Search

CN-122002018-A - Image shooting method and device in three-dimensional reconstruction scene, equipment and storage medium

CN122002018ACN 122002018 ACN122002018 ACN 122002018ACN-122002018-A

Abstract

The method comprises the steps of determining a three-dimensional reconstruction scene of a vehicle surrounding environment at the current moment as a three-dimensional scene to be shot in response to receiving a shooting starting instruction, adjusting a camera pose of a first virtual camera in the three-dimensional scene to be shot in response to receiving an instruction for adjusting the first virtual camera in the three-dimensional scene to be shot, and determining a target shooting image based on the adjusted camera pose and scene data of the three-dimensional scene to be shot. According to the technical scheme, the three-dimensional reconstruction scene when shooting is started is determined to be the three-dimensional scene to be shot, and the image acquisition is carried out on the three-dimensional scene to be shot based on the adjusted virtual camera, so that the current three-dimensional reconstruction scene of the vehicle can be frozen when the shooting mode is triggered, and a user is allowed to carry out free mirror composition, and the problems that the screenshot function of the user is limited and the creation freedom degree is lacking in the vehicle-mounted SR environment are solved.

Inventors

  • LIN TAO
  • GONG YICHEN

Assignees

  • XG科技私人有限公司

Dates

Publication Date
20260508
Application Date
20260130

Claims (11)

  1. 1. An image capturing method in a three-dimensional reconstruction scene of a vehicle, comprising: In response to receiving an instruction for starting shooting, determining a three-dimensional reconstruction scene of the surrounding environment of the vehicle at the current moment as a three-dimensional scene to be shot; Responding to a command for adjusting a first virtual camera in the three-dimensional scene to be shot, and adjusting the camera pose of the first virtual camera in the three-dimensional scene to be shot; and determining a target shooting image based on the adjusted camera pose and the scene data of the three-dimensional scene to be shot.
  2. 2. The method of claim 1, wherein the determining, in response to receiving the instruction to start shooting, that the three-dimensional reconstructed scene of the surrounding environment of the vehicle at the current moment is the three-dimensional scene to be shot comprises: Triggering an interrupt signal in response to receiving an instruction for starting shooting; Responding to the interrupt signal, stopping acquiring the sensing data of the surrounding environment of the vehicle after the current moment, so that the three-dimensional reconstruction scene of the vehicle is kept in the scene triggered by the interrupt signal; And determining the three-dimensional reconstruction scene at the current moment as the three-dimensional scene to be shot.
  3. 3. The method of claim 2, wherein the determining that the three-dimensional reconstructed scene at the current time is a three-dimensional scene to be photographed comprises: Determining resource data corresponding to a scene where the vehicle is located at the current moment; Carrying out serialization processing on the dynamic data in the resource data to obtain serialized dynamic data; Storing the serialized dynamic data and the static data in the resource data to determine a three-dimensional reconstruction scene at the current moment; and determining the three-dimensional reconstruction scene at the current moment as the three-dimensional scene to be shot.
  4. 4. The method of claim 1, further comprising, prior to said responding to receiving an instruction to initiate shooting: Saving scene data of the three-dimensional reconstruction scene of the surrounding environment of the vehicle at the current moment and the previous moment to determine a three-dimensional reconstruction scene sequence; Correspondingly, the responding to the receiving of the shooting starting instruction, determining the three-dimensional reconstruction scene of the surrounding environment of the vehicle at the current moment as the three-dimensional scene to be shot comprises the following steps: Responding to the received shooting starting instruction, and displaying a time line interactive interface corresponding to the three-dimensional reconstruction scene sequence to determine a target moment; and determining the three-dimensional reconstruction scene corresponding to the target moment in the three-dimensional reconstruction scene sequence as the three-dimensional scene to be shot.
  5. 5. The method of claim 1, further comprising, prior to the adjusting the camera pose of the first virtual camera in the three-dimensional scene to be photographed in response to receiving an instruction to adjust the first virtual camera in the three-dimensional scene to be photographed: creating the first virtual camera based on the three-dimensional reconstructed scene, or, Determining a second virtual camera having an association with the vehicle; and releasing the association relation between the second virtual camera and the vehicle, and taking the second virtual camera after the association relation is released as the first virtual camera.
  6. 6. The method of claim 5, wherein the releasing the association between the second virtual camera and the vehicle and taking the second virtual camera after releasing the association as the first virtual camera comprises: determining a father node of the second virtual camera based on the association relationship; Removing the parent node from under a vehicle node of the vehicle; and adding the removed father node to a scene node of the three-dimensional reconstruction scene.
  7. 7. The method of any of claims 1-6, wherein the determining a target captured image based on the adjusted camera pose and scene data of the three-dimensional scene to be captured comprises: determining a shooting image based on the adjusted camera pose and the scene data of the three-dimensional scene to be shot; and responding to the received command of stylized updating the shooting image, and performing stylized processing on the shooting image to obtain the target shooting image.
  8. 8. The method of any of claims 1-6, wherein the determining a target captured image based on the adjusted camera pose and scene data of the three-dimensional scene to be captured comprises: determining a rendering instruction based on the adjusted camera pose and the scene data of the three-dimensional scene to be shot; Sending the rendering instruction to a graphic processor of the vehicle, so that the graphic processor can create an off-screen rendering target, and performing rendering operation based on the off-screen rendering target and the rendering instruction to obtain the target shooting image; the resolution of the off-screen rendering target is higher than the display resolution of the display screen of the vehicle.
  9. 9. An image capture device in a three-dimensional reconstructed scene of a vehicle, comprising: the three-dimensional scene determining module is used for determining a three-dimensional reconstruction scene of the surrounding environment of the vehicle at the current moment as a three-dimensional scene to be shot in response to receiving a shooting starting instruction; The camera pose adjusting module is used for adjusting the camera pose of the first virtual camera in the three-dimensional scene to be shot in response to receiving an instruction for adjusting the first virtual camera in the three-dimensional scene to be shot; And the target image determining module is used for determining a target shooting image based on the adjusted camera pose and the scene data of the three-dimensional scene to be shot.
  10. 10. A computer-readable storage medium storing a computer program for executing the image capturing method in a three-dimensional reconstruction scene of a vehicle according to any one of the preceding claims 1 to 8.
  11. 11. An electronic device, the electronic device comprising: A processor; a memory for storing the processor-executable instructions; The processor is configured to read the executable instructions from the memory and execute the instructions to implement the image capturing method in the three-dimensional reconstruction scene of the vehicle according to any one of claims 1 to 8.

