Journal of the Korea Institute of Military Science and Technology (한국군사과학기술학회지)

The Korea Institute of Military Science and Technology (한국군사과학기술학회)
권호 표지
DOI QR코드

DOI QR Code

A Study of Real-time Semantic Segmentation Performance Improvement in Unstructured Outdoor Environment

비정형 야지환경 주행상황에서의 실시간 의미론적 영상 분할 알고리즘 성능 향상에 관한 연구

  • Daeyoung, Kim (Department of Electrical and Computer Engineering, Seoul National University) ;
  • Seunguk, Ahn (Department of Defense Robotics and Autonomous Systems Development, Hanwha Defense Co., Ltd.) ;
  • Seung-Woo, Seo (Department of Electrical and Computer Engineering, Seoul National University)
  • 김대영 (서울대학교 전기정보공학부) ;
  • 안승욱 (한화디펜스(주) 국방로봇사업부 로봇개발그룹) ;
  • 서승우 (서울대학교 전기정보공학부)
  • Received : 2022.04.08
  • Accepted : 2022.11.18
  • Published : 2022.12.05
Download PDF
⟨ Previous Next ⟩

Abstract

Semantic segmentation in autonomous driving for unstructured environments is challenging due to the presence of uneven terrains, unstructured class boundaries, irregular features and strong textures. Current off-road datasets exhibit difficulties like class imbalance and understanding of varying environmental topography. To overcome these issues, we propose a deep learning framework for semantic segmentation that involves a pooled class semantic segmentation with five classes. The evaluation of the framework is carried out on two off-road driving datasets, RUGD and TAS500. The results show that our proposed method achieves high accuracy and real-time performance.

Keywords

Acknowledgement

본 논문은 딥러닝 기반 야지환경 영상인식 기술 연구의 일환으로 한화디펜스의 지원을 받아 수행된 연구입니다.

References

  1. Cordts M, Omran M, Ramos S, Rehfeld T, Enzweiler M, Benenson R, Franke U, Roth S and Schiele B, "The Cityscapes Dataset for Semantic Urban Scene Understanding," In: Proc. IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 2016.
  2. Geiger A, Lenz P and Urtasun R, "Are we ready for Autonomous Driving? the Kitti Vision Benchmark Suite," In: Proc. IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 2012.
  3. A. Valada, G. Oliveira, T. Brox, and W. Burgard, "Deep Multispectral Semantic Scene Understanding of Forested Environments using Multimodal Fusion," in International Symposium on Experimental Robotics (ISER), 2016.
  4. P. Jiang, P. Osteen, M. Wigness, and S. Saripalli, "Rellis-3d Dataset: Data, Benchmarks and Analysis," arXiv, 2020.
  5. A. Valada, G. Oliveira, T. Brox, and W. Burgard, "Deep Multispectral Semantic Scene Understanding of Forested Environments using Multimodal Fusion," in International Symposium on Experimental Robotics (ISER), 2016.
  6. K. A. Metzger, P. Mortimer, and H.-J. Wuensche, "A Fine-Grained Dataset and its Efficient Semantic Segmentation for Unstructured Driving Scenarios," in International Conference on Pattern Recognition (ICPR), Milano, Italy, Jan. 2021.
  7. C. Yu, J. Wang et al., "BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation," in European Conference on Computer Vision(ECCV), 2018.
  8. C. Yu, C. Gao, J. Wang, G. Yu, C. Shen, and N. Sang, "Bisenetv2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation," arXiv, 2020.
  9. He K, Zhang X, Ren S and Sun J, "Deep Residual Learning for Image Recognition," In: Proc. IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 2016.
  10. Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto M and Adam H, "Mobilenets: Efficient Convolutional Neural Networks for Mobile Vision Applications," arXiv, 2017.
  11. Li G, Yun I, Kim J, and Kim J, "Dabnet: Depth-wise Asymmetric Bottleneck for Real-time Semantic Segmentation," In: Proc. British Machine Vision Conference(BMVC), 2019.
  12. Long J, Shelhamer E, Darrel T, "Fully Convolutional Networks for Semantic Segmentation," In: Proc. IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 2015.
  13. Ronneberger O, Fischer P, Brox T, "U-net: Convolutional Networks for Biomedical Image Segmentation," In: Proc. International Conference on Medical Image Computing and Computer-Assisted Intervention(MICCAI), 2015.
  14. Yu C, Wang J, Peng C, Gao C, Yu G, Sang N, "Learning a Discriminative Feature Network for Semantic Segmentation," In: Proc. IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 2018.
  15. Wang J, Sun K, Cheng T, Jiang B, Deng C, Zhao Y, Liu D, Mu Y, Tan M, Wang X, Liu W, Xiao B, "Deep High-resolution Representation Learning for Visual Recognition," IEEE Transactions on Pattern Analysis and Machine Intelligence(TPAMI), 2019.