Search

KR-102963515-B1 - Method for generating boundary line of object in video and apparatus thereof

KR102963515B1KR 102963515 B1KR102963515 B1KR 102963515B1KR-102963515-B1

Abstract

An embodiment of the present invention discloses a method for generating object outlines, comprising the steps of: recognizing at least one object included in a first image acquired during driving and generating a first outline for each recognized object; extracting the object recognized in the first image based on the first outline; obtaining a first coordinate value for a second outline of the object as a result of inputting the extracted object into a first learning model; and merging the object to which the second outline is applied into the first image based on the obtained first coordinate value.

Inventors

  • 조명훈

Assignees

  • 포티투닷 주식회사

Dates

Publication Date
20260513
Application Date
20221020

Claims (16)

  1. A step of recognizing at least one object included in a first image acquired during driving, and generating a first outline for each recognized object; A step of extracting the recognized object from the first image based on the first outline generated above; A step of obtaining a first coordinate value for a second outline of the extracted object as a result of inputting the extracted object into a first learning model; and The method includes the step of merging the object to which the second outline is applied into the first image based on the first coordinate values obtained above; The above second outline is, It is a form in which a rectangle and a trapezoid are combined based on at least one common side, and The rectangle in the second outline above is, Indicates the front or rear of the above-mentioned extracted object, and In the second outline above, the trapezoid is, A method for generating an object outline representing the side of the extracted object.
  2. In paragraph 1, The method further includes the step of calculating a second coordinate value for the position of the extracted object in the first image, and calculating a third coordinate value, which is the coordinate of the second outline, based on the second coordinate value. The step of merging with the first image above is, A method for generating an object outline, wherein the object to which the second outline is applied is merged into the first image by further considering the third coordinate value obtained above.
  3. In paragraph 1, A method for generating an object outline, wherein the first coordinate value above consists of 7 coordinate values.
  4. In paragraph 1, A method for generating an object outline, wherein the first coordinate value above consists of 8 coordinate values.
  5. In paragraph 1, A method for generating an object outline, wherein the first outline is in the form of a polygon.
  6. In paragraph 1, A method for generating an object outline, wherein the first outline is in the shape of a rectangle.
  7. In paragraph 1, The above first outline is an object outline generation method that is generated as a result of inputting the above first image into a second learning model.
  8. In paragraph 1, A method for generating an object outline, wherein the second outline is in the shape of a cuboid.
  9. delete
  10. delete
  11. delete
  12. delete
  13. delete
  14. In paragraph 1, A method for generating an object outline, wherein the specifications of the first outline include the specifications of the second outline.
  15. A computer-readable recording medium storing a program for executing the method according to paragraph 1.
  16. Memory in which at least one program is stored; and By executing at least one of the above programs, the processor performs operations, and The above processor is, Recognizing at least one object included in a first image acquired during driving, and generating a first outline for each recognized object, Based on the first outline generated above, the recognized object in the first image is extracted, and As a result of inputting the above-mentioned extracted object into the first learning model, a first coordinate value for the second outline of the above-mentioned extracted object is obtained, and Based on the first coordinate values obtained above, the object to which the second outline is applied is merged into the first image, and The above second outline is, It is a form in which a rectangle and a trapezoid are combined based on at least one common side, and The rectangle in the second outline above is, Indicates the front or rear of the above-mentioned extracted object, and In the second outline above, the trapezoid is, An object outline generating device representing the side of the extracted object.

Description

Method for generating boundary line of object in video and apparatus thereof The present invention relates to a method for generating an object outline and an apparatus thereof, and more specifically, to a method for generating an outline to represent an object in an image acquired while driving by an autonomous vehicle capable of recognizing objects and driving autonomously, and an apparatus for implementing the method. The smartification of vehicles is rapidly progressing due to the convergence of information and communication technology (ICT) and the automotive industry. As a result of this smartification, vehicles are evolving from simple mechanical devices into smart cars, and self-driving is receiving particular attention as a core technology for smart cars. Self-driving is a technology in which an autonomous driving module installed in the vehicle actively controls the driving state, allowing the vehicle to find its way to a destination on its own without the driver having to operate the steering wheel, accelerator pedal, or brakes. To ensure safe autonomous driving, various studies are being conducted on methods for vehicles to accurately recognize pedestrians or other vehicles and calculate the distance to recognized objects during the driving process. However, since the characteristics of objects that may appear on the road while driving are virtually infinite and there are limitations to the processing capabilities of modules installed in autonomous vehicles, no method is currently known to perfectly recognize objects on the road. In the case of object recognition and distance estimation using cameras, a significant amount of distance information is lost because objects from the real 3D world are projected onto a 2D image. In particular, the error is large due to the large deviations in features frequently used for pedestrian position calculation (such as the pedestrian's height or points touching the ground). In the case of object recognition and distance estimation using radar, the ability to rapidly identify and classify objects is poor due to the characteristics of the radio waves operated by the radar; consequently, it is difficult to determine whether an object is a pedestrian or a vehicle. In particular, recognition results tend to be even worse for pedestrians or two-wheeled vehicles (bicycles or motorcycles) on the road because their signal strength is low. Recently, object recognition and distance estimation technologies using LiDAR have been gaining attention due to their relatively high accuracy; however, high-power lasers pose a risk, so LiDAR must operate based on lower-power lasers. Furthermore, unlike the radio waves used by radar, lasers are significantly affected by the surrounding environment, and the excessively high cost of LiDAR sensors is cited as a limitation. Even if objects included in an image are recognized through the various methods described above, if the shape or arrangement features of the recognized objects cannot be accurately identified, the driving safety of the autonomous vehicle is bound to be extremely low. Therefore, annotation work, which assigns metadata to objects based on their shape or arrangement on the road, is essential; however, manual annotation work performed by humans poses problems due to excessive costs and workload, and when annotation is performed automatically using machine learning (deep learning), the outlines located around the objects are often unstable, do not fit, or are omitted, which is problematic. The aforementioned background technology is technical information that the inventor possessed for the derivation of the present invention or acquired during the process of deriving the present invention, and it cannot be considered as prior art disclosed to the general public prior to the filing of the present invention. FIGS. 1 to 3 are drawings for explaining an autonomous driving method according to one embodiment. Figures 4a and 4b are drawings related to a camera that photographs the exterior of a vehicle operating in autonomous driving mode. FIG. 5 is a schematic diagram illustrating an object recognition method according to one embodiment. FIG. 6 is a diagram illustrating the process of generating a first outline during the operation of an object outline generation device. FIG. 7 is a diagram illustrating the process of an object outline generation device extracting an object surrounded by a first outline. FIGS. 8A and 8B are drawings for explaining the process in which an object outline generating device generates a second outline for an object included in a target frame, and two different objects with the generated second outline are merged into one. Figure 9 is a diagram illustrating an example in which a second outline is generated for each object and then repeatedly merged into the original image as many times as the number of objects. FIG. 10 is a flowchart illustrating a method for generating an object outline according to