Description

Image shooting method and device in three-dimensional reconstruction scene, equipment and storage medium Technical Field The disclosure relates to the technical field of intelligent driving, and in particular relates to an image shooting method, an image shooting device, image shooting equipment and a storage medium in a three-dimensional reconstruction scene. Background Currently, with the development of intelligent driving technology and intelligent cabins, HMI (Human-MACHINE INTERFACE, on-board Human-computer interaction interface) is evolving from simple information presentation to immersive, intelligent 3D (Three-Dimensional) environment interaction. The SR (Surrounding Reality, environmental reconstruction display) technology can visualize real-world environments perceived by vehicle sensors (such as cameras, lidar, etc.) in real-time on a vehicle-mounted screen in 3D form. When a user wants to record a picture generated by an SR at a certain moment, the picture can be realized only through a self-contained screenshot function of the system, so that the user experience is poor. Disclosure of Invention In order to solve the technical problems, the present disclosure provides an image capturing method, an image capturing device and a storage medium in a three-dimensional reconstruction scene. An embodiment of a first aspect of the present disclosure provides an image capturing method in a three-dimensional reconstruction scene of a vehicle, which includes determining, in response to receiving an instruction to start capturing, a three-dimensional reconstruction scene of a surrounding environment of the vehicle at a current time as a three-dimensional scene to be captured, in response to receiving an instruction to adjust a first virtual camera in the three-dimensional scene to be captured, adjusting a camera pose of the first virtual camera in the three-dimensional scene to be captured, and determining a target captured image based on the adjusted camera pose and scene data of the three-dimensional scene to be captured. An embodiment of a second aspect of the present disclosure provides an image capturing device in a three-dimensional reconstruction scene of a vehicle, which includes a three-dimensional scene determining module configured to determine, in response to receiving an instruction to start capturing, a three-dimensional reconstruction scene of a surrounding environment of the vehicle at a current time as a three-dimensional scene to be captured, a camera pose adjusting module configured to adjust a camera pose of a first virtual camera in the three-dimensional scene to be captured in response to receiving an instruction to adjust the camera pose of the first virtual camera in the three-dimensional scene to be captured, and a target image determining module configured to determine a target captured image based on the adjusted camera pose and scene data of the three-dimensional scene to be captured. In a third aspect of the present disclosure, there is provided a computer-readable storage medium storing a computer program for executing the image capturing method in the three-dimensional reconstruction scene of a vehicle provided in the first aspect. In a fourth aspect of the present disclosure, an embodiment provides an electronic device, where the electronic device includes a processor, a memory for storing executable instructions of the processor, and a processor for reading the executable instructions from the memory and executing the instructions to implement the image capturing method in the three-dimensional reconstruction scene of the vehicle provided in the first aspect of the embodiment. A fifth aspect embodiment of the present disclosure provides a computer program product, which when executed by a processor, performs the image capturing method in the three-dimensional reconstruction scene of a vehicle provided by the first aspect embodiment. According to the image shooting method in the three-dimensional reconstruction scene of the vehicle, the three-dimensional reconstruction scene when shooting is started is determined to be the three-dimensional scene to be shot, and the image acquisition is carried out on the three-dimensional scene to be shot based on the adjusted virtual camera, so that the three-dimensional reconstruction scene of the current surrounding environment of the vehicle can be frozen when the shooting mode is triggered, and a user is allowed to carry out free mirror composition, and the problems that the screenshot function of the user in the vehicle-mounted SR environment is limited and the degree of freedom of creation is lacking are solved. Drawings Fig. 1 is a schematic diagram of a vehicle provided in an exemplary embodiment of the present disclosure. Fig. 2 is a flowchart illustrating an image capturing method according to an exemplary embodiment of the present disclosure. Fig. 3 is a flowchart illustrating an image capturing method according to another exempl