Research on Scene Semantic Segmentation Based on Deep Learning

Because of the problem of the low accuracy and slow speed of the traditional semantic segmentation model, making it difficult to actually use. In response to this problem, this paper focuses on the method to improve the precision and speed of the algorithm. According to this theory, based on the convolution neural network, we have designed the PSPNet and ICNet models. Meanwhile, a scene semantic segmentation network based on deep learning was presented. The network effectively improves the accuracy of semantic segmentation of convolutional neural networks by merging multi-level depth and network features. The test results on the LISA traffic sign data set show that the proposed semantic segmentation network has outstanding performance compared with other state of the art semantic segmentation network structures.

[1]  Shuchang Zhou,et al.  EAST: An Efficient and Accurate Scene Text Detector , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Jitendra Malik,et al.  Learning Rich Features from RGB-D Images for Object Detection and Segmentation , 2014, ECCV.

[3]  Fei Yin,et al.  Deep Direct Regression for Multi-oriented Scene Text Detection , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[4]  Dieter Fox,et al.  RGB-(D) scene labeling: Features and algorithms , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[5]  Gui-Song Xia,et al.  Rotation-Sensitive Regression for Oriented Scene Text Detection , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[6]  Ernest Valveny,et al.  ICDAR 2015 competition on Robust Reading , 2015, 2015 13th International Conference on Document Analysis and Recognition (ICDAR).

[7]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.

[8]  Xiang Bai,et al.  Detecting Oriented Text in Natural Images by Linking Segments , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Xuelong Li,et al.  PixelLink: Detecting Scene Text via Instance Segmentation , 2018, AAAI.

[10]  Jia-Hao Syu,et al.  Hierarchical Image Segmentation Based on Iterative Contraction and Merging , 2017, IEEE Transactions on Image Processing.

[11]  Svetha Venkatesh,et al.  Towards automatic extraction of expressive elements from motion pictures: tempo , 2000, 2000 IEEE International Conference on Multimedia and Expo. ICME2000. Proceedings. Latest Advances in the Fast Changing World of Multimedia (Cat. No.00TH8532).

[12]  Xiaolin Li,et al.  Single Shot Text Detector with Regional Attention , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[13]  Ba Tu Truong,et al.  Scene extraction in motion pictures , 2003, IEEE Trans. Circuits Syst. Video Technol..

[14]  Ioannis Pitas,et al.  Video shot segmentation using singular value decomposition , 2003, 2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698).

[15]  Shih-Fu Chang,et al.  Video scene segmentation using video and audio features , 2000, 2000 IEEE International Conference on Multimedia and Expo. ICME2000. Proceedings. Latest Advances in the Fast Changing World of Multimedia (Cat. No.00TH8532).