image processing threads and the image processing nodes are flexibly transformed, so that the hardware calculation power requirement can be reduced in the process of acquiring the auxiliary driving image, and the flexibility of realizing the auxiliary driving scene is improved.

Inventors

ZHANG LIANG
MO BO

Assignees

知行汽车科技(苏州)股份有限公司

Dates

Publication Date: 20260508
Application Date: 20221227

Claims (9)

1. A driving assistance image processing method, comprising: collecting original images around a target vehicle; determining a target image processing thread from preset image processing threads according to the received target instructions, and determining an image processing node of the target image processing thread; the original image is correspondingly processed by utilizing the image processing nodes in the target image processing thread so as to obtain a target driving auxiliary image corresponding to the target instruction; the determining a target image processing thread from preset image processing threads according to the received target instruction, and determining an image processing node of the target image processing thread, includes: If the target instruction is an instruction for acquiring a remote control parking image, a vehicle display thread, an image recognition thread and a drivable region detection thread in a preset image processing thread are respectively determined as a first target image processing thread, a second target image processing thread and a third target image processing thread, and an image view conversion node, an image splicing node and a Tensor conversion node are determined as image processing nodes of the third target image processing thread.
2. The driving assistance image processing method according to claim 1, wherein the determining a target image processing thread from preset image processing threads according to the received target instruction, and determining an image processing node of the target image processing thread, further comprises: If the received target instruction is an instruction for acquiring the panoramic monitoring image, determining a vehicle display thread in a preset image processing thread as a first target image processing thread; and determining an image format conversion node, an image color balance node and an image brightness balance node as image processing nodes of the first target image processing thread.
3. The driving assistance image processing method according to claim 2, wherein the determining a target image processing thread from preset image processing threads according to the received target instruction, and determining an image processing node of the target image processing thread, further comprises: if the target instruction is an instruction for acquiring the parking image of the fixed-point parking space, respectively determining the vehicle display thread and the image recognition thread in the preset image processing threads as a first target image processing thread and a second target image processing thread; And determining the image view conversion node and the Tensor conversion node as the image processing nodes of the second target image processing thread.
4. The driving assistance image processing method according to claim 3, wherein said performing, by using the image processing node in the target image processing thread, the corresponding processing of the original image includes: Activating the first target image processing thread based on a buffer mode, and activating the second target image processing thread and the third target image processing thread based on a time division multiplexing rule; and correspondingly processing the original image by using the image processing nodes in the first target image processing thread, the second target image processing thread and the third target image processing thread.
5. The driving assistance image processing method according to claim 4, wherein the activating the second target image processing thread and the third target image processing thread based on a time-division multiplexing rule includes: Determining a first running period of the second target image processing thread, a second running period of the third target image processing thread and a collection period of the original image, and monitoring a first actual image processing time of the second target image processing thread and a second actual image processing time of the third target image processing thread; and if the first operation period and the second operation period are integer multiples of the acquisition period and the first actual image processing time and the second actual image processing time are respectively smaller than the first operation period and the second operation period, activating the second target image processing thread at the current starting point of the acquisition period and activating the third target image processing thread at the next starting point of the acquisition period.
6. The driving assistance image processing method according to any one of claims 1 to 5, wherein said performing, by using the image processing node in the target image processing thread, a corresponding process on the original image to obtain a target driving assistance image corresponding to the target instruction includes: the original image is correspondingly processed by utilizing the image processing nodes in the target image processing thread so as to obtain a processed auxiliary image; and determining a target offset of the processed auxiliary image in a target offset direction, and determining a region of interest in the processed auxiliary image based on the target offset direction and the target offset, so as to determine the processed auxiliary image corresponding to the region of interest as a target driving auxiliary image corresponding to the target instruction.
7. A driving assistance image processing apparatus, comprising: The image acquisition module is used for acquiring original images around the target vehicle; The processing node determining module is used for determining a target image processing thread from preset image processing threads according to the received target instruction and determining an image processing node of the target image processing thread; The target image acquisition module is used for carrying out corresponding processing on the original image by utilizing the image processing node in the target image processing thread so as to acquire a target driving auxiliary image corresponding to the auxiliary image acquisition instruction; the processing node determining module is specifically configured to: If the target instruction is an instruction for acquiring a remote control parking image, a vehicle display thread, an image recognition thread and a drivable region detection thread in a preset image processing thread are respectively determined as a first target image processing thread, a second target image processing thread and a third target image processing thread, and an image view conversion node, an image splicing node and a Tensor conversion node are determined as image processing nodes of the third target image processing thread.
8. An electronic device, comprising: A memory for storing a computer program; A processor for executing the computer program to implement the steps of the driving assistance image processing method according to any one of claims 1 to 6.
9. A computer-readable storage medium storing a computer program, wherein the computer program when executed by a processor implements the steps of the driving assistance image processing method according to any one of claims 1 to 6.

