드라이브 ㆍ 컨트롤 (Journal of Drive and Control)

  • 제19권3호
  • /
  • Pages.9-15
  • /
  • 2022
  • /
  • 2671-7972(pISSN)
  • /
  • 2671-7980(eISSN)
유공압건설기계학회 (The Korean Society for Fluid Power and Construction Equipment)
권호 표지
DOI QR코드

DOI QR Code

가상 환경에서의 딥러닝 기반 폐색영역 검출을 위한 데이터베이스 구축

Construction of Database for Deep Learning-based Occlusion Area Detection in the Virtual Environment

  • Kim, Kyeong Su (Department of Mechanical Engineering, Sungkyunkwan University) ;
  • Lee, Jae In (Department of Mechanical Engineering, Sungkyunkwan University) ;
  • Gwak, Seok Woo (Department of Mechanical Engineering, Sungkyunkwan University) ;
  • Kang, Won Yul (Institute of Vehicle Engineering) ;
  • Shin, Dae Young (Korea Institute of Industrial Technology) ;
  • Hwang, Sung Ho (Department of Mechanical Engineering, Sungkyunkwan University)
  • 투고 : 2022.05.23
  • 심사 : 2022.08.17
  • 발행 : 2022.09.01
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

This paper proposes a method for constructing and verifying datasets used in deep learning technology, to prevent safety accidents in automated construction machinery or autonomous vehicles. Although open datasets for developing image recognition technologies are challenging to meet requirements desired by users, this study proposes the interface of virtual simulators to facilitate the creation of training datasets desired by users. The pixel-level training image dataset was verified by creating scenarios, including various road types and objects in a virtual environment. Detecting an object from an image may interfere with the accurate path determination due to occlusion areas covered by another object. Thus, we construct a database, for developing an occlusion area detection algorithm in a virtual environment. Additionally, we present the possibility of its use as a deep learning dataset to calculate a grid map, that enables path search considering occlusion areas. Custom datasets are built using the RDBMS system.

키워드

과제정보

본 연구는 국토교통부/국토교통과학기술진흥원 교통물류연구사업의 연구비지원 (22TLRP-C152478-04)과 과학기술정보통신부 및 정보통신기획평가원의 대학ICT연구센터육성지원사업의 연구결과로 수행된 결과물입니다. (IITP-2022-2018-0-01426)

참고문헌

  1. H. J. Jang, et al. "A Study on the Construction of Deep Learning Dataset based on Virtual Lidar Sensor Point Cloud", Kookmin University, 2019.
  2. S. J. Yoon et al. "Development of Autonomous Vehicle Learning Data Generation System", The Journal of The Korea Institute of Intelligent Transportation Systems, Vol.19, No.5 pp 162~177.
  3. A. Krizhevsky, I. Sutskever and G. E. Hinton, "ImageNet Classification with Deep Convolutional Neural Networks", Communication of ACM, Vol.60, Issue 6, pp.84-90, 2017. https://doi.org/10.1145/3065386
  4. K. Simonyan and A. Zisserman, "Very Deep Convolutional Networks for Large-scale Image Recognition", International Conference on Learning Representations, 2015.
  5. K. He, X. Zhang, S. Ren and J. Sun, "Deep Residual Learning for Image Recognition", The IEEE Conference on Computer Vision and Pattern Recognition, pp.770-778, 2016.
  6. J. I. Lee, G. S. Kwak, K. S. Kim, W. Y. Kang, D. Y. Shin, and S. H. Hwang, "Development of Virtual Simulator and Database for Deep Learning-based Object Detection", The Journal of Drive and Control, Vol.18, No.4, pp.9-18, 2021 https://doi.org/10.7839/KSFC.2021.18.4.009
  7. C. Yu, C. Gao, J. Wang, G. Yu, C. Shen, and N. Sang, "BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation," arXiv:2004.02147, 2020.
  8. L. Reiher, B. Lampe, and L. Eckstein, "A Sim2Real Deep Learning Approach for the Transformation of Images from Multiple Vehicle-Mounted Cameras to a Semantically Segmented Image in Bird's Eye View," arXiv:2005.04078, 2020.
  9. M. Cordts, M. Omran, S. Ramos, T. Rehfeld, M. Enzweiler, R. Benenson, U. Franke, S. Roth, and B. Schiele, "The Cityscapes Dataset for Semantic Urban Scene Understanding," Proc. Conf. Computer Vision and Pattern Recognition, pp.3213~3223, 2016.
  10. J. H. Kim, "Excavator Real Time Simulation and Application," The Journal of Drive and Control, Vol.17, No.3, pp.69-75, 2020.