논문 상세보기

정제 모듈을 포함한 컨볼루셔널 뉴럴 네트워크 모델을 이용한 라이다 영상의 분할 KCI 등재

LiDAR Image Segmentation using Convolutional Neural Network Model with Refinement Modules

  • 언어KOR
  • URLhttps://db.koreascholar.com/Article/Detail/342185
서비스가 종료되어 열람이 제한될 수 있습니다.
로봇학회논문지 (The Journal of Korea Robotics Society)
한국로봇학회 (Korea Robotics Society)
초록

This paper proposes a convolutional neural network model for distinguishing areas occupied by obstacles from a LiDAR image converted from a 3D point cloud. The channels of a LiDAR image used as input consist of the distances to 3D points, the reflectivities of 3D points, and the heights of 3D points from the ground. The proposed model uses a LiDAR image as an input and outputs a result of a segmented LiDAR image. The proposed model adopts refinement modules with skip connections to segment a LiDAR image. The refinement modules with skip connections in the proposed model make it possible to construct a complex structure with a small number of parameters than a convolutional neural network model with a linear structure. Using the proposed model, it is possible to distinguish areas in a LiDAR image occupied by obstacles such as vehicles, pedestrians, and bicyclists. The proposed model can be applied to recognize surrounding obstacles and to search for safe paths.

목차
Abstract
 1. 서 론
 2. 라이다 영상 변환
 3. 컨볼루셔널 뉴럴 네트워크 구조
 4. 컨볼루셔널 뉴럴 네트워크 학습
  4.1 데이터셋(Data set)
  4.2 데이터 증강
  4.3 손실 함수
  4.4 클래스 가중치
  4.5 학습 환경 및 방법
 5. 실험 결과
 6. 결 론
 Reference
저자
  • 박병재(ETRI, Daejeonl, South Korea) | Byungjae Park
  • 서범수(ETRI, Daejeonl, South Korea) | Beom-Su Seo
  • 이세진(Division of Mechanical and Automotive Engineering, Kongju National University) | Sejin Lee Corresponding author