Description

Driving assistance image processing method, device, equipment and medium Technical Field The present invention relates to the field of computer technologies, and in particular, to a method, an apparatus, a device, and a medium for processing driving assistance images. Background The auxiliary driving system is used for acquiring real-time images by utilizing the fisheye lens arranged around the vehicle body, the acquired images can be used for visual perception of the driving system and picture display of the vehicle machine after being processed in multiple steps, so that functions of the auxiliary driving system tend to be diversified and complicated, the image processing system is required to have the capability of simultaneously processing multiple tasks and operating at high efficiency, the requirement on hardware computing power is very high, and the image processing nodes are fixed in the current process of acquiring the auxiliary driving images, so that the auxiliary driving scene which can be realized is relatively dead and cannot meet the daily flexible application scene. In summary, how to reduce the hardware calculation power requirement and improve the flexibility of implementing the auxiliary driving scene in the process of implementing the auxiliary driving image is a problem to be solved in the field. Disclosure of Invention In view of the above, the present invention aims to provide a driving assistance image processing method, device, equipment and medium, which can reduce the hardware calculation force requirement and improve the flexibility of implementing the assistance driving scene in the process of implementing the assistance driving image acquisition. The specific scheme is as follows: in a first aspect, the present application discloses a driving assistance image processing method, including: collecting original images around a target vehicle; determining a target image processing thread from preset image processing threads according to the received target instructions, and determining an image processing node of the target image processing thread; And performing corresponding processing on the original image by using the image processing node in the target image processing thread so as to acquire a target driving auxiliary image corresponding to the target instruction. Optionally, the determining a target image processing thread from preset image processing threads according to the received target instruction, and determining an image processing node of the target image processing thread includes: If the received target instruction is an instruction for acquiring the panoramic monitoring image, determining a vehicle display thread in a preset image processing thread as a first target image processing thread; and determining an image format conversion node, an image color balance node and an image brightness balance node as image processing nodes of the first target image processing thread. Optionally, the determining a target image processing thread from preset image processing threads according to the received target instruction, and determining an image processing node of the target image processing thread includes: if the target instruction is an instruction for acquiring the parking image of the fixed-point parking space, respectively determining the vehicle display thread and the image recognition thread in the preset image processing threads as a first target image processing thread and a second target image processing thread; And determining the image view conversion node and the Tensor conversion node as the image processing nodes of the second target image processing thread. Optionally, the determining a target image processing thread from preset image processing threads according to the received target instruction, and determining an image processing node of the target image processing thread includes: If the target instruction is an instruction for acquiring a remote control parking image, determining the vehicle display thread, the image identification thread and a drivable region detection thread in a preset image processing thread as the first target image processing thread, the second target image processing thread and a third target image processing thread respectively; And determining the image view conversion node, the image stitching node and the Tensor conversion node as image processing nodes of the third target image processing thread. Optionally, the performing, by using the image processing node in the target image processing thread, a corresponding process on the original image includes: Activating the first target image processing thread based on a buffer mode, and activating the second target image processing thread and the third target image processing thread based on a time division multiplexing rule; and correspondingly processing the original image by using the image processing nodes in the first target image processing thread, the second target imag