KR-20260065342-A - APPARATUS AND METHOD FOR LABELING 2D LIDAR DATA

Abstract

The present invention relates to a two-dimensional lidar data labeling device comprising a camera and a communication interface configured to communicate with a two-dimensional lidar, and a processor connected to the communication interface, wherein the processor collects an image containing a target object and lidar data corresponding to the image through the communication interface, and performs, for each frame included in the image, an operation of generating a segmentation mask for the target object, an operation of projecting points included in the lidar data onto the image, and an operation of labeling a first label to points among the points included in the lidar data whose projection position corresponds to the segmentation mask.

Inventors

• 오지용
• 정유수
• 이준구

Assignees

• 한국전자통신연구원

Dates

Publication Date

20260508

Application Date

20241101

Claims (1)

1. A communication interface configured to communicate with a camera and a 2D LiDAR; and It includes a processor connected to the above communication interface, The above processor is, An image containing a target object and LiDAR data corresponding to the image are collected through the communication interface, and A two-dimensional LiDAR data labeling device that performs, for each frame included in the image, the operation of generating a segmentation mask for the target object, the operation of projecting points included in the LiDAR data onto the image, and the operation of labeling a first label to points among the points included in the LiDAR data whose projection position corresponds to the segmentation mask.

Description

Apparatus and Method for Labeling 2D LiDAR Data The present invention relates to a two-dimensional LiDAR data labeling device and method. Robots have traditionally been developed to replace human labor, and technologies for transporting heavy loads are still being developed, as transporting such loads requires significant labor. While autonomous driving technology for mobile robots may be suitable for the simple transportation of heavy loads to a designated destination, user-following technology—where the robot follows a specific user—is more appropriate than autonomous driving technology for tasks such as crop harvesting and parcel delivery, where frequent user intervention is required during the load-carrying process. User-following technology requires driving control technology that enables the robot to follow the user, along with user position estimation technology that determines the user's relative position based on the robot. Various sensors, including RGB cameras, stereo cameras, 2D LiDAR, and 3D LiDAR, are utilized for user position estimation. Meanwhile, the development of 2D LiDAR-based object tracking technology requires numerous datasets, namely labeled 2D LiDAR data, but obtaining such datasets is not easy; therefore, it is necessary to develop a technology for generating the datasets required for the development of 2D LiDAR-based object tracking technology. The background technology of the present invention is disclosed in Korean Registered Patent Publication No. 10-2653756 (March 28, 2024). FIG. 1 is a block diagram showing a two-dimensional LiDAR data labeling device according to an embodiment of the present invention. Figure 2 is an example diagram illustrating lidar data generated through a two-dimensional lidar. Figure 3 is an example diagram illustrating a camera and a 2D LiDAR. Figure 4 is an example diagram illustrating the result of generating a segmented mask. Figure 5 is an example diagram illustrating the labeling results for LiDAR data. FIG. 6 is a flowchart showing a two-dimensional LiDAR data labeling method according to an embodiment of the present invention. Hereinafter, embodiments of the two-dimensional LiDAR data labeling device and method according to the present invention will be described. In this process, the thickness of lines or the size of components depicted in the drawings may be exaggerated for the sake of clarity and convenience of explanation. Furthermore, the terms described below are defined considering their functions in the present invention, and these may vary depending on the intent or convention of the user or operator. Therefore, the definitions of these terms should be based on the content throughout this specification. Embodiments of the present invention are described below with reference to the attached drawings so that those skilled in the art can easily implement them. However, the present invention may be embodied in various different forms and is not limited to the embodiments described herein. Furthermore, in order to clearly explain the present invention in the drawings, parts unrelated to the explanation have been omitted, and similar parts throughout the specification are denoted by similar reference numerals. Throughout the specification, when a part is described as "including" a certain component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components. The implementations described herein may be implemented, for example, as methods or processes, devices, software programs, data streams, or signals. Even if discussed only in the context of a single form of implementation (e.g., discussed only as a method), the implementation of the discussed features may also be implemented in other forms (e.g., devices or programs). Devices may be implemented in appropriate hardware, software, and firmware, etc. Methods may be implemented in devices such as processors, which generally refer to processing devices including, for example, computers, microprocessors, integrated circuits, or programmable logic devices. FIG. 1 is a block diagram showing a two-dimensional lidar data labeling device according to an embodiment of the present invention, FIG. 2 is an example diagram for explaining lidar data generated through a two-dimensional lidar, FIG. 3 is an example diagram for explaining a camera and a two-dimensional lidar, FIG. 4 is an example diagram for explaining the result of generating a segmentation mask, and FIG. 5 is an example diagram for explaining the labeling result for lidar data. Referring to FIG. 1, a two-dimensional LiDAR data labeling device (100) according to an embodiment of the present invention may include a communication interface (110), a user interface (120), a memory (130), and a processor (140). The two-dimensional LiDAR data labeling device (100) according to an embodiment of the present invention may further include various components in addition to the comp