Fully convolutional networks semantic segmentation based on conditional random field optimization

Article type: Research Article

Authors: Wu, Qian^{a; b; *} | Gu, Jinan^b | Wu, Chen^a | Li, Jin^a

Affiliations: [a] Suzhou Vocational University, Suzhou, Jiangsu 215104, China | [b] Mechanical Information Research Center of Jiangsu University, Zhenjiang, Jiangsu 212013, China

Correspondence: [*] Corresponding author: Qian Wu, Suzhou Vocational University, Suzhou, Jiangsu 215104, China. E-mail: [email protected].

Abstract: Each pixel can be classified in the image by the semantic segmentation. The segmentation detection results of pixel level can be got which are similar to the contour of the target object. However, the results of semantic segmentation trained by Fully convolutional networks often lead to the loss of detail information. This paper proposes a CRF-FCN model based on CRF optimization. Firstly, the original image is detected based on feature pyramid networks, and the target area information is extracted, which is used to train the high-order potential function of CRF. Then, the high-order CRF is used as the back-end of the complete convolution network to optimize the semantic image segmentation. The algorithm comparison experiment shows that our algorithm makes the target details more obvious, and improves the accuracy and efficiency of semantic segmentation.

Keywords: Conditional random field (CRF), fully convolutional networks (FCNs), semantic segmentation

DOI: 10.3233/JCM-214867

Journal: Journal of Computational Methods in Sciences and Engineering, vol. 21, no. 5, pp. 1405-1415, 2021