Mattress Overlapping Recognition Based on Markov Random Field
Fengyu Hu, Xianqiao Chen
Available Online April 2017.
- 10.2991/eame-17.2017.27How to use a DOI?
- mattress sonar image; image segmentation; MRF model; belief propagation
Mattress overlapping recognition is of great significance in tracing and detecting the quality, and provides reference data of mattress laying. The recognition process includes the generation and image correction of the color sinking sonar image, the image segmentation and the recognition of mattress overlapping; In which the key issue is the segmentation of sonar image segmentation. There are a lot of underwater sonar image noise, and the effect of the traditional segmentation method is poor; Markov Model can accurately show the characteristics and relationship of image content. For segmentation algorithm of mattress image, using belief propagation (BP) algorithm .Experimental results show that it has a good effect.
- © 2017, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - CONF AU - Fengyu Hu AU - Xianqiao Chen PY - 2017/04 DA - 2017/04 TI - Mattress Overlapping Recognition Based on Markov Random Field BT - Proceedings of the 2017 2nd International Conference on Electrical, Automation and Mechanical Engineering (EAME 2017) PB - Atlantis Press SP - 113 EP - 116 SN - 2352-5401 UR - https://doi.org/10.2991/eame-17.2017.27 DO - 10.2991/eame-17.2017.27 ID - Hu2017/04 ER -